From 3fef5adb3fd9810d27c4f0f89fb1b514c9eef313 Mon Sep 17 00:00:00 2001 From: Eugene Berson Date: Sat, 15 Oct 2016 13:07:06 -0700 Subject: [PATCH 1/3] update --- eugenetest.md | 1 + 1 file changed, 1 insertion(+) create mode 100644 eugenetest.md diff --git a/eugenetest.md b/eugenetest.md new file mode 100644 index 0000000..87a03f3 --- /dev/null +++ b/eugenetest.md @@ -0,0 +1 @@ +hello 123 \ No newline at end of file From 3af56bd074e728d59722d6753594851bc37ad64f Mon Sep 17 00:00:00 2001 From: Eugene Berson Date: Sat, 22 Oct 2016 20:31:23 -0700 Subject: [PATCH 2/3] changes --- Eugene project ideas.md | 40 + Yelp_Eugene.ipynb | 861 ++ eugenetest.md | 1 - .../Titanic_Eugene-checkpoint.ipynb | 1620 ++++ labs/Titanic_Eugene.ipynb | 1620 ++++ labs/untitled | 0 .../02_pandas-checkpoint.ipynb | 7213 +++++++++++++++++ .../Yelp_Eugene-checkpoint.ipynb | 861 ++ notebooks/02_pandas.ipynb | 4 +- notebooks/05_bias_variance_tradeoff.ipynb | 4 +- notebooks/05_linear_regression.ipynb | 4 +- notebooks/05_model_evaluation.ipynb | 11 +- 12 files changed, 12227 insertions(+), 12 deletions(-) create mode 100644 Eugene project ideas.md create mode 100644 Yelp_Eugene.ipynb delete mode 100644 eugenetest.md create mode 100644 labs/.ipynb_checkpoints/Titanic_Eugene-checkpoint.ipynb create mode 100644 labs/Titanic_Eugene.ipynb create mode 100644 labs/untitled create mode 100644 notebooks/.ipynb_checkpoints/02_pandas-checkpoint.ipynb create mode 100644 notebooks/.ipynb_checkpoints/Yelp_Eugene-checkpoint.ipynb diff --git a/Eugene project ideas.md b/Eugene project ideas.md new file mode 100644 index 0000000..1534a96 --- /dev/null +++ b/Eugene project ideas.md @@ -0,0 +1,40 @@ +Idea #1 Slack integrations +Parameters: +1) Uses a slash command? +2) Is a bot? +3) Is listed in App Directory? +4) Featured in the app directory (at any point in time)? + +Trying to predict +1) Is it used by paid team or a free team? + + +Idea #2 Strava segment data +Parameters: +1) Number of times riding per week +2) Average distance ridden per week +3) Longest ride ever + +Trying to predict +1) Rider's percentile on the leader board for most popular segment in their area + + +Idea #3: Google Finance +Parameters: +1) P/E ratio average LTM +2) P/E ratio % change LTM +3) Industry sector + +Trying to predict +1) LTM change in stock price + + +Idea #4: Slack credit card payments data from Stripe +Parameters: +1) Country of credit card issue +2) Type of credit card (Visa, MC, etc.) +3) Issuing bank (Chase vs Wells etc) +4) Transaction size (bucketed by size) + +Trying to predict: +1) Will the transaction attempt be successful or will it fail? \ No newline at end of file diff --git a/Yelp_Eugene.ipynb b/Yelp_Eugene.ipynb new file mode 100644 index 0000000..7ab0ba3 --- /dev/null +++ b/Yelp_Eugene.ipynb @@ -0,0 +1,861 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 61, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
business_iddatereview_idstarstexttypeuser_idcoolusefulfunny
09yKzy9PApeiPPOUJEtnvkg2011-01-26fWKvX83p0-ka4JS3dc6E5A5My wife took me here on my birthday for breakf...reviewrLtl8ZkDX5vH5nAx9C3q5Q250
1ZRJwVLyzEJq1VAihDhYiow2011-07-27IjZ33sJrzXqU-0X6U8NwyA5I have no idea why some people give bad review...review0a2KyEL0d3Yb1V6aivbIuQ000
26oRAC4uyJCsJl1X0WZpVSA2012-06-14IESLBzqUCLdSzSqm0eCSxQ4love the gyro plate. Rice is so good and I als...review0hT2KtfLiobPvh6cDC8JQg010
3_1QQZuf4zZOyFCvXc0o6Vg2010-05-27G-WvGaISbqqaMHlNnByodA5Rosie, Dakota, and I LOVE Chaparral Dog Park!!...reviewuZetl9T0NcROGOyFfughhg120
46ozycU1RpktNG2-1BroVtw2012-01-051uJFq2r5QfJG_6ExMRCaGw5General Manager Scott Petello is a good egg!!!...reviewvYmM4KTsC8ZfQBg-j5MWkw000
\n", + "
" + ], + "text/plain": [ + " business_id date review_id stars \\\n", + "0 9yKzy9PApeiPPOUJEtnvkg 2011-01-26 fWKvX83p0-ka4JS3dc6E5A 5 \n", + "1 ZRJwVLyzEJq1VAihDhYiow 2011-07-27 IjZ33sJrzXqU-0X6U8NwyA 5 \n", + "2 6oRAC4uyJCsJl1X0WZpVSA 2012-06-14 IESLBzqUCLdSzSqm0eCSxQ 4 \n", + "3 _1QQZuf4zZOyFCvXc0o6Vg 2010-05-27 G-WvGaISbqqaMHlNnByodA 5 \n", + "4 6ozycU1RpktNG2-1BroVtw 2012-01-05 1uJFq2r5QfJG_6ExMRCaGw 5 \n", + "\n", + " text type \\\n", + "0 My wife took me here on my birthday for breakf... review \n", + "1 I have no idea why some people give bad review... review \n", + "2 love the gyro plate. Rice is so good and I als... review \n", + "3 Rosie, Dakota, and I LOVE Chaparral Dog Park!!... review \n", + "4 General Manager Scott Petello is a good egg!!!... review \n", + "\n", + " user_id cool useful funny \n", + "0 rLtl8ZkDX5vH5nAx9C3q5Q 2 5 0 \n", + "1 0a2KyEL0d3Yb1V6aivbIuQ 0 0 0 \n", + "2 0hT2KtfLiobPvh6cDC8JQg 0 1 0 \n", + "3 uZetl9T0NcROGOyFfughhg 1 2 0 \n", + "4 vYmM4KTsC8ZfQBg-j5MWkw 0 0 0 " + ] + }, + "execution_count": 61, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "from sklearn.linear_model import LinearRegression\n", + "from sklearn.cross_validation import cross_val_score\n", + "from sklearn import metrics\n", + "import statsmodels.formula.api as smf\n", + "from sklearn.neighbors import KNeighborsClassifier\n", + "\n", + "# visualization\n", + "import seaborn as sns\n", + "import matplotlib.pyplot as plt\n", + "%matplotlib inline\n", + "\n", + "data = pd.read_csv('http://localhost:8888/files/data/yelp.csv')\n", + "data.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 62, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAABNQAAAJQCAYAAABGuTl9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "sns.pairplot(data, x_vars=['cool','useful','funny'], y_vars='stars', size=6, aspect=0.7, kind='reg')" + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 63, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA+AAAAPgCAYAAACyJxZ9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\niIhIAv8PHDnCfQbnykwAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "sns.pairplot(data)" + ] + }, + { + "cell_type": "code", + "execution_count": 64, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
starscoolusefulfunny
stars1.0000000.052555-0.023479-0.061306
cool0.0525551.0000000.8871020.764342
useful-0.0234790.8871021.0000000.723406
funny-0.0613060.7643420.7234061.000000
\n", + "
" + ], + "text/plain": [ + " stars cool useful funny\n", + "stars 1.000000 0.052555 -0.023479 -0.061306\n", + "cool 0.052555 1.000000 0.887102 0.764342\n", + "useful -0.023479 0.887102 1.000000 0.723406\n", + "funny -0.061306 0.764342 0.723406 1.000000" + ] + }, + "execution_count": 64, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.corr()" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 65, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAesAAAFhCAYAAABQ2IIfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "sns.heatmap(data.corr())" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Intercept 3.750433\n", + "cool 0.030870\n", + "dtype: float64" + ] + }, + "execution_count": 66, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "### STATSMODELS ###\n", + "\n", + "# create a fitted model\n", + "lm = smf.ols(formula='stars ~ cool', data=data).fit()\n", + "\n", + "# print the coefficients\n", + "lm.params" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
starscoolusefulfunny
count10000.00000010000.00000010000.00000010000.000000
