diff --git a/Spam_Classifiier_NLP.ipynb b/Spam_Classifiier_NLP.ipynb
new file mode 100644
index 0000000..f0e0f10
--- /dev/null
+++ b/Spam_Classifiier_NLP.ipynb
@@ -0,0 +1,438 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import sqlite3\n",
+    "import regex as re\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "from wordcloud import WordCloud"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "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>text</th>\n",
+       "      <th>spam</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Subject: naturally irresistible your corporate...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Subject: the stock trading gunslinger  fanny i...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Subject: unbelievable new homes made easy  im ...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Subject: 4 color printing special  request add...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Subject: do not have money , get software cds ...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                text  spam\n",
+       "0  Subject: naturally irresistible your corporate...     1\n",
+       "1  Subject: the stock trading gunslinger  fanny i...     1\n",
+       "2  Subject: unbelievable new homes made easy  im ...     1\n",
+       "3  Subject: 4 color printing special  request add...     1\n",
+       "4  Subject: do not have money , get software cds ...     1"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('emails.csv')\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "spam count: 1368\n",
+      "not spam count: 4360\n",
+      "(5728, 2)\n",
+      "(5695, 2)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"spam count: \" +str(len(df.loc[df.spam==1])))\n",
+    "print(\"not spam count: \" +str(len(df.loc[df.spam==0])))\n",
+    "print(df.shape)\n",
+    "df['spam'] = df['spam'].astype(int)\n",
+    "\n",
+    "df = df.drop_duplicates()\n",
+    "print(df.shape)\n",
+    "\n",
+    "df = df.reset_index(inplace = False)[['text','spam']]"
+   ]
+  },
+  {
+   "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>text</th>\n",
+       "      <th>spam</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Subject: naturally irresistible your corporate...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Subject: the stock trading gunslinger  fanny i...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Subject: unbelievable new homes made easy  im ...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Subject: 4 color printing special  request add...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Subject: do not have money , get software cds ...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                text  spam\n",
+       "0  Subject: naturally irresistible your corporate...     1\n",
+       "1  Subject: the stock trading gunslinger  fanny i...     1\n",
+       "2  Subject: unbelievable new homes made easy  im ...     1\n",
+       "3  Subject: 4 color printing special  request add...     1\n",
+       "4  Subject: do not have money , get software cds ...     1"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "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>index</th>\n",
+       "      <th>text</th>\n",
+       "      <th>spam</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>subject naturally irresistible your corporate ...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>subject the stock trading gunslinger fanny is ...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>subject unbelievable new homes made easy im wa...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   index                                               text  spam\n",
+       "0      0  subject naturally irresistible your corporate ...     1\n",
+       "1      1  subject the stock trading gunslinger fanny is ...     1\n",
+       "2      2  subject unbelievable new homes made easy im wa...     1"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clean_desc = []\n",
+    "for w in range(len(df.text)):\n",
+    "    desc = df['text'][w].lower()\n",
+    "    \n",
+    "    #remove punctuation\n",
+    "    desc = re.sub('[^a-zA-Z]', ' ', desc)\n",
+    "    \n",
+    "    #remove tags\n",
+    "    desc=re.sub(\"&lt;/?.*?&gt;\",\" &lt;&gt; \",desc)\n",
+    "    \n",
+    "    #remove digits and special chars\n",
+    "    desc=re.sub(\"(\\\\d|\\\\W)+\",\" \",desc)\n",
+    "    \n",
+    "    clean_desc.append(desc)\n",
+    "#assign the cleaned descriptions to the data frame\n",
+    "df['text'] = clean_desc\n",
+    "df = df.reset_index()        \n",
+    "df.head(3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       0.98      0.99      0.98      1926\n",
+      "           1       0.97      0.94      0.95       637\n",
+      "\n",
+      "    accuracy                           0.98      2563\n",
+      "   macro avg       0.97      0.96      0.97      2563\n",
+      "weighted avg       0.98      0.98      0.98      2563\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.feature_extraction.text import CountVectorizer\n",
+    "text_vec = CountVectorizer().fit_transform(df['text'])\n",
+    "\n",
+    "from sklearn.metrics import classification_report\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "X_train, X_test, y_train, y_test = train_test_split(text_vec, df['spam'], test_size = 0.45\n",
+    "                                                    , random_state = 42, shuffle = True)\n",
+    "#from sklearn.tree import DecisionTreeClassifier\n",
+    "#classifier = DecisionTreeClassifier(max_depth = 7)\n",
+    "\n",
+    "#from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier\n",
+    "#classifier = RandomForestClassifier(max_depth=6, n_estimators=8)\n",
+    "#classifier = AdaBoostClassifier()\n",
+    "\n",
+    "from sklearn.svm import SVC\n",
+    "classifier = SVC(kernel=\"linear\", C=0.025)\n",
+    "\n",
+    "#from sklearn import ensemble \n",
+    "#classifier = ensemble.GradientBoostingClassifier(\n",
+    "#    n_estimators = 100, #how many decision trees to build\n",
+    "#    learning_rate = 0.5, #controls rate at which additional decision trees influes overall prediction\n",
+    "#    max_depth = 6, \n",
+    "#     min_samples_split = 21,\n",
+    "#     min_samples_leaf = 19, \n",
+    "    #max_features = 0.9,\n",
+    "    #loss = 'huber'\n",
+    "#)\n",
+    "\n",
+    "classifier.fit(X_train, y_train)\n",
+    "\n",
+    "predictions = classifier.predict(X_test)\n",
+    "\n",
+    "print(classification_report(y_test, predictions))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00      2401\n",
+      "           1       1.00      0.99      1.00       731\n",
+      "\n",
+      "    accuracy                           1.00      3132\n",
+      "   macro avg       1.00      1.00      1.00      3132\n",
+      "weighted avg       1.00      1.00      1.00      3132\n",
+      "\n",
+      "Confusion Matrix: \n",
+      " [[2401    0]\n",
+      " [   4  727]]\n",
+      "\n",
+      "Accuracy:  0.9987228607918263\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.metrics import classification_report,confusion_matrix, accuracy_score\n",
+    "pred = classifier.predict(X_train)\n",
+    "print(classification_report(y_train ,pred ))\n",
+    "print('Confusion Matrix: \\n',confusion_matrix(y_train,pred))\n",
+    "print()\n",
+    "print('Accuracy: ', accuracy_score(y_train,pred))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       0.98      0.99      0.98      1926\n",
+      "           1       0.97      0.94      0.95       637\n",
+      "\n",
+      "    accuracy                           0.98      2563\n",
+      "   macro avg       0.97      0.96      0.97      2563\n",
+      "weighted avg       0.98      0.98      0.98      2563\n",
+      "\n",
+      "Confusion Matrix: \n",
+      " [[1906   20]\n",
+      " [  40  597]]\n",
+      "\n",
+      "Accuracy:  0.9765899336714787\n"
+     ]
+    }
+   ],
+   "source": [
+    "pred = classifier.predict(X_test)\n",
+    "print(classification_report(y_test ,pred ))\n",
+    "print('Confusion Matrix: \\n', confusion_matrix(y_test,pred))\n",
+    "\n",
+    "print()\n",
+    "print('Accuracy: ', accuracy_score(y_test,pred))"
+   ]
+  }
+ ],
+ "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": "3.6.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}