diff --git a/Assignment Colab/.ipynb_checkpoints/Eva Akurut (1)-checkpoint.ipynb b/Assignment Colab/.ipynb_checkpoints/Eva Akurut (1)-checkpoint.ipynb
new file mode 100644
index 0000000..a28068e
--- /dev/null
+++ b/Assignment Colab/.ipynb_checkpoints/Eva Akurut (1)-checkpoint.ipynb	
@@ -0,0 +1,2753 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### ACE_COMPETITION\n",
+    "#### Exploration Data Analysis assignment\n",
+    "- Import the datasets into the notebook\n",
+    "- Find out the Dimensions of the data imported\n",
+    "- Descibe the data using statistics(Descriptive statistics)\n",
+    "- Looking at how the variables correlate with each other\n",
+    "- Data Visualisation\n",
+    "- Preparation of data for Machine Learning\n",
+    "- Evaluate the Performance of Machine Learning Algorithms with Resampling\n",
+    "- Spot-Checking Classiffication Algorithms"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
+    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5"
+   },
+   "outputs": [],
+   "source": [
+    "# Importing the tools to use for the assignment\n",
+    "import numpy as np # linear algebra\n",
+    "import pandas as pd # data structure analysis\n",
+    "import matplotlib.pyplot as plt # for visualisation\n",
+    "import seaborn as sns#\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1)Loading the data to be used into my notebook"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "###Importing the data sets into the notebook using read.csv\n",
+    "Train=pd.read_csv(\"../AMP Data Sets/AMP_TrainSet.csv\")\n",
+    "Test=pd.read_csv(\"../AMP Data Sets/Test.csv\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 2)Checking the dimensions of my data\n",
+    "This sumarries the data type,Number of columns and rows,if the data has missing values \n",
+    "\n",
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??\n",
+    "   \n",
+    "   When you see the above \"??\" these are the things I need to see:\n",
+    "   - Why are you considering what you are doing: in this case check the dimensions\n",
+    "   - What did you learn?\n",
+    "   - How has it informed your next steps.\n",
+    "   - In otherwords I need more information on what you are doing."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>FULL_Charge</th>\n",
+       "      <th>FULL_AcidicMolPerc</th>\n",
+       "      <th>FULL_AURR980107</th>\n",
+       "      <th>FULL_DAYM780201</th>\n",
+       "      <th>FULL_GEOR030101</th>\n",
+       "      <th>FULL_OOBM850104</th>\n",
+       "      <th>NT_EFC195</th>\n",
+       "      <th>AS_MeanAmphiMoment</th>\n",
+       "      <th>AS_DAYM780201</th>\n",
+       "      <th>AS_FUKS010112</th>\n",
+       "      <th>CT_RACS820104</th>\n",
+       "      <th>CLASS</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>5.0</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.951</td>\n",
+       "      <td>74.842</td>\n",
+       "      <td>0.975</td>\n",
+       "      <td>-3.663</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.282</td>\n",
+       "      <td>73.444</td>\n",
+       "      <td>5.661</td>\n",
+       "      <td>1.041</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>4.0</td>\n",
+       "      <td>5.405</td>\n",
+       "      <td>0.931</td>\n",
+       "      <td>71.595</td>\n",
+       "      <td>0.957</td>\n",
+       "      <td>-4.011</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.600</td>\n",
+       "      <td>68.222</td>\n",
+       "      <td>6.537</td>\n",
+       "      <td>1.453</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>5.5</td>\n",
+       "      <td>5.405</td>\n",
+       "      <td>0.873</td>\n",
+       "      <td>73.595</td>\n",
+       "      <td>0.961</td>\n",
+       "      <td>-2.512</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.593</td>\n",
+       "      <td>69.444</td>\n",
+       "      <td>4.934</td>\n",
+       "      <td>1.722</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>5.0</td>\n",
+       "      <td>4.167</td>\n",
+       "      <td>0.895</td>\n",
+       "      <td>66.250</td>\n",
+       "      <td>0.999</td>\n",
+       "      <td>-1.362</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.614</td>\n",
+       "      <td>67.222</td>\n",
+       "      <td>4.316</td>\n",
+       "      <td>1.382</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>7.5</td>\n",
+       "      <td>8.537</td>\n",
+       "      <td>0.932</td>\n",
+       "      <td>64.720</td>\n",
+       "      <td>0.979</td>\n",
+       "      <td>-2.091</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.616</td>\n",
+       "      <td>72.944</td>\n",
+       "      <td>4.540</td>\n",
+       "      <td>1.539</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   FULL_Charge  FULL_AcidicMolPerc  FULL_AURR980107  FULL_DAYM780201  \\\n",
+       "0          5.0               0.000            0.951           74.842   \n",
+       "1          4.0               5.405            0.931           71.595   \n",
+       "2          5.5               5.405            0.873           73.595   \n",
+       "3          5.0               4.167            0.895           66.250   \n",
+       "4          7.5               8.537            0.932           64.720   \n",
+       "\n",
+       "   FULL_GEOR030101  FULL_OOBM850104  NT_EFC195  AS_MeanAmphiMoment  \\\n",
+       "0            0.975           -3.663          0               0.282   \n",
+       "1            0.957           -4.011          1               0.600   \n",
+       "2            0.961           -2.512          0               0.593   \n",
+       "3            0.999           -1.362          0               0.614   \n",
+       "4            0.979           -2.091          0               0.616   \n",
+       "\n",
+       "   AS_DAYM780201  AS_FUKS010112  CT_RACS820104  CLASS  \n",
+       "0         73.444          5.661          1.041      1  \n",
+       "1         68.222          6.537          1.453      1  \n",
+       "2         69.444          4.934          1.722      1  \n",
+       "3         67.222          4.316          1.382      1  \n",
+       "4         72.944          4.540          1.539      1  "
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "Train.head(5)\n",
+    "# To check the first 5 rows on my dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(FULL_Charge           float64\n",
+       " FULL_AcidicMolPerc    float64\n",
+       " FULL_AURR980107       float64\n",
+       " FULL_DAYM780201       float64\n",
+       " FULL_GEOR030101       float64\n",
+       " FULL_OOBM850104       float64\n",
+       " NT_EFC195               int64\n",
+       " AS_MeanAmphiMoment    float64\n",
+       " AS_DAYM780201         float64\n",
+       " AS_FUKS010112         float64\n",
+       " CT_RACS820104         float64\n",
+       " CLASS                   int64\n",
+       " dtype: object, FULL_Charge           float64\n",
+       " FULL_AcidicMolPerc    float64\n",
+       " FULL_AURR980107       float64\n",
+       " FULL_DAYM780201       float64\n",
+       " FULL_GEOR030101       float64\n",
+       " FULL_OOBM850104       float64\n",
+       " NT_EFC195               int64\n",
+       " AS_MeanAmphiMoment    float64\n",
+       " AS_DAYM780201         float64\n",
+       " AS_FUKS010112         float64\n",
+       " CT_RACS820104         float64\n",
+       " dtype: object)"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Checking the datatype of of my data to determine the class of my data\n",
+    "Train.dtypes ,Test.dtypes\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((3038, 12), (758, 11))"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Finding out the rows and columns present in my data set \n",
+    "Train.shape , Test.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 3038 entries, 0 to 3037\n",
+      "Data columns (total 12 columns):\n",
+      "FULL_Charge           3038 non-null float64\n",
+      "FULL_AcidicMolPerc    3038 non-null float64\n",
+      "FULL_AURR980107       3038 non-null float64\n",
+      "FULL_DAYM780201       3038 non-null float64\n",
+      "FULL_GEOR030101       3038 non-null float64\n",
+      "FULL_OOBM850104       3038 non-null float64\n",
+      "NT_EFC195             3038 non-null int64\n",
+      "AS_MeanAmphiMoment    3038 non-null float64\n",
+      "AS_DAYM780201         3038 non-null float64\n",
+      "AS_FUKS010112         3038 non-null float64\n",
+      "CT_RACS820104         3038 non-null float64\n",
+      "CLASS                 3038 non-null int64\n",
+      "dtypes: float64(10), int64(2)\n",
+      "memory usage: 284.9 KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Printing the summary of the data frame\n",
+    "# Summary includes list of all columns with their data types and the number of non-null values in each column. \n",
+    "#we also have the value of rangeindex provided for the index axis.\n",
+    "Train.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['FULL_Charge', 'FULL_AcidicMolPerc', 'FULL_AURR980107',\n",
+       "       'FULL_DAYM780201', 'FULL_GEOR030101', 'FULL_OOBM850104', 'NT_EFC195',\n",
+       "       'AS_MeanAmphiMoment', 'AS_DAYM780201', 'AS_FUKS010112', 'CT_RACS820104',\n",
+       "       'CLASS'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Printing the column names to get to know the names of the columns\n",
+    "Train.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# In general, both the train and Test datasets have float and intenger data types\n",
+    "#The Train Data set has 3038 rows and 12 columns\n",
+    "# The Test Data set has 758 rows plus 11 columns"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 3)Descriptive statistics\n",
+    "Descriptive statistics can give you great insight into the shape of each attribute.\n",
+    "\n",
+    "Often you can create more summaries than you have time to review. The describe() function on the Pandas DataFrame lists 8 statistical properties of each attribute:\n",
+    "Count,Mean,Standard Devaition,Minimum Value,25th Percentile,50th Percentile (Median),75th Percentile,Maximum Value.\n",
+    "\n",
+    "\n",
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>FULL_Charge</th>\n",
+       "      <th>FULL_AcidicMolPerc</th>\n",
+       "      <th>FULL_AURR980107</th>\n",
+       "      <th>FULL_DAYM780201</th>\n",
+       "      <th>FULL_GEOR030101</th>\n",
+       "      <th>FULL_OOBM850104</th>\n",
+       "      <th>NT_EFC195</th>\n",
+       "      <th>AS_MeanAmphiMoment</th>\n",
+       "      <th>AS_DAYM780201</th>\n",
+       "      <th>AS_FUKS010112</th>\n",
+       "      <th>CT_RACS820104</th>\n",
+       "      <th>CLASS</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>2.060237</td>\n",
+       "      <td>8.521520</td>\n",
+       "      <td>0.971410</td>\n",
+       "      <td>73.668760</td>\n",
+       "      <td>0.994007</td>\n",
+       "      <td>-2.432927</td>\n",
+       "      <td>0.088545</td>\n",
+       "      <td>15.683233</td>\n",
+       "      <td>73.650828</td>\n",
+       "      <td>5.911361</td>\n",
+       "      <td>1.235255</td>\n",
+       "      <td>0.500000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>3.819929</td>\n",
+       "      <td>7.586652</td>\n",
+       "      <td>0.107413</td>\n",
+       "      <td>8.527489</td>\n",
+       "      <td>0.031333</td>\n",
+       "      <td>1.707223</td>\n",
+       "      <td>0.284133</td>\n",
+       "      <td>11.575665</td>\n",
+       "      <td>9.166092</td>\n",
+       "      <td>0.693689</td>\n",
+       "      <td>0.210012</td>\n",
+       "      <td>0.500082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>-16.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.684000</td>\n",
+       "      <td>42.750000</td>\n",
+       "      <td>0.866000</td>\n",
+       "      <td>-10.432000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.041000</td>\n",
+       "      <td>42.778000</td>\n",
+       "      <td>3.533000</td>\n",
+       "      <td>0.785000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>2.516000</td>\n",
+       "      <td>0.895000</td>\n",
+       "      <td>68.294000</td>\n",
+       "      <td>0.974000</td>\n",
+       "      <td>-3.606000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>5.587500</td>\n",
+       "      <td>67.556000</td>\n",
+       "      <td>5.459250</td>\n",
+       "      <td>1.082000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>2.000000</td>\n",
+       "      <td>7.143000</td>\n",
+       "      <td>0.963000</td>\n",
+       "      <td>74.059500</td>\n",
+       "      <td>0.994000</td>\n",
+       "      <td>-2.296500</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>14.988500</td>\n",
+       "      <td>73.697000</td>\n",
+       "      <td>5.925500</td>\n",
+       "      <td>1.184000</td>\n",
+       "      <td>0.500000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>4.000000</td>\n",
+       "      <td>13.158000</td>\n",
+       "      <td>1.041000</td>\n",
+       "      <td>79.343750</td>\n",
+       "      <td>1.011000</td>\n",
+       "      <td>-1.283250</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>26.807750</td>\n",
+       "      <td>79.778000</td>\n",
+       "      <td>6.382000</td>\n",
+       "      <td>1.351000</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>30.000000</td>\n",
+       "      <td>46.667000</td>\n",
+       "      <td>1.451000</td>\n",
+       "      <td>101.682000</td>\n",
+       "      <td>1.196000</td>\n",
+       "      <td>3.576000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>51.280000</td>\n",
+       "      <td>103.167000</td>\n",
+       "      <td>8.662000</td>\n",
+       "      <td>2.192000</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       FULL_Charge  FULL_AcidicMolPerc  FULL_AURR980107  FULL_DAYM780201  \\\n",
+       "count  3038.000000         3038.000000      3038.000000      3038.000000   \n",
+       "mean      2.060237            8.521520         0.971410        73.668760   \n",
+       "std       3.819929            7.586652         0.107413         8.527489   \n",
+       "min     -16.000000            0.000000         0.684000        42.750000   \n",
+       "25%       0.000000            2.516000         0.895000        68.294000   \n",
+       "50%       2.000000            7.143000         0.963000        74.059500   \n",
+       "75%       4.000000           13.158000         1.041000        79.343750   \n",
+       "max      30.000000           46.667000         1.451000       101.682000   \n",
+       "\n",
+       "       FULL_GEOR030101  FULL_OOBM850104    NT_EFC195  AS_MeanAmphiMoment  \\\n",
+       "count      3038.000000      3038.000000  3038.000000         3038.000000   \n",
+       "mean          0.994007        -2.432927     0.088545           15.683233   \n",
+       "std           0.031333         1.707223     0.284133           11.575665   \n",
+       "min           0.866000       -10.432000     0.000000            0.041000   \n",
+       "25%           0.974000        -3.606000     0.000000            5.587500   \n",
+       "50%           0.994000        -2.296500     0.000000           14.988500   \n",
+       "75%           1.011000        -1.283250     0.000000           26.807750   \n",
+       "max           1.196000         3.576000     1.000000           51.280000   \n",
+       "\n",
+       "       AS_DAYM780201  AS_FUKS010112  CT_RACS820104        CLASS  \n",
+       "count    3038.000000    3038.000000    3038.000000  3038.000000  \n",
+       "mean       73.650828       5.911361       1.235255     0.500000  \n",
+       "std         9.166092       0.693689       0.210012     0.500082  \n",
+       "min        42.778000       3.533000       0.785000     0.000000  \n",
+       "25%        67.556000       5.459250       1.082000     0.000000  \n",
+       "50%        73.697000       5.925500       1.184000     0.500000  \n",
+       "75%        79.778000       6.382000       1.351000     1.000000  \n",
+       "max       103.167000       8.662000       2.192000     1.000000  "
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Getting the spread of my data\n",
+    "Train.describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x1a10e43d90>"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Splitting my data into by classfication to find out how balanced the v\n",
+    "#A groupby operation involves a combination of splitting the object, \n",
+    "#Then application of a function, and combining the results.\n",
+    "Train.groupby(\"CLASS\").size().plot(kind=\"bar\")                             "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??\n",
+    "   The plot is crowded on the x-axis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x1a10f63510>"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.countplot(x = 'FULL_Charge', data = Train)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 4)Checking how my data correlates with each other \n",
+    "In statistics, correlation or dependence is any statistical relationship, whether causal or not, between two random variables or bivariate data.\n",
+    "Here the intension was to find out if there is a relationship**** between the variables\n",
+    "\n",
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??\n",
+    "   \n",
+    "   Great visuals, but what do they mean?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>FULL_Charge</th>\n",
+       "      <th>FULL_AcidicMolPerc</th>\n",
+       "      <th>FULL_AURR980107</th>\n",
+       "      <th>FULL_DAYM780201</th>\n",
+       "      <th>FULL_GEOR030101</th>\n",
+       "      <th>FULL_OOBM850104</th>\n",
+       "      <th>NT_EFC195</th>\n",
+       "      <th>AS_MeanAmphiMoment</th>\n",
+       "      <th>AS_DAYM780201</th>\n",
+       "      <th>AS_FUKS010112</th>\n",
+       "      <th>CT_RACS820104</th>\n",
+       "      <th>CLASS</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>FULL_Charge</th>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.612996</td>\n",
+       "      <td>-0.490977</td>\n",
+       "      <td>-0.434603</td>\n",
+       "      <td>-0.058725</td>\n",
+       "      <td>-0.283758</td>\n",
+       "      <td>0.088068</td>\n",
+       "      <td>0.355477</td>\n",
+       "      <td>-0.365374</td>\n",
+       "      <td>-0.090570</td>\n",
+       "      <td>0.232929</td>\n",
+       "      <td>0.534602</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>FULL_AcidicMolPerc</th>\n",
+       "      <td>-0.612996</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.794796</td>\n",
+       "      <td>0.541481</td>\n",
+       "      <td>0.115201</td>\n",
+       "      <td>0.513344</td>\n",
+       "      <td>-0.143168</td>\n",
+       "      <td>-0.431590</td>\n",
+       "      <td>0.449621</td>\n",
+       "      <td>0.002334</td>\n",
+       "      <td>-0.213543</td>\n",
+       "      <td>-0.598816</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>FULL_AURR980107</th>\n",
+       "      <td>-0.490977</td>\n",
+       "      <td>0.794796</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.548253</td>\n",
+       "      <td>0.346139</td>\n",
+       "      <td>0.462712</td>\n",
+       "      <td>-0.169540</td>\n",
+       "      <td>-0.426097</td>\n",
+       "      <td>0.456260</td>\n",
+       "      <td>0.032958</td>\n",
+       "      <td>-0.403599</td>\n",
+       "      <td>-0.584111</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>FULL_DAYM780201</th>\n",
+       "      <td>-0.434603</td>\n",
+       "      <td>0.541481</td>\n",
+       "      <td>0.548253</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.010118</td>\n",
+       "      <td>0.334778</td>\n",
+       "      <td>-0.090058</td>\n",
+       "      <td>-0.408793</td>\n",
+       "      <td>0.894191</td>\n",
+       "      <td>0.055915</td>\n",
+       "      <td>-0.326792</td>\n",
+       "      <td>-0.554838</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>FULL_GEOR030101</th>\n",
+       "      <td>-0.058725</td>\n",
+       "      <td>0.115201</td>\n",
+       "      <td>0.346139</td>\n",
+       "      <td>0.010118</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.319157</td>\n",
+       "      <td>-0.230417</td>\n",
+       "      <td>-0.160269</td>\n",
+       "      <td>-0.029085</td>\n",
+       "      <td>0.040480</td>\n",
+       "      <td>-0.151935</td>\n",
+       "      <td>-0.260470</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>FULL_OOBM850104</th>\n",
+       "      <td>-0.283758</td>\n",
+       "      <td>0.513344</td>\n",
+       "      <td>0.462712</td>\n",
+       "      <td>0.334778</td>\n",
+       "      <td>0.319157</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.230561</td>\n",
+       "      <td>-0.336297</td>\n",
+       "      <td>0.275640</td>\n",
+       "      <td>-0.452769</td>\n",
+       "      <td>0.155304</td>\n",
+       "      <td>-0.453287</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>NT_EFC195</th>\n",
+       "      <td>0.088068</td>\n",
+       "      <td>-0.143168</td>\n",
+       "      <td>-0.169540</td>\n",
+       "      <td>-0.090058</td>\n",
+       "      <td>-0.230417</td>\n",
+       "      <td>-0.230561</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.178683</td>\n",
+       "      <td>-0.036844</td>\n",
+       "      <td>0.145924</td>\n",
+       "      <td>0.080898</td>\n",
+       "      <td>0.260702</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AS_MeanAmphiMoment</th>\n",
+       "      <td>0.355477</td>\n",
+       "      <td>-0.431590</td>\n",
+       "      <td>-0.426097</td>\n",
+       "      <td>-0.408793</td>\n",
+       "      <td>-0.160269</td>\n",
+       "      <td>-0.336297</td>\n",
+       "      <td>0.178683</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.322378</td>\n",
+       "      <td>0.025580</td>\n",
+       "      <td>0.171524</td>\n",
+       "      <td>0.693552</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AS_DAYM780201</th>\n",
+       "      <td>-0.365374</td>\n",
+       "      <td>0.449621</td>\n",
+       "      <td>0.456260</td>\n",
+       "      <td>0.894191</td>\n",
+       "      <td>-0.029085</td>\n",
+       "      <td>0.275640</td>\n",
+       "      <td>-0.036844</td>\n",
+       "      <td>-0.322378</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.045562</td>\n",
+       "      <td>-0.256060</td>\n",
+       "      <td>-0.437168</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AS_FUKS010112</th>\n",
+       "      <td>-0.090570</td>\n",
+       "      <td>0.002334</td>\n",
+       "      <td>0.032958</td>\n",
+       "      <td>0.055915</td>\n",
+       "      <td>0.040480</td>\n",
+       "      <td>-0.452769</td>\n",
+       "      <td>0.145924</td>\n",
+       "      <td>0.025580</td>\n",
+       "      <td>0.045562</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.445284</td>\n",
+       "      <td>0.033432</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>CT_RACS820104</th>\n",
+       "      <td>0.232929</td>\n",
+       "      <td>-0.213543</td>\n",
+       "      <td>-0.403599</td>\n",
+       "      <td>-0.326792</td>\n",
+       "      <td>-0.151935</td>\n",
+       "      <td>0.155304</td>\n",
+       "      <td>0.080898</td>\n",
+       "      <td>0.171524</td>\n",
+       "      <td>-0.256060</td>\n",
+       "      <td>-0.445284</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.267652</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>CLASS</th>\n",
+       "      <td>0.534602</td>\n",
+       "      <td>-0.598816</td>\n",
+       "      <td>-0.584111</td>\n",
+       "      <td>-0.554838</td>\n",
+       "      <td>-0.260470</td>\n",
+       "      <td>-0.453287</td>\n",
+       "      <td>0.260702</td>\n",
+       "      <td>0.693552</td>\n",
+       "      <td>-0.437168</td>\n",
+       "      <td>0.033432</td>\n",
+       "      <td>0.267652</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                    FULL_Charge  FULL_AcidicMolPerc  FULL_AURR980107  \\\n",
+       "FULL_Charge            1.000000           -0.612996        -0.490977   \n",
+       "FULL_AcidicMolPerc    -0.612996            1.000000         0.794796   \n",
+       "FULL_AURR980107       -0.490977            0.794796         1.000000   \n",
+       "FULL_DAYM780201       -0.434603            0.541481         0.548253   \n",
+       "FULL_GEOR030101       -0.058725            0.115201         0.346139   \n",
+       "FULL_OOBM850104       -0.283758            0.513344         0.462712   \n",
+       "NT_EFC195              0.088068           -0.143168        -0.169540   \n",
+       "AS_MeanAmphiMoment     0.355477           -0.431590        -0.426097   \n",
+       "AS_DAYM780201         -0.365374            0.449621         0.456260   \n",
+       "AS_FUKS010112         -0.090570            0.002334         0.032958   \n",
+       "CT_RACS820104          0.232929           -0.213543        -0.403599   \n",
+       "CLASS                  0.534602           -0.598816        -0.584111   \n",
+       "\n",
+       "                    FULL_DAYM780201  FULL_GEOR030101  FULL_OOBM850104  \\\n",
+       "FULL_Charge               -0.434603        -0.058725        -0.283758   \n",
+       "FULL_AcidicMolPerc         0.541481         0.115201         0.513344   \n",
+       "FULL_AURR980107            0.548253         0.346139         0.462712   \n",
+       "FULL_DAYM780201            1.000000         0.010118         0.334778   \n",
+       "FULL_GEOR030101            0.010118         1.000000         0.319157   \n",
+       "FULL_OOBM850104            0.334778         0.319157         1.000000   \n",
+       "NT_EFC195                 -0.090058        -0.230417        -0.230561   \n",
+       "AS_MeanAmphiMoment        -0.408793        -0.160269        -0.336297   \n",
+       "AS_DAYM780201              0.894191        -0.029085         0.275640   \n",
+       "AS_FUKS010112              0.055915         0.040480        -0.452769   \n",
+       "CT_RACS820104             -0.326792        -0.151935         0.155304   \n",
+       "CLASS                     -0.554838        -0.260470        -0.453287   \n",
+       "\n",
+       "                    NT_EFC195  AS_MeanAmphiMoment  AS_DAYM780201  \\\n",
+       "FULL_Charge          0.088068            0.355477      -0.365374   \n",
+       "FULL_AcidicMolPerc  -0.143168           -0.431590       0.449621   \n",
+       "FULL_AURR980107     -0.169540           -0.426097       0.456260   \n",
+       "FULL_DAYM780201     -0.090058           -0.408793       0.894191   \n",
+       "FULL_GEOR030101     -0.230417           -0.160269      -0.029085   \n",
+       "FULL_OOBM850104     -0.230561           -0.336297       0.275640   \n",
+       "NT_EFC195            1.000000            0.178683      -0.036844   \n",
+       "AS_MeanAmphiMoment   0.178683            1.000000      -0.322378   \n",
+       "AS_DAYM780201       -0.036844           -0.322378       1.000000   \n",
+       "AS_FUKS010112        0.145924            0.025580       0.045562   \n",
+       "CT_RACS820104        0.080898            0.171524      -0.256060   \n",
+       "CLASS                0.260702            0.693552      -0.437168   \n",
+       "\n",
+       "                    AS_FUKS010112  CT_RACS820104     CLASS  \n",
+       "FULL_Charge             -0.090570       0.232929  0.534602  \n",
+       "FULL_AcidicMolPerc       0.002334      -0.213543 -0.598816  \n",
+       "FULL_AURR980107          0.032958      -0.403599 -0.584111  \n",
+       "FULL_DAYM780201          0.055915      -0.326792 -0.554838  \n",
+       "FULL_GEOR030101          0.040480      -0.151935 -0.260470  \n",
+       "FULL_OOBM850104         -0.452769       0.155304 -0.453287  \n",
+       "NT_EFC195                0.145924       0.080898  0.260702  \n",
+       "AS_MeanAmphiMoment       0.025580       0.171524  0.693552  \n",
+       "AS_DAYM780201            0.045562      -0.256060 -0.437168  \n",
+       "AS_FUKS010112            1.000000      -0.445284  0.033432  \n",
+       "CT_RACS820104           -0.445284       1.000000  0.267652  \n",
+       "CLASS                    0.033432       0.267652  1.000000  "
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "corr=Train.corr(method='pearson')\n",
+    "corr\n",
+    "# The correllation 1 is a positive relationship, -1 a negative relationship and 0 no relationship"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x1a11065f90>"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x864 with 2 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.figure(figsize=(12,12))\n",
+    "sns.heatmap(Train.corr(method='pearson'),annot=True,cmap=\"YlGnBu\")\n",
+    "#Heatmap is a way of representing the data in a 2-dimensional form. The data values are represented as colors in the graph. \n",
+    "#It's goal is to provide a colored visual summary of information\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<seaborn.matrix.ClusterGrid at 0x1a114e2850>"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 720x720 with 4 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#For more depth of understanding the data the clustermap method is used \n",
+    "#The .clustermap() method uses a hierarchical clusters to order data by similarity.\n",
+    "#This reorganizes the data for the rows and columns and displays similar content next to one another \n",
+    "\n",
+    "sns.clustermap(Train.corr(method='pearson'),annot=True, cmap=\"Paired_r\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "FULL_Charge           0.534602\n",
+       "FULL_AcidicMolPerc   -0.598816\n",
+       "FULL_AURR980107      -0.584111\n",
+       "FULL_DAYM780201      -0.554838\n",
+       "FULL_GEOR030101      -0.260470\n",
+       "FULL_OOBM850104      -0.453287\n",
+       "NT_EFC195             0.260702\n",
+       "AS_MeanAmphiMoment    0.693552\n",
+       "AS_DAYM780201        -0.437168\n",
+       "AS_FUKS010112         0.033432\n",
+       "CT_RACS820104         0.267652\n",
+       "CLASS                 1.000000\n",
+       "Name: CLASS, dtype: float64"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Showing how each variable correlates with the CLASS variable\n",
+    "Train.corr(method='pearson')['CLASS']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 5)Data Visualisation\n",
+    "*Data visualizations in python can be done via many packages.\n",
+    "*Using matplot enables one to have a visual figures for the data\n",
+    "*Every Axes has an x-axis and y-axis for plotting. \n",
+    "*Contained within the axes are titles, ticks, labels associated with each axis\n",
+    "\n",
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??\n",
+    "   \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x1a1c29e190>"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#1)To check for skewness in my dataset\n",
+    "#Skew refers to a distribution that is assumed Gaussian (normal or bell curve) that is shifted in one direction or another\n",
+    "Train.skew().plot(kind='bar')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 12 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# 2) Use of the box plot\n",
+    "#Boxplots summarize the distribution of each attribute\n",
+    "#A line for the median (middle value) is drawn while and a box put around the 25th and 75th percentiles.\n",
+    "#The whiskers give an idea of the spread of the data and dots outside of the whiskers show candidate outlier values \n",
+    "# Box plots\n",
+    "Train.plot(kind='box', subplots=True, layout=(4,3), sharex=True,sharey=True)\n",
+    "plt.subplots_adjust(bottom=1, right=2, top=3)\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<seaborn.axisgrid.PairGrid at 0x1a1c29e1d0>"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1080x1080 with 42 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#3) Scatter plot: This is to relationship between two variables as dots in two dimension.\n",
+    "#This is done so we could spot if there is a structured relationship within the two variables\n",
+    "sns.pairplot(data=Train[['FULL_Charge','FULL_DAYM780201','FULL_OOBM850104', 'NT_EFC195',\n",
+    "       'AS_MeanAmphiMoment','CLASS']])\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Figure size 1080x1080 with 0 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 12 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Histograms\n",
+    "plt.figure(figsize=(15,15))\n",
+    "Train.hist(color='red')\n",
+    "\n",
+    "plt.subplots_adjust(bottom=1, right=2, top=3)\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 6)Preparation of data for Machine Learning\n",
+    "Pre-processing of Data is carried out in this section\n",
+    "\n",
+    "\n",
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[0.457 0.    0.348 0.545 0.33  0.483 0.    0.005 0.508 0.415 0.182]\n",
+      " [0.435 0.116 0.322 0.489 0.276 0.458 1.    0.011 0.421 0.586 0.475]\n",
+      " [0.467 0.116 0.246 0.523 0.288 0.565 0.    0.011 0.442 0.273 0.666]\n",