mean3.7775000.8768001.4093000.701300
std1.2146362.0678612.3366471.907942
min1.0000000.0000000.0000000.000000
25%3.0000000.0000000.0000000.000000
50%4.0000000.0000001.0000000.000000
75%5.0000001.0000002.0000001.000000
max5.00000077.00000076.00000057.000000
\n", + "
" + ], + "text/plain": [ + " stars cool useful funny\n", + "count 10000.000000 10000.000000 10000.000000 10000.000000\n", + "mean 3.777500 0.876800 1.409300 0.701300\n", + "std 1.214636 2.067861 2.336647 1.907942\n", + "min 1.000000 0.000000 0.000000 0.000000\n", + "25% 3.000000 0.000000 0.000000 0.000000\n", + "50% 4.000000 0.000000 1.000000 0.000000\n", + "75% 5.000000 1.000000 2.000000 1.000000\n", + "max 5.000000 77.000000 76.000000 57.000000" + ] + }, + "execution_count": 67, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(10000, 10)" + ] + }, + "execution_count": 68, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": { + "collapsed": false, + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Intercept 3.794700\n", + "useful -0.012205\n", + "dtype: float64" + ] + }, + "execution_count": 69, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "### STATSMODELS ###\n", + "\n", + "# create a fitted model\n", + "lm = smf.ols(formula='stars ~ useful', data=data).fit()\n", + "\n", + "# print the coefficients\n", + "lm.params" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Intercept 3.804871\n", + "funny -0.039029\n", + "dtype: float64" + ] + }, + "execution_count": 70, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "### STATSMODELS ###\n", + "\n", + "# create a fitted model\n", + "lm = smf.ols(formula='stars ~ funny', data=data).fit()\n", + "\n", + "# print the coefficients\n", + "lm.params" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "pandas.core.frame.DataFrame" + ] + }, + "execution_count": 71, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "type(data)" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[2, 5, 0],\n", + " [0, 0, 0],\n", + " [0, 1, 0],\n", + " ..., \n", + " [0, 0, 0],\n", + " [0, 0, 0],\n", + " [0, 0, 0]], dtype=int64)" + ] + }, + "execution_count": 72, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn.cross_validation import train_test_split\n", + "features = np.array([data.cool, data.useful, data.funny]).T\n", + "features # 2D array" + ] + }, + { + "cell_type": "code", + "execution_count": 88, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[5],\n", + " [5],\n", + " [4],\n", + " ..., \n", + " [4],\n", + " [2],\n", + " [5]], dtype=int64)" + ] + }, + "execution_count": 88, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "response = np.array([data.stars]).T \n", + "response # 1D array\n" + ] + }, + { + "cell_type": "code", + "execution_count": 74, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "# step 1: split data into training set and test set\n", + "features_train, features_test, response_train, response_test = train_test_split(features, response, random_state=4)\n", + "# the random_state allows us all to get the same random numbers" + ] + }, + { + "cell_type": "code", + "execution_count": 82, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[1, 6, 4],\n", + " [1, 2, 1],\n", + " [0, 1, 0],\n", + " ..., \n", + " [0, 0, 0],\n", + " [2, 3, 2],\n", + " [0, 2, 0]], dtype=int64)" + ] + }, + "execution_count": 82, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "features_train" + ] + }, + { + "cell_type": "code", + "execution_count": 83, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[1, 3, 1],\n", + " [0, 1, 0],\n", + " [0, 0, 0],\n", + " ..., \n", + " [0, 0, 0],\n", + " [0, 0, 0],\n", + " [0, 0, 0]], dtype=int64)" + ] + }, + "execution_count": 83, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "features_test" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[3],\n", + " [5],\n", + " [5],\n", + " ..., \n", + " [4],\n", + " [2],\n", + " [1]], dtype=int64)" + ] + }, + "execution_count": 84, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "response_train" + ] + }, + { + "cell_type": "code", + "execution_count": 85, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[5],\n", + " [5],\n", + " [5],\n", + " ..., \n", + " [3],\n", + " [4],\n", + " [3]], dtype=int64)" + ] + }, + "execution_count": 85, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 89, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\Eugene\\Anaconda2\\envs\\bersonenv\\lib\\site-packages\\ipykernel\\__main__.py:2: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n", + " from ipykernel import kernelapp as app\n" + ] + }, + { + "data": { + "text/plain": [ + "0.35320000000000001" + ] + }, + "execution_count": 89, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "knn = KNeighborsClassifier(n_neighbors=5)\n", + "knn.fit(features_train, response_train) # Note that I fit to the training\n", + "knn.score(features_test, response_test) # and scored on the test set" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 102, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "X = data[['cool', 'useful', 'funny']]\n", + "y = data['stars']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 103, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "from sklearn.cross_validation import cross_val_score\n", + "knn = KNeighborsClassifier(n_neighbors=5)\n", + "scores = cross_val_score(knn, X, y, cv=5, scoring='accuracy')" + ] + }, + { + "cell_type": "code", + "execution_count": 104, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([ 0.28657014, 0.24787606, 0.22011006, 0.17558779, 0.24274274])" + ] + }, + "execution_count": 104, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "scores" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python [bersonenv]", + "language": "python", + "name": "Python [bersonenv]" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.12" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} diff --git a/eugenetest.md b/eugenetest.md deleted file mode 100644 index 87a03f3..0000000 --- a/eugenetest.md +++ /dev/null @@ -1 +0,0 @@ -hello 123 \ No newline at end of file diff --git a/labs/.ipynb_checkpoints/Titanic_Eugene-checkpoint.ipynb b/labs/.ipynb_checkpoints/Titanic_Eugene-checkpoint.ipynb new file mode 100644 index 0000000..2dc8b4a --- /dev/null +++ b/labs/.ipynb_checkpoints/Titanic_Eugene-checkpoint.ipynb @@ -0,0 +1,1620 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked
0103Braund, Mr. Owen Harrismale22.010A/5 211717.2500NaNS
1211Cumings, Mrs. John Bradley (Florence Briggs Th...female38.010PC 1759971.2833C85C
2313Heikkinen, Miss. Lainafemale26.000STON/O2. 31012827.9250NaNS
3411Futrelle, Mrs. Jacques Heath (Lily May Peel)female35.01011380353.1000C123S
4503Allen, Mr. William Henrymale35.0003734508.0500NaNS
\n", + "
" + ], + "text/plain": [ + " PassengerId Survived Pclass \\\n", + "0 1 0 3 \n", + "1 2 1 1 \n", + "2 3 1 3 \n", + "3 4 1 1 \n", + "4 5 0 3 \n", + "\n", + " Name Sex Age SibSp \\\n", + "0 Braund, Mr. Owen Harris male 22.0 1 \n", + "1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 \n", + "2 Heikkinen, Miss. Laina female 26.0 0 \n", + "3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 \n", + "4 Allen, Mr. William Henry male 35.0 0 \n", + "\n", + " Parch Ticket Fare Cabin Embarked \n", + "0 0 A/5 21171 7.2500 NaN S \n", + "1 0 PC 17599 71.2833 C85 C \n", + "2 0 STON/O2. 3101282 7.9250 NaN S \n", + "3 0 113803 53.1000 C123 S \n", + "4 0 373450 8.0500 NaN S " + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "from sklearn.linear_model import LinearRegression\n", + "from sklearn.cross_validation import cross_val_score\n", + "from sklearn import metrics\n", + "import statsmodels.formula.api as smf\n", + "from sklearn.neighbors import KNeighborsClassifier\n", + "\n", + "# visualization\n", + "import seaborn as sns\n", + "import matplotlib.pyplot as plt\n", + "%matplotlib inline\n", + "\n", + "data = pd.read_csv('http://localhost:8888/files/data/titanic.csv')\n", + "data.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\Eugene\\Anaconda2\\envs\\bersonenv\\lib\\site-packages\\numpy\\lib\\function_base.py:3834: RuntimeWarning: Invalid value encountered in percentile\n", + " RuntimeWarning)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PassengerIdSurvivedPclassAgeSibSpParchFare
count891.000000891.000000891.000000714.000000891.000000891.000000891.000000
mean446.0000000.3838382.30864229.6991180.5230080.38159432.204208
std257.3538420.4865920.83607114.5264971.1027430.80605749.693429
min1.0000000.0000001.0000000.4200000.0000000.0000000.000000
25%223.5000000.0000002.000000NaN0.0000000.0000007.910400
50%446.0000000.0000003.000000NaN0.0000000.00000014.454200
75%668.5000001.0000003.000000NaN1.0000000.00000031.000000
max891.0000001.0000003.00000080.0000008.0000006.000000512.329200
\n", + "
" + ], + "text/plain": [ + " PassengerId Survived Pclass Age SibSp \\\n", + "count 891.000000 891.000000 891.000000 714.000000 891.000000 \n", + "mean 446.000000 0.383838 2.308642 29.699118 0.523008 \n", + "std 257.353842 0.486592 0.836071 14.526497 1.102743 \n", + "min 1.000000 0.000000 1.000000 0.420000 0.000000 \n", + "25% 223.500000 0.000000 2.000000 NaN 0.000000 \n", + "50% 446.000000 0.000000 3.000000 NaN 0.000000 \n", + "75% 668.500000 1.000000 3.000000 NaN 1.000000 \n", + "max 891.000000 1.000000 3.000000 80.000000 8.000000 \n", + "\n", + " Parch Fare \n", + "count 891.000000 891.000000 \n", + "mean 0.381594 32.204208 \n", + "std 0.806057 49.693429 \n", + "min 0.000000 0.000000 \n", + "25% 0.000000 7.910400 \n", + "50% 0.000000 14.454200 \n", + "75% 0.000000 31.000000 \n", + "max 6.000000 512.329200 " + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 0.616162\n", + "1 0.383838\n", + "Name: Survived, dtype: float64" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.Survived.value_counts(normalize=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "PassengerId 0\n", + "Survived 0\n", + "Pclass 0\n", + "Name 0\n", + "Sex 0\n", + "Age 177\n", + "SibSp 0\n", + "Parch 0\n", + "Ticket 0\n", + "Fare 0\n", + "Cabin 687\n", + "Embarked 2\n", + "dtype: int64" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.isnull().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PassengerIdSurvivedPclassAgeSibSpParchFare
count183.000000183.000000183.000000183.000000183.000000183.000000183.000000
mean455.3661200.6721311.19125735.6744260.4644810.47541078.682469
std247.0524760.4707250.51518715.6438660.6441590.75461776.347843
min2.0000000.0000001.0000000.9200000.0000000.0000000.000000
25%263.5000000.0000001.00000024.0000000.0000000.00000029.700000
50%457.0000001.0000001.00000036.0000000.0000000.00000057.000000
75%676.0000001.0000001.00000047.5000001.0000001.00000090.000000
max890.0000001.0000003.00000080.0000003.0000004.000000512.329200
\n", + "
" + ], + "text/plain": [ + " PassengerId Survived Pclass Age SibSp \\\n", + "count 183.000000 183.000000 183.000000 183.000000 183.000000 \n", + "mean 455.366120 0.672131 1.191257 35.674426 0.464481 \n", + "std 247.052476 0.470725 0.515187 15.643866 0.644159 \n", + "min 2.000000 0.000000 1.000000 0.920000 0.000000 \n", + "25% 263.500000 0.000000 1.000000 24.000000 0.000000 \n", + "50% 457.000000 1.000000 1.000000 36.000000 0.000000 \n", + "75% 676.000000 1.000000 1.000000 47.500000 1.000000 \n", + "max 890.000000 1.000000 3.000000 80.000000 3.000000 \n", + "\n", + " Parch Fare \n", + "count 183.000000 183.000000 \n", + "mean 0.475410 78.682469 \n", + "std 0.754617 76.347843 \n", + "min 0.000000 0.000000 \n", + "25% 0.000000 29.700000 \n", + "50% 0.000000 57.000000 \n", + "75% 1.000000 90.000000 \n", + "max 4.000000 512.329200 " + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.dropna().describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0AAAAJQCAYAAACnwgRtAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAAPYQAAD2EBqD+naQAAIABJREFUeJzs3Xd0XPd95/339IIZ9MZeJPKSEKlGiVSzrbhbtqXEcbLJ\nkxNn7STr2HHq7tn42U3yPLsne5zd7CbxOrGdbHYV60lz7Niy3BVLcVEjJUqiKIG8JCWSAFGmN2Aa\nZuY+f4AFhAgKBKZiPq9zdETMXMx878wAmM/c3/1+bZZlISIiIiIi0g7sjS5ARERERESkXhSARERE\nRESkbSgAiYiIiIhI21AAEhERERGRtqEAJCIiIiIibUMBSERERERE2oYCkIiIiIiItA0FIBERERER\naRsKQCIiIiIi0jacjS7gWhiG4QGeA37VNM0fLrHNe4E/AK4HXgV+zzTNr9evShERERERaVYtcwTo\nfPj5e2DkKtvcCPwT8FfATcBfAl82DGNvXYoUEREREZGm1hJHgAzD2A383TI2/VngMdM0//z81581\nDON+4KeBo7WqT0REREREWkNLBCDgLcBjwO8C2ats99eA+wqXd9WgJhERERERaTEtEYBM0/z8hX8b\nhnG17cyFXxuGcQPwNuCzNStORERERERaRsucA3StDMPoZ/58oB+ZpvlIo+sREREREZHGW5MByDCM\nIeBxwAJ+qsHliIiIiIhIk2iJJXDXwjCMDcyHnzJwr2masWv5fsuyLJvNVpPaRERkRZrml7L+RoiI\nNJUV/UJeUwHIMAw/8B1gDvgx0zQj13obNpuNdDpHuVypen3NxuGw09npa4v9bad9Be3vWtZO+wqX\n9rdZtNLfiFZ8rajm2mu1ekE110ur1byavw8tH4DOL3dLmaaZB/4jsA24F7Cfvw4gZ5pmerm3WS5X\nKJWa/4mvlnba33baV9D+rmXttK/NptUe+1arF1RzPbRavaCa66UVa75WrXgOkLXo6ynm5/wAfADw\nAQeByQX//WndqhMRERERkabVckeATNN0LPravuDfu+tfkYiIiIiItIpWPAIkIiIiIiKyIgpAIiIi\nIiLSNhSARERERESkbSgAiYiIiIhI21AAEhERERGRtqEAJCIiIiIibUMBSERERERE2oYCkIiIiIiI\ntA0FIBERERERaRsKQCIiIiIi0jYUgEREREREpG0oAImIiIiISNtQABIRERERkbahACQiIiIiIm1D\nAUhERERERNqGApCIiIiIiLQNBSAREREREWkbCkAiIiIiItI2FIBERERERKRtKACJiIiIiEjbUAAS\nEREREZG2oQAkIiIiIiJtQwFIRERERETahgKQiIiIiIi0DQUgERERERFpGwpAIiIiIiLSNhSARERE\nRESkbSgAiYiIiIhI21AAEhERERGRtqEAJCIiIiIibUMBSERERERE2oYCkIiIiIiItA0FIBERERER\naRsKQCIiIiIi0jYUgEREREREpG0oAImIiIiISNtQABIRERERkbahACQiIiIiIm1DAUhERERERNqG\nApCIiIiIiLQNBSAREREREWkbCkAiIiIiItI2FIBERERERKRtKACJiIiIiEjbUAASEREREZG2oQAk\nIiIiIiJtQwFIRERERETahgKQiIiIiIi0DQUgERERERFpGwpAIiIiIiLSNhSARERERESkbSgAiYiI\niIhI21AAEhERERGRtqEAJCIiIiIibUMBSERERERE2oYCkIiIiIiItA0FIBERERERaRsKQCIiIiIi\n0jYUgEREREREpG0oAImIiIiISNtQABIRERERkbahACQiIiIiIi1ncOstQyv5Pme1C6klwzA8wHPA\nr5qm+cMltrkF+BywF3gZ+Jhpms/Xr0oREREREamVSqXCuckIW2569zAQutbvb5kjQOfDz98DI1fZ\nxg98E/gBcCvwNPBNwzB8dSlSRERERERqplAoMD4Zxu7uwO3vLq/kNlriCJBhGLuBv1vGpj8DZE3T\n/J3zX/+mYRj3AT8FPFSr+kREREREpLbSmQzxVA6vvxObzbbi22mVI0BvAR4D7gSutrcHgCcWXfbk\n+e8TEREREZEWY1kWoUiM5EwRrz+w6ttriSNApml+/sK/DcO42qbrmD/vZ6EQcEMNymppH/nDx193\n2f/55FsbUIlUm57btUvPrSxXK75WfuUPH6e44Gs38Pkmr/k/P/gUZ0L5i19vHfLy+x++q4EVXV1q\npsBDj55gOp5luNfPh965k66Ap9FlrTlzpTIvnIqSys7R5XexZ2sPLqej0WW1rHK5zGQois3pw+2p\nTnRplSNAy+UHCosuKwD66V7gSn8Yr3a5tA49t2uXnltZrlZ8rSwOPwDF85c3q8XhB+BMKM9/fvCp\nBlV0damZAp/8i6d58WSE6dgsL56M8Mm/eJrUzOK3TbIac6UyD377OF9/8jRPvTTJ1588zYPfPs5c\naUWnqrS9bC7H+FQUpyeA01m94zYtcQToGuR5fdjxANlruRGHY63lwuVzOtfmvl94TvXcrk3t/vy2\nw3PbTJqxpuVq1tfK4vCz8PJmrXlx+Fl4eTPW/NCjJyiWKpddVixVeOjRE/zWT9/UoKqWp5V+x79w\nKsp0PIvt/BkbNmxMx7O8fCbB7bsGG1zd1TXb45xMpUhkinQEO694/WrqXGsBaAIYXnTZMDB1LTfS\n