+      " [0.457 0.089 0.275 0.399 0.403 0.647 0.    0.011 0.405 0.153 0.424]\n",
+      " [0.511 0.183 0.323 0.373 0.342 0.595 0.    0.011 0.5   0.196 0.536]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "#1) I will need to preapre my data for prepossessing \n",
+    "# My preffered method for Data transformation is \"The Fit and Multiple Transform\" method form the scikit-learn library.\n",
+    "#Split the dataset into the input and output variables for machine learning.\n",
+    "#Apply a pre-processing transform to the input variables.\n",
+    "#Summarize the data to show the change.\n",
+    "#Rescaling the Data:Since the attributes have varying scales\n",
+    "\n",
+    "from numpy import set_printoptions\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "\n",
+    "array = Train.values\n",
+    "# separate array into input and output components\n",
+    "X= array[:,0:11]\n",
+    "Y= array[:,11]\n",
+    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
+    "rescaledX = scaler.fit_transform(X)\n",
+    "# summarize transformed data\n",
+    "set_printoptions(precision=3)\n",
+    "print(rescaledX[0:5,:])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[1. 0. 1. 1. 1. 0. 0. 1. 1. 1. 1.]\n",
+      " [1. 1. 1. 1. 1. 0. 1. 1. 1. 1. 1.]\n",
+      " [1. 1. 1. 1. 1. 0. 0. 1. 1. 1. 1.]\n",
+      " [1. 1. 1. 1. 1. 0. 0. 1. 1. 1. 1.]\n",
+      " [1. 1. 1. 1. 1. 0. 0. 1. 1. 1. 1.]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Looking at when my data is binarized instead\n",
+    "from sklearn.preprocessing import Binarizer\n",
+    "\n",
+    "array2 = Train.values\n",
+    "# separate array into input and output components\n",
+    "X = array2[:,0:11]\n",
+    "Y = array2[:,11]\n",
+    "binarizer = Binarizer(threshold=0.0).fit(X)\n",
+    "binaryX = binarizer.transform(X)\n",
+    "# summarize transformed data\n",
+    "set_printoptions(precision=3)\n",
+    "print(binaryX[0:5,:])\n",
+    "\n",
+    "#NB:This binarised data was not used "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Num Features:  6\n",
+      "Selected Features: [ True False  True False  True  True  True False False False  True]\n",
+      "Feature Ranking:  [1 5 1 4 1 1 1 2 6 3 1]\n",
+      "Num Features:  6\n",
+      "Selected Features: [ True False  True False  True  True  True False False False  True]\n",
+      "Feature Ranking:  [1 5 1 4 1 1 1 2 6 3 1]\n"
+     ]
+    }
+   ],
+   "source": [
+    "#b) Feature Selection\n",
+    "#Select an anttribute will will give the most to the prediction variable \n",
+    "#a)Selection is by The Recursive Feature Elimination (or RFE) \n",
+    "# This works by recursively removing attributes and building a model on those attributes that remain.\n",
+    "from sklearn.feature_selection import RFE\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "\n",
+    "# feature extraction\n",
+    "# feature extraction\n",
+    "model = LogisticRegression()\n",
+    "rfe = RFE(model, 6)\n",
+    "fit = rfe.fit(X, Y)\n",
+    "print(\"Num Features: \",  fit.n_features_)\n",
+    "print(\"Selected Features:\",  fit.support_)\n",
+    "print(\"Feature Ranking: \",  fit.ranking_)\n",
+    "print(\"Num Features: \",  fit.n_features_)\n",
+    "print(\"Selected Features:\",  fit.support_)\n",
+    "print(\"Feature Ranking: \",  fit.ranking_)\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??\n",
+    "   \n",
+    "   Why are you doing PCA?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Explained Variance: [0.605 0.242 0.103]\n",
+      "[[ 1.409e-01 -3.557e-01 -4.743e-03 -4.935e-01 -1.975e-04 -5.101e-02\n",
+      "   2.877e-03  6.020e-01 -4.950e-01 -8.765e-04  4.186e-03]\n",
+      " [-8.867e-03  3.090e-02  4.994e-04  3.921e-01 -5.282e-04 -8.492e-03\n",
+      "   3.437e-03  7.629e-01  5.129e-01  5.018e-03 -2.000e-03]\n",
+      " [-2.731e-01  8.713e-01  8.049e-03 -1.349e-01  4.214e-04  8.143e-02\n",
+      "  -2.941e-03  2.312e-01 -2.966e-01 -1.359e-03 -5.700e-04]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.decomposition import PCA\n",
+    "array = Train.values\n",
+    "X = array[:,0:11]\n",
+    "Y = array[:,11]\n",
+    "# feature extraction\n",
+    "pca = PCA(n_components=3)\n",
+    "fit = pca.fit(X)\n",
+    "# summarize components\n",
+    "print(\"Explained Variance: %s\" % fit.explained_variance_ratio_)\n",
+    "print(fit.components_)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[0.089 0.145 0.077 0.088 0.052 0.075 0.037 0.309 0.051 0.032 0.046]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Feature importance\n",
+    "from sklearn.ensemble import ExtraTreesClassifier\n",
+    "\n",
+    "array = Train.values\n",
+    "A = array[:,0:11]\n",
+    "B = array[:,11]\n",
+    "# feature extraction\n",
+    "model = ExtraTreesClassifier()\n",
+    "model.fit(A, B)\n",
+    "print(model.feature_importances_)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## According to feature importance all the features in the data set were useful hence could not be lost and therefore i kept them all\n",
+    "\n",
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   Could you draw a graph for this?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 7)Evaluate the Performance of Machine Learning Algorithms with Resampling\n",
+    "##There is need to know how well the algorithms will perform on unseen data\n",
+    "##The best way to evaluate the performance of an algorithm is to make predictions for new data to which  answers are known\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy:  91.54135338345864\n"
+     ]
+    }
+   ],
+   "source": [
+    "## Split the  Data into Test and Train\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "test_size = 0.35\n",
+    "seed = 7\n",
+    "\n",
+    "X_train,X_test, Y_train, Y_test = train_test_split(X, Y, test_size=test_size,\n",
+    "random_state=seed)\n",
+    "model = LogisticRegression()\n",
+    "model.fit(X_train, Y_train)\n",
+    "result = model.score(X_test, Y_test)\n",
+    "print(\"Accuracy: \",  (result*100.0))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "383\n",
+      "375\n"
+     ]
+    }
+   ],
+   "source": [
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy:  91.82330827067669\n"
+     ]
+    }
+   ],
+   "source": [
+    "# On rescaled Data\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "array = Train.values\n",
+    "X = array[:,0:11]\n",
+    "Y = array[:,11]\n",
+    "test_size = 0.35\n",
+    "seed = 7\n",
+    "\n",
+    "rescaledX_train,rescaledX_test, Y_train, Y_test = train_test_split(rescaledX, Y, test_size=test_size,\n",
+    "random_state=seed)\n",
+    "model = LogisticRegression()\n",
+    "model.fit(rescaledX_train, Y_train)\n",
+    "result = model.score(rescaledX_test, Y_test)\n",
+    "print(\"Accuracy: \",  (result*100.0))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "746\n",
+      "12\n"
+     ]
+    }
+   ],
+   "source": [
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber1_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Despite having a similar accuracy of 91.82,the rescaled data was giving imbalanced false a.nd true values and therefore i would not use it further"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: (88.66787208086441, 18.91491119508906)\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Classification accuracy:is the number of correct predictions made as a ratio of all predictions made.\n",
+    "from sklearn.model_selection import KFold\n",
+    "from sklearn.model_selection import cross_val_score\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "\n",
+    "array = Train.values\n",
+    "\n",
+    "num_folds = 20#number of folds to use\n",
+    "seed = 7#reproducibility\n",
+    "\n",
+    "kfold = KFold(n_splits=num_folds, random_state=None)\n",
+    "model = LogisticRegression()\n",
+    "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=test_size,\n",
+    "random_state=seed)\n",
+    "model.fit(X_train, Y_train)\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "\n",
+    "print(f\"Accuracy:\", (results.mean()*100.0, results.std()*100.0))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "383\n",
+      "375\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber2_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "         0.0       0.91      0.92      0.92       530\n",
+      "         1.0       0.92      0.91      0.92       534\n",
+      "\n",
+      "    accuracy                           0.92      1064\n",
+      "   macro avg       0.92      0.92      0.92      1064\n",
+      "weighted avg       0.92      0.92      0.92      1064\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "#To check out the classification report \n",
+    "from sklearn.metrics import classification_report\n",
+    "\n",
+    "array = Train.values\n",
+    "X = array[:,0:11]\n",
+    "Y = array[:,11]\n",
+    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
+    "rescaledA = scaler.fit_transform(A)\n",
+    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
+    "rescaledA = scaler.fit_transform(A)\n",
+    "test_size = 0.35\n",
+    "seed = 7\n",
+    "rescaledX_train,rescaledX_test, Y_train, Y_test = train_test_split(rescaledX, Y, test_size=test_size,\n",
+    "random_state=seed)\n",
+    "model = LogisticRegression()\n",
+    "model.fit(rescaledX_train, Y_train)\n",
+    "predicted = model.predict(rescaledX_test)\n",
+    "report = classification_report(Y_test, predicted)\n",
+    "print(report)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MAE: (-0.26434068269258093, 0.156909136567752)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# we then look at the regression M\n",
+    "# The Mean Absolute Error(MAE) is the sum of the absolute differences between predictions and actual values.\n",
+    "# Its aim is to give an idea of how wrong the predictions were. \n",
+    "from pandas import read_csv\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "array = Train.values\n",
+    "X = array[:,0:11]\n",
+    "Y = array[:,11]\n",
+    "kfold = KFold(n_splits=10, random_state=None)\n",
+    "model = LinearRegression()\n",
+    "scoring = 'neg_mean_absolute_error'\n",
+    "results = cross_val_score(model, rescaledX, Y, cv=kfold, scoring=scoring)\n",
+    "print(\"MAE:\",(results.mean(), results.std()))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "R^2: (-1.2197243963358124, 3.6591731890074377)\n"
+     ]
+    }
+   ],
+   "source": [
+    "#The R2 metric provides an indication of the goodness of fit of a set of predictions to the actual values\n",
+    "#Cross Validation Regression R^2\n",
+    "array = Train.values\n",
+    "X = array[:,0:11]\n",
+    "Y = array[:,11]\n",
+    "\n",
+    "kfold = KFold(n_splits=10, random_state=None)\n",
+    "model = LinearRegression()\n",
+    "scoring = 'r2'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)\n",
+    "print(\"R^2:\",(results.mean(), results.std()))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 8)Spot-Checking Classiffication Algorithms\n",
+    "##Algorithms Overview\n",
+    "##looking at six classication algorithms that will help spot-check on your dataset. Starting with two ##linear machine learning algorithms:\n",
+    "\n",
+    "8.1.1) - Logistic Regression.\n",
+    "\n",
+    "8.1.2) - Linear Discriminant Analysis.\n",
+    "Then looking at four nonlinear machine learning algorithms:\n",
+    "\n",
+    "8.2.1) - k-Nearest Neighbors.\n",
+    "\n",
+    "8.2.2) - Naive Bayes.\n",
+    "\n",
+    "8.2.3) - Classication and Regression Trees.\n",
+    "\n",
+    "8.2.4)Support Vector Machines.\n",
+    "\n",
+    "8.2.5)Random Forest\n",
+    "\n",
+    "8.2.6)Gradient Boosting for classification\n",
+    "\n",
+    "8.2.7)An extra-trees classifier.\n",
+    "\n",
+    "8.2.8)Neural Network-MLPC"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    " ## 8.1)Linear Machine Language Alogarithms\n",
+    "### 8.1.1)Logistic Regression\n",
+    "Logistic regression assumes a Gaussian distribution for the numeric input variables and can model binary classiffication problems.\n",
+    "****This is done using the Logisticregression class****"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 91.40839412888656\n",
+      "MCC: 0.8342865299822478\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Logistic Regression Classification\n",
+    "from sklearn.model_selection import KFold\n",
+    "from sklearn.model_selection import cross_val_score\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.metrics import matthews_corrcoef\n",
+    "from sklearn.metrics import plot_confusion_matrix\n",
+    "\n",
+    "#for model set up\n",
+    "model = LogisticRegression()\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "383\n",
+      "375\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the LogisticRegression predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber3_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The difference between Accuracy and MCC model is slight but giving the same output pf 383 True values and 375 false values"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 8.1.2)Linear Discriminant Analysis or LDA \n",
+    "-This a statistical technique for binary and multiclass classiffication. \n",
+    "-It too assumes a Gaussian distribution for the numerical input variables. \n",
+    "-You can construct an LDA model using the LinearDiscriminantAnalysis class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 91.77088761507731\n",
+      "MCC: 0.8377162908048379\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
+    "#Model set up\n",
+    "model = LinearDiscriminantAnalysis()\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=9\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "401\n",
+      "357\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the  LinearDiscriminantAnalysis predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber4_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 8.2 Nonlinear machine learning algorithms.\n",
+    "\n",
+    "### 8.2.1)k-Nearest Neighbors\n",
+    "##The k-Nearest Neighbors algorithm (or KNN) uses a distance metric to find the k most similar instances ##In the training data for a new instance and takes the mean outcome of the neighbors as the prediction. #You can construct a KNN model using the KNeighborsClassifier class."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 90.65117488944769\n",
+      "MCC: 0.8690586462107053\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.neighbors import KNeighborsClassifier\n",
+    "#Model set up\n",
+    "model = KNeighborsClassifier()\n",
+    "# For cross validation of data\n",
+    "num_folds = 5\n",
+    "seed=8\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "402\n",
+      "356\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the  LinearDiscriminantAnalysis predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber5_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 8.2.2) Naive Bayes\n",
+    "-Naive Bayes calculates the probability of each class and the conditional probability of each class given each input value. \n",
+    "-These probabilities are estimated for new data and multiplied together\n",
+    "-The Assumption is that they are all independent (a simple or naive assumption).\n",
+    "-When working with real-valued data, a Gaussian distribution is assumed to easily estimate the probabilities for input variables using the Gaussian Probability Density Function. \n",
+    "##You can construct a Naive Bayes model using the GaussianNB class4"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 91.93546986277575\n",
+      "MCC: 0.8407203694376205\n",
+      "0.9193546986277574\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.naive_bayes import GaussianNB\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = GaussianNB()\n",
+    "\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "print(results.mean())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ True False]\n",
+      "2\n",
+      "370\n",
+      "388\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the  Naive Bayes predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber5_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 8.2.3)Classiffication and Regression Trees\n",
+    "Classiffication and Regression Trees (CART or just decision trees) construct a binary tree from the training data. Split points are chosen greedily by evaluating each attribute and each value of each attribute in the training data in order to minimize a cost function (like the Gini index). You can construct a CART model using the DecisionTreeClassifier class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 89.99337762723641\n",
+      "MCC: 1.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.tree import DecisionTreeClassifier\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = DecisionTreeClassifier()\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ True False]\n",
+      "2\n",
+      "383\n",
+      "375\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the DecisionTreeClassifier  predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber6_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 8.2.4)Support Vector Machines\n",
+    "Support Vector Machines (or SVM) seek a line that best separates two classes. \n",
+    "The data instances closest to the line that best separates the classes are called support vectors and \n",
+    "influence where the line is placed. \n",
+    "SVM supports multiple classes and that of particular importance is the use of dierent kernel functions via the kernel parameter."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 90.88131839499741\n",
+      "MCC: 0.8187103751493263\n",
+      "0.9088131839499741\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.svm import SVC\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = SVC()\n",
+    "\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "print(results.mean())\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "397\n",
+      "361\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the SVC predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber7_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 8.2.5)Random Forest\n",
+    "Random forests or random decision forests are an ensemble learning method for classification, regression and other tasks, that operate by constructing a multitude of decision trees at training time and outputting the class that is the mode of the classes (classification) or mean prediction (regression) of the individual trees.\n",
+    "Random decision forests correct for decision trees’ habit of over fitting to their training set."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 94.00881535521974\n",
+      "MCC: 1.0\n",
+      "0.9377811794337327\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = RandomForestClassifier(bootstrap = True,\n",
+    "                              max_features = None)\n",
+    "\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "print(results.mean())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ True False]\n",
+      "2\n",
+      "388\n",
+      "370\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the Randomforest predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber8_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 8.2.6)Gradient Boosting for classification.\n",
+    "GB builds an additive model in a forward stage-wise fashion; it allows for the optimization of arbitrary differentiable loss functions. \n",
+    "In each stage n_classes_ regression trees are fit on the negative gradient of the binomial or multinomial deviance loss function.\n",
+    "Binary classification is a special case where only a single regression tree is induced."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 92.8236277575126\n",
+      "MCC: 0.9092011960769395\n",
+      "0.928236277575126\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import GradientBoostingClassifier\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = GradientBoostingClassifier(learning_rate = 1.0,\n",
+    "                              max_depth = 1)\n",
+    "\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "print(results.mean())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ True False]\n",
+      "2\n",
+      "382\n",
+      "376\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the GradientBoostingClassifier predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber9_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 8.2.7)An extra-trees classifier.\n",
+    "This class implements a meta estimator that fits a number of randomized decision trees (a.k.a. extra-trees) on various sub-samples of the dataset.\n",
+    "It uses averaging to improve the predictive accuracy and control over-fitting."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 93.54807191245442\n",
+      "MCC: 1.0\n",
+      "0.9358096664929653\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import ExtraTreesClassifier\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = ExtraTreesClassifier()                              \n",
+    "\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "print(results.mean())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ True False]\n",
+      "2\n",
+      "386\n",
+      "372\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the ExtratreeClassifier predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber10_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 8.2.8)Multi-layer Perceptron classifier.\n",
+    "This model optimizes the log-loss function using LBFGS or stochastic gradient descent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 92.42878235191941\n",
+      "MCC: 0.8449130833039031\n",
+      "0.925281179433733\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.neural_network import MLPClassifier\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = MLPClassifier()                              \n",
+    "\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "print(results.mean())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ True False]\n",
+      "2\n",
+      "339\n",
+      "419\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the MLPClassifier predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber11_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 9)Compare Machine Learning Algorithms\n",
+    "It is important to compare the performance of multiple different machine learning algorithms consistently.  The test harness as a template on your own machine learning problems and add more and different algorithms to compare."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "('LR', 0.8353580423831856, 0.27188952844394665)\n",
+      "('LDA', 0.8535044293903076, 0.2571395669719574)\n",
+      "('KNN', 0.8027933385443807, 0.2521136100771112)\n",
+      "('CART', 0.7296117769671704, 0.2875488058821619)\n",
+      "('NB', 0.880815746048289, 0.11642272449162755)\n",
+      "('SVM', 0.8350280093798853, 0.25836507020625044)\n",
+      "('MLPC', 0.8281320566267153, 0.2648801028909581)\n",
+      "('EXTC', 0.8386811707486539, 0.2379985491118143)\n",
+      "('GBC', 0.7902737971165538, 0.28849018693832995)\n",
+      "('RDF', 0.8146343581726592, 0.288019257902208)\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Compare Algorithms\n",
+    "from matplotlib import pyplot\n",
+    "# prepare models and add them to a list\n",
+    "models = []\n",
+    "models.append(('LR', LogisticRegression()))\n",
+    "models.append(('LDA', LinearDiscriminantAnalysis()))\n",
+    "models.append(('KNN', KNeighborsClassifier()))\n",
+    "models.append(('CART', DecisionTreeClassifier()))\n",
+    "models.append(('NB', GaussianNB()))\n",
+    "models.append(('SVM', SVC()))\n",
+    "models.append(('MLPC', MLPClassifier()))\n",
+    "models.append(('EXTC', ExtraTreesClassifier()))\n",
+    "models.append(('GBC', GradientBoostingClassifier()))\n",
+    "models.append(('RDF', RandomForestClassifier()))\n",
+    "# evaluate each model in turn\n",
+    "results = []\n",
+    "names = []\n",
+    "scoring = 'accuracy'\n",
+    "for name, model in models:\n",
+    "    kfold = KFold(n_splits=10, random_state=7)\n",
+    "    cv_results = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)\n",
+    "    results.append(cv_results)\n",
+    "    names.append(name)\n",
+    "    msg = (name, cv_results.mean(), cv_results.std())\n",
+    "    print(msg)\n",
+    "\n",
+    "# boxplot algorithm comparison\n",
+    "fig = pyplot.figure()\n",
+    "fig.suptitle('Algorithm Comparison')\n",
+    "ax = fig.add_subplot(111)\n",
+    "pyplot.boxplot(results)\n",
+    "ax.set_xticklabels(names)\n",
+    "pyplot.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# From the alogarithms above the best was the Gausian Naive Bayes with the highest mean value pf 0.88 followed by LDA with 0.85\n",
+    "# The least fit alogarith was DecisionTreeClassifier(0.72)followed by GradientBoostingClassifier at (0.79)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.4"
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/Assignment Colab/Amber10_csv b/Assignment Colab/Amber10_csv
new file mode 100644
index 0000000..7a262e5
--- /dev/null
+++ b/Assignment Colab/Amber10_csv	
@@ -0,0 +1,759 @@
+Index,CLASS
+0,True
+1,True
+2,True
+3,True
+4,False
+5,True
+6,True
+7,False
+8,True
+9,True
+10,True
+11,True
+12,True
+13,False
+14,False
+15,True
+16,True
+17,True
+18,True
+19,True
+20,True
+21,True
+22,True
+23,True
+24,False
+25,True
+26,True
+27,True
+28,True
+29,False
+30,True
+31,True
+32,False
+33,True
+34,False
+35,False
+36,True
+37,True
+38,True
+39,True
+40,True
+41,True
+42,True
+43,True
+44,False
+45,True
+46,True
+47,True
+48,False
+49,True
+50,True
+51,False
+52,False
+53,True
+54,False
+55,True
+56,True
+57,True
+58,True
+59,True
+60,True
+61,False
+62,True
+63,True
+64,True
+65,True
+66,True
+67,True
+68,True
+69,True
+70,True
+71,True
+72,False
+73,True
+74,True
+75,True
+76,False
+77,True
+78,True
+79,True
+80,True
+81,True
+82,True
+83,True
+84,True
+85,False
+86,False
+87,True
+88,True
+89,True
+90,False
+91,True
+92,True
+93,True
+94,False
+95,False
+96,False
+97,True
+98,True
+99,True
+100,False
+101,True
+102,True
+103,True
+104,True
+105,True
+106,True
+107,True
+108,True
+109,True
+110,True
+111,True
+112,True
+113,False
+114,True
+115,True
+116,True
+117,True
+118,True
+119,True
+120,True
+121,True
+122,True
+123,True
+124,True
+125,True
+126,True
+127,True
+128,True
+129,True
+130,True
+131,True
+132,True
+133,True
+134,True
+135,True
+136,True
+137,True
+138,True
+139,True
+140,True
+141,True
+142,True
+143,True
+144,True
+145,True
+146,True
+147,True
+148,True
+149,True
+150,True
+151,True
+152,True
+153,True
+154,True
+155,True
+156,True
+157,True
+158,True
+159,True
+160,True
+161,True
+162,True
+163,True
+164,True
+165,True
+166,True
+167,True
+168,True
+169,True
+170,True
+171,True
+172,True
+173,True
+174,True
+175,True
+176,True
+177,True
+178,True
+179,True
+180,True
+181,True
+182,True
+183,True
+184,True
+185,True
+186,True
+187,True
+188,True
+189,True
+190,True
+191,True
+192,True
+193,True
+194,True
+195,True
+196,True
+197,True
+198,True
+199,True
+200,True
+201,True
+202,True
+203,True
+204,True
+205,True
+206,True
+207,True
+208,True
+209,True
+210,True
+211,True
+212,True
+213,True
+214,True
+215,True
+216,True
+217,True
+218,True
+219,False
+220,True
+221,True
+222,True
+223,True
+224,True
+225,True
+226,True
+227,True
+228,True
+229,True
+230,True
+231,True
+232,True
+233,True
+234,True
+235,True
+236,True
+237,True
+238,True
+239,True
+240,True
+241,True
+242,True
+243,True
+244,True
+245,True
+246,True
+247,True
+248,True
+249,True
+250,True
+251,True
+252,True
+253,True
+254,True
+255,True
+256,True
+257,True
+258,True
+259,True
+260,True
+261,True
+262,True
+263,True
+264,True
+265,True
+266,True
+267,True
+268,True
+269,True
+270,True
+271,True
+272,True
+273,True
+274,True
+275,True
+276,True
+277,True
+278,True
+279,True
+280,True
+281,True
+282,True
+283,True
+284,True
+285,True
+286,True
+287,True
+288,True
+289,True
+290,True
+291,True
+292,True
+293,True
+294,True
+295,True
+296,False
+297,True
+298,True
+299,True
+300,True
+301,True
+302,True
+303,True
+304,True
+305,True
+306,True
+307,True
+308,True
+309,True
+310,True
+311,True
+312,True
+313,True
+314,True
+315,True
+316,True
+317,True
+318,True
+319,True
+320,True
+321,True
+322,True
+323,True
+324,True
+325,True
+326,True
+327,True
+328,True
+329,True
+330,True
+331,True
+332,True
+333,True
+334,True
+335,True
+336,True
+337,True
+338,True
+339,True
+340,True
+341,True
+342,True
+343,True
+344,True
+345,True
+346,True
+347,True
+348,True
+349,True
+350,True
+351,True
+352,True
+353,True
+354,True
+355,True
+356,True
+357,True
+358,True
+359,True
+360,True
+361,True
+362,True
+363,True
+364,True
+365,True
+366,True
+367,True
+368,True
+369,True
+370,True
+371,True
+372,True
+373,True
+374,True
+375,True
+376,True
+377,True
+378,True
+379,False
+380,False
+381,False
+382,False
+383,False
+384,False
+385,False
+386,False
+387,False
+388,False
+389,False
+390,False
+391,False
+392,False
+393,False
+394,False
+395,False
+396,False
+397,False
+398,False
+399,False
+400,False
+401,False
+402,True
+403,False
+404,False
+405,False
+406,False
+407,False
+408,False
+409,False
+410,False
+411,True
+412,False
+413,False
+414,False
+415,False
+416,False
+417,False
+418,False
+419,False
+420,True
+421,False
+422,False
+423,False
+424,False
+425,False
+426,False
+427,False
+428,False
+429,False
+430,False
+431,False
+432,False
+433,False
+434,False
+435,False
+436,False
+437,False
+438,False
+439,False
+440,False
+441,False
+442,False
+443,False
+444,False
+445,False
+446,False
+447,False
+448,False
+449,False
+450,False
+451,False
+452,False
+453,False
+454,False
+455,False
+456,False
+457,False
+458,False
+459,False
+460,False
+461,False
+462,False
+463,False
+464,False
+465,False
+466,False
+467,False
+468,False
+469,False
+470,True
+471,False
+472,False
+473,False
+474,False
+475,False
+476,False
+477,False
+478,False
+479,False
+480,False
+481,False
+482,False
+483,False
+484,False
+485,False
+486,False
+487,False
+488,False
+489,False
+490,False
+491,False
+492,False
+493,False
+494,False
+495,False
+496,False
+497,False
+498,False
+499,False
+500,False
+501,False
+502,False
+503,False
+504,False
+505,False
+506,False
+507,False
+508,False
+509,False
+510,False
+511,False
+512,False
+513,False
+514,False
+515,False
+516,False
+517,False
+518,False
+519,False
+520,False
+521,False
+522,False
+523,False
+524,False
+525,False
+526,False
+527,False
+528,False
+529,False
+530,False
+531,False
+532,False
+533,False
+534,False
+535,False
+536,False
+537,False
+538,False
+539,False
+540,False
+541,False
+542,False
+543,True
+544,False
+545,False
+546,False
+547,False
+548,False
+549,False
+550,False
+551,False
+552,False
+553,False
+554,False
+555,False
+556,False
+557,True
+558,False
+559,False
+560,False
+561,False
+562,False
+563,False
+564,False
+565,False
+566,False
+567,False
+568,False
+569,False
+570,False
+571,False
+572,False
+573,False
+574,False
+575,False
+576,False
+577,False
+578,False
+579,False
+580,False
+581,False
+582,False
+583,False
+584,False
+585,False
+586,False
+587,True
+588,False
+589,False
+590,False
+591,False
+592,False
+593,False
+594,False
+595,True
+596,False
+597,False
+598,False
+599,False
+600,False
+601,False
+602,False
+603,False
+604,False
+605,False
+606,False
+607,False
+608,False
+609,False
+610,False
+611,False
+612,False
+613,False
+614,False
+615,False
+616,False
+617,False
+618,False
+619,False
+620,False
+621,False
+622,False
+623,False
+624,False
+625,False
+626,False
+627,False
+628,False
+629,False
+630,False
+631,False
+632,False
+633,True
+634,True
+635,False
+636,True
+637,True
+638,False
+639,False
+640,False
+641,False
+642,False
+643,False
+644,False
+645,False
+646,False
+647,True
+648,False
+649,False
+650,False
+651,False
+652,False
+653,False
+654,False
+655,False
+656,True
+657,False
+658,False
+659,False
+660,False
+661,False
+662,False
+663,False
+664,False
+665,False
+666,False
+667,False
+668,False
+669,False
+670,True
+671,False
+672,False
+673,True
+674,False
+675,False
+676,False
+677,False
+678,False
+679,False
+680,False
+681,False
+682,False
+683,False
+684,False
+685,False
+686,True
+687,False
+688,False
+689,False
+690,False
+691,False
+692,False
+693,False
+694,False
+695,False
+696,False
+697,False
+698,False
+699,False
+700,False
+701,False
+702,False
+703,False
+704,False
+705,False
+706,False
+707,False
+708,False
+709,False
+710,False
+711,False
+712,False
+713,False
+714,False
+715,False
+716,False
+717,False
+718,False
+719,False
+720,False
+721,False
+722,False
+723,False
+724,False
+725,False
+726,False
+727,False
+728,False
+729,False
+730,False
+731,False
+732,False
+733,False
+734,False
+735,False
+736,False
+737,False
+738,False
+739,False
+740,False
+741,True
+742,False
+743,True
+744,False
+745,True