2dm+TeN6ejoaXUJN6bld29r1+W2H57aZtPLrrBVfK6q5OqbjV/4seDqebcp6r6QVfvZS2TmcC96Y\nOxw2wEYqO6fHeZksy2JiKgwuD0PDVw4/q7XWAtAzwO8suuxu4A+u5UbS6RzlcuWNN1yDEonZRpdQ\nEw6Hnc5On57bNardn992eG6bSSu/zlrxtaKaq2O418907PV1Dff6m7LehVrpd3yX30WpXMGGDYfD\nRrlsYWHR5XfpcV6GYrHIVDiOw+3H4SiTyy29iKutjwAZhjEEpEzTzANfBj5lGMafAH8J/Arz5wX9\n47XcZrlcoVRq7h+wWlnr+63ndm1r1+e3Hfe5kVr5ddasdbu58jI4N81b89Yh7xWXwW0d8jZlzR96\n505GT8cuWwbndtr50Dt3NmW9V9IKP3t7tvbw7LHQ+SNuNiwshnv97Nna0/S1X9CoxzkzM0MsOYvX\nHzxfh/UG37HyGptjkd+1WfxoTAE/DWCaZgZ4H/Bm4DlgP/Ae0zRzda2wyS3VCajZOwTJG9Nzu3bp\nuZXlasXXyuc/+Vbciy5r9i5wv//hu9g65L3ssmbuAtcV8PCHH72Tm3cMMNzXwc07BvjDj96pLnBV\n5nI6+PB7dvH+u7dx143ref/d2/jwe3apC9wbiMbixDOFi+Gn1myW9Ubpqu1YicRsy6T01XA67fT0\ndNAO+9tO+wra37WsnfYVLu7vyqfdVV/L/I1oxdeKaq69VqsXVHO9NKLmSqXCVCiCZffidLmu6Xsd\nDhu//HsP7n3y739n8QicN9TyS+BERERERKS1FAoFpiMJ3L4gNlt9P+dSABIRERERkbpJpdMk0nm8\n/tp0eXsjCkAiIiIiIlJzlmURjsQpVGx4/YGG1aEAJCIiIiIiNVUul5kMRbG7/LjdjW0KoQAkIiIi\nIiI1k83mCMfTeHyBup/vcyUKQCIiIiIiUhPxRJJ0tlS3FtfLoQAkIiIiIiJVZVkW06EoZVx4ff5G\nl3MZBSAREREREamaYrHIVDiOyxvAabc3upzXUQASEREREZGqyGQyxFK5hrW4Xg4FIBERERERWbVI\nNE62WGloi+vlUAASEREREZEVK5fLTIWjYPfi8XobXc4bUgASEREREZEVyeXzhKJJPL5gU7S4Xg4F\nIBERERERuWbJVIpUptjU5/tciQKQiIiIiIgsm2VZhCIxihU7Hn9Ho8u5ZgpAIiIiIiKyLKVSiclQ\nFIe7A7fb0ehyVkQBSERERERE3tDsbJZIItNyS94WUwASEREREZGrisXjzOQreP3BRpeyagpAIiIi\nIiJyRZVKhelwjAqulmhxvRwKQCIiIiIi8jqFQoGpSAK3N4DTbm90OVWjACQiIiIiIpfJZDLEUrmW\nP9/nShSARERERETkonA0Tn7OwusPNLqUmlAAEhERERERyuUy5yZClGwe3J61GxPW7p6JiIiIiMiy\n5PJ5Euk0dk8Hzkqjq6mttXM2k4iIiIiIXLNkKsV0NIPHH8RmszW6nJrTESARERERkTZkWRahSIxi\nxY7P5290OXWjACQiIiIi0mZKpRKToSgOdwdut6PR5dSVApCIiIiISBuZnc0SSWTWZIvr5VAAEhER\nERFpE/FEgkyujNcfbHQpDaMAJCIiIiKyxlUqFabDMSq48Hjb53yfK1EAEhERERFZw4rFIpPhOG5v\nAKddTaAVgERERERE1qhMJkMslWvb832uRAFIRERERGQNCkfj5IoVvP5Ao0tpKgpAIiIiIiJrSLlc\nZiocBYcPj1dv9xfTIyIiIiIiskbk8nlC0SQeXxCbzdbocpqSApCIiIiIyBqQTKVIZYo63+cNKACJ\niIiIiLQwy7IIRWIUK3Y8/o5Gl9P0FIBERERERFpUuVxmMhTF7vLjdjsaXU5LUAASEREREWlB2VyO\ncCyNxxfQ+T7XQAFIRERERKTFpNJpkukCXn+w0aW0HAUgEREREZEWEo7GKZTQ+T4rpAAkIiIiItIC\nKpUKU6EIlt2Ly+1qdDktSwFIRERERKTJlUolJqajuLwBHHZ7o8tpaQpAIiIiIiJN7EKzA833qQ4F\nIBERERGRJqVmB9WnACQiIiIi0oTU7KA2FIBERERERJrIheGmNqcPl1tv16tNj6iIiIiISJPQcNPa\nUwASEREREWkC8USSzOyczvepMQUgEREREZEGqlQqTIdjVHDpfJ86UAASEREREWmQfD5PKJrE5Q3g\n1HyfulAAEhERERFpgGQqRSpTxKP5PnWlACQiIiIiUkeVSoVQOEbJ5tSStwZQABIRERERqZNCocB0\nNInL04FLS94aQgFIRERERKQOkqkUyUxBXd4aTAFIRERERKSGLMtiOhSlZHPi9QcaXU7bUwASERER\nEamRQqFAKJrEqSVvTUMBSERERESkBpKpNNFEVkvemoxiqIiIiIhIFVmWxeR0hHS2pCVvTUgBSERE\nRESkSkqlEuOTIUq4cbk9jS5HrkBL4EREREREqmB2NkskkaEj2InD4Wh0ObIEBSARERERkVWKxeNk\n8hWd79MCFIBERERERFaoUqkwFYpi2dx4vd5GlyPLoAC0SC6Xo1KpNLoMEREREWlyhUKB6UgClzeA\nQy2uW0ZLBCDDMDzAZ4EPAFngf5im+cdLbPsTwH8BNgEvAL9hmuYLy72veDJDOJKhtyuI3+9bffEi\nIiIisuakMxkSqTwef2ejS5Fr1CpR9b8DtwL3Ah8H/h/DMD6weCPDMEaAv2U+AN0IHAG+aRjGso9H\n2mw2PP4g4eQs4Wgcy7KqUb+IiIiIrBGhSIzkTBGPv6PRpcgKNH0AMgzDD/wi8OumaR4xTfNrwH8D\nPnGFzd8JvGya5t+apnka+L+BYWDkWu/X6/VTrDgZmwxRKBRWsQciIiIishaUy2XGJ0PMWS7cHq0U\nalVNH4CAm5hfqvf0gsueAA5cYdsYcINhGHcZhmEDPgKkgFdXcsdOpxOPr5OpSIpkKrWSmxARERGR\nNSCbyzE+FcXpCeB0tsRZJLKEVghA64CoaZqlBZeFAK9hGH2Ltv0i8C3mA1KR+SNFHzRNc1XpxesP\nMJOzmJwOUy6XV3NTIiIiItJiMpkMkfgMXn8Qm83W6HJklVohvvqBxWvQLny9eLxuH/NL3j4OHAQ+\nBvy1YRi3mKYZXe4dOhx24PJOcA6fB8tyMxmO0d8TIBgIXMMuNKf5/bz0/7WsnfYVtL9rWTvtKzTn\nfjZjTVfSiq8V1Vx7rVYvNL7meCJJJlfCfw3v/S6vuTW6C7dazat5PbRCAMrz+qBz4evsosv/K/CS\naZqfBzAM46PAMeDDwB8t9w4Dgav0TOjuoJDPkytkWTfUvyY+BejsbJ81rO20r6D9XcvaaV+bTas9\n9q1WL6jmemi1eqExNU9NR7B7vAwEF78VXZ6rvqdsUq1Y87VqhQA0AfQbhmE3TfNCHB0GcqZpJhdt\nuw/49IUvTNO0DMM4Amy5ljucmclTLl89+WZzFUKR1xjq78bXokOvHA47nZ0+0uncG+5vq2unfQXt\n71rWTvsKl/a3mbTKY9+KrxXVXHutVi80pmbLspicimA5vTgcDnK5xZ+5X53DYScQ8C7rPWWzaLWa\n1/oRoBeBOeAO4Knzl70JePYK207y+o5vBnDoWu6wXK5QLr9R+2sbTneAiekUQf8Mfb2913IXTaVc\nrlAqNf8LvRraaV9B+7uWtdO+NptWe+xbrV5QzfXQavVC/Woul8tMTEdwegLYsS/jPeGVVM7f1nLe\nUzaLVqt55a+Fpg9ApmnmDMN4CPi8YRgfATYC/xb4BQDDMIaAlGmaeeB/AQ8ahvEc813jfhnYDHyh\nVvV5/R3k5uYYnwyxbrBPXUFEREREWlSxWGQqHMftU7ODtaxVzoD7beAw8DjwGeD3zs8DApgCfhrA\nNM1/ZH4+0H8AngfuBH7sWhogrITT5cLpCXBuOkZmZqaWdyUiIiIiNZDN5ZgMJ/D4OxV+1riWOFxh\nmmaO+UYGH77CdfZFXz8IPFin0i6y2Wx4/UHi6SzZbIHBgV798IiIiIi0gEwmQzyVx+sPNroUqYNW\nOQLUMjxePyWbm7HJEMVisdHliIiIiMhVxBNJ4jNFPP6ORpcidaIAVAMOhwOPr5PJcJJUOt3ockRE\nRETkCkLhGLNFC4+nubpNSm0pANWQ1x8gnSszNR2hUmmtTisiIiIia5VlWUxMhSnhwuVa2YwfaV0K\nQDXmcnmwnD7GJ8Pk8vlGlyMiIiLS1srlMuOTIWwuPw51721LCkB1YLfb8fg7CUczxBOLZ7eKiIiI\nSD0Ui0XOTUVweYPY7Xob3K70zNeRx99BtgCTWhInIiIiUlezs1m1uRZAAajunG43nF8Sl9eSOBER\nEZGaS6ZSRJNZtbkWQAGoIS4siQtFMyRTqUaXIyIiIrJmhaNxMrkyHp+/0aVIk1AAaiCPv4NMvsLU\ndATLshpdjoiIiMiacaHZQbHixOX2NrocaSIKQA12oUvc2ESIQqHQ6HJEREREWt7sbJbxqShOTwCn\nOr3JIgpATeDCkrjpSFqDU0VERERWIRaPE03Nn++jZgdyJQpATcTj7yCVLTEdjmpJnIiIiMg1qFQq\nTEyFyM058Hh1vo8sTQGoybjdXso2D2OTIYrFYqPLEREREWl6uXyesckwdncAp8vV6HKkySkANSGH\nw4HH18lkOKklcSIiIiJXkUqnCUczeDXfR5ZJAWiRfLHc6BIu8voDpLIlpjQ4VUREROR1orE4qdk5\nPP6ORpciLUQBaJHf+p8H+fvvnSSTbY7lZ263F+v84NRsLtfockREREQazrIspqYj5EsO3B5fo8uR\nFqMAtEjFghdPRvnjLx7h6VemqVQa34zgQpe4cHyWSDSuBgkiIiLStorFImOTISoOr873kRVRAFpC\nYa7M1588w+e+9jLnIjONLgcAr89PoeKcH+qlBgkiIiLSZjKZDJPhJB5fJw6Ho9HlSItSAFrE77n8\nh2kiMsvnvvoyjzxxmnyx1KCqLnE6nbjPN0hIJJONLkdERESk5izLIhSOkpgp4vUHGl2OtDgFoEX+\n0y/ewq07+y+7zAKeGQ3xx188wpFTzTGjx+sPMJuHiakQ5XLzNG4QERERqaZCocCZsSnmcOt8H6kK\nBaBFOjvc/Ku37eCX3rebgW7vZdfN5Ob44uOn+D/fOkY02fiGBE63G7s7wPhUVA0SREREZM1JplJM\nhVO4/VryJtWjALSE7eu7+LWfvJF33r4Jp+PynvKvTqT59Jdf4nvPjTNXamx7apvNhtcfJByfJRaP\nN7QWERERkWqoVCpMTUfI5CtqcS1VpwB0FU6HnXtv2cBv/tRNGJu6L7uuXLF4/PkJPv3lI5wYb/y5\nOF6fn9ycg3NaEiciIiItLJfPMz4ZxnL6cLk8jS5H1iAFoGXo7fTyoXcb/Nw7dtLV4b7suni6wF9/\n+zh/970TpGYb25nN6XLhuLAkLqslcSIiItJaYvE4odgMHn8ndrvepkptOBtdQKuw2WzcsK2X6zd2\n8djhczx1dIqFI4Jefi3OyfEUb79tI3fcMIzDblv6xmpcp9cfJJKcJZDP0dfb25A6RERERJarUqkw\nFYpg2b14fd43/gaRVVC0vkYel4P77tjCr35gL5uHLm/DWJgr882nz/LZrx5lPJxpUIXzPF4/udL8\nzKBSqfHtu0VERESuJJfPMzYZxu4OaLCp1IUC0Aqt6+vg39x/Ax9483Z8nssPpE3Fsnz+4Vd4+Eev\nkSs0Lnw4nU5c3iDnpuOk0umG1SEiIiJyJclUinA0g9ffic3WmNUz0loqloU5luCh7xxf8W1oCdwq\n2G02bts1yO6tPXznmTEOn4hcvM4CDh0L88rpOO+5Ywu37Ohv2A+21x8gnSswm40wPNinNbUiIiLS\ncKFwjKJlV5c3WZaZ3ByHzTCHjoVJZAqrui0FoCro8Lr4yXuvY9+uAR7+0WnCiUsNCGbzJb78/Vc5\nbIa5/55tDPX4G1Kjy+XBstyMTUbo7w4QCOiXjYiIiNRfpVJhMhQBhw+XS29FZWmWZXE2lOHgaIiX\nX4tTXngC/iroVVdFW4c7+bWf3MuTL03z2PPnLpsRdHoqw5/901HuuXEdP3brBtzO+g/zutAgIZbO\nMpPNsWHdQN1rEBERkfZVLBaZDMfx+IJa8iZLyhdLvHAyyqHREKFE9TsbKwBVmcNu5803r2fvdX18\n46kzHDubuHhduWLxgxcneenVGO+/eyu7Nvc0pEaP10+5XGZsIkRHh042FBERkdqbnc0SScyf7yNy\nJZPRWQ6OhjhyKkpxwYGEhRx2GyNbe7lr7xCf+tzKzgNSAKqRnqCHn3+XwbGzCb7+5GmSM5dmBCUy\nBR76jsnI1h7ed9dWugP1H/LlcDhwuIOcm0pgp0KgI1j3GkRERKQ9JFMpkjNzeP16vyGXmytVOPpa\njIOjIcbDM0tu1x1ws3/3EPuMAYJ+Nw7Hyo8gKgDV2O4tPVy3vpPHn5/giZemqFiX1i6Onklw6lyK\nt+3byF17h3E0oDmBtyNANJIknVGDBBEREam+cDROvgReX2POg5bmFE3lODQa5vCJyJJdk23Azs3d\nHBgZYufGbuxVmrOpAFQHbpeDdx/YzC07+vnak6c5M3VpRlCxVOHbB8d44WSUB+7Zxpbh+n8y4nK7\nKZWcjE2GGezrwu/z1b0GERERWVsuDDfF4cPt1ltOgXKlwrGzSQ6Nhjg1kVpyuw6fi9uMAfbvHqQn\nWP3BuHo11tFQr59fft8IL5yM8q1nzpLNX0q70/Esf/HIK9xmDPDuA5vxe+t7bs58g4ROwvFZgr4c\nfb29db1/ERERWTtKpRIT01Fc3oBWlwipmQLPHg/z3PEw6ezcktttXRfkwO4hbtjWi9NRu9eNAlCd\n2Ww2bt05wK7NPXz30BjPHg9fdv1zZoTRMwnefWAztxoD2OvcIcXr85Obm2N8MsT6oX4cjvp3qxMR\nEZHWlc3lCMfSanbQ5iqWxalzKQ4dC3H8bIKlOlh7XA5u2dnPgd1DDPXWZ5mkAlCD+L1OfuLN29ln\nzM8Omo5nL16XLZT4yg9f47AZ4YE3bWO4Ti+GC5wuF5bTyfhUlL7uDoKBQF3vX0RERFpTKp0mmS6o\n2UEbm83PcdiMcOhYiHh66YGl6/v8HBgZ4sbr+/G46vuBuwJQg20eCvKrH9jL0y9P873nxi9r+Xc2\nlOHP/ukl7t67jrft24i7ji+OCzOD4uks2WyBwYFe9esXERGRJUWicXJzFh6/hq23G8uyGAvNzA8s\nPR2jVL7y4R6nw8aN1/VzYGSQjQOBhr23VABqAg67jXtuXMfe7b184+mzvHI6fvG6igU/emnq4uyg\nka31PTfH4/VTKpcZmwyxbqAXt9td1/sXERGR5mZZFtOhKGWbG7dH8wXbSaFY5sVTUQ6Ohi5bzbRY\nf5eX/buHuHXnAH5v4+NH4yuQi7oCHn7uHTsxxxI88uQZEplLhw1Ts0X+5tET7Nrcw/vv3lKTjhhL\ncTgcOHydTIaT9HR66erUml4RERGZb3YwGYri9ARwqtlB25iOZzk4GuKFkxGKc1ceWGq32RjZ2sOB\nkSG2r+9sqpVECkBNyNjcw2+u7+L7L0zwwyOTlBecNXZ8LMGrEyneum8Dd+9dV9MOGYt5/QFS2TzZ\nbIQhzQwSERFpa7l8nlA0hccXbKo3t1Ibc6UKr5yOc3A0xNlQZsntujrc3L57kNt2DdLpb86VQwpA\nTcrltPOO2zdx045+HnniNK9Npi9eN1eu8N1D47xwMsr9d29j+/r6HZFxu71UKhXGJ8MM9nfj89bv\nSJSIiIg0h0wmQyyVU7ODNhBL53n2WIjnzMhlI1wW27GxiwMjQxibe3BUaWBprSgANbnBbh+/+N7d\nHDkV45vPnGU2d6l3ejiR46++McotO/p5zx1bCPjqs+7Wbrfj8XcSjmYIduTp7emuy/2KiIhI48Xi\ncWYKFl6/usSuVeWKhTmW4OBoiJPnlh5Y6vc6uc0Y4PbdQ/R1ts6H4gpALcBms3Hzjn6Mzd08+uw4\nh0ZDLOyt8cLJKMfHErxr/2Zu2zVYt9lBHn8H2UKR3FSI4UHNDBIREVnLLjY7wIXH05xLm2R1kpkC\njz03zqHRMKnZ4pLbbRkKcmBkiD3bazuwtFYUgFqIz+PkgXu2cevOAb72xGkmo7MXr8sVyjz8o9M8\nfyLCA/dsY11ffVpQOt1uLMvF+FSUgZ4gHR31nVkkIiIitVcul5kMRbG7/Dj1geeaYlkWr06kOXQs\nxOiZBBXryi2sPS4HN+/o58DIUN1nVFabAlAL2jQY4OM/vodnRkP887PjFObKF68bC83w5185yp03\nDPP22zbhcdf+l9SFmUGRVJZsLs9Af31bdYuIiEjtzDc7SKrZwRqTzZd4/kSEg8dCxFL5Jbdb1+dn\n/+4hbr7MijyaAAAgAElEQVS+vy7vK+tBAWgRy7Kwlki+zcRut3HXnmH2bOvlm0+f5ehrsYvXVSx4\n8uVpjr4W4713bWXPtvoMMfV6/RRKJcYnQ6wb7MPp1MtLRESklaUzGeKpHF6/RmCsBZZlcS4yP7D0\npVevPrB07/Y+DowMsWmwcQNLa0XvUBcZGugllZogn6/g9TX/4b3ODjc/+/Yd3HZugEeeOEMsfSnB\np7Nz/P33TrJzUxfvv3tbXU5Oczqd4AxybjpGX5efYFDdYURERFpROBonP6dmB2tBca7MkfMDSydj\nSw8sHej2cfvuQW7Z0U+Hd+0OtVUAWsTpdLJuqJ/Z2RyxRIpi2YbXV5/zaVZjx8Zufv2DN/KDFyf4\nwYuXzw46MZ7i0186wr23bODNN62vy8lqXn+QxEyO2VyUoYG+NffJgYiIyFpVLpeZCkfB7sXtWbtv\ngttBKJ7l4LEQL5yIXnbKxEI2G+ze0sOde4bZd8M6Mukc5SWODK0VCkBL8Hg8rB8eJJ/PE02kKePA\n4/E1uqyrcjntvP22Tdy8o59HnjjDqYlLbQtLZYvvPXeOF09GeeCebVy3oavm9bg9PsrlMmMTIYYH\nevB4PDW/TxEREVm5bC5HOKbhpq2sVD4/sPRYiDNTSw8sDfpd3L5rkNt3DdIV8OBw2OrWSbjRFIDe\ngNfrZeM6L7PZLPFkBsvuwu1u7j7n/V0+PnzfLo6+FuObT58lk700OyiayvO/v3mMm67v4/13b6Wr\nq7bL/BwOBw5/J1ORFN1BD91dtQ9eIiIicu3iiSSZ2Tmd79OiEpk8h46Fee54mNmrDCy9fkMX+0eG\n2L2lG4e99VpYV4MC0DJ1+P10+P3MzMySzMxQwYG7iY8I2Ww2bryun52buvnn587xzCvTLOztcORU\nDHMsyY/fez03beupeT1ef4BMrkA2F2F4sA97m/7AiYiINJsL831KOPH4m3/Zv1xSqVicGE9ycDTE\nifEkSy1c83kc7Ns5yP7dg/R3N+/713pRALpGgUAHgUAH2VyOeDJDqdLc5wh53U7ef9fW+dlBP3qN\nc5FLs4PyxTL/8KjJE4MdPHD3NjYM1PYkR5fbg2W5GZsMM9jXhd+nH0AREZFGKhQKTEUSuL0BXPpw\nsmVkskUOmxEOHQuRnFl6YOmmwQAHRobYu70Pl1PP7wUKQCvk9/nw+3zk83liyTRzZXtTd43b0N/B\nrzywh0PHQjz67Dj54qUT4c6FZ/nswy9zx8gw77h9I1537V4W8zODOgnHZwn6cvT1amaQiIhII6jF\ndWuxLIvTU2kOjoZ45fTSA0vdTjs3XT8/sHR9f/N+SN9ICkCr5PV62TDspVAoEEukKZbA4/M35YmD\ndruNO24Y5oZtvXz7mTFePBW9eJ1lwdOvTPPyazHuu3MLN15X285tXp+fXKnE2MQ0wwO9uN3umt2X\niIiIXGJZFqFwlNmCWly3glyhxAsnIxwcDRNJ5pbcbqjHx4GRIW7e0V/TD7PXAj06VTLfNW6Aubk5\nYvEU+bkKHl9HUwahoN/NT7/1em7fPcgjT54hFL/UDz6Tm+OLj5/isBnh/nu20t9Vu2Vq8zODOpkM\nJ+nscNPb012z+xIREREolUqcGZtiDjduj5ZENbOJyAzPjIZ46VSMuXLlits47Db2bO/lwMgQW4bU\nuW+5FICqzOVyMTzUT6lUIhpPkiuW8fqac4Lu9Ru7+N2PHOAbPzzFY4fPXTYN+NREik9/6SXecvN6\n3nLzhpquG/X6A2QLRWYnQ6wb7JsPRiIiIlJV842csgyuG8Qxl13zs15aUbFU5qVTMQ4eCzGx4Lzt\nxXqCHvbvHmSfMUjAp1lN10rvNGvE6XQyPNhPuVwmFk+RLczh8vhxOByNLu0yLqedt+7byN7tfXz9\nyTOY48mL15UrFo8/P8GLp6Lcf/c2dm6q3REap9uNZbmYCMXpCqhdtoiISDXF4nEy+QodHVry1ozC\nidz5gaWRy87TXshmg12bezgwMsT1G7vaZmZPLSgA1ZjD4WBwoJdKpUIimSSTzeJ0+5ruKEdvp5cP\nvdvgldNxvvH0WdKzlzqKxNMF/vrbx9m7vZf33rmVzo7anK9js9nw+C61yx4a6G26wCgiItJKyuUy\nU+Eo2L14vc09x7DdlMoVRs8kODga4vRUesntgj4Xt+0a5Pbdg3QHNFS+GprrXfgaZrfb6evtpbfH\nIpVOk56dwe7w4HQ1z2FLm83Gnu197NjYzWOHz/HUy1NUFhwdP/panBPjKd5x+0YOjAzjsNfmk4cL\n7bLHp6IM9ATp6Gje7noiIiLNKpfPE4om8fh0bkgzSWQKPHt8fmDpTG5uye22r+/kwMgQI1t72nZg\naa0oANWZzWaju6uL7i5IplKkMmnsLh+uJgpCHreD++7cwi07+3n4R6cZD89cvK4wV+YbT53leTPC\nA2/azqbB2hxKn2+XHSSSypLN5RnoV7tsERGR5Zp/j1FUi+smUalYnDyX5OBoGHM8wRIdrPG6Hdy6\nc4D9I0MMamBpzSgANVB3VxddnZ3zR4RmMtic3qYKQuv6OvjoAzdw+HiY7xwaI1e4tCZ1Mpbl8w+/\nzO27B3nX/s34PLV5KXm9fgqlEuNqkCAiIvKGLMtiOhSlZHPi8WsGTKPN5OY4NBri0LEwiUxhye02\nDnTMDyy9rg+3U8v/a60l3k0ahuEBPgt8AMgC/8M0zT9eYtu957fdB5wEfsM0ze/XqdRrduGI0IUg\nlJrJ4HA1zzlCdpuN23cPsXtrL985OMbzJyIXr7OAQ8fCvHImwX13bObm6/trcoh9vl12kHPTMfq6\n/ASDwarfh4iISKsrFotMheO4vAFcWjLVMJZlcXoyw+EfvMbzx8OUK1c+3ONy2Lnp+j4OjAyxYUDN\nKeqpOd5lv7H/DtwK3AtsBR4yDOOMaZpfWbiRYRidwKPAw8AvAB8CvmoYxg7TNKM0sYVBKJlKkZ5t\nriAU8Ln44L3Xsc8Y4GtPnCacuDSIazY3x5f+5dXzs4O21eyQrdcfJDGTYzYXZWigtoNaRUREWkkm\nkyGWymnJWwPliyVeOBnl0GiIUGLpgaUD3V4OjAxxy46Bmq2gkatr+kfdMAw/8IvAu0zTPAIcMQzj\nvwGfAL6yaPN/DWRM0/zY+a//X8Mw3gPcBnynTiWvis1mo6e7m+4ui0QyRSbbXEFo27pOPvGBvTx5\ndIrHD09cNpjrtck0n/nyS7zpxnXce+uGmhzCdXt8VCoVxiZCDPR14fdpfayIiLQvy7IIR+IUyvNz\n9aT+JqOzHBwNceRUlGJp6YGlI1vnB5ZuW6emFI3WHO+qr+4m5ut8esFlTwD/4QrbvgX42sILTNM8\nULvSasdms9Hb001P96WucTa7C5e78e0PnQ47b7l5Azde1883njrDsbOJi9eVKxbff3GSI6/GuP/u\nrRibe6p+/3a7HY+/k3B8lg5Pjv6+Hv0iERGRtlMqlZgKx7A5fbh1JKGu5koVjr4W4+Bo6LJmUYv1\nBD3cvmuQfcYAQX9txojItWuFn5Z1QNQ0zdKCy0KA1zCMPtM0Ywsu3w4cMgzjL4D7gdPAvzNN86n6\nlVtdC7vGZTIZkpkMZRx4vY1vDd0T9PDz7zI4dibO1586Q3Lm0uygRKbAF75jcsPWXt531xa6atC3\n3uu71CBheKAXt1u/WEREpD3MzmaJJmdwewP6ELCOoqkch0bDHD4RIVcoXXEbG2Bs7uZt+7ewsc+3\nZMc3aZxWCEB+YHHbjAtfL35XHQB+B/g08G7gZ4FHDcMwTNOcqGmVdRAMBgkGg2RzORKpDHMlGx6f\nv+G/+HZv7eW6DV08/vwET7w0RWXBT/orZ+KcPJfk7bdt4s491Z8dNN8goZPJcJLuoIfurq6q3r6I\niEizicXjZPIVvD4teauHcqXCsbNJDo2GODWRWnK7Dp+L24wB9u8epL/bR1eXn1QqS7msBNRsWiEA\n5Xl90LnwdXbR5SXgBdM0/9P5r48YhvFO4OeBP1zuHToczd05pTPYQWewg2KxSCyRJl+s4PVde6vL\nC/s5//8rr1ldLp/DyXvv2sK+XQM8/MPXOD2VuXhdsVThW8+c5YWTEX78zdvZOlz9Lm4dwSC5YpFC\nJMbwYC8Ox+XnH12+r2uf9nftaqd9hebcz2as6Upa8bWimq+uUqkwOR3Bcnjp6FjZW7hq/u2vl0bV\nnJopcOhYmEPHQqRnlx5Yum1dkDtuGGbP9l6ci14PepxrZzU/c60QgCaAfsMw7KZpXng2hoGcaZrJ\nRdtOAccXXXYC2HQtd9jZ2Son1ncwNNRDoVAgFEkwV3HgXUFTgEDAW7WKurr8/PutfTx9dIqv/Mup\nyyYcT8WyfO6rL3P3Tev5iXuvJ+Cr9swjP5ZlkZrNMNjXRTDw+lDYOs9tdWh/16522tdm02qPfavV\nC6r5SvL5PJPTKXoGBqqy8qOaf/vrpR41VyyL42fi/OD5CY6eil62qmUhr8fBHTes4823bGD9VVpY\n63FuTq0QgF4E5oA7gAvn8rwJePYK2z4DvHnRZbuAv72WO0ync5TLzZ98Fwp2zC+Ni4XCWHY3rmWc\nD+Nw2AkEvMzM5Ku+vzds6Wbrz9zEt58Z49lj4cuue/LIJC+aYe67cwv7jOr8Ir+ck1Nnonhdl9pl\nOxx2Ojt9LfncroT2d+1qp32FS/vbTFrlsW/F14pqvrJkKkUyU8Tj85NPL91eeTlq+be/VupR82x+\njueORzg4GiKWyi+53fr+Du64YYibd/Tjcc2vNkmlFi9I0uNcD2v6CJBpmjnDMB4CPm8YxkeAjcC/\nZX7OD4ZhDAEp0zTzwOeBTxiG8fvMh55fALYBf3Mt91kuVygt0cawmbldHtYNDZDJZIin08tonz2/\nj+VypSbrU70uJz/xpu3cumN+dtB0/NIviNl8iS/9y6s8eyzMA/dsY6i3uk0dnC4vxUqF18amGerr\nIhCYv/1WfW5XSvu7drXTvjabVnvsW61eUM0XWJbFdChKyebE5fZV6W91bf/210ZtarYsi/HwDAdH\nQxx9LUZpidt2OmzceF0/B0YG2ThwqenE1WvR41x7K/95a/oAdN5vA58FHgdSwO+Zpnmh3fUU8/N/\nHjJNc8wwjHcBnwE+CRwD7jNNc6r+JTdOMBgkEAiQSM4PVHV5/K87J6aetgwH+dUP7OXpl6f53nPj\nl/XIPzOd4TP/dJR7bhzmrbduxO2qXp12ux2PL0gomqE4V6Sn59rPkxIREWmEQqHAdDSJy9OBy946\n50S1gkKxzIunohw6FmIq9vqjNxf0d3nZv3uIW3cO4Pe2yltmWY6WeDZN08wBHz7/3+Lr7Iu+fpr5\nwadtbeEcoVg8wWwuh9vb0bCOcQ67jXtuXMee7b1886mzvHImfvG6imXxwyNTvPRqjPfdtZWRrb1V\nvW+Pv4OZQomz41N0+DqYb1ApIiLSnFLpNIl0Hq+/+k2D2tl0PMvB0RAvnoxSmCtfcRu7bb677YGR\nIa5b39nwTrtSGy0RgGTlbDYb/X299JTLRKIJ8nMWXn/jjoR0Bzz83Dt3Yo4leOTJMyQylzqcJ2eK\n/M2jJ9i1uYf3372VnmD1Zge5XC4cHh/jkxG6gj6CAbUOFRGR5mJZFqFIjGLFjtevv1PVMFeq8PLp\n+YGlY6GlB