+746,False
+747,False
+748,False
+749,False
+750,False
+751,False
+752,False
+753,False
+754,False
+755,False
+756,False
+757,False
diff --git a/Assignment Colab/Amber11_csv b/Assignment Colab/Amber11_csv
new file mode 100644
index 0000000..c254388
--- /dev/null
+++ b/Assignment Colab/Amber11_csv	
@@ -0,0 +1,759 @@
+Index,CLASS
+0,True
+1,True
+2,True
+3,True
+4,False
+5,True
+6,True
+7,True
+8,True
+9,True
+10,True
+11,True
+12,True
+13,True
+14,False
+15,True
+16,True
+17,True
+18,True
+19,True
+20,True
+21,True
+22,True
+23,True
+24,False
+25,True
+26,True
+27,True
+28,True
+29,False
+30,True
+31,True
+32,False
+33,True
+34,True
+35,True
+36,True
+37,True
+38,True
+39,True
+40,True
+41,True
+42,True
+43,True
+44,False
+45,False
+46,True
+47,True
+48,False
+49,True
+50,True
+51,True
+52,False
+53,True
+54,True
+55,True
+56,True
+57,True
+58,True
+59,True
+60,True
+61,True
+62,True
+63,True
+64,True
+65,True
+66,True
+67,True
+68,True
+69,True
+70,True
+71,True
+72,True
+73,True
+74,True
+75,True
+76,True
+77,True
+78,True
+79,True
+80,True
+81,True
+82,True
+83,True
+84,True
+85,True
+86,False
+87,True
+88,True
+89,True
+90,True
+91,True
+92,True
+93,True
+94,True
+95,False
+96,False
+97,True
+98,True
+99,True
+100,True
+101,True
+102,True
+103,True
+104,True
+105,True
+106,True
+107,True
+108,True
+109,True
+110,True
+111,True
+112,True
+113,True
+114,True
+115,True
+116,True
+117,True
+118,True
+119,True
+120,True
+121,True
+122,True
+123,True
+124,True
+125,True
+126,True
+127,True
+128,True
+129,True
+130,True
+131,True
+132,True
+133,True
+134,True
+135,True
+136,True
+137,True
+138,True
+139,True
+140,True
+141,True
+142,True
+143,True
+144,True
+145,True
+146,True
+147,True
+148,True
+149,True
+150,True
+151,True
+152,True
+153,True
+154,True
+155,True
+156,True
+157,True
+158,True
+159,True
+160,True
+161,True
+162,True
+163,True
+164,True
+165,True
+166,True
+167,True
+168,True
+169,True
+170,True
+171,True
+172,True
+173,True
+174,True
+175,True
+176,True
+177,True
+178,True
+179,True
+180,True
+181,True
+182,True
+183,True
+184,True
+185,True
+186,True
+187,True
+188,True
+189,True
+190,True
+191,True
+192,True
+193,True
+194,True
+195,True
+196,True
+197,True
+198,True
+199,True
+200,True
+201,True
+202,True
+203,True
+204,True
+205,True
+206,True
+207,True
+208,True
+209,True
+210,True
+211,True
+212,True
+213,True
+214,True
+215,True
+216,True
+217,True
+218,True
+219,True
+220,True
+221,True
+222,True
+223,True
+224,True
+225,True
+226,True
+227,True
+228,True
+229,True
+230,True
+231,True
+232,True
+233,True
+234,True
+235,True
+236,True
+237,True
+238,True
+239,True
+240,True
+241,True
+242,True
+243,True
+244,True
+245,True
+246,True
+247,True
+248,True
+249,True
+250,True
+251,True
+252,True
+253,True
+254,True
+255,True
+256,True
+257,True
+258,True
+259,True
+260,True
+261,True
+262,True
+263,True
+264,True
+265,True
+266,True
+267,True
+268,True
+269,True
+270,True
+271,True
+272,True
+273,True
+274,True
+275,True
+276,True
+277,True
+278,True
+279,True
+280,True
+281,True
+282,True
+283,True
+284,True
+285,True
+286,True
+287,True
+288,True
+289,True
+290,True
+291,True
+292,True
+293,True
+294,True
+295,True
+296,True
+297,True
+298,True
+299,True
+300,True
+301,True
+302,True
+303,True
+304,True
+305,True
+306,True
+307,True
+308,True
+309,True
+310,True
+311,True
+312,True
+313,True
+314,True
+315,True
+316,True
+317,True
+318,True
+319,True
+320,True
+321,True
+322,True
+323,True
+324,True
+325,True
+326,True
+327,True
+328,True
+329,True
+330,True
+331,True
+332,True
+333,True
+334,True
+335,True
+336,True
+337,True
+338,True
+339,True
+340,True
+341,True
+342,True
+343,True
+344,True
+345,True
+346,True
+347,True
+348,True
+349,True
+350,True
+351,True
+352,True
+353,True
+354,True
+355,True
+356,True
+357,True
+358,True
+359,True
+360,True
+361,True
+362,True
+363,True
+364,True
+365,True
+366,True
+367,True
+368,True
+369,True
+370,True
+371,True
+372,True
+373,True
+374,True
+375,True
+376,True
+377,True
+378,True
+379,False
+380,False
+381,False
+382,False
+383,False
+384,False
+385,False
+386,False
+387,False
+388,False
+389,False
+390,False
+391,False
+392,False
+393,False
+394,False
+395,False
+396,False
+397,False
+398,False
+399,False
+400,False
+401,False
+402,False
+403,False
+404,False
+405,False
+406,False
+407,False
+408,False
+409,False
+410,False
+411,True
+412,False
+413,False
+414,False
+415,False
+416,False
+417,False
+418,False
+419,False
+420,False
+421,False
+422,False
+423,False
+424,False
+425,False
+426,False
+427,False
+428,False
+429,False
+430,False
+431,False
+432,False
+433,False
+434,False
+435,False
+436,False
+437,False
+438,False
+439,False
+440,False
+441,False
+442,False
+443,False
+444,False
+445,False
+446,False
+447,False
+448,False
+449,False
+450,False
+451,False
+452,False
+453,False
+454,False
+455,False
+456,False
+457,False
+458,False
+459,False
+460,False
+461,False
+462,False
+463,False
+464,False
+465,False
+466,False
+467,False
+468,False
+469,False
+470,True
+471,True
+472,False
+473,False
+474,False
+475,False
+476,False
+477,False
+478,False
+479,False
+480,False
+481,True
+482,False
+483,False
+484,False
+485,False
+486,False
+487,False
+488,False
+489,False
+490,False
+491,False
+492,False
+493,False
+494,False
+495,True
+496,False
+497,False
+498,False
+499,False
+500,False
+501,False
+502,False
+503,False
+504,False
+505,False
+506,False
+507,False
+508,False
+509,False
+510,False
+511,False
+512,False
+513,False
+514,False
+515,False
+516,False
+517,False
+518,False
+519,False
+520,False
+521,False
+522,False
+523,False
+524,False
+525,False
+526,False
+527,False
+528,False
+529,False
+530,False
+531,False
+532,False
+533,True
+534,False
+535,False
+536,False
+537,False
+538,False
+539,False
+540,False
+541,False
+542,False
+543,True
+544,False
+545,False
+546,False
+547,False
+548,False
+549,False
+550,True
+551,False
+552,False
+553,False
+554,True
+555,True
+556,False
+557,True
+558,False
+559,True
+560,False
+561,False
+562,True
+563,False
+564,False
+565,False
+566,False
+567,False
+568,False
+569,False
+570,False
+571,False
+572,False
+573,False
+574,False
+575,False
+576,False
+577,True
+578,False
+579,False
+580,False
+581,False
+582,False
+583,False
+584,False
+585,False
+586,False
+587,True
+588,False
+589,False
+590,False
+591,True
+592,False
+593,False
+594,False
+595,True
+596,False
+597,False
+598,False
+599,False
+600,False
+601,True
+602,False
+603,False
+604,False
+605,False
+606,False
+607,False
+608,True
+609,False
+610,False
+611,False
+612,False
+613,False
+614,False
+615,False
+616,False
+617,False
+618,False
+619,False
+620,False
+621,False
+622,False
+623,False
+624,False
+625,False
+626,False
+627,False
+628,False
+629,False
+630,False
+631,False
+632,False
+633,True
+634,True
+635,False
+636,True
+637,True
+638,True
+639,False
+640,False
+641,False
+642,False
+643,False
+644,False
+645,False
+646,False
+647,True
+648,False
+649,True
+650,False
+651,False
+652,False
+653,True
+654,False
+655,False
+656,True
+657,False
+658,True
+659,False
+660,False
+661,False
+662,False
+663,False
+664,False
+665,False
+666,False
+667,False
+668,True
+669,False
+670,True
+671,False
+672,False
+673,True
+674,False
+675,False
+676,False
+677,True
+678,False
+679,False
+680,False
+681,False
+682,False
+683,False
+684,False
+685,False
+686,True
+687,True
+688,False
+689,False
+690,False
+691,False
+692,False
+693,False
+694,False
+695,False
+696,False
+697,False
+698,False
+699,False
+700,False
+701,False
+702,False
+703,False
+704,False
+705,True
+706,True
+707,True
+708,False
+709,False
+710,False
+711,False
+712,False
+713,False
+714,False
+715,False
+716,True
+717,True
+718,True
+719,True
+720,False
+721,True
+722,False
+723,False
+724,False
+725,False
+726,False
+727,False
+728,False
+729,False
+730,False
+731,False
+732,True
+733,False
+734,True
+735,False
+736,False
+737,False
+738,False
+739,False
+740,True
+741,True
+742,False
+743,True
+744,True
+745,True
+746,False
+747,False
+748,False
+749,False
+750,True
+751,False
+752,False
+753,False
+754,False
+755,False
+756,True
+757,False
diff --git a/Assignment Colab/Amber1_csv b/Assignment Colab/Amber1_csv
new file mode 100644
index 0000000..3708ebe
--- /dev/null
+++ b/Assignment Colab/Amber1_csv	
@@ -0,0 +1,759 @@
+Index,CLASS
+0,False
+1,False
+2,False
+3,False
+4,False
+5,False
+6,False
+7,False
+8,False
+9,False
+10,False
+11,False
+12,False
+13,False
+14,False
+15,False
+16,False
+17,False
+18,False
+19,False
+20,False
+21,False
+22,False
+23,False
+24,False
+25,False
+26,False
+27,False
+28,False
+29,False
+30,False
+31,False
+32,False
+33,False
+34,False
+35,False
+36,False
+37,False
+38,False
+39,False
+40,False
+41,False
+42,False
+43,False
+44,False
+45,False
+46,False
+47,False
+48,False
+49,False
+50,False
+51,False
+52,False
+53,False
+54,False
+55,False
+56,False
+57,False
+58,False
+59,False
+60,False
+61,False
+62,False
+63,False
+64,False
+65,False
+66,False
+67,False
+68,False
+69,False
+70,False
+71,False
+72,False
+73,False
+74,False
+75,False
+76,False
+77,False
+78,False
+79,False
+80,False
+81,False
+82,False
+83,False
+84,False
+85,False
+86,False
+87,False
+88,False
+89,False
+90,False
+91,False
+92,False
+93,False
+94,False
+95,False
+96,False
+97,False
+98,False
+99,False
+100,False
+101,False
+102,False
+103,False
+104,False
+105,False
+106,False
+107,False
+108,False
+109,False
+110,False
+111,False
+112,False
+113,False
+114,False
+115,False
+116,False
+117,False
+118,False
+119,False
+120,False
+121,False
+122,False
+123,False
+124,False
+125,False
+126,False
+127,False
+128,False
+129,False
+130,False
+131,False
+132,False
+133,False
+134,False
+135,False
+136,False
+137,False
+138,False
+139,False
+140,False
+141,False
+142,False
+143,False
+144,False
+145,False
+146,False
+147,False
+148,False
+149,False
+150,False
+151,False
+152,False
+153,False
+154,False
+155,False
+156,False
+157,False
+158,False
+159,False
+160,False
+161,False
+162,False
+163,False
+164,False
+165,False
+166,False
+167,False
+168,False
+169,False
+170,False
+171,False
+172,False
+173,False
+174,False
+175,False
+176,False
+177,False
+178,False
+179,False
+180,False
+181,False
+182,False
+183,False
+184,False
+185,False
+186,False
+187,False
+188,False
+189,False
+190,False
+191,False
+192,False
+193,False
+194,False
+195,True
+196,False
+197,False
+198,False
+199,False
+200,False
+201,False
+202,True
+203,False
+204,False
+205,False
+206,False
+207,False
+208,False
+209,False
+210,False
+211,False
+212,False
+213,False
+214,False
+215,False
+216,False
+217,False
+218,False
+219,False
+220,False
+221,False
+222,False
+223,False
+224,False
+225,False
+226,False
+227,False
+228,False
+229,False
+230,False
+231,False
+232,True
+233,False
+234,False
+235,False
+236,False
+237,False
+238,False
+239,False
+240,False
+241,False
+242,False
+243,False
+244,False
+245,False
+246,False
+247,True
+248,False
+249,False
+250,False
+251,False
+252,False
+253,False
+254,False
+255,False
+256,True
+257,False
+258,False
+259,False
+260,False
+261,False
+262,False
+263,False
+264,False
+265,True
+266,False
+267,False
+268,False
+269,True
+270,False
+271,False
+272,False
+273,False
+274,False
+275,False
+276,True
+277,False
+278,False
+279,False
+280,False
+281,False
+282,False
+283,False
+284,False
+285,False
+286,False
+287,False
+288,False
+289,False
+290,False
+291,False
+292,False
+293,False
+294,False
+295,False
+296,False
+297,False
+298,False
+299,False
+300,False
+301,False
+302,False
+303,False
+304,False
+305,False
+306,False
+307,False
+308,False
+309,False
+310,False
+311,False
+312,True
+313,False
+314,False
+315,False
+316,False
+317,False
+318,False
+319,False
+320,False
+321,False
+322,False
+323,False
+324,False
+325,False
+326,False
+327,False
+328,False
+329,False
+330,False
+331,False
+332,False
+333,False
+334,False
+335,False
+336,False
+337,False
+338,False
+339,False
+340,False
+341,False
+342,False
+343,False
+344,False
+345,False
+346,True
+347,False
+348,False
+349,False
+350,True
+351,False
+352,False
+353,False
+354,False
+355,False
+356,False
+357,False
+358,False
+359,False
+360,False
+361,False
+362,False
+363,False
+364,False
+365,False
+366,False
+367,False
+368,False
+369,False
+370,True
+371,False
+372,False
+373,False
+374,False
+375,False
+376,False
+377,False
+378,False
+379,False
+380,False
+381,False
+382,False
+383,False
+384,False
+385,False
+386,False
+387,False
+388,False
+389,False
+390,False
+391,False
+392,False
+393,False
+394,False
+395,False
+396,False
+397,False
+398,False
+399,False
+400,False
+401,False
+402,False
+403,False
+404,False
+405,False
+406,False
+407,False
+408,False
+409,False
+410,False
+411,False
+412,False
+413,False
+414,False
+415,False
+416,False
+417,False
+418,False
+419,False
+420,False
+421,False
+422,False
+423,False
+424,False
+425,False
+426,False
+427,False
+428,False
+429,False
+430,False
+431,False
+432,False
+433,False
+434,False
+435,False
+436,False
+437,False
+438,False
+439,False
+440,False
+441,False
+442,False
+443,False
+444,False
+445,False
+446,False
+447,False
+448,False
+449,False
+450,False
+451,False
+452,False
+453,False
+454,False
+455,False
+456,False
+457,False
+458,False
+459,False
+460,False
+461,False
+462,False
+463,False
+464,False
+465,False
+466,False
+467,False
+468,False
+469,False
+470,False
+471,False
+472,False
+473,False
+474,False
+475,False
+476,False
+477,False
+478,False
+479,False
+480,False
+481,False
+482,False
+483,False
+484,False
+485,False
+486,False
+487,False
+488,False
+489,False
+490,False
+491,False
+492,False
+493,False
+494,False
+495,False
+496,False
+497,False
+498,False
+499,False
+500,False
+501,False
+502,False
+503,False
+504,False
+505,False
+506,False
+507,False
+508,False
+509,False
+510,False
+511,False
+512,False
+513,False
+514,False
+515,False
+516,False
+517,False
+518,False
+519,False
+520,False
+521,False
+522,False
+523,False
+524,False
+525,False
+526,False
+527,False
+528,False
+529,False
+530,False
+531,False
+532,False
+533,False
+534,False
+535,False
+536,False
+537,False
+538,False
+539,False
+540,False
+541,False
+542,False
+543,False
+544,False
+545,False
+546,False
+547,False
+548,False
+549,False
+550,False
+551,False
+552,False
+553,False
+554,False
+555,False
+556,False
+557,False
+558,False
+559,False
+560,False
+561,False
+562,False
+563,False
+564,False
+565,False
+566,False
+567,False
+568,False
+569,False
+570,False
+571,False
+572,False
+573,False
+574,False
+575,False
+576,False
+577,False
+578,False
+579,False
+580,False
+581,False
+582,False
+583,False
+584,False
+585,False
+586,False
+587,False
+588,False
+589,False
+590,False
+591,False
+592,False
+593,False
+594,False
+595,False
+596,False
+597,False
+598,False
+599,False
+600,False
+601,False
+602,False
+603,False
+604,False
+605,False
+606,False
+607,False
+608,False
+609,False
+610,False
+611,False
+612,False
+613,False
+614,False
+615,False
+616,False
+617,False
+618,False
+619,False
+620,False
+621,False
+622,False
+623,False
+624,False
+625,False
+626,False
+627,False
+628,False
+629,False
+630,False
+631,False
+632,False
+633,False
+634,False
+635,False
+636,False
+637,False
+638,False
+639,False
+640,False
+641,False
+642,False
+643,False
+644,False
+645,False
+646,False
+647,False
+648,False
+649,False
+650,False
+651,False
+652,False
+653,False
+654,False
+655,False
+656,False
+657,False
+658,False
+659,False
+660,False
+661,False
+662,False
+663,False
+664,False
+665,False
+666,False
+667,False
+668,False
+669,False
+670,False
+671,False
+672,False
+673,False
+674,False
+675,False
+676,False
+677,False
+678,False
+679,False
+680,False
+681,False
+682,False
+683,False
+684,False
+685,False
+686,False
+687,False
+688,False
+689,False
+690,False
+691,False
+692,False
+693,False
+694,False
+695,False
+696,False
+697,False
+698,False
+699,False
+700,False
+701,False
+702,False
+703,False
+704,False
+705,False
+706,False
+707,False
+708,False
+709,False
+710,False
+711,False
+712,False
+713,False
+714,False
+715,False
+716,False
+717,False
+718,False
+719,False
+720,False
+721,False
+722,False
+723,False
+724,False
+725,False
+726,False
+727,False
+728,False
+729,False
+730,False
+731,False
+732,False
+733,False
+734,False
+735,False
+736,False
+737,False
+738,False
+739,False
+740,False
+741,False
+742,False
+743,False
+744,False
+745,False
+746,False
+747,False
+748,False
+749,False
+750,False
+751,False
+752,False
+753,False
+754,False
+755,False
+756,False
+757,False
diff --git a/Assignment Colab/Amber2_csv b/Assignment Colab/Amber2_csv
new file mode 100644
index 0000000..2907729
--- /dev/null
+++ b/Assignment Colab/Amber2_csv	
@@ -0,0 +1,759 @@
+Index,CLASS
+0,False
+1,False
+2,True
+3,True
+4,False
+5,True
+6,True
+7,False
+8,True
+9,True
+10,True
+11,True
+12,False
+13,False
+14,False
+15,True
+16,False
+17,True
+18,False
+19,True
+20,False
+21,True
+22,True
+23,True
+24,False
+25,True
+26,True
+27,True
+28,True
+29,False
+30,True
+31,True
+32,False
+33,True
+34,False
+35,False
+36,True
+37,True
+38,True
+39,True
+40,True
+41,True
+42,False
+43,True
+44,False
+45,False
+46,True
+47,True
+48,False
+49,True
+50,True
+51,False
+52,False
+53,True
+54,True
+55,True
+56,True
+57,True
+58,True
+59,True
+60,True
+61,False
+62,True
+63,True
+64,True
+65,True
+66,True
+67,True
+68,True
+69,True
+70,True
+71,True
+72,True
+73,True
+74,True
+75,True
+76,True
+77,True
+78,True
+79,True
+80,True
+81,True
+82,True
+83,True
+84,True
+85,False
+86,False
+87,True
+88,True
+89,True
+90,False
+91,True
+92,True
+93,True
+94,True
+95,False
+96,False
+97,True
+98,True
+99,True
+100,False
+101,True
+102,True
+103,True
+104,True
+105,True
+106,True
+107,True
+108,True
+109,True
+110,True
+111,True
+112,True
+113,True
+114,True
+115,True
+116,True
+117,True
+118,True
+119,True
+120,True
+121,True
+122,True
+123,True
+124,True
+125,True
+126,True
+127,True
+128,True
+129,True
+130,True
+131,True
+132,False
+133,True
+134,True
+135,True
+136,True
+137,True
+138,True
+139,True
+140,True
+141,True
+142,True
+143,True
+144,True
+145,True
+146,True
+147,True
+148,True
+149,True
+150,True
+151,True
+152,False
+153,True
+154,True
+155,True
+156,True
+157,True
+158,True
+159,True
+160,True
+161,False
+162,True
+163,True
+164,True
+165,True
+166,True
+167,True
+168,True
+169,True
+170,True
+171,True
+172,True
+173,True
+174,True
+175,True
+176,True
+177,True
+178,True
+179,True
+180,True
+181,True
+182,True
+183,True
+184,True
+185,True
+186,True
+187,True
+188,True
+189,True
+190,True
+191,True
+192,True
+193,True
+194,True
+195,True
+196,True
+197,True
+198,False
+199,True
+200,True
+201,True
+202,True
+203,True
+204,True
+205,True
+206,True
+207,True
+208,True
+209,True
+210,True
+211,True
+212,True
+213,True
+214,True
+215,True
+216,True
+217,True
+218,True
+219,False
+220,True
+221,True
+222,True
+223,True
+224,True
+225,True
+226,True
+227,True
+228,True
+229,True
+230,True
+231,True
+232,True
+233,True
+234,True
+235,True
+236,True
+237,True
+238,True
+239,True
+240,True
+241,True
+242,True
+243,True
+244,True
+245,True
+246,True
+247,True
+248,True
+249,True
+250,True
+251,True
+252,True
+253,True
+254,True
+255,True
+256,True
+257,True
+258,True
+259,False
+260,True
+261,True
+262,True
+263,True
+264,True
+265,True
+266,True
+267,True
+268,True
+269,True
+270,True
+271,True
+272,True
+273,False
+274,True
+275,True
+276,True
+277,True
+278,True
+279,True
+280,True
+281,True
+282,True
+283,True
+284,True
+285,True
+286,True
+287,True
+288,True
+289,True
+290,True
+291,True
+292,True
+293,True
+294,True
+295,True
+296,False
+297,True
+298,True
+299,True
+300,True
+301,True
+302,True
+303,True
+304,True
+305,True
+306,True
+307,True
+308,True
+309,True
+310,True
+311,True
+312,True
+313,True
+314,True
+315,True
+316,True
+317,True
+318,True
+319,True
+320,True
+321,True
+322,True
+323,True
+324,True
+325,True
+326,True
+327,True
+328,True
+329,True
+330,True
+331,True
+332,True
+333,True
+334,True
+335,True
+336,True
+337,True
+338,True
+339,True
+340,True
+341,True
+342,True
+343,True
+344,True
+345,True
+346,True
+347,True
+348,True
+349,True
+350,True
+351,True
+352,True
+353,True
+354,True
+355,True
+356,True
+357,True
+358,True
+359,True
+360,True
+361,True
+362,True
+363,True
+364,True
+365,True
+366,True
+367,True
+368,True
+369,True
+370,True
+371,True
+372,True
+373,True
+374,True
+375,True
+376,True
+377,True
+378,True
+379,False
+380,False
+381,False
+382,False
+383,False
+384,False
+385,False
+386,False
+387,False
+388,False
+389,False
+390,False
+391,False
+392,False
+393,False
+394,False
+395,False
+396,False
+397,False
+398,False
+399,False
+400,False
+401,False
+402,False
+403,False
+404,False
+405,False
+406,False
+407,False
+408,False
+409,False
+410,False
+411,False
+412,False
+413,False
+414,False
+415,False
+416,False
+417,False
+418,False
+419,False
+420,False
+421,False
+422,False
+423,False
+424,False
+425,False
+426,False
+427,False
+428,False
+429,False
+430,False
+431,False
+432,False
+433,False
+434,False
+435,False
+436,False
+437,False
+438,False
+439,False
+440,False
+441,False
+442,False
+443,False
+444,False
+445,False
+446,False
+447,False
+448,False
+449,False
+450,False
+451,False
+452,False
+453,False
+454,False
+455,False
+456,False
+457,False
+458,False
+459,False
+460,False
+461,False
+462,False
+463,False
+464,False
+465,False
+466,False
+467,False
+468,False
+469,False
+470,False
+471,False
+472,False
+473,False
+474,False
+475,False
+476,False
+477,False
+478,False
+479,False
+480,False
+481,False
+482,False
+483,False
+484,False
+485,False
+486,False
+487,False
+488,False
+489,False
+490,False
+491,False
+492,False
+493,False
+494,False
+495,False
+496,False
+497,False
+498,False
+499,False
+500,False
+501,False
+502,False
+503,False
+504,False
+505,False
+506,False
+507,False
+508,False
+509,False
+510,False
+511,False
+512,False
+513,False
+514,False
+515,False
+516,False
+517,False
+518,False
+519,False
+520,False
+521,False
+522,False
+523,False
+524,False
+525,False
+526,False
+527,False
+528,False
+529,False
+530,False
+531,False
+532,False
+533,False
+534,False
+535,False
+536,False
+537,False
+538,False
+539,False
+540,False
+541,False
+542,False
+543,True
+544,False
+545,False
+546,False
+547,False
+548,False
+549,False
+550,False
+551,False
+552,False
+553,False
+554,False
+555,True
+556,False
+557,True
+558,False
+559,False
+560,False
+561,False
+562,False
+563,False
+564,False
+565,False
+566,False
+567,False
+568,False
+569,False
+570,False
+571,False
+572,False
+573,False
+574,False
+575,False
+576,False
+577,False
+578,False
+579,False
+580,False
+581,False
+582,False
+583,False
+584,False
+585,False
+586,False
+587,True
+588,False
+589,False
+590,False
+591,False
+592,False
+593,False
+594,False
+595,True
+596,False
+597,False
+598,False
+599,False
+600,False
+601,False
+602,False
+603,False
+604,False
+605,False
+606,False
+607,False
+608,True
+609,False
+610,False
+611,False
+612,False
+613,False
+614,False
+615,False
+616,False
+617,False
+618,False
+619,False
+620,False
+621,False
+622,False
+623,False
+624,False
+625,False
+626,False
+627,False
+628,False
+629,False
+630,False
+631,False
+632,False
+633,False
+634,True
+635,False
+636,True
+637,True
+638,False
+639,False
+640,False
+641,False
+642,False
+643,False
+644,False
+645,False
+646,False
+647,True
+648,False
+649,True
+650,False
+651,False
+652,False
+653,True
+654,False
+655,False
+656,True
+657,False
+658,True
+659,False
+660,False
+661,False
+662,False
+663,False
+664,False
+665,False
+666,False
+667,False
+668,True
+669,False
+670,True
+671,False
+672,False
+673,True
+674,False
+675,False
+676,False
+677,True
+678,False
+679,False
+680,False
+681,False
+682,False
+683,False
+684,False
+685,False
+686,True
+687,True
+688,False
+689,False
+690,False
+691,False
+692,False
+693,False
+694,False
+695,False
+696,False
+697,False
+698,False
+699,False
+700,False
+701,False
+702,False
+703,False
+704,False
+705,False
+706,True
+707,True
+708,False
+709,False
+710,False
+711,False
+712,False
+713,False
+714,False
+715,False
+716,True
+717,True
+718,True
+719,True
+720,False
+721,False
+722,False
+723,False
+724,False
+725,False
+726,False
+727,False
+728,False
+729,False
+730,False
+731,False
+732,False
+733,True
+734,False
+735,False
+736,False
+737,True
+738,False
+739,False
+740,True
+741,True
+742,False
+743,True
+744,False
+745,True
+746,False
+747,False
+748,False
+749,False
+750,False
+751,False
+752,False
+753,False
+754,False
+755,False
+756,False
+757,False
diff --git a/Assignment Colab/Amber3_csv b/Assignment Colab/Amber3_csv
new file mode 100644
index 0000000..04dda38
--- /dev/null
+++ b/Assignment Colab/Amber3_csv	
@@ -0,0 +1,759 @@
+Index,CLASS
+0,False
+1,False
+2,True
+3,True
+4,False
+5,True
+6,True
+7,False
+8,True
+9,True
+10,False
+11,True
+12,False
+13,False
+14,False
+15,True
+16,False
+17,True
+18,False
+19,True
+20,False
+21,True
+22,True
+23,True
+24,False
+25,True
+26,True
+27,True
+28,True
+29,False
+30,True
+31,True
+32,False
+33,True
+34,False
+35,False
+36,True
+37,True
+38,True
+39,True
+40,True
+41,True
+42,False
+43,True
+44,False
+45,False
+46,True
+47,True
+48,False
+49,True
+50,True
+51,False
+52,False
+53,True
+54,True
+55,True
+56,True
+57,True
+58,True
+59,True
+60,True
+61,False
+62,True
+63,True
+64,True
+65,True
+66,True
+67,True
+68,True
+69,True
+70,True
+71,True
+72,False
+73,True
+74,True
+75,True
+76,False
+77,True
+78,True
+79,True
+80,True
+81,True
+82,True
+83,True
+84,True
+85,False
+86,False
+87,True
+88,True
+89,True
+90,False
+91,True
+92,True
+93,True
+94,True
+95,False
+96,False
+97,True
+98,True
+99,True
+100,False
+101,True
+102,True
+103,True
+104,True
+105,True
+106,True
+107,True
+108,True
+109,True
+110,True
+111,True
+112,True
+113,True
+114,True
+115,True
+116,True
+117,True
+118,True
+119,True
+120,True
+121,True
+122,True
+123,True
+124,True
+125,True
+126,True
+127,True
+128,True
+129,True
+130,True
+131,True
+132,False
+133,True
+134,True
+135,True
+136,True
+137,True
+138,True
+139,True
+140,True
+141,True
+142,True
+143,True
+144,True
+145,True
+146,True
+147,True
+148,True
+149,True
+150,True
+151,True
+152,False
+153,True
+154,True
+155,True
+156,True
+157,True
+158,True
+159,True
+160,True
+161,False
+162,True
+163,True
+164,True
+165,True
+166,True
+167,True
+168,True
+169,True
+170,True
+171,True
+172,True
+173,True
+174,True
+175,True
+176,True
+177,True
+178,True
+179,True
+180,True
+181,True
+182,True
+183,True
+184,True
+185,True
+186,True
+187,True
+188,True
+189,True
+190,True
+191,True
+192,True
+193,True
+194,True
+195,True
+196,True
+197,True
+198,False
+199,True
+200,True
+201,True
+202,True
+203,True
+204,True
+205,True
+206,True
+207,True
+208,True
+209,True
+210,True
+211,True
+212,True
+213,True
+214,True
+215,True
+216,True
+217,True
+218,True
+219,False
+220,True
+221,True
+222,True
+223,True
+224,True
+225,True
+226,True
+227,True
+228,True
+229,True
+230,True
+231,True
+232,True
+233,True
+234,True
+235,True
+236,True
+237,True
+238,True
+239,True
+240,True
+241,True
+242,True
+243,True
+244,True
+245,True
+246,True
+247,True
+248,True
+249,True
+250,True
+251,True
+252,True
+253,True
+254,True
+255,True
+256,True
+257,True
+258,True
+259,False
+260,True
+261,True
+262,True
+263,True
+264,True
+265,True
+266,True
+267,True
+268,True
+269,True
+270,True
+271,True
+272,True
+273,True
+274,True
+275,True
+276,True
+277,True
+278,True
+279,True
+280,True
+281,True
+282,True
+283,True
+284,True
+285,True
+286,True
+287,True
+288,True
+289,True
+290,True
+291,True
+292,True
+293,True
+294,True
+295,True
+296,False
+297,True
+298,True
+299,True
+300,True
+301,True
+302,True
+303,True
+304,True
+305,True
+306,True
+307,True
+308,True
+309,True
+310,True
+311,True
+312,True
+313,True
+314,True
+315,True
+316,True
+317,True
+318,True
+319,True
+320,True
+321,True
+322,True
+323,True
+324,True
+325,True
+326,True
+327,True
+328,True
+329,True
+330,True
+331,True
+332,True
+333,True
+334,True
+335,True
+336,True
+337,True
+338,True
+339,True
+340,True
+341,True
+342,True
+343,True
+344,True
+345,True
+346,True
+347,True
+348,True
+349,True
+350,True
+351,True
+352,True
+353,True
+354,True
+355,True
+356,True
+357,True
+358,True
+359,True
+360,True
+361,True
+362,True
+363,True
+364,True
+365,True
+366,True
+367,True
+368,True
+369,True
+370,True
+371,True
+372,True
+373,True
+374,True
+375,True
+376,True
+377,True
+378,True
+379,False
+380,False
+381,False
+382,False
+383,False
+384,False
+385,False
+386,False
+387,False
+388,False
+389,False
+390,False
+391,False
+392,False
+393,False
+394,False
+395,False
+396,False
+397,False
+398,False
+399,False
+400,False
+401,False
+402,False
+403,False
+404,False
+405,False
+406,False
+407,False
+408,False
+409,False
+410,False
+411,False
+412,False
+413,False
+414,False
+415,False
+416,False
+417,False
+418,False
+419,False
+420,False
+421,False
+422,False
+423,False
+424,False
+425,False
+426,False
+427,False
+428,False
+429,False
+430,False
+431,False
+432,False
+433,False
+434,False
+435,False
+436,False
+437,False
+438,False
+439,False
+440,False
+441,False
+442,False
+443,False
+444,False
+445,False
+446,False
+447,False
+448,False
+449,False
+450,False
+451,False
+452,False
+453,False
+454,False
+455,False
+456,False
+457,False
+458,False
+459,False
+460,False
+461,False
+462,False
+463,False
+464,False
+465,False
+466,False
+467,False
+468,False
+469,False
+470,False
+471,False
+472,False
+473,False
+474,False
+475,False
+476,False
+477,False
+478,False
+479,False
+480,False
+481,False
+482,False
+483,False
+484,False
+485,False
+486,False
+487,False
+488,False
+489,False
+490,False
+491,False
+492,False
+493,False
+494,False
+495,False
+496,False
+497,False
+498,False
+499,False
+500,False
+501,False
+502,False
+503,False
+504,False
+505,False
+506,False
+507,False
+508,False
+509,False
+510,False
+511,False
+512,False
+513,False
+514,False
+515,False
+516,False
+517,False
+518,False
+519,False
+520,False
+521,False
+522,False
+523,False
+524,False
+525,False
+526,False
+527,False
+528,False
+529,False
+530,False
+531,False
+532,False
+533,False
+534,False
+535,False
+536,False
+537,False
+538,False
+539,False
+540,False
+541,False
+542,False
+543,True
+544,False
+545,False
+546,False
+547,False
+548,False
+549,False
+550,False
+551,False
+552,False
+553,False
+554,False
+555,True
+556,False
+557,True
+558,False
+559,False
+560,False
+561,False
+562,False
+563,False
+564,False
+565,False
+566,False
+567,False
+568,False
+569,False
+570,False
+571,False
+572,False
+573,False
+574,False
+575,False
+576,False
+577,False
+578,False
+579,False
+580,False
+581,False
+582,False
+583,False
+584,False
+585,False
+586,False
+587,True
+588,False
+589,False
+590,False
+591,False
+592,False
+593,False
+594,False
+595,True
+596,False
+597,False
+598,False
+599,False
+600,False
+601,False
+602,False
+603,False
+604,False
+605,False
+606,False
+607,False
+608,True
+609,False
+610,False
+611,False
+612,False
+613,False
+614,False
+615,False
+616,False
+617,False
+618,False
+619,False
+620,False
+621,False
+622,False
+623,False
+624,False
+625,False
+626,False
+627,False
+628,False
+629,False
+630,False
+631,False
+632,False
+633,False
+634,True
+635,False
+636,True
+637,True
+638,True
+639,False
+640,False
+641,False
+642,False
+643,False
+644,False
+645,False
+646,False
+647,True
+648,False
+649,True
+650,False
+651,False
+652,False
+653,True
+654,False
+655,False
+656,True
+657,False
+658,True
+659,False
+660,False
+661,False
+662,False
+663,False
+664,False
+665,False
+666,False
+667,False
+668,True
+669,False
+670,True
+671,False
+672,False
+673,True
+674,False
+675,False
+676,False
+677,True
+678,False
+679,False
+680,False
+681,False
+682,False
+683,False
+684,False
+685,False
+686,True
+687,True
+688,False
+689,False
+690,False
+691,False
+692,False
+693,False
+694,False
+695,False
+696,False
+697,False
+698,False
+699,False
+700,False
+701,False
+702,False
+703,False
+704,False
+705,False
+706,True
+707,True
+708,False
+709,False
+710,False
+711,False
+712,False
+713,False
+714,False
+715,False
+716,True
+717,True
+718,True
+719,True
+720,False
+721,True
+722,False
+723,False
+724,False
+725,False
+726,False
+727,False
+728,False
+729,False
+730,False
+731,False
+732,False
+733,True
+734,False
+735,False
+736,False
+737,True
+738,False
+739,False
+740,True
+741,True
+742,False
+743,True
+744,False
+745,True
+746,False
+747,False
+748,False
+749,False
+750,False
+751,False
+752,False
+753,False
+754,False
+755,False
+756,False
+757,False
diff --git a/Assignment Colab/Amber4_csv b/Assignment Colab/Amber4_csv
new file mode 100644
index 0000000..77b9064
--- /dev/null
+++ b/Assignment Colab/Amber4_csv	
@@ -0,0 +1,759 @@
+Index,CLASS
+0,False
+1,True
+2,True
+3,False
+4,False
+5,True
+6,True
+7,False
+8,True
+9,True
+10,False
+11,True
+12,False
+13,False
+14,False
+15,True
+16,False
+17,True
+18,False
+19,True
+20,False
+21,False
+22,True
+23,True
+24,False
+25,True
+26,True
+27,False
+28,True
+29,False
+30,True
+31,True
+32,False
+33,True
+34,False
+35,False
+36,False
+37,True