5Z2dbi5bdcgt+8apLNDcwXXOgWgNuFwOBge6qdQKBBNpChZDvz+xg1TNTb38BvrO/n+\nC5P86Mgk5cqltabHxxK8OpHirfs2cPfedRdbSq6WzWbD4w+QyGSZzeYvNkgQERFptFKpxGQoisPd\ngdvduGXra0UsnefQaIjDZoTsEgNLAXZs7OLAyBDG5p6qzyqU5qUA1GY8Hg8bhgeZmZklPTNDyV/t\nVtTL53Y6eOftm7j5+n6+9sRpTk+lL143V67w3UPjvHAyygP3bGPbus7q3a/HR6VSYWwyzEBvJ/4V\ntA4XERGplpmZWaLJGbz+6v2ta0flioU5luDgaIiT55YeWOr3ONlnDLB/ZIi+zrXf8lleTwGoTQUC\nHXR3B8FWIh6bwebwNqxRwmCPj196325ePBXlW8+MMbtgdlA4keN/fX2UW3cO8O4Dm6s2O+hCg4Rw\nfBa/J8dAX4+OBomISN3F4nEy+YrO91mF9GyR58wwzx4Lk5otLrndlqEg+0cG2bOtD5dTjSXamQJQ\nm+vp7sKqOAiFY8xkc3h8jWmUYLPZuGXHALs29/DdQ/OzgxY2YHz+RIRjZxO8e/8m9u0axF6lGr0+\nP3PlMmMTIYb6u/F69UmQiIjUXqVSYSoUxbK59bdnBSzL4tXJNAdHQxw7k1hyYKnbZeeWHQPs3z3I\nuj51g5V5yw5AhmEsHjC6JNM0f7iycqQRLmuUEEuQLzauUYLP4+TH37SdfcYAX/vRaSYXtKfMFUp8\n9UenOXwiwgP3bKvaLzKHw4HD38l0bIYOT5Z+HQ0SEZEayuZyhGMp3N4ADrW4vibZfInnT0Q4dCxE\n9CoDS4d7/RwYGeLm6/vx6JwqWeRajgB9H7CY7yG8MGZfeKe48DK90lqQw+FgeLCfYrFINJ5krmLH\n421Mo4RNg0E+9hN7OTg6zT8/e+6ydpVjoRn+/CtHuXPPMG/ft6lqv9i8Pj+FUklHg0REpGZi8TiZ\nXEXn+1wDy7I4PZniewfPcuRU9KoDS/ds6+PAyBCbhwL6MFOWdC0BaNuCf78N+D3gN4GngDngduBP\ngf9ateqkIdxuN+uHB8nmcsQSabC7cbmr15J6uRx2G3ftWceebX188+kzHH1t4ewgePLoNEdfi/O+\nO7dww7beqvyiczqdOJ3zR4P8nqzODRIRkaoolUpMhWPYHF68Pn3AthzFuTJHTkU5eCzMZHR2ye16\nOz0c2D3ErcYAHd7GNXeS1rHsAGSa5tkL/zYM45PAL5mm+diCTf7ZMIyPA18AHqpeidIofp8Pv89H\nJjNDIpPB1qAg1Nnh5mffvpN940keefI08fSl2UHp2SJ/972T7NzUzf13b6W3St1cFp4b1N/TSUdH\n41qGi4hIa0umUiQzBTU6WKZQYn5g6Qsnlh5YarPB7i098wNLN3RV7dxgaQ8rbYKwHpi4wuUJoHfl\n5UgzCgYDBIMBZmZmSaQzWHYXbnf9P73auamb3/jgTfzgxQl+8OLls4NOjCf50y8d4d5bNvDmm9ZX\nZXbQhXODoqks6cwsQ4N92LVWW0RElqlcLhOKxKjg1mDTN1AqV3jldJyDx0KcmcosuV2n33VxYGlX\noP4fysrasNIAdBD4A8Mw/rVpmjMAhmH0An8E/KBaxUlzCQQ6CAQ6GhqEXE47b79tfnbQI0+e4dTE\npT7/pbLF9547x4snozzwpm1ct76rKvfp8frPzw2K0NflJxjUJ3giInJ1F2b7eHwBnDo6saREJs+h\nY2GeMyOXjcFYbNfWXm43+tm5qVuNI2TVVhqAfh14DJg0DOMEYAd2AiHgrVWqTZrUhSA0O5slkZ6h\njAOPp77DRPu7fXz4vl289GqMbz19lsyCX5rRVJ7//Y1j3Hx9P++5YzNBv3vV92e32/H6g8RncszM\nRhgc6G3Y3CQREWlelmURiSXIzVla8raESsXixHiSg6MhTownuXJLA/B5HOzbOcide4a4bksfqVSW\n8hINEESuxYoCkGmarxiGsRP4WWAP8x3g/gz4B9M0s1f9ZlkzOjr8dHT4mc1mSaRmqODAXccgZLPZ\nuOn6fozN3Tz67DgHR0MsHAPw4qkox8cSvHP/Ju68Ybgq9+nx+LAsi/GpKP3dAQIBzRQQEZF5xWKR\n6Ugcu8uPx6NRi4tlskUOm/MtrJMzSw8s3TQY4MDIEHu3zw8sdTh0BE2qa8U/naZppg3DeJD57nCv\nnb9s6WOXsmZ1+P10+P1kczniyQxlq77ts71uJ/ffvY19Owd4+InTTEQudYrJF8s88sQZnj8R4UP3\njdDlW/0fJJvNhtcfJJbOMpvNMzhQnQ50IiLSuuKJJPFUXu2tF7Esi9NT8wNLXzl9lYGlTjs3Xd/P\ngZEh1vfrw0WprRW9GzQMwwZ8ivmlcG7ml7/9F8MwZoGPKQi1pwtd4xoVhDYMBPjYA3s4dCzEdw+N\nX9Y55lx4lk994dnzs4M24nWvPgh5vH5K5TLjk2EG+rrwaW6QiEjbKRaLnBlLM1u0qdHBArlCiRdO\nRjg4GiaSzC253WCPjwMjQ9yyo78qf5tFlmOlr7RfA34e+Djw5+cvexj4LPPnAf3H1ZcmrepCEMrl\ncsRTGeYqdrx1CkJ2u407bhjmhm29fOuZsxw5Fbt4nWXBU0enOXoqxnvv2sLe7X2rPnLjcDhw+IKE\nYjN0eLL0a26QiEjbyMzMkMrkGVw3gLOo81MAzkVmODga4qVTMebKlStu47Db2LO9lwMjQ2wZCurv\nptTdSgPQR4FPmKb5VcMwPgNgmuYXDcMoAn+CApAAPp+PDT4f+XyeeDJNsWTD4/PX5Rdd0O/mX711\nB/uMQR554jTRVP7idZncHP/w2CmeOx7h/nu20t+1+vOWvD4/RR0NEhFpG9FYnNmihd+v5VrFUpmX\nTsU4eCx02TL0xXqCHvbvHmSfMUjAp4Gl0jgrDUDbgBeucPkRoDpnm8ua4fV6WT/spVgsEk+kyc9V\n8Pg66hKErt/Qxa9/8EaeODrF44cnKC34NOrURIr/+eWXeMvN87ODXM7VtdW8cDQoHM0Q7MjT29O9\n2vJFRKTJVCoVpkJRLLsHj6e938SHkzkOjYZ4/kSEfHHpgaXGph4OjAyyY1O3BpZKU1hpADoD3H7+\n/wu9h/MNEUQWc7vdDA/1Uy6XiSVS5PIl3N7aByGnw87b9m3kTbds5P/71jFOjCcvXlcqWzx2eH52\n0P33bGXHxtWHFo+/g2yhSH46wrCGp4qIrBmFQoHpSAKXN9C2s2hK5QqjZxIcHA1xeiq95HYB3/zA\n0v27B+nWwFJpMisNQH8EfNYwjHXMzwB6m2EY/4b5pgi/Xa3iZG1yOBwM9vdSLpeJxpLkiuW6HBEa\n6PHzkffu4sipGN986gzp7KVeHbF0nge/dZwbr+vjvju30LnK2UFOtxvLcjE2GWawrwu/r75zkkRE\npLpS6TSJdPt2eUvOFOYHlh4PM3OVgaXb13dyYGSIka09bRsSpfmtdA7Qg4ZhuIDfBXzAXwAR4HdN\n0/x8FeuTNczhcDA02EepVCIaS5Kfs/DWeC21zWZj7/Y+dm7s5nuHx3nq5enLZge99GoMcyzJO27f\nxB0jQ9jtKw9l8+2yOwknZvHP5hhQgwQRkZZjWRbhSJxCmbbr8laxLE6dS3FwNMTxsQRLdLDG63Zw\n684B9o8MMditD/yk+a20DXbANM2/BP7SMIx+wG6aZri6pUm7cDqdDA/1UygUiCXSFMs2vL7ado3z\nuB28986t3LJjgK89cZrx8MzF6wpzZb7x1PzsoB+/ZxsbB1f3B8/r9TNXLjM+FWaorxuPR0sBRERa\nwYUlb05PB26Po9Hl1M1Mbo7DZphDx8IkMoUlt9s40DE/sPS6PtzO9nl8pPWtdAnctGEY/wT8tWma\n/1LNgqR9eTwe1g8PkM/niSXTdWmfvb6/g48+cAPPHQ/z3UNj5AqXTuKcjM7yuYdfZv/IEO+8fRO+\nVUz1djgcOBxBpiNpgh0uNUgQEWly8USS9GyxbZa8WZbFmenM+YGlccqVKx/ucTns3HR9H/tHhtg4\n0F5HxGTtWOk7uo8DPwc8ahjGBPAF4AumaaoBgqya1+tlw7D3UvvsGgchu83G/t1DjGzt5TsHz/L8\niejF6yy4+Mfgvju2cNP1q5sd5PF3kC3OMTsZYt1gH06nhr6JiDQTy7KYDkUp42qLJW/5YokXTkY5\nNBoilFh6YOlAt/f8wNKBVX0gKNIMVnoO0EPAQ4ZhDAH/1/n/ftcwjCeBB03TfLCKNUqbutA++2IQ\nKttrujQu4HPxwXuvZ58xyNeeOE14wR+Cmdwc//gvp3jODHP/PdtWtcbZ6XJhOZ2cm47R0+mjq7M9\nPl0UEWl2lUqFiekIdpcfp2NtL+majM7y1NFpjpyKUiwtPbB0ZOv8wNJt6zSwVNaOVUV40zRDwJ8Y\nhvFnwC8DnwL+ClAAkqq5EITmzxFK1TwIbVvXySc+sJcnz88OWjjJ+rXJNJ/58ku86ab1/NgtG1Y8\nO2i+QUKQdLZAZjbE8ICOBomINFKpVOLcdBSPb+2+0Z8rVXjxVJxnj4c5Pbl0C+vugJv9u4fYZwwQ\nXGVXVJFmtKp3XIZh3MP8UrifOn9bX0LhR2pk/hyhwboEIafDzltu3sCN1/Xx9SfPcHzs0uygcsXi\n+y9McORUlPvv3oqxuWfF9+NyewAP56bjBP0u+npXflsiIrIy+Xye6WhqzZ7vE03lODQa5vCJCLlC\n6Yrb2IAdm7q5Y2SInZu6V9UFVaTZrbQL3KeAnwE2AT8Afgv4smmaSy8eFamSy4NQbbvG9QS9/Py7\nDI6dTfD1J8+Qmi1evC6RKfCF75jcsK2X9925ha5VDHrz+gPk5uYYm5hmeKAXt1ufuInI/8/enUfH\ncV8Hvv/W0tV7N9AAugGQAAluTUIiKVFctHqV5V1SvCWTmZyMJ/FM4nHGSea8d+bMvLzMmTPnzXtz\nJrGzOHH22JNZYsmLJEd2ZFtetHKRKG4giztBEktjaTS60XtVvT8aAAGKENGNBojlfs7BkdBVXfUr\nAujuW/f3u1cshUxmguGxCTy+4J0eSl1Zts3pK2Mc6hnk/PXUnPv5PTp7t0fZtz1KJORZwhEKcefU\nmgH6DJVMz9dM07xSx/EIMW9TVeOmM0KLVCxBUSpzoDevC/PiG9d45UQ/M4vjnLo0yrlrYzx6XwcP\n3N2KVuNdM93lApeLvsQYIb8hleKEEGKRjaVSjGVKq6rYQSpT4PCZSsPSmQ2/b9bVFmT/jhh3dUXQ\nNWlYKtaWWosgbK73QISo1VRGaKp8dtlWcS9CIOR2aXz4/g3cu62FZ166xJXB9PS2Ysnm+devcPTc\nEHA4RoQAACAASURBVE883EVnrPY7iR5fYLpSXFT6BgkhxKIYGh4lV3IWve/cUrAdhwvXJxuWXkky\nRwVr3C6N++ItPHpgA35DxbLm2FGIVW7eAVA8Hn8R+IRpmmOT/z8n0zTft+CRCVGlqfLZE9kso2Np\nUI3JNTb11Rrx8bnHu3nTHOL7B3vJzphP3T+S5avPnGLf9igf3N+Jz1NbknUqGzQwNI7Xo9HS1Lhq\nF+UKIcRSsiyL/sQwqB4Mt+tOD2dBsvkSb5hDHDqdYGQ8P+d+7U0+DnTH2LWlGZ9HJxz2kUpll3Ck\nQiwv1Xw6uwJMdYnspdIiRYhlx+/z4ff5SKfTjI6nUXUPmlbfNTWqorB3e5TujY18/2AvR8yhWdsP\nn0lw6nKld9C9W5trDl7cPj8ly6K3L0FTOEAg4K/H8IUQYk3K5fMMDo+t6EpvjuNwNZHhYM8gJy6O\nUJ4ji6NrCrs2N3OgO8r6lsCKvV4hFsO8AyDTND8749svmKaZWYTxCFE3wWCQYDDIWCpFJpfBWkCR\ngrn4PC4+8e7N3BeP8p2XLs5qIpfNl3n6Jxc4YiZ44uEuYo21TbPQNA3NG2QknWMimyfaEpE3MiGE\nqNJYKkUqXVyxld4KRYu3zg9z6PQg/SNzZ2+awx7274ixZ1tLzbMQhFjtav3LGIjH498E/tY0zR/X\nc0BC1FtDOExTRMGyi4xkM6guL6pa3wWfG1qDfOGTO3n1xAA/euParKZyl/vT/NHTJ3hkdxvv3bMO\nQ6+tuZ7b7aVsWfT2DdImleKEEGJebNtmIDGChY7bt/Ky6AOjWQ72DPLWuWEKJeuW+6iKQvfGRvZ3\nx9jcHpKbZELcRq0B0Oep9P95IR6PXwe+RqUi3MW6jUyIOlIUhZbmCKriIjE0SiZbwvD46xoIaarK\nI7vb2bm5ie++epmey8npbbbj8NO3+jh2fpiPP9TFjg219fupZINC9CXGCAcMGhukUpwQQswlm8uR\nGEnh9gZxraCgoFS2OXVplIM9g7MK7tws7DfYtyPK3niUkF9uigkxX7VWgfs68PV4PB4DfnHy6/+K\nx+OvAH9jmqY0QxXLkqqqNDdFiNg2o8mxRQmEGgJu/tljcc5cSfLcq5dJpgvT28YyRf77P5rs2NDI\nxx/aSEON0/I8vgAT+SIT/YO0RZvRtNqySkIIsVqNpVKkMqUVNeVtZDzP4dODHDGHyOZv3bAUYOv6\nMAe6Y8Q7G2tuvSDEWragyaGmaQ4CX4rH438MfA74L8BfUukRJMSytRSB0PYNjWxaF+Inb17npeP9\nWDPqkp6+kuT89RTv37Oeh3a1otVwXt0wcBwXV/uHaQr7CAZXVxM/IYSoheM4DAwOU1Z03CugxLVl\nO5i9SQ72DHLu2twNS31unfviLezvjtEkDUuFWJAFBUDxePxhKlPhPj15rKeQ4EesIDMDoeHRMbLZ\nMm6vv27zpw1d47H9ndyztYVnXr7Ipf4bUxlKZZvvH+qt9A56pIuNrdXfpVQUBY8vSHIiz/hEglhz\nBF2XRa9CiLWpXC7TNziMZvhxLfPM+PhEkSNmgsOnE6QminPu1xkLcKA7xt1dTbh0aVgqRD3U9Ekp\nHo//F+AXgA7gp8BvAU+bppl7xycKsUypqkq0OYJlWQwNJ8mXqWtzvGijl1/9WDdvnRvm+devMDFj\nasNgMsefP9vDfdta+ND9nfg91felMIzK3cBrA6MEfTrRlqa6jV0IIVaC1Pg4Y+k8bu/ynfLmOA4X\n+sY52DPI6ctJbOfWJawNl8q9W1vYvyNKW9PKK9wgxHJX663iz1DJ9HzNNM0rdRyPEHeUpmm0xpop\nFAoMJ1OUbRW3pz6BkKIo3LuthXhnIy8c7uXw6cSsZlpvnB2i50qSDx3o5L54C2oNWSiPL0CuXObK\n9UFcLgCZGy6EWN0sy2JwaARLceH2Bu70cG4pmy/z5tkhDp0eZDg1d8PS1kilYek9W5pxG8s7gyXE\nSlZrAHQCeEqCH7Faud1u1rVGyeZyjI6lcVQXLld9+gj5PDpPPrKJPdtaeOblS7P6OeQKZb79s4u8\nYSZ48pFNtEaqD750XUfTggyl8kyk0jSGg7jd9e+BJIQQd1o6k2FkbAK3N7Dsqrw5jsO1oQkO9gxy\n/MLwOzYsvburiQPdMTpj0rBUiKVQawD0HmDuLlxCrBI+rxef10s6nSGZTqOqbvQ69d/pjAX5/M/t\n5PVTA/zgyFWKpRu9g3oHM/zxN4/z4M423n/fetyu6u8Eut0e8m6b/qEUIb9BpFFKZgshVgfHcUgM\njZIvO3h8y6sATLFkcezCCAd7Bukbnphzv0jIzYEdMfbEW2qa+iyEqF2tAdDfAv81Ho//J+C8aZqF\n2+wvxIoWDAYIBgOMp8dJjqfRdA+6a+FvWJqq8NDONu7e1MQ/vHaZkxdHp7fZDrx8vJ8TF0b46IMb\nuWtjY013Bj2+ANlCkayUzBZCrAKFQoHB4TE0w4fbs3xezwZHs7x2cpCj54bIF2/dsFRRYMeGRg50\nx9i8LlzTVGchxMLVGgB9FNgMfAogHo/P2mia5vJ5RRKijkLBEKFgiLFUirF0GpfbV5eAIuw3+MVH\nt3H26hjPvnKJ0fEb9xRSE0X+5w/OEu9o4OMPbSRSQ/lTKZkthFgNKq+9hWWT9SlbNicuJjliDnHu\n6tic+4V8LvZuj7Jve5Rwjf3fhBD1U2sA9J/rOgohVpiGcJhwKMTwSJKJbK5upbO3dTTwxU/t5qdv\nXeenb/XN6h1kXh3jwlPHeN+e9Ty8qw1dq64c6syS2emJBFEpmS2EWCFs22YgMYKNC4/vzhc6SKbz\nHDqd4Ig5xESuNOd+W9aF2d8dY8eGhpr6vQkhFkdNn35M0/xavQcixEqjKAotzREidS6d7dJVHt3b\nwT1bmnnmlUtcuD4+va1sObxw+CpHzw3x+MNdbG4PV318w/BUFucOjMraICHEsjcxkWV4LI3hCaDf\nwSljtu1w9uoYB3sGOXt1jFuXNACvW+O+bVH2d0dpDnuXdIxCiPmptQ/Q//1O203T/E+1DUeIlefm\n0tmWo2G4F/6m19zg5V98ZAfHL4zw/GtXSM+4yzg0luevvnuae7Y08+H7Own6qivMUMkGBcgWS0z0\nDdIWbZJskBBiWamUtx6l7Ki4vXduyls6W+QNs1LCeizzzg1L9++IsXOTNCwVYrmr9RPPZ29xnBhQ\nAl5Z0IiEWKGmSmdPZLOMjqVBNXAZC5vrrSgKu7c0E+9s4IXDVzl4anDWXce3zg9zpjfJB/d3sm9H\ntOoFtbrLhaPrXBsYoTHkJRxavg0EhRBrR3JsjNFUHsPjx7gDWR/HcbjUX2lYeurSOzQs1VXu2dbM\nBw5sJOTRsOYodS2EWF5qnQLXdfNj8Xg8BPwV8OpCByXESub3+fD7fKTTaUbH02gu74KzKx5D5/GH\nuiq9g166xPUZpVXzRYtnXr403Tuovbm6ruFTa4NS2TzZ7BCxaBOqzFUXQtwBuXyeVO84mYJyR5qa\n5gpljp4b4mBPgqGx3Jz7RRu9HOiOce/WZvxeF+Gwj1RKuoMIsVLUbc6LaZrj8Xj8d4EXgC/V67hC\nrFTBYJBAIMBYKkUqU5+KcetbAvz6k3dz8PQgLxy6SqF0o9TqtaEJvvLtE9x/VysfOtBBtauDDMOD\nbdtc7R+iuSGI37/w9UxCCDEftm2TGB6l7ChEY83oxeySZlOuDWUqDUvPj1Cy7Fvuo6kKd3VFONAd\nY2NrUBqWCnGHOY6DVczV9MGq3pP+w4CsqBZikqIoNDY00BB2GBlNMpHLYXgWVjFOVRUeuKuVu7oi\nPP/aFY5fGJne5jjw2skBTl4c4ec/EGdLW3V3UFW1Mtd+KJVlIpenpam23kNCCDEfjuOQHEuRzhZx\nuX01NX2uVbFscfz8CAdPD3J9aO6GpY1BN/t3RLkvHiXglYalQiw2x3Eol8vYVhnbtsGxUVUFVVXQ\nFAVFUdBUBUNXOXfwqcvwH6s+Rz2LIISAnwderOWYQqxmiqLQ3BSh0bIYGkmSLzp4fNVNVbtZyGfw\nC+/fyt54lGdfucRwKj+9LZ0t8ZfPnGRbR5iPP9hFU7i63kEej4+SZXG1L0FLUxivp/reQ0II8U7G\n0+OMjedQXd4lne6WGMtxqGeQN8++c8PSeEcjB7qjbO1okIalQtSBbdtY5TKWXa50e2cysFEmv6aC\nHFUh4HNhGB40TZtzGYGuq4xcO5WqZSz1KoIAUAR+BPz7Go8pxKqnaRqt0fpWjNuyPsy/+dQufnas\nj58cvU55xrSRs1dT/MHTx3j3Pet49z3tVfUO0jQNzRtkcCSDz52VbJAQoi4ymQlGxzMoqoGxRNXd\nLNum53KSgz2DXOwbn3O/gLfSsHT/jigN0rBUiHkpl8vYtoVtlXEcG4XKlNGpoGYqY+PWVVxeF4ar\nsiSgHo3ka7XgIgjxeLwFeBcwYJqmVIATYh6mK8ZNZBlJpVFVN7pRXSnrmXRN5X171rN7SzPPvXKJ\ns1dv3BApWw4/euMab50f5omHutiyvrrVQR5vJRvU25egJRLC55W+FkKI6uXyeUaS49iKjuFZmsBn\nLFPg8OkER84kZrUSuNmm9hAHumN0b2yUhqVCMHsamuM4OLb1tmloqloJdHxeHV1z43IF0HV9Rdws\nrSoAisfjvwN8EbjfNM3z8Xj8AeB7QHBy+4vA46Zpzl06RQgxze/34ff7pgsl6MbCCiU0hTz88oe2\n03MlyXdfvUIqU5jeNpLK89fPn2bX5iY+8sAGQlX0DprKBiWSE/gmcpINEkLMm+M4DI0kyRZtPJ7F\nn+pmOw7nr6U42DPImd4kc1SwxmNo7NnWwv7uGNEGubEj1gbLsrCsSsYG2wac6WloiktDsRQ0J4+q\nMK9paCvVvK8mHo//S+A/UKnwlph8+G+ALPAgkAK+Cfw74HfrO0whVreGcJhwKMTIaJJMNofbW3uh\nBEVR2LW5ib13tfHNH53llRP9sz4AHL8wgtk7xmP7OjjQHUNV538eWRskhKhGNpdjaHQc3fDh8Szu\ndJdMrsQbZoJDpxMk04U591vf4udAd4ydm5sw9Ds3BUeIenEcZzqwcWwbx7FurKmB6cyNqih4DA3D\n5UbXdXRdn9X2QtdVGhv9JN0TlMu3roa4WlQTzv0q8G9N0/wKQDwe3wtsA/6DaZo9k4/9Z+D3kABI\niKrNKpQwnCRfWlihBK9b5+MPbeSeLc088/IlriYy09sKJYvnXr3Mm2eHeOKRLta3zP+urKwNEkLc\nTrlcZnhkjHwZPIu4zsdxHK4MpjnYM8jJi6NY9q3TPS5NZfeWJvZ3x6p6vRPiTpouGmCVK2Veb1U0\nQFHQNAXDq+Ny+dB1HU3T5H35NqoJgHZQ6fEz5X2AAzw/47FTwIY6jEuINUvTNFpjMwoloGMYtWda\n2pv9/Ksn7uLw6QT/eKh3VtWj68MT/Om3T3KgO8YH9nXgdc//JUHWBgkhbjYd+JRs3F4/HtfifAjL\nF8scPTfMoZ5BBpNzz7pvafBMNixtqer1TYjFtBKLBqw21bwaKFQCninvAkZN0zw247EQlSlxQogF\nmiqUkMlMMJJKo7m8Nc/BVRVleoHv9w/2cvTc8PQ2B3i9Z5CTl0b5yP0b2L2lad53jmauDfKms7Q0\nN85Kpwsh1gZrusT/4gY+fcMTHOwZ5Nj5YYpzTNFRFYW7uho50B2jqy0kd8LFkiqXy5TLRTQcPC6L\ncj6PbTuzSjx7PRoufWUVDVhtqvk0dQJ4CDgfj8cbgPcC37lpn09P7ieEqJNAwD+rUILh8dccZAR9\nBp9+7xbui0d55uVLDI3duHOayZX4xo/Pc8RM8MTDXbRUsSjY4/Fh2TZX+4doCgcIBBbW40gIsTLY\nts3w6BjZfLkS+Pjq/0GuVLY5cXGEgz2Ds6by3qwhYLBve4y921sIVlHkRYhqTFVHs6wS2HalEpqi\noGnqdEU0jzuE1+smEgmQTK7+9TQrUTUB0B8DX43H4/dQKXrgBv4AIB6PtwP/FPg/gF+p9yCFWOsU\nRaGxoYFwqPJhYyJbwuMN1HzXaFN7iN/45E5ePt7Pj9+8Tsm68eJ8sW+cP3z6OO/a3c577l2HS59f\nsKWqKm5vkNF0jvFMllhLRNL1QqxCjuOQyWTITOQplB0Mjw+Pr/4FUYZTOQ71JHjj7BC5QvmW+yjA\n1o4GDnTHiHc0VFXURYgpjuPgOA62bePYNrZj4zg22A6OY6NrCpqqoqoKLk0h4DNwu724XK4534cl\nq7O8zTsAMk3zf8TjcTfw64AN/LxpmocmN/974HPA/2ea5t/Vf5hCCKgEGdHmyE0LjH01HUvXVN5z\n7zp2bW7iu69e5kzv2PQ2y3b48dHrHDs/zOMPd7Gto2HexzXcXhzH4Wr/CCG/QWNDWN4IhFgFLMti\neGSMXLGMprtxGX48dU60WJbNUTPBjw73cv7a3A3e/R6dvduj7NseJRKSapRitvJk4YC5KqIpk0UE\nUEBVKsGKqlWyOKrqQtc0VFVFm/yvvIetPlUtKDBN86+Bv77Fpv8C/K5pmiN1GZUQ4h3puj6rUELZ\n0XC7aytCEAl5+KUPxjl9Jclzr1wmNVGc3jaaLvC33zvD3V0RPvrgRsL++X3aURQFjy9AtlQm05eg\nWYokCLFi3Qh8rEWb5paaKHL49CBHzATjE3M3LN3YFuTAjhh3dUXQNVlvuBZNT0Erl8CxURSmm3NO\nrbHxeXUMqYgm3kFdSqKYpnm9HseZy2Tm6U+AT1ApsvB7pmn+/m2es5HKeqSPmqb5s8UcnxB3ysxC\nCaOpNKruQXe5qj6Ooih0b4yweV2YF9+4xisn+plZTfbkpVHOXhvj0fs6eODuVrR5TjPRdR30IEPJ\nCYxUhqhMixNixXhbYYM6Bz6243Dh+mTD0itJ5qhgjdulce+2Zg7siBGL1JbxFivHdKPOyQppqqJg\nuDScEihWDkOBgM/AMDy4XC4pvCNqslJqQv43YA/wHmAj8PV4PH7ZNM1vvcNz/hSQV0qxJgQCfgIB\nP2OpFGPpdM39g9wujQ/fv4F7t7XwzEuXuDKYnt5WLNk8//oVjp4b4omHu+iMzb+3h9vjm5wWN0xD\n0ENDOFzT+IQQi69cLjM8Wsn4eLyBugc+2XyJN8whDp1OMDKen3O/9iYfB7pj7NrSjNslN05Wqqle\nNrZtTa61sabLPk9NRZsq+6yqTDfqnFkhbbpBpxQUEHWy7AOgeDzuo1JY4YOTJbePxePx/wp8Abhl\nABSPx/8pIJ3OxJrTEA4TDoVIjafIZdM4Tm13xlojPj73eDdvmkN872DvrAXI/SNZ/uyZU+zdHuWD\n+zvxeeb3MlKZFhckky+RnhikORLG65G5+0IsB7ZtM55OM5ErUiqD2+vDW8fAx3EcriYyHOwZ5MTF\nEcrWrdM9uqawr7uVPVubaG/yy9SlZci2bSzLwrGtStGAyYBmZoNORakEM6pyo5eNS/dO97KRn6u4\n05Z9AATspjLO12Y89jKVwgtvE4/Hm4D/F3iMSmNWIdYURVFobooQCnkwz10jn7NqygipisLe7VF2\nTPYOesMcmt7mAIfPJOi5PFrJGG1tnvcbmu5ygcvF4GgGj5ahpblRpsUJcQdUqrlNkJnIUbQcNJcH\n3fCj1bGwQaFk8da5YQ6dHqR/ZO42gU1hDwd2xNi3o4W2WJhUKos1R5AkFsfMqWc4DopyozmnMlko\nYKo5p+7WcbncssZGrFgrIQBqA4ZN05xZA3MQ8MTj8aZbFF74feBvTdM8HY/Hl2yQQiw3mqbRFmtm\nYiJXKZRgq7g91c8K9XtcfPLdm7kv3sJ3XrpEYkbX9Yl8mad/coE3zASPP9xFrHH+x/fItDghlly5\nXCadyZDPlylaNppmoBt+3HU+z8BoloM9g7x1bphCybrlPqoCOzZGONAdY3N7pWGppskH6XpxHAfL\nsrDtSmCjOA7g4NI1Sm4bq5jHsZ3pwGZq6plhBCWoEaveSgiAfEDhpsemvp/1mh2Pxx+l0qPocws5\nobZGKstMXedauN61dK0w+3r9fi9+v5dsLsfI6DiOauAyqr/Fu3ldmN/89C5ePt7PD45cozRjHval\n/jR/9M0TvGt3G++/bz3GvOfrK+jBENlSidzgELGWRowaxraWfr5r6VpheV7nchzTrWiaim3bZCYy\njKfzlMoWNgouw4Puddf9A0CpbHPy4givnxrk8kB6zv1CfoMD3TH274gSuqmy5Ozf75Wx1uNOjdmy\nLEqlItg2msqsdTSVamgqulfDpRvouo6u65OlnVVCIS/j4zksayX+G68MMubFt5BxroQAKA9vuzk1\n9f10Pj0ej3uArwK/bppmkQUIhdZWud61dL1r6Vph9vU2NvpZ197M+Hia4dE0mrtSIrRaj79nKw/f\n28Hf//Asx87dmBZn2w4/OdrH8Quj/MJjcXZtaa762OmJDAHFItbSVNPdx7X0811L17rcLOd/e8dx\nyOfzpNITFCYsEkkb3eWhobm2wijzMZTM8tJbfbx6vI9Mbu4S1t1dEd5173p2bmlCu03lrkBg5a0P\nrPeYS6USVrmEbVtok6WeVVVFmyz17Ha78XkjGIaxZl4vZcxLYyWOuVqK4yzvObbxePwB4KeAxzRN\ne/Kx9wDfNU0zMGO/dwE/BiaoNIcG8AM54GumaX5+nqd0VtJdkYVYiXeBarWWrhVuf72O45AcSzGe\nKeDy+GouI9pzeZRnX75