+38,True
+39,True
+40,True
+41,True
+42,False
+43,True
+44,False
+45,False
+46,True
+47,True
+48,False
+49,True
+50,True
+51,False
+52,False
+53,True
+54,True
+55,True
+56,True
+57,True
+58,True
+59,True
+60,True
+61,False
+62,True
+63,True
+64,True
+65,True
+66,True
+67,True
+68,True
+69,True
+70,True
+71,True
+72,False
+73,True
+74,True
+75,True
+76,True
+77,True
+78,True
+79,True
+80,True
+81,True
+82,True
+83,True
+84,True
+85,False
+86,False
+87,True
+88,True
+89,True
+90,False
+91,True
+92,True
+93,True
+94,True
+95,False
+96,False
+97,True
+98,False
+99,True
+100,False
+101,True
+102,True
+103,True
+104,True
+105,True
+106,True
+107,True
+108,True
+109,False
+110,True
+111,True
+112,True
+113,False
+114,True
+115,True
+116,True
+117,True
+118,True
+119,True
+120,True
+121,True
+122,True
+123,True
+124,True
+125,True
+126,True
+127,True
+128,True
+129,True
+130,True
+131,True
+132,False
+133,True
+134,True
+135,True
+136,True
+137,True
+138,True
+139,True
+140,True
+141,True
+142,True
+143,True
+144,True
+145,True
+146,True
+147,True
+148,True
+149,True
+150,True
+151,True
+152,True
+153,True
+154,True
+155,True
+156,True
+157,True
+158,True
+159,True
+160,True
+161,False
+162,True
+163,True
+164,True
+165,True
+166,True
+167,True
+168,True
+169,True
+170,True
+171,True
+172,True
+173,True
+174,True
+175,True
+176,True
+177,True
+178,True
+179,True
+180,True
+181,True
+182,True
+183,True
+184,True
+185,True
+186,True
+187,True
+188,True
+189,True
+190,True
+191,True
+192,True
+193,True
+194,True
+195,True
+196,True
+197,True
+198,False
+199,True
+200,True
+201,True
+202,True
+203,True
+204,True
+205,True
+206,True
+207,True
+208,True
+209,True
+210,True
+211,True
+212,True
+213,True
+214,True
+215,True
+216,True
+217,True
+218,True
+219,False
+220,True
+221,True
+222,True
+223,True
+224,True
+225,True
+226,True
+227,True
+228,True
+229,True
+230,True
+231,True
+232,True
+233,True
+234,True
+235,True
+236,True
+237,True
+238,True
+239,True
+240,True
+241,True
+242,True
+243,True
+244,True
+245,True
+246,True
+247,True
+248,True
+249,True
+250,True
+251,True
+252,True
+253,True
+254,True
+255,True
+256,True
+257,False
+258,True
+259,False
+260,True
+261,True
+262,True
+263,True
+264,True
+265,True
+266,True
+267,True
+268,True
+269,True
+270,True
+271,True
+272,True
+273,True
+274,True
+275,True
+276,True
+277,True
+278,True
+279,True
+280,True
+281,True
+282,True
+283,True
+284,True
+285,True
+286,True
+287,True
+288,True
+289,True
+290,True
+291,True
+292,True
+293,True
+294,True
+295,True
+296,False
+297,True
+298,True
+299,True
+300,True
+301,True
+302,True
+303,True
+304,True
+305,True
+306,True
+307,True
+308,True
+309,True
+310,True
+311,True
+312,True
+313,True
+314,True
+315,True
+316,True
+317,True
+318,True
+319,True
+320,True
+321,True
+322,True
+323,True
+324,True
+325,True
+326,True
+327,True
+328,True
+329,True
+330,True
+331,True
+332,True
+333,True
+334,True
+335,True
+336,True
+337,True
+338,True
+339,True
+340,True
+341,True
+342,True
+343,True
+344,True
+345,True
+346,True
+347,True
+348,True
+349,True
+350,True
+351,True
+352,True
+353,True
+354,True
+355,True
+356,True
+357,True
+358,True
+359,True
+360,True
+361,True
+362,True
+363,True
+364,True
+365,True
+366,True
+367,True
+368,True
+369,True
+370,True
+371,True
+372,True
+373,True
+374,True
+375,True
+376,True
+377,True
+378,True
+379,False
+380,False
+381,False
+382,False
+383,False
+384,False
+385,False
+386,False
+387,False
+388,False
+389,False
+390,False
+391,False
+392,False
+393,False
+394,False
+395,False
+396,False
+397,False
+398,False
+399,False
+400,False
+401,False
+402,False
+403,False
+404,False
+405,False
+406,False
+407,False
+408,False
+409,False
+410,False
+411,False
+412,False
+413,False
+414,False
+415,False
+416,False
+417,False
+418,False
+419,False
+420,False
+421,False
+422,False
+423,False
+424,False
+425,False
+426,False
+427,False
+428,False
+429,False
+430,False
+431,False
+432,False
+433,False
+434,False
+435,False
+436,False
+437,False
+438,False
+439,False
+440,False
+441,False
+442,False
+443,False
+444,False
+445,False
+446,False
+447,False
+448,False
+449,False
+450,False
+451,False
+452,False
+453,False
+454,False
+455,False
+456,False
+457,False
+458,False
+459,False
+460,False
+461,False
+462,False
+463,False
+464,False
+465,False
+466,False
+467,False
+468,False
+469,False
+470,False
+471,False
+472,False
+473,False
+474,False
+475,False
+476,False
+477,False
+478,False
+479,False
+480,False
+481,False
+482,False
+483,False
+484,False
+485,False
+486,False
+487,False
+488,False
+489,False
+490,False
+491,False
+492,False
+493,False
+494,False
+495,False
+496,False
+497,False
+498,False
+499,False
+500,False
+501,False
+502,False
+503,False
+504,False
+505,False
+506,False
+507,False
+508,False
+509,False
+510,False
+511,False
+512,False
+513,False
+514,False
+515,False
+516,False
+517,False
+518,False
+519,False
+520,False
+521,False
+522,False
+523,False
+524,False
+525,False
+526,False
+527,False
+528,False
+529,False
+530,False
+531,False
+532,False
+533,False
+534,False
+535,False
+536,False
+537,False
+538,False
+539,False
+540,False
+541,False
+542,False
+543,True
+544,False
+545,False
+546,False
+547,False
+548,False
+549,False
+550,False
+551,False
+552,False
+553,False
+554,False
+555,False
+556,False
+557,False
+558,False
+559,False
+560,False
+561,False
+562,False
+563,False
+564,False
+565,False
+566,False
+567,False
+568,False
+569,False
+570,False
+571,False
+572,False
+573,False
+574,False
+575,False
+576,False
+577,False
+578,False
+579,False
+580,False
+581,False
+582,False
+583,False
+584,False
+585,False
+586,False
+587,True
+588,False
+589,False
+590,False
+591,False
+592,False
+593,False
+594,False
+595,False
+596,False
+597,False
+598,False
+599,False
+600,False
+601,False
+602,False
+603,False
+604,False
+605,False
+606,False
+607,False
+608,False
+609,False
+610,False
+611,False
+612,False
+613,False
+614,False
+615,False
+616,False
+617,False
+618,False
+619,False
+620,False
+621,False
+622,False
+623,False
+624,False
+625,False
+626,False
+627,False
+628,False
+629,False
+630,False
+631,False
+632,False
+633,False
+634,True
+635,False
+636,True
+637,True
+638,False
+639,False
+640,False
+641,False
+642,False
+643,False
+644,False
+645,False
+646,False
+647,True
+648,False
+649,True
+650,False
+651,False
+652,False
+653,False
+654,False
+655,False
+656,True
+657,False
+658,True
+659,False
+660,False
+661,False
+662,False
+663,False
+664,False
+665,False
+666,False
+667,False
+668,True
+669,False
+670,True
+671,False
+672,False
+673,True
+674,False
+675,False
+676,False
+677,False
+678,False
+679,False
+680,False
+681,False
+682,False
+683,False
+684,False
+685,False
+686,True
+687,False
+688,False
+689,False
+690,False
+691,False
+692,False
+693,False
+694,False
+695,False
+696,False
+697,False
+698,False
+699,False
+700,False
+701,False
+702,False
+703,False
+704,False
+705,False
+706,True
+707,True
+708,False
+709,False
+710,False
+711,False
+712,False
+713,False
+714,False
+715,False
+716,False
+717,True
+718,False
+719,False
+720,False
+721,False
+722,False
+723,False
+724,False
+725,False
+726,False
+727,False
+728,True
+729,False
+730,False
+731,False
+732,False
+733,False
+734,False
+735,False
+736,False
+737,False
+738,False
+739,False
+740,True
+741,True
+742,False
+743,True
+744,False
+745,True
+746,False
+747,False
+748,False
+749,False
+750,False
+751,False
+752,False
+753,False
+754,False
+755,False
+756,False
+757,False
diff --git a/Assignment Colab/Amber5_csv b/Assignment Colab/Amber5_csv
new file mode 100644
index 0000000..d5d0b48
--- /dev/null
+++ b/Assignment Colab/Amber5_csv	
@@ -0,0 +1,759 @@
+Index,CLASS
+0,True
+1,True
+2,True
+3,True
+4,False
+5,True
+6,True
+7,True
+8,True
+9,True
+10,True
+11,True
+12,True
+13,False
+14,False
+15,True
+16,False
+17,True
+18,True
+19,True
+20,True
+21,True
+22,True
+23,True
+24,False
+25,True
+26,True
+27,True
+28,True
+29,False
+30,True
+31,True
+32,False
+33,True
+34,False
+35,True
+36,True
+37,True
+38,True
+39,True
+40,True
+41,True
+42,True
+43,True
+44,True
+45,False
+46,True
+47,True
+48,False
+49,True
+50,True
+51,False
+52,False
+53,True
+54,False
+55,True
+56,True
+57,True
+58,True
+59,True
+60,True
+61,False
+62,True
+63,True
+64,True
+65,True
+66,True
+67,True
+68,True
+69,True
+70,True
+71,True
+72,True
+73,True
+74,True
+75,True
+76,False
+77,True
+78,True
+79,True
+80,True
+81,True
+82,True
+83,True
+84,True
+85,False
+86,False
+87,True
+88,True
+89,True
+90,False
+91,True
+92,True
+93,True
+94,True
+95,False
+96,False
+97,True
+98,True
+99,True
+100,False
+101,True
+102,True
+103,True
+104,True
+105,True
+106,True
+107,True
+108,True
+109,True
+110,True
+111,True
+112,True
+113,False
+114,True
+115,True
+116,True
+117,True
+118,True
+119,True
+120,True
+121,True
+122,True
+123,True
+124,True
+125,True
+126,True
+127,True
+128,True
+129,True
+130,True
+131,True
+132,False
+133,True
+134,True
+135,True
+136,True
+137,True
+138,True
+139,True
+140,True
+141,True
+142,True
+143,True
+144,True
+145,True
+146,True
+147,True
+148,True
+149,True
+150,True
+151,True
+152,False
+153,True
+154,True
+155,True
+156,True
+157,True
+158,True
+159,True
+160,True
+161,False
+162,True
+163,True
+164,True
+165,True
+166,True
+167,True
+168,True
+169,False
+170,True
+171,True
+172,True
+173,True
+174,True
+175,True
+176,True
+177,True
+178,True
+179,True
+180,True
+181,True
+182,True
+183,True
+184,True
+185,True
+186,True
+187,True
+188,True
+189,True
+190,True
+191,True
+192,True
+193,True
+194,True
+195,True
+196,True
+197,True
+198,False
+199,True
+200,True
+201,True
+202,True
+203,True
+204,True
+205,True
+206,True
+207,True
+208,True
+209,True
+210,True
+211,True
+212,True
+213,True
+214,True
+215,True
+216,True
+217,True
+218,True
+219,False
+220,True
+221,True
+222,True
+223,True
+224,True
+225,True
+226,True
+227,True
+228,True
+229,True
+230,True
+231,True
+232,True
+233,True
+234,True
+235,True
+236,True
+237,True
+238,True
+239,True
+240,True
+241,True
+242,True
+243,False
+244,True
+245,True
+246,True
+247,True
+248,True
+249,True
+250,True
+251,True
+252,True
+253,True
+254,True
+255,True
+256,True
+257,True
+258,True
+259,False
+260,True
+261,True
+262,True
+263,True
+264,True
+265,True
+266,True
+267,True
+268,True
+269,True
+270,True
+271,True
+272,True
+273,True
+274,True
+275,True
+276,True
+277,True
+278,True
+279,True
+280,True
+281,True
+282,True
+283,True
+284,True
+285,True
+286,True
+287,True
+288,True
+289,True
+290,True
+291,True
+292,True
+293,True
+294,True
+295,True
+296,False
+297,True
+298,True
+299,False
+300,True
+301,True
+302,True
+303,True
+304,True
+305,True
+306,True
+307,True
+308,True
+309,True
+310,True
+311,True
+312,True
+313,True
+314,True
+315,True
+316,True
+317,True
+318,True
+319,True
+320,True
+321,True
+322,True
+323,True
+324,True
+325,True
+326,True
+327,True
+328,True
+329,True
+330,True
+331,True
+332,True
+333,True
+334,True
+335,True
+336,True
+337,True
+338,True
+339,True
+340,True
+341,True
+342,True
+343,True
+344,True
+345,True
+346,True
+347,True
+348,True
+349,True
+350,True
+351,True
+352,True
+353,False
+354,True
+355,True
+356,True
+357,True
+358,True
+359,True
+360,True
+361,True
+362,True
+363,True
+364,True
+365,True
+366,True
+367,True
+368,True
+369,True
+370,True
+371,True
+372,True
+373,True
+374,True
+375,True
+376,True
+377,True
+378,True
+379,False
+380,False
+381,False
+382,False
+383,False
+384,False
+385,False
+386,False
+387,False
+388,False
+389,False
+390,False
+391,False
+392,False
+393,False
+394,False
+395,False
+396,False
+397,False
+398,False
+399,False
+400,False
+401,False
+402,True
+403,False
+404,False
+405,True
+406,False
+407,False
+408,False
+409,False
+410,False
+411,True
+412,False
+413,False
+414,False
+415,False
+416,False
+417,False
+418,False
+419,False
+420,True
+421,False
+422,False
+423,False
+424,False
+425,False
+426,False
+427,False
+428,False
+429,False
+430,False
+431,False
+432,False
+433,False
+434,False
+435,False
+436,False
+437,False
+438,False
+439,False
+440,False
+441,False
+442,False
+443,False
+444,False
+445,False
+446,False
+447,False
+448,False
+449,False
+450,True
+451,False
+452,False
+453,False
+454,False
+455,True
+456,False
+457,False
+458,False
+459,False
+460,False
+461,False
+462,False
+463,False
+464,False
+465,False
+466,False
+467,False
+468,False
+469,False
+470,True
+471,False
+472,False
+473,False
+474,False
+475,False
+476,False
+477,False
+478,False
+479,False
+480,False
+481,False
+482,False
+483,False
+484,False
+485,False
+486,False
+487,False
+488,False
+489,False
+490,False
+491,False
+492,False
+493,False
+494,True
+495,True
+496,False
+497,False
+498,False
+499,False
+500,False
+501,False
+502,False
+503,False
+504,False
+505,False
+506,False
+507,False
+508,True
+509,False
+510,False
+511,False
+512,False
+513,False
+514,False
+515,False
+516,False
+517,False
+518,False
+519,False
+520,True
+521,False
+522,False
+523,False
+524,False
+525,False
+526,False
+527,False
+528,False
+529,False
+530,False
+531,False
+532,False
+533,False
+534,False
+535,False
+536,False
+537,False
+538,False
+539,False
+540,False
+541,False
+542,False
+543,True
+544,False
+545,False
+546,False
+547,False
+548,False
+549,False
+550,True
+551,False
+552,False
+553,False
+554,True
+555,True
+556,False
+557,True
+558,False
+559,True
+560,False
+561,False
+562,False
+563,False
+564,False
+565,False
+566,False
+567,False
+568,False
+569,False
+570,False
+571,False
+572,False
+573,False
+574,False
+575,False
+576,False
+577,False
+578,False
+579,False
+580,False
+581,False
+582,False
+583,False
+584,False
+585,False
+586,False
+587,True
+588,False
+589,False
+590,False
+591,True
+592,False
+593,False
+594,False
+595,True
+596,False
+597,False
+598,False
+599,False
+600,False
+601,False
+602,False
+603,False
+604,False
+605,False
+606,False
+607,False
+608,False
+609,False
+610,False
+611,False
+612,False
+613,False
+614,False
+615,False
+616,False
+617,False
+618,False
+619,False
+620,False
+621,False
+622,False
+623,False
+624,False
+625,False
+626,False
+627,False
+628,True
+629,False
+630,False
+631,False
+632,False
+633,True
+634,True
+635,False
+636,True
+637,True
+638,True
+639,False
+640,False
+641,False
+642,False
+643,False
+644,False
+645,True
+646,False
+647,True
+648,False
+649,False
+650,False
+651,False
+652,False
+653,False
+654,False
+655,False
+656,True
+657,False
+658,False
+659,False
+660,False
+661,False
+662,False
+663,False
+664,False
+665,False
+666,False
+667,False
+668,False
+669,False
+670,True
+671,False
+672,False
+673,True
+674,False
+675,False
+676,False
+677,False
+678,False
+679,False
+680,False
+681,False
+682,False
+683,False
+684,False
+685,False
+686,True
+687,True
+688,False
+689,False
+690,False
+691,False
+692,False
+693,False
+694,False
+695,False
+696,False
+697,False
+698,False
+699,False
+700,False
+701,False
+702,False
+703,False
+704,False
+705,False
+706,True
+707,False
+708,True
+709,False
+710,False
+711,False
+712,False
+713,False
+714,False
+715,False
+716,False
+717,True
+718,False
+719,True
+720,False
+721,False
+722,False
+723,False
+724,False
+725,False
+726,False
+727,False
+728,True
+729,False
+730,False
+731,False
+732,False
+733,False
+734,False
+735,False
+736,False
+737,False
+738,False
+739,False
+740,True
+741,True
+742,False
+743,True
+744,False
+745,True
+746,False
+747,False
+748,False
+749,False
+750,False
+751,False
+752,False
+753,False
+754,False
+755,False
+756,False
+757,False
diff --git a/Assignment Colab/Amber6_csv b/Assignment Colab/Amber6_csv
new file mode 100644
index 0000000..fb5b165
--- /dev/null
+++ b/Assignment Colab/Amber6_csv	
@@ -0,0 +1,759 @@
+Index,CLASS
+0,True
+1,True
+2,False
+3,False
+4,False
+5,True
+6,True
+7,True
+8,True
+9,True
+10,True
+11,True
+12,False
+13,False
+14,False
+15,True
+16,True
+17,True
+18,True
+19,True
+20,True
+21,True
+22,True
+23,True
+24,False
+25,True
+26,True
+27,False
+28,True
+29,False
+30,True
+31,True
+32,True
+33,True
+34,True
+35,False
+36,True
+37,True
+38,True
+39,True
+40,False
+41,True
+42,True
+43,True
+44,False
+45,False
+46,True
+47,True
+48,False
+49,True
+50,False
+51,False
+52,False
+53,True
+54,True
+55,True
+56,False
+57,True
+58,True
+59,True
+60,True
+61,False
+62,True
+63,True
+64,False
+65,False
+66,True
+67,True
+68,False
+69,True
+70,False
+71,True
+72,False
+73,True
+74,True
+75,True
+76,False
+77,True
+78,True
+79,True
+80,False
+81,True
+82,False
+83,True
+84,False
+85,False
+86,False
+87,True
+88,False
+89,False
+90,False
+91,True
+92,False
+93,True
+94,False
+95,False
+96,True
+97,True
+98,True
+99,True
+100,False
+101,False
+102,True
+103,True
+104,True
+105,True
+106,True
+107,True
+108,True
+109,True
+110,True
+111,True
+112,True
+113,False
+114,True
+115,True
+116,True
+117,False
+118,True
+119,True
+120,True
+121,True
+122,True
+123,True
+124,True
+125,True
+126,True
+127,False
+128,True
+129,True
+130,True
+131,True
+132,True
+133,True
+134,True
+135,True
+136,True
+137,True
+138,True
+139,True
+140,True
+141,True
+142,True
+143,True
+144,True
+145,True
+146,True
+147,True
+148,True
+149,True
+150,True
+151,True
+152,True
+153,True
+154,True
+155,True
+156,True
+157,True
+158,True
+159,True
+160,True
+161,True
+162,True
+163,True
+164,True
+165,True
+166,True
+167,True
+168,True
+169,True
+170,True
+171,True
+172,True
+173,True
+174,True
+175,True
+176,True
+177,False
+178,True
+179,True
+180,True
+181,True
+182,True
+183,True
+184,True
+185,True
+186,True
+187,True
+188,True
+189,True
+190,True
+191,True
+192,True
+193,True
+194,True
+195,True
+196,True
+197,True
+198,False
+199,True
+200,True
+201,True
+202,True
+203,True
+204,True
+205,True
+206,True
+207,True
+208,True
+209,True
+210,True
+211,True
+212,True
+213,True
+214,True
+215,True
+216,True
+217,True
+218,True
+219,True
+220,True
+221,True
+222,True
+223,True
+224,True
+225,True
+226,True
+227,True
+228,True
+229,True
+230,True
+231,True
+232,True
+233,True
+234,True
+235,True
+236,True
+237,True
+238,True
+239,True
+240,True
+241,True
+242,True
+243,True
+244,True
+245,True
+246,True
+247,True
+248,True
+249,True
+250,True
+251,True
+252,True
+253,True
+254,True
+255,True
+256,True
+257,True
+258,True
+259,True
+260,True
+261,True
+262,True
+263,True
+264,True
+265,True
+266,True
+267,True
+268,True
+269,True
+270,True
+271,True
+272,True
+273,True
+274,True
+275,True
+276,True
+277,True
+278,True
+279,True
+280,True
+281,True
+282,True
+283,True
+284,True
+285,True
+286,True
+287,True
+288,True
+289,True
+290,True
+291,True
+292,True
+293,True
+294,True
+295,True
+296,True
+297,True
+298,True
+299,True
+300,True
+301,True
+302,True
+303,True
+304,True
+305,True
+306,True
+307,True
+308,True
+309,True
+310,True
+311,True
+312,True
+313,True
+314,True
+315,True
+316,True
+317,True
+318,True
+319,False
+320,True
+321,True
+322,True
+323,True
+324,True
+325,True
+326,True
+327,True
+328,True
+329,True
+330,True
+331,True
+332,True
+333,True
+334,True
+335,True
+336,True
+337,True
+338,True
+339,True
+340,True
+341,True
+342,True
+343,True
+344,True
+345,True
+346,True
+347,True
+348,True
+349,True
+350,True
+351,True
+352,True
+353,True
+354,True
+355,True
+356,True
+357,True
+358,True
+359,True
+360,True
+361,True
+362,True
+363,True
+364,True
+365,True
+366,True
+367,True
+368,True
+369,True
+370,True
+371,True
+372,True
+373,True
+374,True
+375,True
+376,True
+377,True
+378,True
+379,False
+380,False
+381,False
+382,False
+383,False
+384,False
+385,False
+386,False
+387,False
+388,False
+389,False
+390,True
+391,False
+392,False
+393,False
+394,False
+395,False
+396,False
+397,False
+398,False
+399,False
+400,False
+401,False
+402,True
+403,False
+404,False
+405,False
+406,False
+407,False
+408,False
+409,False
+410,False
+411,True
+412,False
+413,False
+414,False
+415,False
+416,False
+417,True
+418,False
+419,False
+420,False
+421,False
+422,False
+423,False
+424,False
+425,False
+426,False
+427,False
+428,False
+429,False
+430,False
+431,False
+432,False
+433,False
+434,False
+435,False
+436,False
+437,False
+438,False
+439,False
+440,False
+441,False
+442,False
+443,False
+444,False
+445,False
+446,False
+447,False
+448,False
+449,False
+450,True
+451,False
+452,False
+453,False
+454,False
+455,True
+456,False
+457,False
+458,False
+459,False
+460,False
+461,False
+462,False
+463,False
+464,False
+465,False
+466,False
+467,False
+468,False
+469,True
+470,False
+471,False
+472,False
+473,False
+474,False
+475,False
+476,False
+477,False
+478,False
+479,False
+480,False
+481,False
+482,False
+483,False
+484,False
+485,False
+486,False
+487,False
+488,False
+489,False
+490,False
+491,False
+492,False
+493,False
+494,False
+495,False
+496,False
+497,False
+498,False
+499,False
+500,False
+501,False
+502,False
+503,False
+504,False
+505,True
+506,False
+507,False
+508,True
+509,False
+510,False
+511,False
+512,False
+513,False
+514,False
+515,False
+516,False
+517,False
+518,False
+519,False
+520,True
+521,False
+522,False
+523,False
+524,False
+525,False
+526,False
+527,True
+528,False
+529,False
+530,False
+531,False
+532,False
+533,False
+534,False
+535,False
+536,True
+537,True
+538,False
+539,False
+540,False
+541,False
+542,False
+543,True
+544,True
+545,False
+546,False
+547,False
+548,False
+549,False
+550,False
+551,False
+552,False
+553,False
+554,True
+555,False
+556,False
+557,True
+558,False
+559,False
+560,False
+561,False
+562,True
+563,False
+564,False
+565,False
+566,False
+567,False
+568,False
+569,False
+570,False
+571,False
+572,False
+573,False
+574,False
+575,False
+576,False
+577,False
+578,False
+579,False
+580,False
+581,False
+582,False
+583,False
+584,True
+585,False
+586,False
+587,True
+588,False
+589,False
+590,False
+591,True
+592,True
+593,False
+594,False
+595,False
+596,False
+597,False
+598,False
+599,False
+600,False
+601,False
+602,False
+603,False
+604,False
+605,False
+606,False
+607,False
+608,False
+609,False
+610,False
+611,False
+612,False
+613,False
+614,False
+615,False
+616,False
+617,False
+618,False
+619,False
+620,False
+621,False
+622,False
+623,False
+624,True
+625,False
+626,False
+627,False
+628,False
+629,True
+630,True
+631,False
+632,False
+633,True
+634,False
+635,False
+636,False
+637,False
+638,False
+639,False
+640,False
+641,False
+642,True
+643,False
+644,False
+645,False
+646,False
+647,False
+648,False
+649,False
+650,False
+651,False
+652,False
+653,False
+654,False
+655,False
+656,True
+657,False
+658,False
+659,False
+660,False
+661,True
+662,False
+663,False
+664,False
+665,False
+666,False
+667,False
+668,False
+669,False
+670,False
+671,False
+672,False
+673,False
+674,False
+675,False
+676,False
+677,False
+678,False
+679,False
+680,False
+681,False
+682,False
+683,False
+684,False
+685,False
+686,False
+687,False
+688,False
+689,False
+690,False
+691,False
+692,False
+693,False
+694,False
+695,False
+696,False
+697,False
+698,False
+699,False
+700,False
+701,False
+702,False
+703,False
+704,False
+705,False
+706,False
+707,False
+708,False
+709,False
+710,False
+711,False
+712,False
+713,False
+714,False
+715,False
+716,False
+717,True
+718,False
+719,True
+720,False
+721,True
+722,False
+723,False
+724,False
+725,False
+726,False
+727,False
+728,True
+729,False
+730,False
+731,False
+732,False
+733,False
+734,False
+735,False
+736,True
+737,False
+738,False
+739,False
+740,False
+741,True
+742,False
+743,True
+744,True
+745,True
+746,False
+747,False
+748,False
+749,False
+750,False
+751,False
+752,True
+753,False
+754,False
+755,False
+756,False
+757,True
diff --git a/Assignment Colab/Amber7_csv b/Assignment Colab/Amber7_csv
new file mode 100644
index 0000000..b442490
--- /dev/null
+++ b/Assignment Colab/Amber7_csv	
@@ -0,0 +1,759 @@
+Index,CLASS
+0,False
+1,False
+2,True
+3,True
+4,False
+5,False
+6,True
+7,False
+8,True
+9,False
+10,False
+11,False
+12,False
+13,False
+14,False
+15,False
+16,True
+17,True
+18,False
+19,True
+20,False
+21,True
+22,True
+23,True
+24,False
+25,False
+26,True
+27,True
+28,True
+29,False
+30,True
+31,False
+32,False
+33,True
+34,False
+35,False
+36,True
+37,True
+38,True
+39,True
+40,True
+41,True
+42,True
+43,True
+44,False
+45,False
+46,True
+47,True
+48,False
+49,False
+50,True
+51,False
+52,False
+53,True
+54,False
+55,True
+56,False
+57,True
+58,False
+59,True
+60,False
+61,False
+62,True
+63,True
+64,True
+65,True
+66,True
+67,True
+68,True
+69,True
+70,False
+71,True
+72,True
+73,True
+74,True
+75,True
+76,False
+77,True
+78,True
+79,True
+80,True
+81,True
+82,True
+83,True
+84,True
+85,False
+86,False
+87,True
+88,True
+89,True
+90,False
+91,False
+92,True
+93,True
+94,True
+95,False
+96,False
+97,True
+98,True
+99,True
+100,False
+101,True
+102,True
+103,True
+104,True
+105,True
+106,True
+107,True
+108,True
+109,True
+110,True
+111,True
+112,True
+113,True
+114,True
+115,True
+116,True
+117,True
+118,True
+119,True
+120,True
+121,True
+122,True
+123,True
+124,True
+125,True
+126,True
+127,True
+128,True
+129,True
+130,True
+131,True
+132,False
+133,True
+134,True
+135,True
+136,True
+137,True
+138,True
+139,True
+140,True
+141,True
+142,True
+143,True
+144,True
+145,True
+146,True
+147,True
+148,True
+149,True
+150,True
+151,True
+152,False
+153,True
+154,True
+155,True
+156,True
+157,True
+158,True
+159,True
+160,True
+161,True
+162,True
+163,True
+164,True
+165,True
+166,True
+167,True
+168,True
+169,True
+170,True
+171,True
+172,True
+173,True
+174,True
+175,True
+176,True
+177,True
+178,True
+179,True
+180,True
+181,True
+182,True
+183,True
+184,True
+185,True
+186,True
+187,True
+188,True
+189,True
+190,True
+191,True
+192,True
+193,True
+194,True
+195,True
+196,True
+197,True
+198,False
+199,True
+200,True
+201,True
+202,True
+203,True
+204,True
+205,True
+206,True
+207,True
+208,True
+209,True
+210,True
+211,True
+212,True
+213,True
+214,True
+215,True
+216,True
+217,True
+218,True
+219,False
+220,True
+221,True
+222,True
+223,True
+224,True
+225,True
+226,True
+227,True
+228,True
+229,True
+230,True
+231,True
+232,True
+233,True
+234,True
+235,True
+236,True
+237,True
+238,True
+239,True
+240,True
+241,True
+242,True
+243,True
+244,True
+245,True
+246,True
+247,True
+248,True
+249,True
+250,True
+251,True
+252,True
+253,True
+254,True
+255,True
+256,True
+257,True
+258,True
+259,False
+260,True
+261,True
+262,True
+263,True
+264,True
+265,True
+266,True
+267,True
+268,True
+269,True
+270,True
+271,True
+272,True
+273,True
+274,True
+275,True
+276,True
+277,True
+278,True
+279,True
+280,True
+281,True
+282,True
+283,True
+284,True
+285,True
+286,True
+287,True
+288,True
+289,True
+290,True
+291,True
+292,True
+293,True
+294,True
+295,True
+296,True
+297,True
+298,True
+299,True
+300,True
+301,True
+302,True
+303,True
+304,True
+305,True
+306,True
+307,True
+308,True
+309,True
+310,True
+311,True
+312,True
+313,True
+314,True
+315,True
+316,True
+317,True
+318,True
+319,True
+320,True
+321,True
+322,True
+323,True
+324,True
+325,True
+326,True
+327,True
+328,True
+329,True
+330,True
+331,True
+332,True
+333,True
+334,True
+335,True
+336,True
+337,True
+338,True
+339,True
+340,True
+341,True
+342,True
+343,True
+344,True
+345,True
+346,True
+347,True
+348,True
+349,True
+350,True
+351,True
+352,True
+353,True
+354,True
+355,True
+356,True
+357,True
+358,True
+359,True
+360,True
+361,True
+362,True
+363,True
+364,True
+365,True
+366,True
+367,True
+368,True
+369,True
+370,True
+371,True
+372,True
+373,True
+374,True
+375,True
+376,True
+377,True
+378,True
+379,False
+380,False
+381,False
+382,False
+383,False
+384,False
+385,False
+386,False
+387,False
+388,False
+389,False
+390,False
+391,False
+392,False
+393,False
+394,False
+395,False
+396,False
+397,False
+398,False
+399,False
+400,False
+401,False
+402,False
+403,False
+404,False
+405,False
+406,False
+407,False
+408,False
+409,False
+410,False
+411,False
+412,False
+413,False
+414,False
+415,False
+416,False
+417,False
+418,False
+419,False
+420,False
+421,False
+422,False
+423,False
+424,False
+425,False
+426,False
+427,False
+428,False
+429,False
+430,False
+431,False
+432,False
+433,False
+434,False
+435,False
+436,False
+437,False
+438,False
+439,False
+440,False
+441,False
+442,False
+443,False
+444,False
+445,False
+446,False
+447,False
+448,False
+449,False
+450,False
+451,False
+452,False
+453,False
+454,False
+455,False
+456,False
+457,False
+458,False
+459,False
+460,False
+461,False
+462,False
+463,False
+464,False
+465,False
+466,False
+467,False
+468,False
+469,False
+470,False
+471,False
+472,False
+473,False
+474,False
+475,False
+476,False
+477,False
+478,False
+479,False
+480,False
+481,False
+482,False
+483,False
+484,False
+485,False
+486,False
+487,False
+488,False
+489,False
+490,False
+491,False
+492,False
+493,False
+494,False
+495,False
+496,False
+497,False
+498,False
+499,False
+500,False
+501,False
+502,False
+503,False
+504,False
+505,False
+506,False
+507,False
+508,False
+509,False
+510,False
+511,False
+512,False
+513,False
+514,False
+515,False
+516,False
+517,False
+518,False
+519,False
+520,False
+521,False
+522,False
+523,False
+524,False
+525,False
+526,False
+527,False
+528,False
+529,False
+530,False
+531,False
+532,False
+533,False
+534,False
+535,False
+536,False
+537,False
+538,False
+539,False
+540,False
+541,False
+542,False
+543,False
+544,False
+545,False
+546,False
+547,False
+548,False
+549,False
+550,False
+551,False
+552,False
+553,False
+554,True
+555,False
+556,False
+557,False
+558,False
+559,False
+560,False
+561,False
+562,False
+563,False
+564,False
+565,False
+566,False
+567,False
+568,False
+569,False
+570,False
+571,False
+572,False
+573,False
+574,False
+575,False
+576,False
+577,False
+578,False
+579,False
+580,False
+581,False
+582,False
+583,False
+584,False
+585,False
+586,False
+587,True
+588,False
+589,False
+590,False
+591,False
+592,False
+593,False
+594,False
+595,True
+596,False
+597,False
+598,False
+599,False
+600,False
+601,False
+602,False
+603,False
+604,False
+605,False
+606,False
+607,False
+608,False
+609,False
+610,False
+611,False
+612,False
+613,False
+614,False
+615,False
+616,False
+617,False
+618,False
+619,False
+620,False
+621,False
+622,False
+623,False
+624,False
+625,False
+626,False
+627,False
+628,False
+629,False
+630,False
+631,False
+632,False
+633,True
+634,True
+635,False
+636,True
+637,True
+638,True
+639,False
+640,False
+641,False
+642,True
+643,False
+644,False
+645,False
+646,False
+647,True
+648,False
+649,True
+650,False
+651,False
+652,False
+653,True
+654,False
+655,False
+656,True
+657,False
+658,True
+659,False
+660,False
+661,False
+662,False
+663,False
+664,False
+665,False
+666,False
+667,True
+668,True
+669,False
+670,True
+671,False
+672,False
+673,True
+674,False
+675,False
+676,False
+677,False
+678,False
+679,False
+680,False
+681,False
+682,False
+683,False
+684,False
+685,False
+686,True
+687,False
+688,False
+689,False
+690,False
+691,False
+692,False
+693,False
+694,False
+695,False
+696,False
+697,False
+698,False
+699,False
+700,False
+701,False
+702,False
+703,False
+704,False
+705,False
+706,True
+707,True
+708,False
+709,False
+710,False
+711,False
+712,False
+713,False
+714,False
+715,False
+716,False
+717,True
+718,False
+719,False
+720,False
+721,True
+722,False
+723,False
+724,False
+725,False
+726,False
+727,False
+728,True
+729,False
+730,False
+731,False
+732,False
+733,False
+734,False
+735,False
+736,False
+737,False
+738,False
+739,False
+740,True
+741,True
+742,False
+743,False
+744,False
+745,True
+746,False
+747,False
+748,False
+749,False
+750,True
+751,False
+752,False
+753,False
+754,False
+755,False
+756,False
+757,False
diff --git a/Assignment Colab/Amber8_csv b/Assignment Colab/Amber8_csv
new file mode 100644
index 0000000..296d234
--- /dev/null
+++ b/Assignment Colab/Amber8_csv	
@@ -0,0 +1,759 @@
+Index,CLASS
+0,True
+1,True
+2,True
+3,True
+4,False
+5,True
+6,True
+7,True
+8,True
+9,True
+10,True
+11,True
+12,False
+13,False
+14,False
+15,True
+16,True
+17,True
+18,True
+19,True
+20,True
+21,True
+22,True
+23,True
+24,False
+25,True
+26,True
+27,False
+28,True
+29,False
+30,True
+31,True
+32,False
+33,True
+34,True
+35,False
+36,True
+37,True
+38,True
+39,True
+40,True
+41,True
+42,True
+43,True
+44,False
+45,True
+46,True
+47,True
+48,False
+49,True
+50,True
+51,False
+52,False
+53,True
+54,True
+55,True
+56,True
+57,True
+58,True
+59,True
+60,False
+61,False
+62,True
+63,True
+64,True
+65,True
+66,True
+67,True
+68,True
+69,True
+70,True
+71,True
+72,False
+73,True
+74,True
+75,True
+76,False
+77,True
+78,False
+79,True
+80,False
+81,True
+82,True
+83,True
+84,True
+85,False
+86,False
+87,True
+88,True
+89,True
+90,False
+91,True
+92,True
+93,True
+94,True
+95,False
+96,False
+97,True
+98,True
+99,True
+100,False
+101,True
+102,True
+103,True
+104,True
+105,True
+106,True
+107,True
+108,True
+109,True
+110,True
+111,True
+112,True
+113,True
+114,True
+115,True
+116,True
+117,True
+118,True
+119,True
+120,True
+121,True
+122,True
+123,True
+124,True
+125,True
+126,True
+127,True
+128,True
+129,True
+130,True
+131,True
+132,False
+133,True
+134,True
+135,True
+136,True
+137,True
+138,True
+139,True
+140,True
+141,True
+142,True
+143,True
+144,True
+145,True
+146,True
+147,True
+148,True
+149,True
+150,True
+151,True
+152,True
+153,True
+154,True
+155,True
+156,True
+157,True
+158,True
+159,True
+160,True
+161,True
+162,True
+163,True
+164,True
+165,True
+166,True
+167,True
+168,True
+169,True
+170,True
+171,True
+172,True
+173,True
+174,True
+175,True
+176,True
+177,True
+178,True
+179,True
+180,True
+181,True
+182,True
+183,True
+184,True
+185,True
+186,True
+187,True
+188,True
+189,True
+190,True
+191,True
+192,True
+193,True
+194,True
+195,True
+196,True
+197,True
+198,True
+199,True
+200,True
+201,True
+202,True
+203,True
+204,True
+205,True
+206,True
+207,True
+208,True
+209,True
+210,True
+211,True
+212,True
+213,True
+214,True
+215,True
+216,True
+217,True
+218,True
+219,True
+220,True
+221,True
+222,True
+223,True
+224,True
+225,True
+226,True
+227,True
+228,True
+229,True
+230,True
+231,True
+232,True
+233,True
+234,True
+235,True
+236,True
+237,True
+238,True
+239,True
+240,True
+241,True
+242,True
+243,True
+244,True
+245,True
+246,True
+247,True
+248,True
+249,True
+250,True
+251,True
+252,True
+253,True
+254,True
+255,True
+256,True
+257,True
+258,True
+259,True
+260,True
+261,True
+262,True
+263,True
+264,True
+265,True
+266,True
+267,True
+268,True
+269,True
+270,True
+271,True
+272,True
+273,True
+274,True
+275,True
+276,True
+277,True
+278,True
+279,True
+280,True
+281,True
+282,True
+283,True
+284,True
+285,True
+286,True
+287,True
+288,True
+289,True
+290,True
+291,True
+292,True
+293,True
+294,True
+295,True
+296,True
+297,True
+298,True
+299,True
+300,True
+301,True
+302,True
+303,True
+304,True
+305,True
+306,True
+307,True
+308,True
+309,True
+310,True
+311,True
+312,True
+313,True
+314,True
+315,True
+316,True
+317,True
+318,True
+319,True
+320,True
+321,True
+322,True
+323,True
+324,True
+325,True
+326,True
+327,True
+328,True
+329,True
+330,True
+331,True
+332,True
+333,True
+334,True
+335,True
+336,True
+337,True
+338,True
+339,True
+340,True
+341,True
+342,True
+343,True
+344,True
+345,True
+346,True
+347,True
+348,True
+349,True
+350,True
+351,True
+352,True
+353,True
+354,True
+355,True
+356,True
+357,True
+358,True
+359,True
+360,True
+361,True
+362,True
+363,True
+364,True
+365,True
+366,True
+367,True
+368,True
+369,True
+370,True
+371,True
+372,True
+373,True
+374,True
+375,True
+376,True
+377,True
+378,True
+379,False
+380,False
+381,False
+382,False
+383,False
+384,False
+385,False
+386,False
+387,False
+388,False
+389,False
+390,True
+391,False
+392,False
+393,False
+394,False
+395,False
+396,False
+397,False
+398,False
+399,False
+400,False
+401,False
+402,True
+403,False
+404,False
+405,False
+406,False
+407,False
+408,False
+409,False
+410,False
+411,True
+412,False
+413,False
+414,False
+415,False
+416,False
+417,False
+418,False
+419,False
+420,True
+421,False
+422,False
+423,False
+424,False
+425,False
+426,False
+427,False
+428,False
+429,False
+430,False
+431,False
+432,False
+433,False
+434,False
+435,False
+436,False
+437,False
+438,False
+439,False
+440,False
+441,False
+442,False
+443,False
+444,False
+445,False
+446,False
+447,False
+448,False
+449,False
+450,False
+451,False
+452,False
+453,False
+454,False
+455,True
+456,False
+457,False
+458,False
+459,False
+460,False
+461,False
+462,False
+463,False
+464,False
+465,False
+466,False
+467,False
+468,False
+469,False
+470,True
+471,False
+472,False
+473,False
+474,False
+475,False
+476,False
+477,False
+478,False
+479,False
+480,False
+481,False
+482,False
+483,False
+484,False
+485,False
+486,False
+487,False
+488,False
+489,False
+490,False
+491,False
+492,False
+493,False
+494,False
+495,False
+496,False
+497,False
+498,False
+499,False
+500,False
+501,False
+502,False
+503,False
+504,False
+505,False
+506,False
+507,False
+508,False
+509,False
+510,False
+511,False
+512,False
+513,False
+514,False
+515,False
+516,False
+517,False
+518,False
+519,False
+520,False
+521,False
+522,False
+523,False
+524,False
+525,False
+526,False
+527,False
+528,False
+529,False
+530,False
+531,False
+532,False
+533,True
+534,False
+535,False
+536,False
+537,False
+538,False
+539,False
+540,False
+541,False
+542,False
+543,False
+544,False
+545,False
+546,False
+547,False
+548,False
+549,False
+550,False
+551,False
+552,False
+553,False
+554,False
+555,False
+556,False
+557,True
+558,False
+559,False
+560,False
+561,False
+562,False
+563,False
+564,False
+565,False
+566,False
+567,False
+568,False
+569,False
+570,False
+571,False
+572,False
+573,False
+574,False
+575,False
+576,False
+577,False
+578,False
+579,False
+580,False
+581,False
+582,False
+583,False
+584,False
+585,False
+586,False
+587,True
+588,False
+589,False
+590,False
+591,False
+592,False
+593,False
+594,False
+595,True
+596,False
+597,False
+598,False
+599,False
+600,False
+601,False
+602,False
+603,False
+604,False
+605,False
+606,False
+607,False
+608,False
+609,False
+610,False
+611,False
+612,False
+613,False
+614,False
+615,False
+616,False
+617,False
+618,False
+619,False
+620,False
+621,False
+622,False
+623,False
+624,False
+625,False
+626,False
+627,False
+628,False
+629,False
+630,False
+631,False
+632,False
+633,False
+634,True
+635,False
+636,True
+637,True
+638,False
+639,False
+640,False
+641,False
+642,False
+643,False
+644,False
+645,False
+646,False
+647,False
+648,False
+649,False
+650,False
+651,False
+652,False
+653,False
+654,False
+655,False
+656,True
+657,False
+658,False
+659,False
+660,False
+661,False
+662,False
+663,False
+664,False
+665,False
+666,False
+667,False
+668,False
+669,False
+670,True
+671,False
+672,False
+673,True
+674,False
+675,False
+676,False
+677,False
+678,False
+679,False
+680,False
+681,False
+682,False
+683,False
+684,False
+685,False
+686,False
+687,False
+688,False
+689,False
+690,False
+691,False
+692,False
+693,False
+694,False
+695,False
+696,False
+697,False
+698,False
+699,False
+700,False
+701,False
+702,False
+703,False
+704,False
+705,False
+706,False
+707,False
+708,False
+709,False
+710,False
+711,False
+712,False
+713,False
+714,False
+715,False
+716,False
+717,False
+718,False
+719,False
+720,False
+721,False
+722,False
+723,False
+724,False
+725,False
+726,False
+727,False
+728,False
+729,False
+730,False
+731,False
+732,False
+733,False
+734,False
+735,False
+736,False
+737,False
+738,False
+739,False
+740,False
+741,False
+742,False
+743,True
+744,False
+745,False
+746,False
+747,False
+748,False
+749,False
+750,False
+751,False
+752,False
+753,False
+754,False
+755,False
+756,False
+757,False
diff --git a/Assignment Colab/Amber9_csv b/Assignment Colab/Amber9_csv
new file mode 100644
index 0000000..bc9f6b4
--- /dev/null
+++ b/Assignment Colab/Amber9_csv	
@@ -0,0 +1,759 @@
+Index,CLASS
+0,True
+1,True
+2,False
+3,True
+4,False
+5,True
+6,True
+7,True
+8,True
+9,True
+10,True
+11,True
+12,True
+13,True
+14,False
+15,True
+16,False
+17,True
+18,True
+19,True
+20,True
+21,True
+22,True
+23,True
+24,False
+25,True
+26,True
+27,True
+28,True
+29,False
+30,True
+31,True
+32,False
+33,True
+34,False
+35,True
+36,True
+37,True
+38,True
+39,True
+40,True
+41,True
+42,True
+43,True
+44,True
+45,False
+46,True
+47,True
+48,False
+49,True
+50,True
+51,False
+52,False
+53,True
+54,True
+55,True
+56,False
+57,True
+58,True
+59,True
+60,False
+61,False
+62,True
+63,True
+64,True
+65,True
+66,True
+67,True
+68,True
+69,True
+70,True
+71,True
+72,False
+73,True
+74,True
+75,True
+76,True
+77,True
+78,True
+79,True
+80,True
+81,True
+82,True
+83,True
+84,True
+85,True
+86,False
+87,True
+88,True
+89,True
+90,False
+91,True
+92,True
+93,False
+94,False
+95,False
+96,True
+97,True
+98,True
+99,True
+100,True
+101,True
+102,True
+103,True
+104,True
+105,True
+106,True
+107,True
+108,True
+109,True
+110,True
+111,True
+112,True
+113,True
+114,True
+115,True
+116,True
+117,True
+118,True
+119,True
+120,True
+121,True
+122,True
+123,True
+124,True
+125,True
+126,True
+127,True
+128,True
+129,True
+130,True
+131,True
+132,True
+133,True
+134,True
+135,True
+136,True
+137,True
+138,True
+139,True
+140,True
+141,True
+142,True
+143,True
+144,True
+145,True
+146,True
+147,True
+148,True
+149,True
+150,True
+151,True
+152,True
+153,True
+154,True
+155,True
+156,True
+157,True
+158,True
+159,True
+160,True
+161,True
+162,True
+163,True
+164,True
+165,True
+166,True
+167,True
+168,True
+169,True
+170,True
+171,True
+172,True
+173,True
+174,True
+175,True
+176,True
+177,True
+178,True
+179,True
+180,True
+181,True
+182,True
+183,True
+184,True
+185,True
+186,True
+187,True
+188,True
+189,True
+190,True
+191,True
+192,True
+193,True
+194,True
+195,True
+196,True
+197,True
+198,True
+199,True
+200,True
+201,True
+202,True
+203,True
+204,True
+205,True
+206,True
+207,True
+208,True
+209,True
+210,True
+211,True
+212,True
+213,True
+214,True
+215,True
+216,True
+217,True
+218,True
+219,False
+220,True
+221,True
+222,True
+223,True
+224,True
+225,True
+226,True
+227,True
+228,True
+229,True
+230,True
+231,True
+232,True
+233,True
+234,True
+235,True
+236,True
+237,True
+238,True
+239,True
+240,True
+241,True
+242,True
+243,True
+244,True
+245,True
+246,True
+247,True
+248,True
+249,True
+250,True
+251,True
+252,True
+253,True
+254,True
+255,True
+256,True
+257,True
+258,True
+259,True
+260,True
+261,True
+262,True
+263,True
+264,True
+265,True
+266,True
+267,True
+268,True
+269,True
+270,True
+271,True
+272,True
+273,True
+274,True
+275,True
+276,True
+277,True
+278,True
+279,True
+280,True
+281,True
+282,True
+283,True
+284,True
+285,True
+286,True
+287,True
+288,True
+289,True
+290,True
+291,True
+292,True
+293,True
+294,True
+295,True
+296,True
+297,True
+298,True
+299,True
+300,True
+301,True
+302,True
+303,True
+304,True
+305,True
+306,True
+307,True
+308,True
+309,True
+310,True
+311,True
+312,True
+313,True
+314,True
+315,True
+316,True
+317,True
+318,True
+319,True
+320,True
+321,True
+322,True
+323,True
+324,True
+325,True
+326,True
+327,True
+328,True
+329,True
+330,True
+331,True
+332,True
+333,True
+334,True
+335,True
+336,True
+337,True
+338,True
+339,True
+340,True
+341,True
+342,True
+343,True
+344,True
+345,True
+346,True
+347,True
+348,True
+349,True
+350,True
+351,True
+352,True
+353,True
+354,True
+355,True
+356,True
+357,True
+358,True
+359,True
+360,True
+361,True
+362,True
+363,True
+364,True
+365,True
+366,True
+367,True
+368,True
+369,True
+370,True
+371,True
+372,True
+373,True
+374,True
+375,True
+376,True
+377,True
+378,True
+379,False
+380,False
+381,False
+382,False
+383,False
+384,False
+385,False
+386,False
+387,False
+388,False
+389,False
+390,False
+391,False
+392,False
+393,False
+394,False
+395,False
+396,False
+397,False
+398,False
+399,False
+400,False
+401,False
+402,False
+403,False
+404,False
+405,False
+406,False
+407,False
+408,False
+409,False
+410,False
+411,False
+412,False
+413,False
+414,False
+415,False
+416,False
+417,False
+418,False
+419,False
+420,False
+421,False
+422,False
+423,False
+424,False
+425,False
+426,False
+427,False
+428,False
+429,False
+430,False
+431,False
+432,False
+433,False
+434,False
+435,False
+436,False
+437,False
+438,False
+439,False
+440,False
+441,False
+442,False
+443,False
+444,False
+445,False
+446,False
+447,False
+448,False
+449,False
+450,False
+451,False
+452,False
+453,False
+454,False
+455,True
+456,False
+457,False
+458,False
+459,False
+460,False
+461,False
+462,False
+463,False
+464,False
+465,False
+466,False
+467,False
+468,False
+469,False
+470,True
+471,False
+472,False
+473,False
+474,False
+475,False
+476,False
+477,False
+478,False
+479,False
+480,False
+481,False
+482,False
+483,False
+484,False
+485,False
+486,False
+487,False
+488,False
+489,False
+490,False
+491,False
+492,False
+493,False
+494,False
+495,False
+496,False
+497,False
+498,False
+499,False
+500,False
+501,False
+502,False
+503,False
+504,False
+505,False
+506,False
+507,False
+508,False
+509,False
+510,False
+511,False
+512,False
+513,False
+514,False
+515,False
+516,False
+517,False
+518,False
+519,False
+520,False
+521,False
+522,False
+523,False
+524,False
+525,False
+526,False
+527,False
+528,False
+529,False
+530,False
+531,False
+532,False
+533,False
+534,False
+535,False
+536,False
+537,False
+538,False
+539,False
+540,False
+541,False
+542,False
+543,True
+544,False
+545,False
+546,False
+547,False
+548,False
+549,False
+550,False
+551,False
+552,False
+553,False
+554,False
+555,False
+556,False
+557,True
+558,False
+559,False
+560,False
+561,False
+562,False
+563,False
+564,False
+565,False
+566,False
+567,False
+568,False
+569,False
+570,False
+571,False
+572,False
+573,False
+574,False
+575,False
+576,False
+577,True
+578,False
+579,False
+580,False
+581,False
+582,False
+583,False
+584,False
+585,False
+586,False
+587,True
+588,False
+589,False
+590,False
+591,False
+592,False
+593,False
+594,False
+595,True
+596,False
+597,False
+598,False
+599,False
+600,False
+601,False
+602,False
+603,False
+604,False
+605,False
+606,False
+607,False
+608,True
+609,False
+610,False
+611,False
+612,False
+613,False
+614,False
+615,False
+616,False
+617,False
+618,False
+619,False
+620,False
+621,False
+622,False
+623,False
+624,False
+625,False
+626,False
+627,False
+628,False
+629,False
+630,False
+631,False
+632,False
+633,True
+634,True
+635,False
+636,True
+637,False
+638,True
+639,False
+640,False
+641,False
+642,False
+643,False
+644,False
+645,False
+646,False
+647,False
+648,False
+649,True
+650,False
+651,False
+652,False
+653,False
+654,False
+655,False
+656,True
+657,False
+658,False
+659,False
+660,False
+661,False
+662,False
+663,False
+664,False
+665,False
+666,False
+667,False
+668,False
+669,False
+670,False
+671,False
+672,False
+673,False
+674,False
+675,False
+676,False
+677,False
+678,False
+679,False
+680,False
+681,False
+682,False
+683,False
+684,False
+685,False
+686,False
+687,False
+688,False
+689,False
+690,False
+691,False
+692,False
+693,False
+694,False
+695,False
+696,False
+697,False
+698,False
+699,False
+700,False
+701,False
+702,False
+703,False
+704,False
+705,False
+706,True
+707,False
+708,False
+709,False
+710,False
+711,False
+712,False
+713,False
+714,False
+715,False
+716,False
+717,False
+718,False
+719,False
+720,False
+721,False
+722,False
+723,False
+724,False
+725,False
+726,False
+727,False
+728,True
+729,False
+730,False
+731,False
+732,False
+733,False
+734,False
+735,False
+736,False
+737,False
+738,False
+739,False
+740,False
+741,False
+742,False
+743,True
+744,False
+745,True
+746,False
+747,False
+748,False
+749,False
+750,True
+751,False
+752,False
+753,False
+754,False
+755,False
+756,False
+757,False
diff --git a/Assignment Colab/Amber_csv b/Assignment Colab/Amber_csv
new file mode 100644
index 0000000..2907729
--- /dev/null
+++ b/Assignment Colab/Amber_csv	
@@ -0,0 +1,759 @@
+Index,CLASS
+0,False
+1,False
+2,True
+3,True
+4,False
+5,True
+6,True
+7,False
+8,True
+9,True
+10,True
+11,True
+12,False
+13,False
+14,False
+15,True
+16,False
+17,True
+18,False
+19,True
+20,False
+21,True
+22,True
+23,True
+24,False
+25,True
+26,True
+27,True
+28,True
+29,False
+30,True
+31,True
+32,False
+33,True
+34,False
+35,False
+36,True
+37,True
+38,True
+39,True
+40,True
+41,True
+42,False
+43,True
+44,False
+45,False
+46,True
+47,True
+48,False
+49,True
+50,True
+51,False
+52,False
+53,True
+54,True
+55,True
+56,True
+57,True
+58,True
+59,True
+60,True
+61,False
+62,True
+63,True
+64,True
+65,True
+66,True
+67,True
+68,True
+69,True
+70,True
+71,True
+72,True
+73,True
+74,True
+75,True
+76,True
+77,True
+78,True
+79,True
+80,True
+81,True
+82,True
+83,True
+84,True
+85,False
+86,False
+87,True
+88,True
+89,True
+90,False
+91,True
+92,True
+93,True
+94,True
+95,False
+96,False
+97,True
+98,True
+99,True
+100,False
+101,True
+102,True
+103,True
+104,True
+105,True
+106,True
+107,True
+108,True
+109,True
+110,True
+111,True
+112,True
+113,True
+114,True
+115,True
+116,True
+117,True
+118,True
+119,True
+120,True
+121,True
+122,True
+123,True
+124,True
+125,True
+126,True
+127,True
+128,True
+129,True
+130,True
+131,True
+132,False
+133,True
+134,True
+135,True
+136,True
+137,True
+138,True
+139,True
+140,True
+141,True
+142,True
+143,True
+144,True
+145,True
+146,True
+147,True
+148,True
+149,True
+150,True
+151,True
+152,False
+153,True
+154,True
+155,True
+156,True
+157,True
+158,True
+159,True
+160,True
+161,False
+162,True
+163,True
+164,True
+165,True
+166,True
+167,True
+168,True
+169,True
+170,True
+171,True
+172,True
+173,True
+174,True
+175,True
+176,True
+177,True
+178,True
+179,True
+180,True
+181,True
+182,True
+183,True
+184,True
+185,True
+186,True
+187,True
+188,True
+189,True
+190,True
+191,True
+192,True
+193,True
+194,True
+195,True
+196,True
+197,True
+198,False
+199,True
+200,True
+201,True
+202,True
+203,True
+204,True
+205,True
+206,True
+207,True
+208,True
+209,True
+210,True
+211,True
+212,True
+213,True
+214,True
+215,True
+216,True
+217,True
+218,True
+219,False
+220,True
+221,True
+222,True
+223,True
+224,True
+225,True
+226,True
+227,True
+228,True
+229,True
+230,True
+231,True
+232,True
+233,True
+234,True
+235,True
+236,True
+237,True
+238,True
+239,True
+240,True
+241,True
+242,True
+243,True
+244,True
+245,True
+246,True
+247,True
+248,True
+249,True
+250,True
+251,True
+252,True
+253,True
+254,True
+255,True
+256,True
+257,True
+258,True
+259,False
+260,True
+261,True
+262,True
+263,True
+264,True
+265,True
+266,True
+267,True
+268,True
+269,True
+270,True
+271,True
+272,True
+273,False
+274,True
+275,True
+276,True
+277,True
+278,True
+279,True
+280,True
+281,True
+282,True
+283,True
+284,True
+285,True
+286,True
+287,True
+288,True
+289,True
+290,True
+291,True
+292,True
+293,True
+294,True
+295,True
+296,False
+297,True
+298,True
+299,True
+300,True
+301,True
+302,True
+303,True
+304,True
+305,True
+306,True
+307,True
+308,True
+309,True
+310,True
+311,True
+312,True
+313,True
+314,True
+315,True
+316,True
+317,True
+318,True
+319,True
+320,True
+321,True
+322,True
+323,True
+324,True
+325,True
+326,True
+327,True
+328,True
+329,True
+330,True
+331,True
+332,True
+333,True
+334,True
+335,True
+336,True
+337,True
+338,True
+339,True
+340,True
+341,True
+342,True
+343,True
+344,True
+345,True
+346,True
+347,True
+348,True
+349,True
+350,True
+351,True
+352,True
+353,True
+354,True
+355,True
+356,True
+357,True
+358,True
+359,True
+360,True
+361,True
+362,True
+363,True
+364,True
+365,True
+366,True
+367,True
+368,True
+369,True
+370,True
+371,True
+372,True
+373,True
+374,True
+375,True
+376,True
+377,True
+378,True
+379,False
+380,False
+381,False
+382,False
+383,False
+384,False
+385,False
+386,False
+387,False
+388,False
+389,False
+390,False
+391,False
+392,False
+393,False
+394,False
+395,False
+396,False
+397,False
+398,False
+399,False
+400,False
+401,False
+402,False
+403,False
+404,False
+405,False
+406,False
+407,False
+408,False
+409,False
+410,False
+411,False
+412,False
+413,False
+414,False
+415,False
+416,False
+417,False
+418,False
+419,False
+420,False
+421,False
+422,False
+423,False
+424,False
+425,False
+426,False
+427,False
+428,False
+429,False
+430,False
+431,False
+432,False
+433,False
+434,False
+435,False
+436,False
+437,False
+438,False
+439,False
+440,False
+441,False
+442,False
+443,False
+444,False
+445,False
+446,False
+447,False
+448,False
+449,False
+450,False
+451,False
+452,False
+453,False
+454,False
+455,False
+456,False
+457,False
+458,False
+459,False
+460,False
+461,False
+462,False
+463,False
+464,False
+465,False
+466,False
+467,False
+468,False
+469,False
+470,False
+471,False
+472,False
+473,False
+474,False
+475,False
+476,False
+477,False
+478,False
+479,False
+480,False
+481,False
+482,False
+483,False
+484,False
+485,False
+486,False
+487,False
+488,False
+489,False
+490,False
+491,False
+492,False
+493,False
+494,False
+495,False
+496,False
+497,False
+498,False
+499,False
+500,False
+501,False
+502,False
+503,False
+504,False
+505,False
+506,False
+507,False
+508,False
+509,False
+510,False
+511,False
+512,False
+513,False
+514,False
+515,False
+516,False
+517,False
+518,False
+519,False
+520,False
+521,False
+522,False
+523,False
+524,False
+525,False
+526,False
+527,False
+528,False
+529,False
+530,False
+531,False
+532,False
+533,False
+534,False
+535,False
+536,False
+537,False
+538,False
+539,False
+540,False
+541,False
+542,False
+543,True
+544,False
+545,False
+546,False
+547,False
+548,False
+549,False
+550,False
+551,False
+552,False
+553,False
+554,False
+555,True
+556,False
+557,True
+558,False
+559,False
+560,False
+561,False
+562,False
+563,False
+564,False
+565,False
+566,False
+567,False
+568,False
+569,False
+570,False
+571,False
+572,False
+573,False
+574,False
+575,False
+576,False
+577,False
+578,False
+579,False
+580,False
+581,False
+582,False
+583,False
+584,False
+585,False
+586,False
+587,True
+588,False
+589,False
+590,False
+591,False
+592,False
+593,False
+594,False
+595,True
+596,False
+597,False
+598,False
+599,False
+600,False
+601,False
+602,False
+603,False
+604,False
+605,False
+606,False
+607,False
+608,True
+609,False
+610,False
+611,False
+612,False
+613,False
+614,False
+615,False
+616,False
+617,False
+618,False
+619,False
+620,False
+621,False
+622,False
+623,False
+624,False
+625,False
+626,False
+627,False
+628,False
+629,False
+630,False
+631,False
+632,False
+633,False
+634,True
+635,False
+636,True
+637,True
+638,False
+639,False
+640,False
+641,False
+642,False
+643,False
+644,False
+645,False
+646,False
+647,True
+648,False
+649,True
+650,False
+651,False
+652,False
+653,True
+654,False
+655,False
+656,True
+657,False
+658,True
+659,False
+660,False
+661,False
+662,False
+663,False
+664,False
+665,False
+666,False
+667,False
+668,True
+669,False
+670,True
+671,False
+672,False
+673,True
+674,False
+675,False
+676,False
+677,True
+678,False
+679,False
+680,False
+681,False
+682,False
+683,False
+684,False
+685,False
+686,True
+687,True
+688,False
+689,False
+690,False
+691,False
+692,False
+693,False
+694,False
+695,False
+696,False
+697,False
+698,False
+699,False
+700,False
+701,False
+702,False
+703,False
+704,False
+705,False
+706,True
+707,True
+708,False
+709,False
+710,False
+711,False
+712,False
+713,False
+714,False
+715,False
+716,True
+717,True
+718,True
+719,True
+720,False
+721,False
+722,False
+723,False
+724,False
+725,False
+726,False
+727,False
+728,False
+729,False
+730,False
+731,False
+732,False
+733,True
+734,False
+735,False
+736,False
+737,True
+738,False
+739,False
+740,True
+741,True
+742,False
+743,True
+744,False
+745,True
+746,False
+747,False
+748,False
+749,False
+750,False
+751,False
+752,False
+753,False
+754,False
+755,False
+756,False
+757,False
diff --git a/Assignment Colab/Eva Akurut (1).ipynb b/Assignment Colab/Eva Akurut (1).ipynb
new file mode 100644
index 0000000..a28068e
--- /dev/null
+++ b/Assignment Colab/Eva Akurut (1).ipynb	
@@ -0,0 +1,2753 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### ACE_COMPETITION\n",
+    "#### Exploration Data Analysis assignment\n",
+    "- Import the datasets into the notebook\n",
+    "- Find out the Dimensions of the data imported\n",
+    "- Descibe the data using statistics(Descriptive statistics)\n",
+    "- Looking at how the variables correlate with each other\n",
+    "- Data Visualisation\n",
+    "- Preparation of data for Machine Learning\n",
+    "- Evaluate the Performance of Machine Learning Algorithms with Resampling\n",
+    "- Spot-Checking Classiffication Algorithms"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
+    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5"
+   },
+   "outputs": [],
+   "source": [
+    "# Importing the tools to use for the assignment\n",
+    "import numpy as np # linear algebra\n",
+    "import pandas as pd # data structure analysis\n",
+    "import matplotlib.pyplot as plt # for visualisation\n",
+    "import seaborn as sns#\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 1)Loading the data to be used into my notebook"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "###Importing the data sets into the notebook using read.csv\n",
+    "Train=pd.read_csv(\"../AMP Data Sets/AMP_TrainSet.csv\")\n",
+    "Test=pd.read_csv(\"../AMP Data Sets/Test.csv\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 2)Checking the dimensions of my data\n",
+    "This sumarries the data type,Number of columns and rows,if the data has missing values \n",
+    "\n",
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??\n",
+    "   \n",
+    "   When you see the above \"??\" these are the things I need to see:\n",
+    "   - Why are you considering what you are doing: in this case check the dimensions\n",
+    "   - What did you learn?\n",
+    "   - How has it informed your next steps.\n",
+    "   - In otherwords I need more information on what you are doing."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>FULL_Charge</th>\n",
+       "      <th>FULL_AcidicMolPerc</th>\n",
+       "      <th>FULL_AURR980107</th>\n",
+       "      <th>FULL_DAYM780201</th>\n",
+       "      <th>FULL_GEOR030101</th>\n",
+       "      <th>FULL_OOBM850104</th>\n",
+       "      <th>NT_EFC195</th>\n",
+       "      <th>AS_MeanAmphiMoment</th>\n",
+       "      <th>AS_DAYM780201</th>\n",
+       "      <th>AS_FUKS010112</th>\n",
+       "      <th>CT_RACS820104</th>\n",
+       "      <th>CLASS</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>5.0</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.951</td>\n",
+       "      <td>74.842</td>\n",
+       "      <td>0.975</td>\n",
+       "      <td>-3.663</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.282</td>\n",
+       "      <td>73.444</td>\n",
+       "      <td>5.661</td>\n",
+       "      <td>1.041</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>4.0</td>\n",
+       "      <td>5.405</td>\n",
+       "      <td>0.931</td>\n",
+       "      <td>71.595</td>\n",
+       "      <td>0.957</td>\n",
+       "      <td>-4.011</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.600</td>\n",
+       "      <td>68.222</td>\n",
+       "      <td>6.537</td>\n",
+       "      <td>1.453</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>5.5</td>\n",
+       "      <td>5.405</td>\n",
+       "      <td>0.873</td>\n",
+       "      <td>73.595</td>\n",
+       "      <td>0.961</td>\n",
+       "      <td>-2.512</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.593</td>\n",
+       "      <td>69.444</td>\n",
+       "      <td>4.934</td>\n",
+       "      <td>1.722</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>5.0</td>\n",
+       "      <td>4.167</td>\n",
+       "      <td>0.895</td>\n",
+       "      <td>66.250</td>\n",
+       "      <td>0.999</td>\n",
+       "      <td>-1.362</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.614</td>\n",
+       "      <td>67.222</td>\n",
+       "      <td>4.316</td>\n",
+       "      <td>1.382</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>7.5</td>\n",
+       "      <td>8.537</td>\n",
+       "      <td>0.932</td>\n",
+       "      <td>64.720</td>\n",
+       "      <td>0.979</td>\n",
+       "      <td>-2.091</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.616</td>\n",
+       "      <td>72.944</td>\n",
+       "      <td>4.540</td>\n",
+       "      <td>1.539</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   FULL_Charge  FULL_AcidicMolPerc  FULL_AURR980107  FULL_DAYM780201  \\\n",
+       "0          5.0               0.000            0.951           74.842   \n",
+       "1          4.0               5.405            0.931           71.595   \n",
+       "2          5.5               5.405            0.873           73.595   \n",
+       "3          5.0               4.167            0.895           66.250   \n",
+       "4          7.5               8.537            0.932           64.720   \n",
+       "\n",
+       "   FULL_GEOR030101  FULL_OOBM850104  NT_EFC195  AS_MeanAmphiMoment  \\\n",
+       "0            0.975           -3.663          0               0.282   \n",
+       "1            0.957           -4.011          1               0.600   \n",
+       "2            0.961           -2.512          0               0.593   \n",
+       "3            0.999           -1.362          0               0.614   \n",
+       "4            0.979           -2.091          0               0.616   \n",
+       "\n",
+       "   AS_DAYM780201  AS_FUKS010112  CT_RACS820104  CLASS  \n",
+       "0         73.444          5.661          1.041      1  \n",
+       "1         68.222          6.537          1.453      1  \n",
+       "2         69.444          4.934          1.722      1  \n",
+       "3         67.222          4.316          1.382      1  \n",
+       "4         72.944          4.540          1.539      1  "
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "Train.head(5)\n",
+    "# To check the first 5 rows on my dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(FULL_Charge           float64\n",
+       " FULL_AcidicMolPerc    float64\n",
+       " FULL_AURR980107       float64\n",
+       " FULL_DAYM780201       float64\n",
+       " FULL_GEOR030101       float64\n",
+       " FULL_OOBM850104       float64\n",
+       " NT_EFC195               int64\n",
+       " AS_MeanAmphiMoment    float64\n",
+       " AS_DAYM780201         float64\n",
+       " AS_FUKS010112         float64\n",
+       " CT_RACS820104         float64\n",
+       " CLASS                   int64\n",
+       " dtype: object, FULL_Charge           float64\n",
+       " FULL_AcidicMolPerc    float64\n",
+       " FULL_AURR980107       float64\n",
+       " FULL_DAYM780201       float64\n",
+       " FULL_GEOR030101       float64\n",
+       " FULL_OOBM850104       float64\n",
+       " NT_EFC195               int64\n",
+       " AS_MeanAmphiMoment    float64\n",
+       " AS_DAYM780201         float64\n",
+       " AS_FUKS010112         float64\n",
+       " CT_RACS820104         float64\n",
+       " dtype: object)"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Checking the datatype of of my data to determine the class of my data\n",
+    "Train.dtypes ,Test.dtypes\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((3038, 12), (758, 11))"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Finding out the rows and columns present in my data set \n",
+    "Train.shape , Test.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 3038 entries, 0 to 3037\n",
+      "Data columns (total 12 columns):\n",
+      "FULL_Charge           3038 non-null float64\n",
+      "FULL_AcidicMolPerc    3038 non-null float64\n",
+      "FULL_AURR980107       3038 non-null float64\n",
+      "FULL_DAYM780201       3038 non-null float64\n",
+      "FULL_GEOR030101       3038 non-null float64\n",
+      "FULL_OOBM850104       3038 non-null float64\n",
+      "NT_EFC195             3038 non-null int64\n",
+      "AS_MeanAmphiMoment    3038 non-null float64\n",
+      "AS_DAYM780201         3038 non-null float64\n",
+      "AS_FUKS010112         3038 non-null float64\n",
+      "CT_RACS820104         3038 non-null float64\n",
+      "CLASS                 3038 non-null int64\n",
+      "dtypes: float64(10), int64(2)\n",
+      "memory usage: 284.9 KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Printing the summary of the data frame\n",
+    "# Summary includes list of all columns with their data types and the number of non-null values in each column. \n",
+    "#we also have the value of rangeindex provided for the index axis.\n",
+    "Train.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['FULL_Charge', 'FULL_AcidicMolPerc', 'FULL_AURR980107',\n",
+       "       'FULL_DAYM780201', 'FULL_GEOR030101', 'FULL_OOBM850104', 'NT_EFC195',\n",
+       "       'AS_MeanAmphiMoment', 'AS_DAYM780201', 'AS_FUKS010112', 'CT_RACS820104',\n",
+       "       'CLASS'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Printing the column names to get to know the names of the columns\n",
+    "Train.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# In general, both the train and Test datasets have float and intenger data types\n",
+    "#The Train Data set has 3038 rows and 12 columns\n",
+    "# The Test Data set has 758 rows plus 11 columns"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 3)Descriptive statistics\n",
+    "Descriptive statistics can give you great insight into the shape of each attribute.\n",
+    "\n",
+    "Often you can create more summaries than you have time to review. The describe() function on the Pandas DataFrame lists 8 statistical properties of each attribute:\n",
+    "Count,Mean,Standard Devaition,Minimum Value,25th Percentile,50th Percentile (Median),75th Percentile,Maximum Value.\n",
+    "\n",
+    "\n",
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>FULL_Charge</th>\n",
+       "      <th>FULL_AcidicMolPerc</th>\n",
+       "      <th>FULL_AURR980107</th>\n",
+       "      <th>FULL_DAYM780201</th>\n",
+       "      <th>FULL_GEOR030101</th>\n",
+       "      <th>FULL_OOBM850104</th>\n",
+       "      <th>NT_EFC195</th>\n",
+       "      <th>AS_MeanAmphiMoment</th>\n",
+       "      <th>AS_DAYM780201</th>\n",
+       "      <th>AS_FUKS010112</th>\n",
+       "      <th>CT_RACS820104</th>\n",
+       "      <th>CLASS</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "      <td>3038.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>2.060237</td>\n",
+       "      <td>8.521520</td>\n",
+       "      <td>0.971410</td>\n",
+       "      <td>73.668760</td>\n",
+       "      <td>0.994007</td>\n",
+       "      <td>-2.432927</td>\n",
+       "      <td>0.088545</td>\n",
+       "      <td>15.683233</td>\n",
+       "      <td>73.650828</td>\n",
+       "      <td>5.911361</td>\n",
+       "      <td>1.235255</td>\n",
+       "      <td>0.500000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>3.819929</td>\n",
+       "      <td>7.586652</td>\n",
+       "      <td>0.107413</td>\n",
+       "      <td>8.527489</td>\n",
+       "      <td>0.031333</td>\n",
+       "      <td>1.707223</td>\n",
+       "      <td>0.284133</td>\n",
+       "      <td>11.575665</td>\n",
+       "      <td>9.166092</td>\n",
+       "      <td>0.693689</td>\n",
+       "      <td>0.210012</td>\n",
+       "      <td>0.500082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>-16.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.684000</td>\n",
+       "      <td>42.750000</td>\n",
+       "      <td>0.866000</td>\n",
+       "      <td>-10.432000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.041000</td>\n",
+       "      <td>42.778000</td>\n",
+       "      <td>3.533000</td>\n",
+       "      <td>0.785000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>2.516000</td>\n",
+       "      <td>0.895000</td>\n",
+       "      <td>68.294000</td>\n",
+       "      <td>0.974000</td>\n",
+       "      <td>-3.606000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>5.587500</td>\n",
+       "      <td>67.556000</td>\n",
+       "      <td>5.459250</td>\n",
+       "      <td>1.082000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>2.000000</td>\n",
+       "      <td>7.143000</td>\n",
+       "      <td>0.963000</td>\n",
+       "      <td>74.059500</td>\n",
+       "      <td>0.994000</td>\n",
+       "      <td>-2.296500</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>14.988500</td>\n",
+       "      <td>73.697000</td>\n",
+       "      <td>5.925500</td>\n",
+       "      <td>1.184000</td>\n",
+       "      <td>0.500000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>4.000000</td>\n",
+       "      <td>13.158000</td>\n",
+       "      <td>1.041000</td>\n",
+       "      <td>79.343750</td>\n",
+       "      <td>1.011000</td>\n",
+       "      <td>-1.283250</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>26.807750</td>\n",
+       "      <td>79.778000</td>\n",
+       "      <td>6.382000</td>\n",
+       "      <td>1.351000</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>30.000000</td>\n",
+       "      <td>46.667000</td>\n",
+       "      <td>1.451000</td>\n",
+       "      <td>101.682000</td>\n",
+       "      <td>1.196000</td>\n",
+       "      <td>3.576000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>51.280000</td>\n",
+       "      <td>103.167000</td>\n",
+       "      <td>8.662000</td>\n",
+       "      <td>2.192000</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       FULL_Charge  FULL_AcidicMolPerc  FULL_AURR980107  FULL_DAYM780201  \\\n",
+       "count  3038.000000         3038.000000      3038.000000      3038.000000   \n",
+       "mean      2.060237            8.521520         0.971410        73.668760   \n",
+       "std       3.819929            7.586652         0.107413         8.527489   \n",
+       "min     -16.000000            0.000000         0.684000        42.750000   \n",
+       "25%       0.000000            2.516000         0.895000        68.294000   \n",
+       "50%       2.000000            7.143000         0.963000        74.059500   \n",
+       "75%       4.000000           13.158000         1.041000        79.343750   \n",
+       "max      30.000000           46.667000         1.451000       101.682000   \n",
+       "\n",
+       "       FULL_GEOR030101  FULL_OOBM850104    NT_EFC195  AS_MeanAmphiMoment  \\\n",
+       "count      3038.000000      3038.000000  3038.000000         3038.000000   \n",
+       "mean          0.994007        -2.432927     0.088545           15.683233   \n",
+       "std           0.031333         1.707223     0.284133           11.575665   \n",
+       "min           0.866000       -10.432000     0.000000            0.041000   \n",
+       "25%           0.974000        -3.606000     0.000000            5.587500   \n",
+       "50%           0.994000        -2.296500     0.000000           14.988500   \n",
+       "75%           1.011000        -1.283250     0.000000           26.807750   \n",
+       "max           1.196000         3.576000     1.000000           51.280000   \n",
+       "\n",
+       "       AS_DAYM780201  AS_FUKS010112  CT_RACS820104        CLASS  \n",
+       "count    3038.000000    3038.000000    3038.000000  3038.000000  \n",
+       "mean       73.650828       5.911361       1.235255     0.500000  \n",
+       "std         9.166092       0.693689       0.210012     0.500082  \n",
+       "min        42.778000       3.533000       0.785000     0.000000  \n",
+       "25%        67.556000       5.459250       1.082000     0.000000  \n",
+       "50%        73.697000       5.925500       1.184000     0.500000  \n",
+       "75%        79.778000       6.382000       1.351000     1.000000  \n",
+       "max       103.167000       8.662000       2.192000     1.000000  "
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Getting the spread of my data\n",
+    "Train.describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x1a10e43d90>"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Splitting my data into by classfication to find out how balanced the v\n",
+    "#A groupby operation involves a combination of splitting the object, \n",
+    "#Then application of a function, and combining the results.\n",
+    "Train.groupby(\"CLASS\").size().plot(kind=\"bar\")                             "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??\n",
+    "   The plot is crowded on the x-axis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x1a10f63510>"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.countplot(x = 'FULL_Charge', data = Train)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 4)Checking how my data correlates with each other \n",
+    "In statistics, correlation or dependence is any statistical relationship, whether causal or not, between two random variables or bivariate data.\n",
+    "Here the intension was to find out if there is a relationship**** between the variables\n",
+    "\n",
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??\n",
+    "   \n",
+    "   Great visuals, but what do they mean?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>FULL_Charge</th>\n",
+       "      <th>FULL_AcidicMolPerc</th>\n",
+       "      <th>FULL_AURR980107</th>\n",
+       "      <th>FULL_DAYM780201</th>\n",
+       "      <th>FULL_GEOR030101</th>\n",
+       "      <th>FULL_OOBM850104</th>\n",
+       "      <th>NT_EFC195</th>\n",
+       "      <th>AS_MeanAmphiMoment</th>\n",
+       "      <th>AS_DAYM780201</th>\n",
+       "      <th>AS_FUKS010112</th>\n",
+       "      <th>CT_RACS820104</th>\n",
+       "      <th>CLASS</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>FULL_Charge</th>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.612996</td>\n",
+       "      <td>-0.490977</td>\n",
+       "      <td>-0.434603</td>\n",
+       "      <td>-0.058725</td>\n",
+       "      <td>-0.283758</td>\n",
+       "      <td>0.088068</td>\n",
+       "      <td>0.355477</td>\n",
+       "      <td>-0.365374</td>\n",
+       "      <td>-0.090570</td>\n",
+       "      <td>0.232929</td>\n",
+       "      <td>0.534602</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>FULL_AcidicMolPerc</th>\n",
+       "      <td>-0.612996</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.794796</td>\n",
+       "      <td>0.541481</td>\n",
+       "      <td>0.115201</td>\n",
+       "      <td>0.513344</td>\n",
+       "      <td>-0.143168</td>\n",
+       "      <td>-0.431590</td>\n",
+       "      <td>0.449621</td>\n",
+       "      <td>0.002334</td>\n",
+       "      <td>-0.213543</td>\n",
+       "      <td>-0.598816</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>FULL_AURR980107</th>\n",
+       "      <td>-0.490977</td>\n",
+       "      <td>0.794796</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.548253</td>\n",
+       "      <td>0.346139</td>\n",
+       "      <td>0.462712</td>\n",
+       "      <td>-0.169540</td>\n",
+       "      <td>-0.426097</td>\n",
+       "      <td>0.456260</td>\n",
+       "      <td>0.032958</td>\n",
+       "      <td>-0.403599</td>\n",
+       "      <td>-0.584111</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>FULL_DAYM780201</th>\n",
+       "      <td>-0.434603</td>\n",
+       "      <td>0.541481</td>\n",
+       "      <td>0.548253</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.010118</td>\n",
+       "      <td>0.334778</td>\n",
+       "      <td>-0.090058</td>\n",
+       "      <td>-0.408793</td>\n",
+       "      <td>0.894191</td>\n",
+       "      <td>0.055915</td>\n",
+       "      <td>-0.326792</td>\n",
+       "      <td>-0.554838</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>FULL_GEOR030101</th>\n",
+       "      <td>-0.058725</td>\n",
+       "      <td>0.115201</td>\n",
+       "      <td>0.346139</td>\n",
+       "      <td>0.010118</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.319157</td>\n",
+       "      <td>-0.230417</td>\n",
+       "      <td>-0.160269</td>\n",
+       "      <td>-0.029085</td>\n",
+       "      <td>0.040480</td>\n",
+       "      <td>-0.151935</td>\n",
+       "      <td>-0.260470</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>FULL_OOBM850104</th>\n",
+       "      <td>-0.283758</td>\n",
+       "      <td>0.513344</td>\n",
+       "      <td>0.462712</td>\n",
+       "      <td>0.334778</td>\n",
+       "      <td>0.319157</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.230561</td>\n",
+       "      <td>-0.336297</td>\n",
+       "      <td>0.275640</td>\n",
+       "      <td>-0.452769</td>\n",
+       "      <td>0.155304</td>\n",
+       "      <td>-0.453287</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>NT_EFC195</th>\n",
+       "      <td>0.088068</td>\n",
+       "      <td>-0.143168</td>\n",
+       "      <td>-0.169540</td>\n",
+       "      <td>-0.090058</td>\n",
+       "      <td>-0.230417</td>\n",
+       "      <td>-0.230561</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.178683</td>\n",
+       "      <td>-0.036844</td>\n",
+       "      <td>0.145924</td>\n",
+       "      <td>0.080898</td>\n",
+       "      <td>0.260702</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AS_MeanAmphiMoment</th>\n",
+       "      <td>0.355477</td>\n",
+       "      <td>-0.431590</td>\n",
+       "      <td>-0.426097</td>\n",
+       "      <td>-0.408793</td>\n",
+       "      <td>-0.160269</td>\n",
+       "      <td>-0.336297</td>\n",
+       "      <td>0.178683</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.322378</td>\n",
+       "      <td>0.025580</td>\n",
+       "      <td>0.171524</td>\n",
+       "      <td>0.693552</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AS_DAYM780201</th>\n",
+       "      <td>-0.365374</td>\n",
+       "      <td>0.449621</td>\n",
+       "      <td>0.456260</td>\n",
+       "      <td>0.894191</td>\n",
+       "      <td>-0.029085</td>\n",
+       "      <td>0.275640</td>\n",
+       "      <td>-0.036844</td>\n",
+       "      <td>-0.322378</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.045562</td>\n",
+       "      <td>-0.256060</td>\n",
+       "      <td>-0.437168</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>AS_FUKS010112</th>\n",
+       "      <td>-0.090570</td>\n",
+       "      <td>0.002334</td>\n",
+       "      <td>0.032958</td>\n",
+       "      <td>0.055915</td>\n",
+       "      <td>0.040480</td>\n",
+       "      <td>-0.452769</td>\n",
+       "      <td>0.145924</td>\n",
+       "      <td>0.025580</td>\n",
+       "      <td>0.045562</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.445284</td>\n",
+       "      <td>0.033432</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>CT_RACS820104</th>\n",
+       "      <td>0.232929</td>\n",
+       "      <td>-0.213543</td>\n",
+       "      <td>-0.403599</td>\n",
+       "      <td>-0.326792</td>\n",
+       "      <td>-0.151935</td>\n",
+       "      <td>0.155304</td>\n",
+       "      <td>0.080898</td>\n",
+       "      <td>0.171524</td>\n",
+       "      <td>-0.256060</td>\n",
+       "      <td>-0.445284</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.267652</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>CLASS</th>\n",
+       "      <td>0.534602</td>\n",
+       "      <td>-0.598816</td>\n",
+       "      <td>-0.584111</td>\n",
+       "      <td>-0.554838</td>\n",
+       "      <td>-0.260470</td>\n",
+       "      <td>-0.453287</td>\n",
+       "      <td>0.260702</td>\n",
+       "      <td>0.693552</td>\n",
+       "      <td>-0.437168</td>\n",
+       "      <td>0.033432</td>\n",
+       "      <td>0.267652</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                    FULL_Charge  FULL_AcidicMolPerc  FULL_AURR980107  \\\n",
+       "FULL_Charge            1.000000           -0.612996        -0.490977   \n",
+       "FULL_AcidicMolPerc    -0.612996            1.000000         0.794796   \n",
+       "FULL_AURR980107       -0.490977            0.794796         1.000000   \n",
+       "FULL_DAYM780201       -0.434603            0.541481         0.548253   \n",
+       "FULL_GEOR030101       -0.058725            0.115201         0.346139   \n",
+       "FULL_OOBM850104       -0.283758            0.513344         0.462712   \n",
+       "NT_EFC195              0.088068           -0.143168        -0.169540   \n",
+       "AS_MeanAmphiMoment     0.355477           -0.431590        -0.426097   \n",
+       "AS_DAYM780201         -0.365374            0.449621         0.456260   \n",
+       "AS_FUKS010112         -0.090570            0.002334         0.032958   \n",
+       "CT_RACS820104          0.232929           -0.213543        -0.403599   \n",
+       "CLASS                  0.534602           -0.598816        -0.584111   \n",
+       "\n",
+       "                    FULL_DAYM780201  FULL_GEOR030101  FULL_OOBM850104  \\\n",
+       "FULL_Charge               -0.434603        -0.058725        -0.283758   \n",
+       "FULL_AcidicMolPerc         0.541481         0.115201         0.513344   \n",
+       "FULL_AURR980107            0.548253         0.346139         0.462712   \n",
+       "FULL_DAYM780201            1.000000         0.010118         0.334778   \n",
+       "FULL_GEOR030101            0.010118         1.000000         0.319157   \n",
+       "FULL_OOBM850104            0.334778         0.319157         1.000000   \n",
+       "NT_EFC195                 -0.090058        -0.230417        -0.230561   \n",
+       "AS_MeanAmphiMoment        -0.408793        -0.160269        -0.336297   \n",
+       "AS_DAYM780201              0.894191        -0.029085         0.275640   \n",
+       "AS_FUKS010112              0.055915         0.040480        -0.452769   \n",
+       "CT_RACS820104             -0.326792        -0.151935         0.155304   \n",
+       "CLASS                     -0.554838        -0.260470        -0.453287   \n",
+       "\n",
+       "                    NT_EFC195  AS_MeanAmphiMoment  AS_DAYM780201  \\\n",
+       "FULL_Charge          0.088068            0.355477      -0.365374   \n",
+       "FULL_AcidicMolPerc  -0.143168           -0.431590       0.449621   \n",
+       "FULL_AURR980107     -0.169540           -0.426097       0.456260   \n",
+       "FULL_DAYM780201     -0.090058           -0.408793       0.894191   \n",
+       "FULL_GEOR030101     -0.230417           -0.160269      -0.029085   \n",
+       "FULL_OOBM850104     -0.230561           -0.336297       0.275640   \n",
+       "NT_EFC195            1.000000            0.178683      -0.036844   \n",
+       "AS_MeanAmphiMoment   0.178683            1.000000      -0.322378   \n",
+       "AS_DAYM780201       -0.036844           -0.322378       1.000000   \n",
+       "AS_FUKS010112        0.145924            0.025580       0.045562   \n",
+       "CT_RACS820104        0.080898            0.171524      -0.256060   \n",
+       "CLASS                0.260702            0.693552      -0.437168   \n",
+       "\n",
+       "                    AS_FUKS010112  CT_RACS820104     CLASS  \n",
+       "FULL_Charge             -0.090570       0.232929  0.534602  \n",
+       "FULL_AcidicMolPerc       0.002334      -0.213543 -0.598816  \n",
+       "FULL_AURR980107          0.032958      -0.403599 -0.584111  \n",
+       "FULL_DAYM780201          0.055915      -0.326792 -0.554838  \n",
+       "FULL_GEOR030101          0.040480      -0.151935 -0.260470  \n",
+       "FULL_OOBM850104         -0.452769       0.155304 -0.453287  \n",
+       "NT_EFC195                0.145924       0.080898  0.260702  \n",
+       "AS_MeanAmphiMoment       0.025580       0.171524  0.693552  \n",
+       "AS_DAYM780201            0.045562      -0.256060 -0.437168  \n",
+       "AS_FUKS010112            1.000000      -0.445284  0.033432  \n",
+       "CT_RACS820104           -0.445284       1.000000  0.267652  \n",
+       "CLASS                    0.033432       0.267652  1.000000  "
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "corr=Train.corr(method='pearson')\n",
+    "corr\n",
+    "# The correllation 1 is a positive relationship, -1 a negative relationship and 0 no relationship"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x1a11065f90>"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x864 with 2 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.figure(figsize=(12,12))\n",
+    "sns.heatmap(Train.corr(method='pearson'),annot=True,cmap=\"YlGnBu\")\n",
+    "#Heatmap is a way of representing the data in a 2-dimensional form. The data values are represented as colors in the graph. \n",
+    "#It's goal is to provide a colored visual summary of information\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<seaborn.matrix.ClusterGrid at 0x1a114e2850>"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 720x720 with 4 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#For more depth of understanding the data the clustermap method is used \n",
+    "#The .clustermap() method uses a hierarchical clusters to order data by similarity.\n",
+    "#This reorganizes the data for the rows and columns and displays similar content next to one another \n",
+    "\n",
+    "sns.clustermap(Train.corr(method='pearson'),annot=True, cmap=\"Paired_r\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "FULL_Charge           0.534602\n",
+       "FULL_AcidicMolPerc   -0.598816\n",
+       "FULL_AURR980107      -0.584111\n",
+       "FULL_DAYM780201      -0.554838\n",
+       "FULL_GEOR030101      -0.260470\n",
+       "FULL_OOBM850104      -0.453287\n",
+       "NT_EFC195             0.260702\n",
+       "AS_MeanAmphiMoment    0.693552\n",
+       "AS_DAYM780201        -0.437168\n",
+       "AS_FUKS010112         0.033432\n",
+       "CT_RACS820104         0.267652\n",
+       "CLASS                 1.000000\n",
+       "Name: CLASS, dtype: float64"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Showing how each variable correlates with the CLASS variable\n",
+    "Train.corr(method='pearson')['CLASS']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 5)Data Visualisation\n",
+    "*Data visualizations in python can be done via many packages.\n",
+    "*Using matplot enables one to have a visual figures for the data\n",
+    "*Every Axes has an x-axis and y-axis for plotting. \n",
+    "*Contained within the axes are titles, ticks, labels associated with each axis\n",
+    "\n",
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??\n",
+    "   \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x1a1c29e190>"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#1)To check for skewness in my dataset\n",
+    "#Skew refers to a distribution that is assumed Gaussian (normal or bell curve) that is shifted in one direction or another\n",
+    "Train.skew().plot(kind='bar')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 12 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# 2) Use of the box plot\n",
+    "#Boxplots summarize the distribution of each attribute\n",
+    "#A line for the median (middle value) is drawn while and a box put around the 25th and 75th percentiles.\n",
+    "#The whiskers give an idea of the spread of the data and dots outside of the whiskers show candidate outlier values \n",
+    "# Box plots\n",
+    "Train.plot(kind='box', subplots=True, layout=(4,3), sharex=True,sharey=True)\n",
+    "plt.subplots_adjust(bottom=1, right=2, top=3)\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<seaborn.axisgrid.PairGrid at 0x1a1c29e1d0>"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1080x1080 with 42 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#3) Scatter plot: This is to relationship between two variables as dots in two dimension.\n",
+    "#This is done so we could spot if there is a structured relationship within the two variables\n",
+    "sns.pairplot(data=Train[['FULL_Charge','FULL_DAYM780201','FULL_OOBM850104', 'NT_EFC195',\n",
+    "       'AS_MeanAmphiMoment','CLASS']])\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Figure size 1080x1080 with 0 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 12 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Histograms\n",
+    "plt.figure(figsize=(15,15))\n",
+    "Train.hist(color='red')\n",
+    "\n",
+    "plt.subplots_adjust(bottom=1, right=2, top=3)\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 6)Preparation of data for Machine Learning\n",
+    "Pre-processing of Data is carried out in this section\n",
+    "\n",
+    "\n",
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[0.457 0.    0.348 0.545 0.33  0.483 0.    0.005 0.508 0.415 0.182]\n",
+      " [0.435 0.116 0.322 0.489 0.276 0.458 1.    0.011 0.421 0.586 0.475]\n",
+      " [0.467 0.116 0.246 0.523 0.288 0.565 0.    0.011 0.442 0.273 0.666]\n",
+      " [0.457 0.089 0.275 0.399 0.403 0.647 0.    0.011 0.405 0.153 0.424]\n",
+      " [0.511 0.183 0.323 0.373 0.342 0.595 0.    0.011 0.5   0.196 0.536]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "#1) I will need to preapre my data for prepossessing \n",
+    "# My preffered method for Data transformation is \"The Fit and Multiple Transform\" method form the scikit-learn library.\n",
+    "#Split the dataset into the input and output variables for machine learning.\n",
+    "#Apply a pre-processing transform to the input variables.\n",
+    "#Summarize the data to show the change.\n",
+    "#Rescaling the Data:Since the attributes have varying scales\n",
+    "\n",
+    "from numpy import set_printoptions\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "\n",
+    "array = Train.values\n",
+    "# separate array into input and output components\n",
+    "X= array[:,0:11]\n",
+    "Y= array[:,11]\n",
+    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
+    "rescaledX = scaler.fit_transform(X)\n",
+    "# summarize transformed data\n",
+    "set_printoptions(precision=3)\n",
+    "print(rescaledX[0:5,:])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[1. 0. 1. 1. 1. 0. 0. 1. 1. 1. 1.]\n",
+      " [1. 1. 1. 1. 1. 0. 1. 1. 1. 1. 1.]\n",
+      " [1. 1. 1. 1. 1. 0. 0. 1. 1. 1. 1.]\n",
+      " [1. 1. 1. 1. 1. 0. 0. 1. 1. 1. 1.]\n",
+      " [1. 1. 1. 1. 1. 0. 0. 1. 1. 1. 1.]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Looking at when my data is binarized instead\n",
+    "from sklearn.preprocessing import Binarizer\n",
+    "\n",
+    "array2 = Train.values\n",
+    "# separate array into input and output components\n",
+    "X = array2[:,0:11]\n",
+    "Y = array2[:,11]\n",
+    "binarizer = Binarizer(threshold=0.0).fit(X)\n",
+    "binaryX = binarizer.transform(X)\n",
+    "# summarize transformed data\n",
+    "set_printoptions(precision=3)\n",
+    "print(binaryX[0:5,:])\n",
+    "\n",
+    "#NB:This binarised data was not used "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Num Features:  6\n",
+      "Selected Features: [ True False  True False  True  True  True False False False  True]\n",
+      "Feature Ranking:  [1 5 1 4 1 1 1 2 6 3 1]\n",
+      "Num Features:  6\n",
+      "Selected Features: [ True False  True False  True  True  True False False False  True]\n",
+      "Feature Ranking:  [1 5 1 4 1 1 1 2 6 3 1]\n"
+     ]
+    }
+   ],
+   "source": [
+    "#b) Feature Selection\n",
+    "#Select an anttribute will will give the most to the prediction variable \n",
+    "#a)Selection is by The Recursive Feature Elimination (or RFE) \n",
+    "# This works by recursively removing attributes and building a model on those attributes that remain.\n",
+    "from sklearn.feature_selection import RFE\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "\n",
+    "# feature extraction\n",
+    "# feature extraction\n",
+    "model = LogisticRegression()\n",
+    "rfe = RFE(model, 6)\n",
+    "fit = rfe.fit(X, Y)\n",
+    "print(\"Num Features: \",  fit.n_features_)\n",
+    "print(\"Selected Features:\",  fit.support_)\n",
+    "print(\"Feature Ranking: \",  fit.ranking_)\n",
+    "print(\"Num Features: \",  fit.n_features_)\n",
+    "print(\"Selected Features:\",  fit.support_)\n",
+    "print(\"Feature Ranking: \",  fit.ranking_)\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   ## ??\n",
+    "   \n",
+    "   Why are you doing PCA?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Explained Variance: [0.605 0.242 0.103]\n",
+      "[[ 1.409e-01 -3.557e-01 -4.743e-03 -4.935e-01 -1.975e-04 -5.101e-02\n",
+      "   2.877e-03  6.020e-01 -4.950e-01 -8.765e-04  4.186e-03]\n",
+      " [-8.867e-03  3.090e-02  4.994e-04  3.921e-01 -5.282e-04 -8.492e-03\n",
+      "   3.437e-03  7.629e-01  5.129e-01  5.018e-03 -2.000e-03]\n",
+      " [-2.731e-01  8.713e-01  8.049e-03 -1.349e-01  4.214e-04  8.143e-02\n",
+      "  -2.941e-03  2.312e-01 -2.966e-01 -1.359e-03 -5.700e-04]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.decomposition import PCA\n",
+    "array = Train.values\n",
+    "X = array[:,0:11]\n",
+    "Y = array[:,11]\n",
+    "# feature extraction\n",
+    "pca = PCA(n_components=3)\n",
+    "fit = pca.fit(X)\n",
+    "# summarize components\n",
+    "print(\"Explained Variance: %s\" % fit.explained_variance_ratio_)\n",
+    "print(fit.components_)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[0.089 0.145 0.077 0.088 0.052 0.075 0.037 0.309 0.051 0.032 0.046]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Feature importance\n",
+    "from sklearn.ensemble import ExtraTreesClassifier\n",
+    "\n",
+    "array = Train.values\n",
+    "A = array[:,0:11]\n",
+    "B = array[:,11]\n",
+    "# feature extraction\n",
+    "model = ExtraTreesClassifier()\n",
+    "model.fit(A, B)\n",
+    "print(model.feature_importances_)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## According to feature importance all the features in the data set were useful hence could not be lost and therefore i kept them all\n",
+    "\n",
+    "<div class ='alert alert-info'>\n",
+    "    \n",
+    "   Could you draw a graph for this?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 7)Evaluate the Performance of Machine Learning Algorithms with Resampling\n",
+    "##There is need to know how well the algorithms will perform on unseen data\n",
+    "##The best way to evaluate the performance of an algorithm is to make predictions for new data to which  answers are known\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy:  91.54135338345864\n"
+     ]
+    }
+   ],
+   "source": [
+    "## Split the  Data into Test and Train\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "test_size = 0.35\n",
+    "seed = 7\n",
+    "\n",
+    "X_train,X_test, Y_train, Y_test = train_test_split(X, Y, test_size=test_size,\n",
+    "random_state=seed)\n",
+    "model = LogisticRegression()\n",
+    "model.fit(X_train, Y_train)\n",
+    "result = model.score(X_test, Y_test)\n",
+    "print(\"Accuracy: \",  (result*100.0))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "383\n",
+      "375\n"
+     ]
+    }
+   ],
+   "source": [
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy:  91.82330827067669\n"
+     ]
+    }
+   ],
+   "source": [
+    "# On rescaled Data\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "array = Train.values\n",
+    "X = array[:,0:11]\n",
+    "Y = array[:,11]\n",
+    "test_size = 0.35\n",
+    "seed = 7\n",
+    "\n",
+    "rescaledX_train,rescaledX_test, Y_train, Y_test = train_test_split(rescaledX, Y, test_size=test_size,\n",
+    "random_state=seed)\n",
+    "model = LogisticRegression()\n",
+    "model.fit(rescaledX_train, Y_train)\n",
+    "result = model.score(rescaledX_test, Y_test)\n",
+    "print(\"Accuracy: \",  (result*100.0))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "746\n",
+      "12\n"
+     ]
+    }
+   ],
+   "source": [
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber1_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Despite having a similar accuracy of 91.82,the rescaled data was giving imbalanced false a.nd true values and therefore i would not use it further"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: (88.66787208086441, 18.91491119508906)\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Classification accuracy:is the number of correct predictions made as a ratio of all predictions made.\n",
+    "from sklearn.model_selection import KFold\n",
+    "from sklearn.model_selection import cross_val_score\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "\n",
+    "array = Train.values\n",
+    "\n",
+    "num_folds = 20#number of folds to use\n",
+    "seed = 7#reproducibility\n",
+    "\n",
+    "kfold = KFold(n_splits=num_folds, random_state=None)\n",
+    "model = LogisticRegression()\n",
+    "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=test_size,\n",
+    "random_state=seed)\n",
+    "model.fit(X_train, Y_train)\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "\n",
+    "print(f\"Accuracy:\", (results.mean()*100.0, results.std()*100.0))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "383\n",
+      "375\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber2_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "         0.0       0.91      0.92      0.92       530\n",
+      "         1.0       0.92      0.91      0.92       534\n",
+      "\n",
+      "    accuracy                           0.92      1064\n",
+      "   macro avg       0.92      0.92      0.92      1064\n",
+      "weighted avg       0.92      0.92      0.92      1064\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "#To check out the classification report \n",
+    "from sklearn.metrics import classification_report\n",
+    "\n",
+    "array = Train.values\n",
+    "X = array[:,0:11]\n",
+    "Y = array[:,11]\n",
+    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
+    "rescaledA = scaler.fit_transform(A)\n",
+    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
+    "rescaledA = scaler.fit_transform(A)\n",
+    "test_size = 0.35\n",
+    "seed = 7\n",
+    "rescaledX_train,rescaledX_test, Y_train, Y_test = train_test_split(rescaledX, Y, test_size=test_size,\n",
+    "random_state=seed)\n",
+    "model = LogisticRegression()\n",
+    "model.fit(rescaledX_train, Y_train)\n",
+    "predicted = model.predict(rescaledX_test)\n",
+    "report = classification_report(Y_test, predicted)\n",
+    "print(report)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MAE: (-0.26434068269258093, 0.156909136567752)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# we then look at the regression M\n",
+    "# The Mean Absolute Error(MAE) is the sum of the absolute differences between predictions and actual values.\n",
+    "# Its aim is to give an idea of how wrong the predictions were. \n",
+    "from pandas import read_csv\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "array = Train.values\n",
+    "X = array[:,0:11]\n",
+    "Y = array[:,11]\n",
+    "kfold = KFold(n_splits=10, random_state=None)\n",
+    "model = LinearRegression()\n",
+    "scoring = 'neg_mean_absolute_error'\n",
+    "results = cross_val_score(model, rescaledX, Y, cv=kfold, scoring=scoring)\n",
+    "print(\"MAE:\",(results.mean(), results.std()))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "R^2: (-1.2197243963358124, 3.6591731890074377)\n"
+     ]
+    }
+   ],
+   "source": [
+    "#The R2 metric provides an indication of the goodness of fit of a set of predictions to the actual values\n",
+    "#Cross Validation Regression R^2\n",
+    "array = Train.values\n",
+    "X = array[:,0:11]\n",
+    "Y = array[:,11]\n",
+    "\n",
+    "kfold = KFold(n_splits=10, random_state=None)\n",
+    "model = LinearRegression()\n",
+    "scoring = 'r2'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)\n",
+    "print(\"R^2:\",(results.mean(), results.std()))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 8)Spot-Checking Classiffication Algorithms\n",
+    "##Algorithms Overview\n",
+    "##looking at six classication algorithms that will help spot-check on your dataset. Starting with two ##linear machine learning algorithms:\n",
+    "\n",
+    "8.1.1) - Logistic Regression.\n",
+    "\n",
+    "8.1.2) - Linear Discriminant Analysis.\n",
+    "Then looking at four nonlinear machine learning algorithms:\n",
+    "\n",
+    "8.2.1) - k-Nearest Neighbors.\n",
+    "\n",
+    "8.2.2) - Naive Bayes.\n",
+    "\n",
+    "8.2.3) - Classication and Regression Trees.\n",
+    "\n",
+    "8.2.4)Support Vector Machines.\n",
+    "\n",
+    "8.2.5)Random Forest\n",
+    "\n",
+    "8.2.6)Gradient Boosting for classification\n",
+    "\n",
+    "8.2.7)An extra-trees classifier.\n",
+    "\n",
+    "8.2.8)Neural Network-MLPC"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    " ## 8.1)Linear Machine Language Alogarithms\n",
+    "### 8.1.1)Logistic Regression\n",
+    "Logistic regression assumes a Gaussian distribution for the numeric input variables and can model binary classiffication problems.\n",
+    "****This is done using the Logisticregression class****"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 91.40839412888656\n",
+      "MCC: 0.8342865299822478\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Logistic Regression Classification\n",
+    "from sklearn.model_selection import KFold\n",
+    "from sklearn.model_selection import cross_val_score\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.metrics import matthews_corrcoef\n",
+    "from sklearn.metrics import plot_confusion_matrix\n",
+    "\n",
+    "#for model set up\n",
+    "model = LogisticRegression()\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "383\n",
+      "375\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the LogisticRegression predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber3_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The difference between Accuracy and MCC model is slight but giving the same output pf 383 True values and 375 false values"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 8.1.2)Linear Discriminant Analysis or LDA \n",
+    "-This a statistical technique for binary and multiclass classiffication. \n",
+    "-It too assumes a Gaussian distribution for the numerical input variables. \n",
+    "-You can construct an LDA model using the LinearDiscriminantAnalysis class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 91.77088761507731\n",
+      "MCC: 0.8377162908048379\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
+    "#Model set up\n",
+    "model = LinearDiscriminantAnalysis()\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=9\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "401\n",
+      "357\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the  LinearDiscriminantAnalysis predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber4_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 8.2 Nonlinear machine learning algorithms.\n",
+    "\n",
+    "### 8.2.1)k-Nearest Neighbors\n",
+    "##The k-Nearest Neighbors algorithm (or KNN) uses a distance metric to find the k most similar instances ##In the training data for a new instance and takes the mean outcome of the neighbors as the prediction. #You can construct a KNN model using the KNeighborsClassifier class."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 90.65117488944769\n",
+      "MCC: 0.8690586462107053\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.neighbors import KNeighborsClassifier\n",
+    "#Model set up\n",
+    "model = KNeighborsClassifier()\n",
+    "# For cross validation of data\n",
+    "num_folds = 5\n",
+    "seed=8\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "402\n",
+      "356\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the  LinearDiscriminantAnalysis predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber5_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 8.2.2) Naive Bayes\n",
+    "-Naive Bayes calculates the probability of each class and the conditional probability of each class given each input value. \n",
+    "-These probabilities are estimated for new data and multiplied together\n",
+    "-The Assumption is that they are all independent (a simple or naive assumption).\n",
+    "-When working with real-valued data, a Gaussian distribution is assumed to easily estimate the probabilities for input variables using the Gaussian Probability Density Function. \n",
+    "##You can construct a Naive Bayes model using the GaussianNB class4"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 91.93546986277575\n",
+      "MCC: 0.8407203694376205\n",
+      "0.9193546986277574\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.naive_bayes import GaussianNB\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = GaussianNB()\n",
+    "\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "print(results.mean())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ True False]\n",
+      "2\n",
+      "370\n",
+      "388\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the  Naive Bayes predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber5_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 8.2.3)Classiffication and Regression Trees\n",
+    "Classiffication and Regression Trees (CART or just decision trees) construct a binary tree from the training data. Split points are chosen greedily by evaluating each attribute and each value of each attribute in the training data in order to minimize a cost function (like the Gini index). You can construct a CART model using the DecisionTreeClassifier class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 89.99337762723641\n",
+      "MCC: 1.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.tree import DecisionTreeClassifier\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = DecisionTreeClassifier()\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ True False]\n",
+      "2\n",
+      "383\n",
+      "375\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the DecisionTreeClassifier  predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber6_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 8.2.4)Support Vector Machines\n",
+    "Support Vector Machines (or SVM) seek a line that best separates two classes. \n",
+    "The data instances closest to the line that best separates the classes are called support vectors and \n",
+    "influence where the line is placed. \n",
+    "SVM supports multiple classes and that of particular importance is the use of dierent kernel functions via the kernel parameter."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 90.88131839499741\n",
+      "MCC: 0.8187103751493263\n",
+      "0.9088131839499741\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.svm import SVC\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = SVC()\n",
+    "\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "print(results.mean())\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[False  True]\n",
+      "2\n",
+      "397\n",
+      "361\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the SVC predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber7_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 8.2.5)Random Forest\n",
+    "Random forests or random decision forests are an ensemble learning method for classification, regression and other tasks, that operate by constructing a multitude of decision trees at training time and outputting the class that is the mode of the classes (classification) or mean prediction (regression) of the individual trees.\n",
+    "Random decision forests correct for decision trees’ habit of over fitting to their training set."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 94.00881535521974\n",
+      "MCC: 1.0\n",
+      "0.9377811794337327\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = RandomForestClassifier(bootstrap = True,\n",
+    "                              max_features = None)\n",
+    "\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "print(results.mean())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ True False]\n",
+      "2\n",
+      "388\n",
+      "370\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the Randomforest predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber8_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 8.2.6)Gradient Boosting for classification.\n",
+    "GB builds an additive model in a forward stage-wise fashion; it allows for the optimization of arbitrary differentiable loss functions. \n",
+    "In each stage n_classes_ regression trees are fit on the negative gradient of the binomial or multinomial deviance loss function.\n",
+    "Binary classification is a special case where only a single regression tree is induced."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 92.8236277575126\n",
+      "MCC: 0.9092011960769395\n",
+      "0.928236277575126\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import GradientBoostingClassifier\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = GradientBoostingClassifier(learning_rate = 1.0,\n",
+    "                              max_depth = 1)\n",
+    "\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "print(results.mean())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ True False]\n",
+      "2\n",
+      "382\n",
+      "376\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the GradientBoostingClassifier predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber9_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 8.2.7)An extra-trees classifier.\n",
+    "This class implements a meta estimator that fits a number of randomized decision trees (a.k.a. extra-trees) on various sub-samples of the dataset.\n",
+    "It uses averaging to improve the predictive accuracy and control over-fitting."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 93.54807191245442\n",
+      "MCC: 1.0\n",
+      "0.9358096664929653\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import ExtraTreesClassifier\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = ExtraTreesClassifier()                              \n",
+    "\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "print(results.mean())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ True False]\n",
+      "2\n",
+      "386\n",
+      "372\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the ExtratreeClassifier predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber10_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 8.2.8)Multi-layer Perceptron classifier.\n",
+    "This model optimizes the log-loss function using LBFGS or stochastic gradient descent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy 92.42878235191941\n",
+      "MCC: 0.8449130833039031\n",
+      "0.925281179433733\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.neural_network import MLPClassifier\n",
+    "# For cross validation of data\n",
+    "num_folds = 10\n",
+    "seed=7\n",
+    "kfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n",
+    "model = MLPClassifier()                              \n",
+    "\n",
+    "#For accuracy of model\n",
+    "scoring='accuracy'\n",
+    "results = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\n",
+    "print('accuracy',results.mean()*100)\n",
+    "#Training the model to make a prediction\n",
+    "model.fit(X,Y)\n",
+    "kmodel=model.predict(Test)\n",
+    "#With Mathews correlation cofficient on the model\n",
+    "kmcc=matthews_corrcoef(model.predict(X),Y)\n",
+    "print('MCC:',kmcc)\n",
+    "\n",
+    "results = cross_val_score(model, X, Y, cv=kfold)\n",
+    "print(results.mean())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ True False]\n",
+      "2\n",
+      "339\n",
+      "419\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Converting the MLPClassifier predicted model first to data frame then a CSV file\n",
+    "out= model.predict(Test.values)\n",
+    "\n",
+    "Eva = pd.DataFrame(out) #Converting to data frame\n",
+    "Eva.columns=[\"CLASS\"] #Naming the column\n",
+    "Eva.index.name=\"Index\" #Creating a column index\n",
+    "Eva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n",
+    "\n",
+    "Eva.to_csv(\"Amber11_csv\") ## Writing a csv file\n",
+    "print(Eva['CLASS'].unique())\n",
+    "print(Eva['CLASS'].nunique())\n",
+    "\n",
+    "#printing the numbers of False and True\n",
+    "print(Eva.groupby('CLASS').size()[0].sum()) #\n",
+    "print(Eva.groupby('CLASS').size()[1].sum())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 9)Compare Machine Learning Algorithms\n",
+    "It is important to compare the performance of multiple different machine learning algorithms consistently.  The test harness as a template on your own machine learning problems and add more and different algorithms to compare."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "('LR', 0.8353580423831856, 0.27188952844394665)\n",
+      "('LDA', 0.8535044293903076, 0.2571395669719574)\n",
+      "('KNN', 0.8027933385443807, 0.2521136100771112)\n",
+      "('CART', 0.7296117769671704, 0.2875488058821619)\n",
+      "('NB', 0.880815746048289, 0.11642272449162755)\n",
+      "('SVM', 0.8350280093798853, 0.25836507020625044)\n",
+      "('MLPC', 0.8281320566267153, 0.2648801028909581)\n",
+      "('EXTC', 0.8386811707486539, 0.2379985491118143)\n",
+      "('GBC', 0.7902737971165538, 0.28849018693832995)\n",
+      "('RDF', 0.8146343581726592, 0.288019257902208)\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Compare Algorithms\n",
+    "from matplotlib import pyplot\n",
+    "# prepare models and add them to a list\n",
+    "models = []\n",
+    "models.append(('LR', LogisticRegression()))\n",
+    "models.append(('LDA', LinearDiscriminantAnalysis()))\n",
+    "models.append(('KNN', KNeighborsClassifier()))\n",
+    "models.append(('CART', DecisionTreeClassifier()))\n",
+    "models.append(('NB', GaussianNB()))\n",
+    "models.append(('SVM', SVC()))\n",
+    "models.append(('MLPC', MLPClassifier()))\n",
+    "models.append(('EXTC', ExtraTreesClassifier()))\n",
+    "models.append(('GBC', GradientBoostingClassifier()))\n",
+    "models.append(('RDF', RandomForestClassifier()))\n",
+    "# evaluate each model in turn\n",
+    "results = []\n",
+    "names = []\n",
+    "scoring = 'accuracy'\n",
+    "for name, model in models:\n",
+    "    kfold = KFold(n_splits=10, random_state=7)\n",
+    "    cv_results = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)\n",
+    "    results.append(cv_results)\n",
+    "    names.append(name)\n",
+    "    msg = (name, cv_results.mean(), cv_results.std())\n",
+    "    print(msg)\n",
+    "\n",
+    "# boxplot algorithm comparison\n",
+    "fig = pyplot.figure()\n",
+    "fig.suptitle('Algorithm Comparison')\n",
+    "ax = fig.add_subplot(111)\n",
+    "pyplot.boxplot(results)\n",
+    "ax.set_xticklabels(names)\n",
+    "pyplot.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# From the alogarithms above the best was the Gausian Naive Bayes with the highest mean value pf 0.88 followed by LDA with 0.85\n",
+    "# The least fit alogarith was DecisionTreeClassifier(0.72)followed by GradientBoostingClassifier at (0.79)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.4"
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/Assignment Colab/Eva Akurut.ipynb b/Assignment Colab/Eva Akurut.ipynb
new file mode 100644
index 0000000..5ee2598
--- /dev/null
+++ b/Assignment Colab/Eva Akurut.ipynb	
@@ -0,0 +1 @@
+{"cells":[{"metadata":{},"cell_type":"markdown","source":"### ACE_COMPETITION\n#### Exploration Data Analysis assignment\n1)Import the datasets into the notebook\n2)Find out the Dimensions of the data imported\n3)Descibe the data using statistics(Descriptive statistics)\n4)Looking at how the variables correlate with each other\n5)Data Visualisation\n6)Preparation of data for Machine Learning\n7)Evaluate the Performance of Machine Learning Algorithms with Resampling\n8)Spot-Checking Classiffication Algorithms"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# Importing the tools to use for the assignment\nimport numpy as np # linear algebra\nimport pandas as pd # data structure analysis\nimport matplotlib.pyplot as plt # for visualisation\nimport seaborn as sns#\nimport warnings\nwarnings.filterwarnings('ignore')\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 1)Loading the data to be used into my notebook"},{"metadata":{"trusted":true},"cell_type":"code","source":"###Importing the data sets into the notebook using read.csv\nTrain=pd.read_csv(\"../input/ace-class-assignment/AMP_TrainSet.csv\")\nTest=pd.read_csv(\"../input/ace-class-assignment/Test.csv\")","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 2)Checking the dimensions of my data\nThis sumarries the data type,Number of columns and rows,if the data has missing values "},{"metadata":{"trusted":true},"cell_type":"code","source":"Train.head(5)\n# To check the first 5 rows on my dataset","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Checking the datatype of of my data to determine the class of my data\nTrain.dtypes ,Test.dtypes\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Finding out the rows and columns present in my data set \nTrain.shape , Test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Printing the summary of the data frame\n# Summary includes list of all columns with their data types and the number of non-null values in each column. \n#we also have the value of rangeindex provided for the index axis.\nTrain.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Printing the column names to get to know the names of the columns\nTrain.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# In general, both the train and Test datasets have float and intenger data types\n#The Train Data set has 3038 rows and 12 columns\n# The Test Data set has 758 rows plus 11 columns","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 3)Descriptive statistics\nDescriptive statistics can give you great insight into the shape of each attribute.\n\nOften you can create more summaries than you have time to review. The describe() function on the Pandas DataFrame lists 8 statistical properties of each attribute:\nCount,Mean,Standard Devaition,Minimum Value,25th Percentile,50th Percentile (Median),75th Percentile,Maximum Value.\n\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"#Getting the spread of my data\nTrain.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Splitting my data into by classfication to find out how balanced the v\n#A groupby operation involves a combination of splitting the object, \n#Then application of a function, and combining the results.\nTrain.groupby(\"CLASS\").size().plot(kind=\"bar\")                             ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x = 'FULL_Charge', data = Train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 4)Checking how my data correlates with each other \nIn statistics, correlation or dependence is any statistical relationship, whether causal or not, between two random variables or bivariate data.\nHere the intension was to find out if there is a relationship**** between the variables"},{"metadata":{"trusted":true},"cell_type":"code","source":"corr=Train.corr(method='pearson')\ncorr\n# The correllation 1 is a positive relationship, -1 a negative relationship and 0 no relationship","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(12,12))\nsns.heatmap(Train.corr(method='pearson'),annot=True,cmap=\"YlGnBu\")\n#Heatmap is a way of representing the data in a 2-dimensional form. The data values are represented as colors in the graph. \n#It's goal is to provide a colored visual summary of information\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#For more depth of understanding the data the clustermap method is used \n#The .clustermap() method uses a hierarchical clusters to order data by similarity.\n#This reorganizes the data for the rows and columns and displays similar content next to one another \n\nsns.clustermap(Train.corr(method='pearson'),annot=True, cmap=\"Paired_r\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Showing how each variable correlates with the CLASS variable\nTrain.corr(method='pearson')['CLASS']","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 5)Data Visualisation\n*Data visualizations in python can be done via many packages.\n*Using matplot enables one to have a visual figures for the data\n*Every Axes has an x-axis and y-axis for plotting. \n*Contained within the axes are titles, ticks, labels associated with each axis\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"#1)To check for skewness in my dataset\n#Skew refers to a distribution that is assumed Gaussian (normal or bell curve) that is shifted in one direction or another\nTrain.skew().plot(kind='bar')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 2) Use of the box plot\n#Boxplots summarize the distribution of each attribute\n#A line for the median (middle value) is drawn while and a box put around the 25th and 75th percentiles.\n#The whiskers give an idea of the spread of the data and dots outside of the whiskers show candidate outlier values \n# Box plots\nTrain.plot(kind='box', subplots=True, layout=(4,3), sharex=True,sharey=True)\nplt.subplots_adjust(bottom=1, right=2, top=3)\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#3) Scatter plot: This is to relationship between two variables as dots in two dimension.\n#This is done so we could spot if there is a structured relationship within the two variables\nsns.pairplot(data=Train[['FULL_Charge','FULL_DAYM780201','FULL_OOBM850104', 'NT_EFC195',\n       'AS_MeanAmphiMoment','CLASS']])\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Histograms\nplt.figure(figsize=(15,15))\nTrain.hist(color='red')\n\nplt.subplots_adjust(bottom=1, right=2, top=3)\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 6)Preparation of data for Machine Learning\nPre-processing of Data is carried out in this section\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"#1) I will need to preapre my data for prepossessing \n# My preffered method for Data transformation is \"The Fit and Multiple Transform\" method form the scikit-learn library.\n#Split the dataset into the input and output variables for machine learning.\n#Apply a pre-processing transform to the input variables.\n#Summarize the data to show the change.\n#Rescaling the Data:Since the attributes have varying scales\n\nfrom numpy import set_printoptions\nfrom sklearn.preprocessing import MinMaxScaler\n\narray = Train.values\n# separate array into input and output components\nX= array[:,0:11]\nY= array[:,11]\nscaler = MinMaxScaler(feature_range=(0, 1))\nrescaledX = scaler.fit_transform(X)\n# summarize transformed data\nset_printoptions(precision=3)\nprint(rescaledX[0:5,:])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Looking at when my data is binarized instead\nfrom sklearn.preprocessing import Binarizer\n\narray2 = Train.values\n# separate array into input and output components\nX = array2[:,0:11]\nY = array2[:,11]\nbinarizer = Binarizer(threshold=0.0).fit(X)\nbinaryX = binarizer.transform(X)\n# summarize transformed data\nset_printoptions(precision=3)\nprint(binaryX[0:5,:])\n\n#NB:This binarised data was not used ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#b) Feature Selection\n#Select an anttribute will will give the most to the prediction variable \n#a)Selection is by The Recursive Feature Elimination (or RFE) \n# This works by recursively removing attributes and building a model on those attributes that remain.\nfrom sklearn.feature_selection import RFE\nfrom sklearn.linear_model import LogisticRegression\n\n# feature extraction\n# feature extraction\nmodel = LogisticRegression()\nrfe = RFE(model, 6)\nfit = rfe.fit(X, Y)\nprint(\"Num Features: \",  fit.n_features_)\nprint(\"Selected Features:\",  fit.support_)\nprint(\"Feature Ranking: \",  fit.ranking_)\nprint(\"Num Features: \",  fit.n_features_)\nprint(\"Selected Features:\",  fit.support_)\nprint(\"Feature Ranking: \",  fit.ranking_)\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.decomposition import PCA\narray = Train.values\nX = array[:,0:11]\nY = array[:,11]\n# feature extraction\npca = PCA(n_components=3)\nfit = pca.fit(X)\n# summarize components\nprint(\"Explained Variance: %s\" % fit.explained_variance_ratio_)\nprint(fit.components_)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Feature importance\nfrom sklearn.ensemble import ExtraTreesClassifier\n\narray = Train.values\nA = array[:,0:11]\nB = array[:,11]\n# feature extraction\nmodel = ExtraTreesClassifier()\nmodel.fit(A, B)\nprint(model.feature_importances_)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"## According to feature importance all the features in the data set were useful hence could not be lost and therefore i kept them all","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 7)Evaluate the Performance of Machine Learning Algorithms with Resampling\n##There is need to know how well the algorithms will perform on unseen data\n##The best way to evaluate the performance of an algorithm is to make predictions for new data to which  answers are known\n\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"## Split the  Data into Test and Train\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LogisticRegression\ntest_size = 0.35\nseed = 7\n\nX_train,X_test, Y_train, Y_test = train_test_split(X, Y, test_size=test_size,\nrandom_state=seed)\nmodel = LogisticRegression()\nmodel.fit(X_train, Y_train)\nresult = model.score(X_test, Y_test)\nprint(\"Accuracy: \",  (result*100.0))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"out= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# On rescaled Data\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LogisticRegression\narray = Train.values\nX = array[:,0:11]\nY = array[:,11]\ntest_size = 0.35\nseed = 7\n\nrescaledX_train,rescaledX_test, Y_train, Y_test = train_test_split(rescaledX, Y, test_size=test_size,\nrandom_state=seed)\nmodel = LogisticRegression()\nmodel.fit(rescaledX_train, Y_train)\nresult = model.score(rescaledX_test, Y_test)\nprint(\"Accuracy: \",  (result*100.0))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"out= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber1_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"## Despite having a similar accuracy of 91.82,the rescaled data was giving imbalanced false a.nd true values and therefore i would not use it further","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Classification accuracy:is the number of correct predictions made as a ratio of all predictions made.\nfrom sklearn.model_selection import KFold\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.linear_model import LogisticRegression\n\narray = Train.values\n\nnum_folds = 20#number of folds to use\nseed = 7#reproducibility\n\nkfold = KFold(n_splits=num_folds, random_state=None)\nmodel = LogisticRegression()\nX_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=test_size,\nrandom_state=seed)\nmodel.fit(X_train, Y_train)\nresults = cross_val_score(model, X, Y, cv=kfold)\n\nprint(f\"Accuracy:\", (results.mean()*100.0, results.std()*100.0))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber2_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#To check out the classification report \nfrom sklearn.metrics import classification_report\n\narray = Train.values\nX = array[:,0:11]\nY = array[:,11]\nscaler = MinMaxScaler(feature_range=(0, 1))\nrescaledA = scaler.fit_transform(A)\nscaler = MinMaxScaler(feature_range=(0, 1))\nrescaledA = scaler.fit_transform(A)\ntest_size = 0.35\nseed = 7\nrescaledX_train,rescaledX_test, Y_train, Y_test = train_test_split(rescaledX, Y, test_size=test_size,\nrandom_state=seed)\nmodel = LogisticRegression()\nmodel.fit(rescaledX_train, Y_train)\npredicted = model.predict(rescaledX_test)\nreport = classification_report(Y_test, predicted)\nprint(report)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# we then look at the regression M\n# The Mean Absolute Error(MAE) is the sum of the absolute differences between predictions and actual values.\n# Its aim is to give an idea of how wrong the predictions were. \nfrom pandas import read_csv\nfrom sklearn.linear_model import LinearRegression\narray = Train.values\nX = array[:,0:11]\nY = array[:,11]\nkfold = KFold(n_splits=10, random_state=None)\nmodel = LinearRegression()\nscoring = 'neg_mean_absolute_error'\nresults = cross_val_score(model, rescaledX, Y, cv=kfold, scoring=scoring)\nprint(\"MAE:\",(results.mean(), results.std()))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#The R2 metric provides an indication of the goodness of fit of a set of predictions to the actual values\n#Cross Validation Regression R^2\narray = Train.values\nX = array[:,0:11]\nY = array[:,11]\n\nkfold = KFold(n_splits=10, random_state=None)\nmodel = LinearRegression()\nscoring = 'r2'\nresults = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)\nprint(\"R^2:\",(results.mean(), results.std()))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 8)Spot-Checking Classiffication Algorithms\n##Algorithms Overview\n##looking at six classication algorithms that will help spot-check on your dataset. Starting with two ##linear machine learning algorithms:\n\n8.1.1)Logistic Regression.\n8.1.2)Linear Discriminant Analysis.\nThen looking at four nonlinear machine learning algorithms:\n\n8.2.1)k-Nearest Neighbors.\n8.2.2)Naive Bayes.\n8.2.3)Classication and Regression Trees.\n8.2.4)Support Vector Machines.\n8.2.5)Random Forest\n8.2.6)Gradient Boosting for classification\n8.2.7)An extra-trees classifier.\n8.2.8)Neural Network-MLPC"},{"metadata":{},"cell_type":"markdown","source":" ## 8.1)Linear Machine Language Alogarithms\n### 8.1.1)Logistic Regression\nLogistic regression assumes a Gaussian distribution for the numeric input variables and can model binary classiffication problems.\n****This is done using the Logisticregression class"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Logistic Regression Classification\nfrom sklearn.model_selection import KFold\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.metrics import matthews_corrcoef\nfrom sklearn.metrics import plot_confusion_matrix\n\n#for model set up\nmodel = LogisticRegression()\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the LogisticRegression predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber3_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# The difference between Accuracy and MCC model is slight but giving the same output pf 383 True values and 375 false values","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 8.1.2)Linear Discriminant Analysis or LDA \n-This a statistical technique for binary and multiclass classiffication. \n-It too assumes a Gaussian distribution for the numerical input variables. \n-You can construct an LDA model using the LinearDiscriminantAnalysis class"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n#Model set up\nmodel = LinearDiscriminantAnalysis()\n# For cross validation of data\nnum_folds = 10\nseed=9\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the  LinearDiscriminantAnalysis predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber4_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 8.2 Nonlinear machine learning algorithms.\n\n### 8.2.1)k-Nearest Neighbors\n##The k-Nearest Neighbors algorithm (or KNN) uses a distance metric to find the k most similar instances ##In the training data for a new instance and takes the mean outcome of the neighbors as the prediction. #You can construct a KNN model using the KNeighborsClassifier class."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.neighbors import KNeighborsClassifier\n#Model set up\nmodel = KNeighborsClassifier()\n# For cross validation of data\nnum_folds = 5\nseed=8\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the  LinearDiscriminantAnalysis predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber5_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 8.2.2) Naive Bayes\n-Naive Bayes calculates the probability of each class and the conditional probability of each class given each input value. \n-These probabilities are estimated for new data and multiplied together\n-The Assumption is that they are all independent (a simple or naive assumption).\n-When working with real-valued data, a Gaussian distribution is assumed to easily estimate the probabilities for input variables using the Gaussian Probability Density Function. \n##You can construct a Naive Bayes model using the GaussianNB class4"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.naive_bayes import GaussianNB\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = GaussianNB()\n\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\nresults = cross_val_score(model, X, Y, cv=kfold)\nprint(results.mean())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the  Naive Bayes predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber5_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 8.2.3)Classiffication and Regression Trees\nClassiffication and Regression Trees (CART or just decision trees) construct a binary tree from the training data. Split points are chosen greedily by evaluating each attribute and each value of each attribute in the training data in order to minimize a cost function (like the Gini index). You can construct a CART model using the DecisionTreeClassifier class"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.tree import DecisionTreeClassifier\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = DecisionTreeClassifier()\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the DecisionTreeClassifier  predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber6_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 8.2.4)Support Vector Machines\nSupport Vector Machines (or SVM) seek a line that best separates two classes. \nThe data instances closest to the line that best separates the classes are called support vectors and \ninfluence where the line is placed. \nSVM supports multiple classes and that of particular importance is the use of dierent kernel functions via the kernel parameter."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.svm import SVC\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = SVC()\n\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\nresults = cross_val_score(model, X, Y, cv=kfold)\nprint(results.mean())\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the SVC predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber7_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 8.2.5)Random Forest\nRandom forests or random decision forests are an ensemble learning method for classification, regression and other tasks, that operate by constructing a multitude of decision trees at training time and outputting the class that is the mode of the classes (classification) or mean prediction (regression) of the individual trees.\nRandom decision forests correct for decision trees’ habit of over fitting to their training set."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.ensemble import RandomForestClassifier\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = RandomForestClassifier(bootstrap = True,\n                              max_features = None)\n\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\nresults = cross_val_score(model, X, Y, cv=kfold)\nprint(results.mean())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the Randomforest predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber8_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 8.2.6)Gradient Boosting for classification.\nGB builds an additive model in a forward stage-wise fashion; it allows for the optimization of arbitrary differentiable loss functions. \nIn each stage n_classes_ regression trees are fit on the negative gradient of the binomial or multinomial deviance loss function.\nBinary classification is a special case where only a single regression tree is induced."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.ensemble import GradientBoostingClassifier\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = GradientBoostingClassifier(learning_rate = 1.0,\n                              max_depth = 1)\n\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\nresults = cross_val_score(model, X, Y, cv=kfold)\nprint(results.mean())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the GradientBoostingClassifier predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber9_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 8.2.7)An extra-trees classifier.\nThis class implements a meta estimator that fits a number of randomized decision trees (a.k.a. extra-trees) on various sub-samples of the dataset.\nIt uses averaging to improve the predictive accuracy and control over-fitting."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.ensemble import ExtraTreesClassifier\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = ExtraTreesClassifier()                              \n\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\nresults = cross_val_score(model, X, Y, cv=kfold)\nprint(results.mean())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the ExtratreeClassifier predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber10_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 8.2.8)Multi-layer Perceptron classifier.\nThis model optimizes the log-loss function using LBFGS or stochastic gradient descent."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.neural_network import MLPClassifier\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = MLPClassifier()                              \n\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\nresults = cross_val_score(model, X, Y, cv=kfold)\nprint(results.mean())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the MLPClassifier predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber11_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 9)Compare Machine Learning Algorithms\nIt is important to compare the performance of multiple different machine learning algorithms consistently.  The test harness as a template on your own machine learning problems and add more and different algorithms to compare."},{"metadata":{"trusted":true},"cell_type":"code","source":"# Compare Algorithms\nfrom matplotlib import pyplot\n# prepare models and add them to a list\nmodels = []\nmodels.append(('LR', LogisticRegression()))\nmodels.append(('LDA', LinearDiscriminantAnalysis()))\nmodels.append(('KNN', KNeighborsClassifier()))\nmodels.append(('CART', DecisionTreeClassifier()))\nmodels.append(('NB', GaussianNB()))\nmodels.append(('SVM', SVC()))\nmodels.append(('MLPC', MLPClassifier()))\nmodels.append(('EXTC', ExtraTreesClassifier()))\nmodels.append(('GBC', GradientBoostingClassifier()))\nmodels.append(('RDF', RandomForestClassifier()))\n# evaluate each model in turn\nresults = []\nnames = []\nscoring = 'accuracy'\nfor name, model in models:\n    kfold = KFold(n_splits=10, random_state=7)\n    cv_results = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)\n    results.append(cv_results)\n    names.append(name)\n    msg = (name, cv_results.mean(), cv_results.std())\n    print(msg)\n\n# boxplot algorithm comparison\nfig = pyplot.figure()\nfig.suptitle('Algorithm Comparison')\nax = fig.add_subplot(111)\npyplot.boxplot(results)\nax.set_xticklabels(names)\npyplot.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# From the alogarithms above the best was the Gausian Naive Bayes with the highest mean value pf 0.88 followed by LDA with 0.85\n# The least fit alogarith was DecisionTreeClassifier(0.72)followed by GradientBoostingClassifier at (0.79)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}
\ No newline at end of file
diff --git a/Eva Akurut.ipynb b/Eva Akurut.ipynb
new file mode 100644
index 0000000..5ee2598
--- /dev/null
+++ b/Eva Akurut.ipynb	
@@ -0,0 +1 @@
+{"cells":[{"metadata":{},"cell_type":"markdown","source":"### ACE_COMPETITION\n#### Exploration Data Analysis assignment\n1)Import the datasets into the notebook\n2)Find out the Dimensions of the data imported\n3)Descibe the data using statistics(Descriptive statistics)\n4)Looking at how the variables correlate with each other\n5)Data Visualisation\n6)Preparation of data for Machine Learning\n7)Evaluate the Performance of Machine Learning Algorithms with Resampling\n8)Spot-Checking Classiffication Algorithms"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# Importing the tools to use for the assignment\nimport numpy as np # linear algebra\nimport pandas as pd # data structure analysis\nimport matplotlib.pyplot as plt # for visualisation\nimport seaborn as sns#\nimport warnings\nwarnings.filterwarnings('ignore')\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 1)Loading the data to be used into my notebook"},{"metadata":{"trusted":true},"cell_type":"code","source":"###Importing the data sets into the notebook using read.csv\nTrain=pd.read_csv(\"../input/ace-class-assignment/AMP_TrainSet.csv\")\nTest=pd.read_csv(\"../input/ace-class-assignment/Test.csv\")","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 2)Checking the dimensions of my data\nThis sumarries the data type,Number of columns and rows,if the data has missing values "},{"metadata":{"trusted":true},"cell_type":"code","source":"Train.head(5)\n# To check the first 5 rows on my dataset","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Checking the datatype of of my data to determine the class of my data\nTrain.dtypes ,Test.dtypes\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Finding out the rows and columns present in my data set \nTrain.shape , Test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Printing the summary of the data frame\n# Summary includes list of all columns with their data types and the number of non-null values in each column. \n#we also have the value of rangeindex provided for the index axis.\nTrain.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Printing the column names to get to know the names of the columns\nTrain.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# In general, both the train and Test datasets have float and intenger data types\n#The Train Data set has 3038 rows and 12 columns\n# The Test Data set has 758 rows plus 11 columns","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 3)Descriptive statistics\nDescriptive statistics can give you great insight into the shape of each attribute.\n\nOften you can create more summaries than you have time to review. The describe() function on the Pandas DataFrame lists 8 statistical properties of each attribute:\nCount,Mean,Standard Devaition,Minimum Value,25th Percentile,50th Percentile (Median),75th Percentile,Maximum Value.\n\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"#Getting the spread of my data\nTrain.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Splitting my data into by classfication to find out how balanced the v\n#A groupby operation involves a combination of splitting the object, \n#Then application of a function, and combining the results.\nTrain.groupby(\"CLASS\").size().plot(kind=\"bar\")                             ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x = 'FULL_Charge', data = Train)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 4)Checking how my data correlates with each other \nIn statistics, correlation or dependence is any statistical relationship, whether causal or not, between two random variables or bivariate data.\nHere the intension was to find out if there is a relationship**** between the variables"},{"metadata":{"trusted":true},"cell_type":"code","source":"corr=Train.corr(method='pearson')\ncorr\n# The correllation 1 is a positive relationship, -1 a negative relationship and 0 no relationship","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(12,12))\nsns.heatmap(Train.corr(method='pearson'),annot=True,cmap=\"YlGnBu\")\n#Heatmap is a way of representing the data in a 2-dimensional form. The data values are represented as colors in the graph. \n#It's goal is to provide a colored visual summary of information\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#For more depth of understanding the data the clustermap method is used \n#The .clustermap() method uses a hierarchical clusters to order data by similarity.\n#This reorganizes the data for the rows and columns and displays similar content next to one another \n\nsns.clustermap(Train.corr(method='pearson'),annot=True, cmap=\"Paired_r\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Showing how each variable correlates with the CLASS variable\nTrain.corr(method='pearson')['CLASS']","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 5)Data Visualisation\n*Data visualizations in python can be done via many packages.\n*Using matplot enables one to have a visual figures for the data\n*Every Axes has an x-axis and y-axis for plotting. \n*Contained within the axes are titles, ticks, labels associated with each axis\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"#1)To check for skewness in my dataset\n#Skew refers to a distribution that is assumed Gaussian (normal or bell curve) that is shifted in one direction or another\nTrain.skew().plot(kind='bar')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 2) Use of the box plot\n#Boxplots summarize the distribution of each attribute\n#A line for the median (middle value) is drawn while and a box put around the 25th and 75th percentiles.\n#The whiskers give an idea of the spread of the data and dots outside of the whiskers show candidate outlier values \n# Box plots\nTrain.plot(kind='box', subplots=True, layout=(4,3), sharex=True,sharey=True)\nplt.subplots_adjust(bottom=1, right=2, top=3)\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#3) Scatter plot: This is to relationship between two variables as dots in two dimension.\n#This is done so we could spot if there is a structured relationship within the two variables\nsns.pairplot(data=Train[['FULL_Charge','FULL_DAYM780201','FULL_OOBM850104', 'NT_EFC195',\n       'AS_MeanAmphiMoment','CLASS']])\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Histograms\nplt.figure(figsize=(15,15))\nTrain.hist(color='red')\n\nplt.subplots_adjust(bottom=1, right=2, top=3)\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 6)Preparation of data for Machine Learning\nPre-processing of Data is carried out in this section\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"#1) I will need to preapre my data for prepossessing \n# My preffered method for Data transformation is \"The Fit and Multiple Transform\" method form the scikit-learn library.\n#Split the dataset into the input and output variables for machine learning.\n#Apply a pre-processing transform to the input variables.\n#Summarize the data to show the change.\n#Rescaling the Data:Since the attributes have varying scales\n\nfrom numpy import set_printoptions\nfrom sklearn.preprocessing import MinMaxScaler\n\narray = Train.values\n# separate array into input and output components\nX= array[:,0:11]\nY= array[:,11]\nscaler = MinMaxScaler(feature_range=(0, 1))\nrescaledX = scaler.fit_transform(X)\n# summarize transformed data\nset_printoptions(precision=3)\nprint(rescaledX[0:5,:])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Looking at when my data is binarized instead\nfrom sklearn.preprocessing import Binarizer\n\narray2 = Train.values\n# separate array into input and output components\nX = array2[:,0:11]\nY = array2[:,11]\nbinarizer = Binarizer(threshold=0.0).fit(X)\nbinaryX = binarizer.transform(X)\n# summarize transformed data\nset_printoptions(precision=3)\nprint(binaryX[0:5,:])\n\n#NB:This binarised data was not used ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#b) Feature Selection\n#Select an anttribute will will give the most to the prediction variable \n#a)Selection is by The Recursive Feature Elimination (or RFE) \n# This works by recursively removing attributes and building a model on those attributes that remain.\nfrom sklearn.feature_selection import RFE\nfrom sklearn.linear_model import LogisticRegression\n\n# feature extraction\n# feature extraction\nmodel = LogisticRegression()\nrfe = RFE(model, 6)\nfit = rfe.fit(X, Y)\nprint(\"Num Features: \",  fit.n_features_)\nprint(\"Selected Features:\",  fit.support_)\nprint(\"Feature Ranking: \",  fit.ranking_)\nprint(\"Num Features: \",  fit.n_features_)\nprint(\"Selected Features:\",  fit.support_)\nprint(\"Feature Ranking: \",  fit.ranking_)\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.decomposition import PCA\narray = Train.values\nX = array[:,0:11]\nY = array[:,11]\n# feature extraction\npca = PCA(n_components=3)\nfit = pca.fit(X)\n# summarize components\nprint(\"Explained Variance: %s\" % fit.explained_variance_ratio_)\nprint(fit.components_)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Feature importance\nfrom sklearn.ensemble import ExtraTreesClassifier\n\narray = Train.values\nA = array[:,0:11]\nB = array[:,11]\n# feature extraction\nmodel = ExtraTreesClassifier()\nmodel.fit(A, B)\nprint(model.feature_importances_)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"## According to feature importance all the features in the data set were useful hence could not be lost and therefore i kept them all","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 7)Evaluate the Performance of Machine Learning Algorithms with Resampling\n##There is need to know how well the algorithms will perform on unseen data\n##The best way to evaluate the performance of an algorithm is to make predictions for new data to which  answers are known\n\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"## Split the  Data into Test and Train\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LogisticRegression\ntest_size = 0.35\nseed = 7\n\nX_train,X_test, Y_train, Y_test = train_test_split(X, Y, test_size=test_size,\nrandom_state=seed)\nmodel = LogisticRegression()\nmodel.fit(X_train, Y_train)\nresult = model.score(X_test, Y_test)\nprint(\"Accuracy: \",  (result*100.0))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"out= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# On rescaled Data\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LogisticRegression\narray = Train.values\nX = array[:,0:11]\nY = array[:,11]\ntest_size = 0.35\nseed = 7\n\nrescaledX_train,rescaledX_test, Y_train, Y_test = train_test_split(rescaledX, Y, test_size=test_size,\nrandom_state=seed)\nmodel = LogisticRegression()\nmodel.fit(rescaledX_train, Y_train)\nresult = model.score(rescaledX_test, Y_test)\nprint(\"Accuracy: \",  (result*100.0))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"out= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber1_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"## Despite having a similar accuracy of 91.82,the rescaled data was giving imbalanced false a.nd true values and therefore i would not use it further","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Classification accuracy:is the number of correct predictions made as a ratio of all predictions made.\nfrom sklearn.model_selection import KFold\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.linear_model import LogisticRegression\n\narray = Train.values\n\nnum_folds = 20#number of folds to use\nseed = 7#reproducibility\n\nkfold = KFold(n_splits=num_folds, random_state=None)\nmodel = LogisticRegression()\nX_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=test_size,\nrandom_state=seed)\nmodel.fit(X_train, Y_train)\nresults = cross_val_score(model, X, Y, cv=kfold)\n\nprint(f\"Accuracy:\", (results.mean()*100.0, results.std()*100.0))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber2_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#To check out the classification report \nfrom sklearn.metrics import classification_report\n\narray = Train.values\nX = array[:,0:11]\nY = array[:,11]\nscaler = MinMaxScaler(feature_range=(0, 1))\nrescaledA = scaler.fit_transform(A)\nscaler = MinMaxScaler(feature_range=(0, 1))\nrescaledA = scaler.fit_transform(A)\ntest_size = 0.35\nseed = 7\nrescaledX_train,rescaledX_test, Y_train, Y_test = train_test_split(rescaledX, Y, test_size=test_size,\nrandom_state=seed)\nmodel = LogisticRegression()\nmodel.fit(rescaledX_train, Y_train)\npredicted = model.predict(rescaledX_test)\nreport = classification_report(Y_test, predicted)\nprint(report)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# we then look at the regression M\n# The Mean Absolute Error(MAE) is the sum of the absolute differences between predictions and actual values.\n# Its aim is to give an idea of how wrong the predictions were. \nfrom pandas import read_csv\nfrom sklearn.linear_model import LinearRegression\narray = Train.values\nX = array[:,0:11]\nY = array[:,11]\nkfold = KFold(n_splits=10, random_state=None)\nmodel = LinearRegression()\nscoring = 'neg_mean_absolute_error'\nresults = cross_val_score(model, rescaledX, Y, cv=kfold, scoring=scoring)\nprint(\"MAE:\",(results.mean(), results.std()))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#The R2 metric provides an indication of the goodness of fit of a set of predictions to the actual values\n#Cross Validation Regression R^2\narray = Train.values\nX = array[:,0:11]\nY = array[:,11]\n\nkfold = KFold(n_splits=10, random_state=None)\nmodel = LinearRegression()\nscoring = 'r2'\nresults = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)\nprint(\"R^2:\",(results.mean(), results.std()))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 8)Spot-Checking Classiffication Algorithms\n##Algorithms Overview\n##looking at six classication algorithms that will help spot-check on your dataset. Starting with two ##linear machine learning algorithms:\n\n8.1.1)Logistic Regression.\n8.1.2)Linear Discriminant Analysis.\nThen looking at four nonlinear machine learning algorithms:\n\n8.2.1)k-Nearest Neighbors.\n8.2.2)Naive Bayes.\n8.2.3)Classication and Regression Trees.\n8.2.4)Support Vector Machines.\n8.2.5)Random Forest\n8.2.6)Gradient Boosting for classification\n8.2.7)An extra-trees classifier.\n8.2.8)Neural Network-MLPC"},{"metadata":{},"cell_type":"markdown","source":" ## 8.1)Linear Machine Language Alogarithms\n### 8.1.1)Logistic Regression\nLogistic regression assumes a Gaussian distribution for the numeric input variables and can model binary classiffication problems.\n****This is done using the Logisticregression class"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Logistic Regression Classification\nfrom sklearn.model_selection import KFold\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.metrics import matthews_corrcoef\nfrom sklearn.metrics import plot_confusion_matrix\n\n#for model set up\nmodel = LogisticRegression()\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the LogisticRegression predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber3_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# The difference between Accuracy and MCC model is slight but giving the same output pf 383 True values and 375 false values","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 8.1.2)Linear Discriminant Analysis or LDA \n-This a statistical technique for binary and multiclass classiffication. \n-It too assumes a Gaussian distribution for the numerical input variables. \n-You can construct an LDA model using the LinearDiscriminantAnalysis class"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n#Model set up\nmodel = LinearDiscriminantAnalysis()\n# For cross validation of data\nnum_folds = 10\nseed=9\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the  LinearDiscriminantAnalysis predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber4_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 8.2 Nonlinear machine learning algorithms.\n\n### 8.2.1)k-Nearest Neighbors\n##The k-Nearest Neighbors algorithm (or KNN) uses a distance metric to find the k most similar instances ##In the training data for a new instance and takes the mean outcome of the neighbors as the prediction. #You can construct a KNN model using the KNeighborsClassifier class."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.neighbors import KNeighborsClassifier\n#Model set up\nmodel = KNeighborsClassifier()\n# For cross validation of data\nnum_folds = 5\nseed=8\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the  LinearDiscriminantAnalysis predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber5_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 8.2.2) Naive Bayes\n-Naive Bayes calculates the probability of each class and the conditional probability of each class given each input value. \n-These probabilities are estimated for new data and multiplied together\n-The Assumption is that they are all independent (a simple or naive assumption).\n-When working with real-valued data, a Gaussian distribution is assumed to easily estimate the probabilities for input variables using the Gaussian Probability Density Function. \n##You can construct a Naive Bayes model using the GaussianNB class4"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.naive_bayes import GaussianNB\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = GaussianNB()\n\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\nresults = cross_val_score(model, X, Y, cv=kfold)\nprint(results.mean())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the  Naive Bayes predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber5_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 8.2.3)Classiffication and Regression Trees\nClassiffication and Regression Trees (CART or just decision trees) construct a binary tree from the training data. Split points are chosen greedily by evaluating each attribute and each value of each attribute in the training data in order to minimize a cost function (like the Gini index). You can construct a CART model using the DecisionTreeClassifier class"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.tree import DecisionTreeClassifier\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = DecisionTreeClassifier()\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the DecisionTreeClassifier  predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber6_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 8.2.4)Support Vector Machines\nSupport Vector Machines (or SVM) seek a line that best separates two classes. \nThe data instances closest to the line that best separates the classes are called support vectors and \ninfluence where the line is placed. \nSVM supports multiple classes and that of particular importance is the use of dierent kernel functions via the kernel parameter."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.svm import SVC\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = SVC()\n\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\nresults = cross_val_score(model, X, Y, cv=kfold)\nprint(results.mean())\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the SVC predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber7_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 8.2.5)Random Forest\nRandom forests or random decision forests are an ensemble learning method for classification, regression and other tasks, that operate by constructing a multitude of decision trees at training time and outputting the class that is the mode of the classes (classification) or mean prediction (regression) of the individual trees.\nRandom decision forests correct for decision trees’ habit of over fitting to their training set."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.ensemble import RandomForestClassifier\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = RandomForestClassifier(bootstrap = True,\n                              max_features = None)\n\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\nresults = cross_val_score(model, X, Y, cv=kfold)\nprint(results.mean())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the Randomforest predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber8_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 8.2.6)Gradient Boosting for classification.\nGB builds an additive model in a forward stage-wise fashion; it allows for the optimization of arbitrary differentiable loss functions. \nIn each stage n_classes_ regression trees are fit on the negative gradient of the binomial or multinomial deviance loss function.\nBinary classification is a special case where only a single regression tree is induced."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.ensemble import GradientBoostingClassifier\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = GradientBoostingClassifier(learning_rate = 1.0,\n                              max_depth = 1)\n\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\nresults = cross_val_score(model, X, Y, cv=kfold)\nprint(results.mean())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the GradientBoostingClassifier predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber9_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 8.2.7)An extra-trees classifier.\nThis class implements a meta estimator that fits a number of randomized decision trees (a.k.a. extra-trees) on various sub-samples of the dataset.\nIt uses averaging to improve the predictive accuracy and control over-fitting."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.ensemble import ExtraTreesClassifier\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = ExtraTreesClassifier()                              \n\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\nresults = cross_val_score(model, X, Y, cv=kfold)\nprint(results.mean())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the ExtratreeClassifier predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber10_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### 8.2.8)Multi-layer Perceptron classifier.\nThis model optimizes the log-loss function using LBFGS or stochastic gradient descent."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.neural_network import MLPClassifier\n# For cross validation of data\nnum_folds = 10\nseed=7\nkfold = KFold(n_splits=num_folds, random_state=seed,shuffle=True)\nmodel = MLPClassifier()                              \n\n#For accuracy of model\nscoring='accuracy'\nresults = cross_val_score(model, X, Y, cv=kfold,scoring=scoring)\nprint('accuracy',results.mean()*100)\n#Training the model to make a prediction\nmodel.fit(X,Y)\nkmodel=model.predict(Test)\n#With Mathews correlation cofficient on the model\nkmcc=matthews_corrcoef(model.predict(X),Y)\nprint('MCC:',kmcc)\n\nresults = cross_val_score(model, X, Y, cv=kfold)\nprint(results.mean())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Converting the MLPClassifier predicted model first to data frame then a CSV file\nout= model.predict(Test.values)\n\nEva = pd.DataFrame(out) #Converting to data frame\nEva.columns=[\"CLASS\"] #Naming the column\nEva.index.name=\"Index\" #Creating a column index\nEva[\"CLASS\"]=Eva[\"CLASS\"].map({0.0:False,1.0:True}) # Chaninging 0 to \"False\" 1 to \"True\"\n\nEva.to_csv(\"Amber11_csv\") ## Writing a csv file\nprint(Eva['CLASS'].unique())\nprint(Eva['CLASS'].nunique())\n\n#printing the numbers of False and True\nprint(Eva.groupby('CLASS').size()[0].sum()) #\nprint(Eva.groupby('CLASS').size()[1].sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 9)Compare Machine Learning Algorithms\nIt is important to compare the performance of multiple different machine learning algorithms consistently.  The test harness as a template on your own machine learning problems and add more and different algorithms to compare."},{"metadata":{"trusted":true},"cell_type":"code","source":"# Compare Algorithms\nfrom matplotlib import pyplot\n# prepare models and add them to a list\nmodels = []\nmodels.append(('LR', LogisticRegression()))\nmodels.append(('LDA', LinearDiscriminantAnalysis()))\nmodels.append(('KNN', KNeighborsClassifier()))\nmodels.append(('CART', DecisionTreeClassifier()))\nmodels.append(('NB', GaussianNB()))\nmodels.append(('SVM', SVC()))\nmodels.append(('MLPC', MLPClassifier()))\nmodels.append(('EXTC', ExtraTreesClassifier()))\nmodels.append(('GBC', GradientBoostingClassifier()))\nmodels.append(('RDF', RandomForestClassifier()))\n# evaluate each model in turn\nresults = []\nnames = []\nscoring = 'accuracy'\nfor name, model in models:\n    kfold = KFold(n_splits=10, random_state=7)\n    cv_results = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)\n    results.append(cv_results)\n    names.append(name)\n    msg = (name, cv_results.mean(), cv_results.std())\n    print(msg)\n\n# boxplot algorithm comparison\nfig = pyplot.figure()\nfig.suptitle('Algorithm Comparison')\nax = fig.add_subplot(111)\npyplot.boxplot(results)\nax.set_xticklabels(names)\npyplot.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# From the alogarithms above the best was the Gausian Naive Bayes with the highest mean value pf 0.88 followed by LDA with 0.85\n# The least fit alogarith was DecisionTreeClassifier(0.72)followed by GradientBoostingClassifier at (0.79)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}
\ No newline at end of file
diff --git a/Reading Material/Pandas Cookbook/Pandas-Cookbook b/Reading Material/Pandas Cookbook/Pandas-Cookbook
new file mode 160000
index 0000000..b45d95c
--- /dev/null
+++ b/Reading Material/Pandas Cookbook/Pandas-Cookbook	
@@ -0,0 +1 @@
+Subproject commit b45d95ccef24b020fdf28ecb5a07e3348bee62f1