MMn1zkhbu6mrk4w910RisbnKNZVlYxRwNIS/hUGhez1lLP9+1dK0wfb3L\naS7OsnyPmMhmGUtNUCzbqLoLl8tA1zUCAQ+ZTL7u47VshzNXkrx+aoCzV+duWOrz6OzbHuVAd4ym\n8O0DBE1TF23Mi6XWMTuOQ6lUwrEtHMuaDHAUdK3y5XG7cbuN6cxNPce70l5DZMxLY6WNeSHvDysh\nA/QWUALuB16dfOwR4PBN+x0Ett702HkqFeR+WM0JLcteU2UW19L1rqVrhXe+3lAwRMBvMzwyxkSh\njMdXfeHEeEcjX/xUiB8fvc5Lx/qxZ9xQOXUpybmrKd5/33oe3Nl62zu+N6hohp/R8QLJ1ADRpoZ5\nT4tbSz/ftXSty81y+bcvl8tkc1lSmTw2lWbIU7NPbZvpDzCWZdetoMD4RJEjZoLDpxOzmibfrDMW\n4EB3jLu7mnDp6uQ45jOG+o958d16zJZlVTI4lgXY0wUFprM4moLPZ2C4vLhcrjmzOLZdqbxWb8vl\n97gaMualsRLHXK1lHwCZppmLx+NfB74aj8f/BbAe+LfALwPE4/EYkDJNMw9cnPncySIIfaZpDi/t\nqIVYGVRVJdoSoVgsMjw6RqmGQgmGS+OD+zu5Z0szz7xyicv9M3oHlW2+d7CXN88O8eQjm9jQOv/e\nQS7DDbjpS4wR9OlEGhtlUa5Ys4rFIuPpDIWiheU42LaDg4ruMnC5F7frg+M4XOgb52DPIKcvJ2fd\n6JjJcKncu7WF/TuitDUt3pS75cCyLMrlEo5to6kOXsOmXJgqKlC5M+0xNNwBL4ZhSKVLIZaZZR8A\nTfpt4E+AF4EU8DumaT4zua0f+OfA12/xvJVy+0iIO8owDNpbo5VCCclxUI3JAGT+YhEfn/tYN0fP\nDfP861fI5m8UbhxM5vizZ0+xN97Chw504vO45n1cjy9Arlzmal+C5kgIn3f1z00Wa5tt2+TzeXL5\nPKWyQ7FUxqZyc0JzKyzVR+lcocybZ4c42DPIcGruhqWtkUrD0nu2NOM2Vv4Hfdu2KU9mbhzbQtMq\nmZupxp1TFdPcgUrmxuMxpEmnECvMigiATNPMAZ+d/Lp525zzakzTXPmvxEIsIZ/Xi8/rJZ1OkxxP\no7q8VRVKUBSFPdta2N7ZyD8e6uXwmcSs7UfMIXouJ/nQgU72xFtQ59s7SNdBDzKUnMCVyhBtbqyp\ngIMQy43jOGRzObLZPGXLpmTZ2DaT63jcKLqCsYS/6o7jcG1ogoM9gxy/MPyODUvv7mriQHeMzlhg\nxWVnHcehXCphWWVwLDRNRZ+snOZ2qbh9bgzDkNcZIVYp+csWQrxNMBgkEAgwmhwjnc3h9lb3Acfn\n0fm5d23ivngLz7x8aVYDxGyhzLd+dpE3zCGeeKSL1sj8p9y5J3sHXRsYlWlxYkWyLItCocBENk+x\nbFG2HFTNhcvwoKhgzD85WlfFksWxCyMc7Bmkb3hizv0iITcHdsTYE2/BX0Um904pFYtvC3JUVcGl\nqQSDBh53QIIcIdYg+asXQtySoig0RRppCFsMDSfJl8HjrW59UGcsyOd/bievnRzgh29cpVi6MT3k\nymCaP/7mcR7a2cb77luPe569gxRFweMLkLcsevsSNIa8RBobqhqXEEuhXC6Ty+XJ5YvT2R3HuZHd\n0Yylm842l8FklkM9CY6eGyJfvHXDUkWBHRsaKw1L14XnnbldKo7jUC6XscolcGxUFXRVRddVGvwG\nXq8EOUKI2eQVQQjxjjRNozXWTKFQYGg0ha3oGMb8+11oqsLDu9rYuSnCP7x2hZOXRqe32Q68dLyf\n4xdG+NiDG+neOP+MjqZpaN4gqYkCE9lBPJ72qq9NiHoplUrk8wVyhSLl8lSwo6C5DFwuD6r29oZ2\nd0rZsjl1aZSDpwdnFS25WcjnYu/2KPu2RwkH7vzoLcuiXCpi22U0VUFXVVRVwdAVAj4Dw/Dgcrnq\nWjJaCLE6SQAkhJgXt9vN+rYomcwEI6k0WpXrg8IBN7/4gW2YvUmee+UyozN6B6UmivyPH5wl3tnA\nxx/cSCQ0/wDLZbjRNA/9Q+PkszkiDWGpuCQWzXg6w/BoknzewrYdLMeplJtWVDR9Mtgxlk+wM1My\nnefQ6QRHzCEm3qFh6ZZ1YfZ3x9ixoaGK8vX1UyqVyGezlQagk00/NbVSVc0bCtTc+FMIIaZIACSE\nqEog4Mfv95EcS5HOZnC5q2ukGu9sZFN7mJ8cvc7PjvVh2TcWWZu9Y1y8fpz37lnHw7va0LX5t8eF\nugAAIABJREFUH9ft9ZErOFwbGCHglfVBYnEMDmco2gbooFL5Ws4rYWzb4fTlJK+dHODs1bE5S6N6\n3Rr3bYuyvztKc3hpKy0WiwXscglNU9DdGo1+DwEjguPI368QYnFIACSEqJqiKEQaG2gI2wyPjpHN\nlnF7/fMOOFy6ygf2dXDP1maeefkSF/vGp7eVLJsXDl/l6Llhnni4i03toarG5fZWymb39iVobgji\n91e3bkmId6JqGorlsNy7LKSzRd48O8ThM0OMjs9dwrojWmlYunPTjYali8lxHAqFHIpj49Iq63Qi\nQTc+bxh1ct1OOCwlpYUQi0sCICFEzVRVJdocoVwukxhOUrAVPFU0Um1p8PIrH93BsQsjPP/aFTIz\npuUMjeX4y+/2cO/WZj58/wYC3vnfZ9d1HV0PMjKeI5WekLLZYk1wHIdL/ZWGpT2Xk7OyqzO5dJV7\ntjRzoDtGe/PiNyy1LItSIYdLr/TPaYwE8HjmP81VCCHqTT4RCCEWTNd12ltbyOXzjCTHcdRKlav5\nUBSFe7Y0E+9o4IXDVznUMzjr3vrRc8Oc6U3y2L5O9u2IVlWBynB7pWy2WPVyhTJHzw1xsCfB0Fhu\nzv2ijV4OdMe4d2sznkVsLlTpsVOkXC7i0hR8HoPWSJOszRNCLBsSAAkh6sbr8bC+zUM6nWY0NY5m\n+OadefG6dZ54uIv7trXwnZcvzepFkitYPPPyJd48O8QTD3dVddd6qmy2TIsTq831oQwHTyc4dn6Y\n0hzTxTRVYeemCPt2xNjYGlyUGwAzp7UZuoquqYRDHjyesFRkE0IsSxIACSHqbiGNVNdHA3z+ybs5\n2DPIC4evUijd6E1yNZHhK98+wYN3tfLo3g7cxvzvKE9NixtOZUmlJ4i1ROSOtFhximWL4+dHOHh6\nkOtDczcsbQy6OdAd4337N+CUy1hWfdcsOY5DIZ/DpTl4DI2m5hCGYdT1HEIIsVgkABJCLIpZjVRH\nkhSKDm7f/DI3qqrwwN2t3LUpwvOvXeH4hZHpbY4Dr5wc4MTFET764Ebu7ooA87+r7fb4cByHq/0j\nhPwGjQ1hmRYnlr3EWI5DPYO8efadG5bGOxo50B1l6/oGXC6VkN8glSrXbRylUgm7XMBr6KyLhnG5\nlnMNPCGEuDUJgIQQi0rTNFqjzRSLRYZHxyjZKu55FkoI+Qx+4f1buS/ewrMvX2ZkRjWr8WyJ//XD\nc2zrCPPkI5sIh+c/rW1qWly2VCbTl6CpMYjfJ9PixPJi2TY9l5Mc7BmcVSnxZgFvpWHp/h1RGhah\nYanjOBRyWVw6hP1ugoEWuWkghFjRJAASQiwJwzBob42SzeUYHh1HraKR6tb1DfybT+3iZ8f6+Olb\n1ynPmM5z9mqK3//7t/jwg13cv6MFpYpskK7roAcZHssyPj5BVKbFiWVgLFPg8OkER84kSL9Dw9JN\n7SEOdMfo3ti4KA1LS6USVimPz+1iXaxBsj1CiFVDAiAhxJLyeb10tHsYTSZJZ/N4fIF5Pc+lq7z/\nvvXs3tLEc69c5ty11PS2suXw3EsXee14H48/3MWWdeGqxjQ1Le7awAhBn0yLE0vPdhzOX0txsGeQ\nM71JnDmW7HgMjT3bWtjfHSPaUP+GpTPX9lSyPVH5WxBCrDoSAAkhllxlfVCEYKDI4HASRXWjz3MB\ndXPYyz//8HZOXBzlH167TDp74w75cCrPX//DaXZtbuKjD2wg6Jv/ouypJqrZUpl0X4JIyEcwGKz2\n0oSoSiZX4g0zwaHTCZLpwpz7rW/xVxqWbm7C0OufpZxa2+N2qbS3SEEDIcTqJgGQEOKOMQyDjvYY\nY6kUY+n0vKvFKYrCrs1NbOsI84Mj13j91MCsO+bHL4xg9o7x2P4ODuyIoarVTYvT9SDJiTypTIKW\nSBi3u/7rKsTa5TgOVwbTHOwZ5OTF0bkblmoqu7c0sb87xvqW+WVKq1UqFnCsIqGAh3BI1vYIIdYG\nCYCEEHdcQzhMMBBgcGiEEjqGMb8u8R5D5+MPbmTf9haefeUKl/tvLBQvlCyee+XydO+gaj9ATo2h\nfziN15WhpblRepqIBckXyxw9N8yhnkEGk3M3LG1p8Ew2LG3B616ct+lSqRL4NAZ9BIONi3IOIYRY\nriQAEkIsC5qm0d4aJZ1OM5KafzYIYF1LgP/zl/byg9cv8b3Xe2eVCb4+NMGffvskB7pjPLa/A49R\n3cuex+vDsm16+4ZoCsu0OFG9vuEJDvYMcuz8MMU5GpaqisJdXY0c6I7R1RZatExMpaJbhkjYSygY\nW5RzCCHEcicBkBBiWQkGg/h8PhJDoxTR5p0NUlWF++9qZXtnI997vZe3zg9Pb3OA13sGOXVplI88\nsIFdm5uq+oCpqioeX5CxbEGmxYl5KZVtTlwc4WDPIFcTmTn3awgY7NseY+/2lqrWrNWiXCyCU6Cj\nrVmqHQoh1jQJgIQQy46mabS1tkxngwyPf97Tz4I+g8+8bwv3bW/h2ZcvMTR2o3dQOlfi7188zxEz\nwRMPddFcZRUtl8sNuOkfTuPR07Q0N8oHSTHLcCrHoZ4Eb5wdIle4dQNSBdja0cCB7hjxjoaq1qjV\nwrIsCrks4YCbhrBkfYQQQgIgIcSyFQwG8fv9JIZHyRfBM88GqgCb28P8xid38dKxfn589Nqs3kEX\nro/zB08f5933tPPue9bh0qtb2+Px3iib7XPrNEUaZH3QGmbZDqevJDnUM8j566k59/N7dPZuj7Jv\ne5RIaH6ZzYWwbZt8No1HLxNta5bfUSGEmCQBkBBiWVNVldZoM9lcjqHRcXTDN++si66pvHfPOnZv\naeLZVy5z9urY9DbLdnjxzeu8dX6YJx7uYuv6hqrGNVU2u2hZ9PYNEfK7pX/QGpOaKHL49CBHziQY\nz87dsHRja5AD3THu6oqga0sThOSzGUIBF10d60mlcpTnWHskhBBrkQRAQogVwef10tnuYWQ0SSab\nm3cDVYBIyMMvfyjOqUujfPe1K4xPFKe3jY4X+Jvnz7BzU4SPPrCRkL+6dRiapqH5gpX+QdcHiYT9\nUihhFbMdh7NXx3jt5ABnriSZo4I1bpfGvVub2d8dozUy/8zlQpWLRRy7QFtLA36/V7I+QghxCxIA\nCSFWDEVRaG6KECwUSIyMVdVAVVEU7t7UxNb1DfzojWu8erJ/1ofXExdHOXs1xaN713P/Xa1oVa7L\nqPQPCkn/oFXu//naUYZT+Tm3tzf5ONAdY9eWZtyupV0fls9maAjKOh8hhLgdCYCEECuO2+2ebqCa\nymTw+uefDXIbGh95YAP3bmvmmZcv0Tt4o0JXoWTxD69d4ejZIZ54pIuOaPWZnJn9gwxtnOZIGGOe\nQZpY/m4V/OhapTHvgcmGpUs9DdK2bUr5DO3RiPyuCSHEPEgAJIRYsRrCYQL+MsPJMQqF6u62tzX5\n+ZeP38Ub5hDfP9g7q2JX30iWr37nFPt2RPng/s6amlF6vJVpT32JFB6XQlMkjMvlqvo4YvlqDnvY\nvyPGnm0t+Dx35u20XCyiUaJzXUzWnwkhxDxJACSEWNF0XWd9WxRNszk/mkA3/PP+IKgqCvu2R9mx\noZF/PNjLG2eHprc5wKHTCU5dTvKRA53cs7W5pg+YHp8fx3G4PjiGoUNTY0imxq1gqgLdXRH274ix\nuX3xGpbejmVZlApZQn43kcaWOzIGIYRYqSQAEkKsCqFQkA3r4HrfEAVbwV1FyeyA18Un37OZPfEW\nnnn5EolkbnrbRK7EUz+5wBFziCce7iLaWF3vIKisP/L4/MDU1LgUTY2yRmgl+o+/she3y4VlzVH9\nYJGVy2XKxRxBn0H7uqhkfYQQogZSHkYIsWqoqkpbawtNIS+F7DiWZVX1/K62EL/xyZ18aH/n23oD\nXeof54++eZx/PNRLsVzdcWfyeH2oRoCBoXEGEyPYtpQnXkmqrRJYL5Zlkc+m8Rs2G9ZFaYo0SvAj\nhBA1kgBICLHqBAJ+OtfFcCkl8tmJqp6rqSrvuqed3/z0bnZsaJy1zbIdfvpWH3/w1HHO9CYXNEa3\nz4+luuntGyI5Nnb7J4g1yXEc8tkMbrXEhnVRGhsaJPARQogFkgBICLEqKYpCtDlCW0uIYm6ccrF4\n+yfN0Bh080sfjPNLj22jITD7rn8yXeDr3zf5uxdMxjKFmseoqioeX5CJgkLv9UEmJrI1H0usPqVS\nAaeUpaOtieamiAQ+QghRJ7IGSAixqrndbjrXtTKWSjGWTuP2VlemeMfGCJvXhXnxzWu8fHwA27mx\n9qPncpLz11K8/771PLizFa3GppO6ywUuF8OpLKl0huZIg5QzXuNu9PSRAgdCCFFvkgESQqwJDeEw\nHW3NKOUc+Xx1mRbDpfGhAxv4wid3srF1dm+gYtnmewd7+cq3TnJlIL2gMbo9lfVB/YkUA4PDlMvl\n2z9JrCrlUolSPk17tIGGcPhOD0cIIVYlCYCEEGuGpmm0xpqJNvop5NJVF0lojfj43Me7+eS7N72t\n78vAaJY/e/YU3/rpBbL50oLG6fb5cXQv1wZGSQyNVj1OsfJMrfXxGQ4d7THJAAohxCKSAEgIseb4\nvF4626M1FUlQFIX74lF++zO72bs9+rbtR8whfv/vj3HkTGLWdLlqVUpnBygrBtcGRhgeGZWKcatU\nsZjHKU2wvjVCpLHhTg9HCCFWPQmAhBBr0tuKJJSqy9r4PC4+8a5N/NoTd9Eamd1zKFso862fXeQv\nnuthYHRhhQ1UVcXtDVCwXVztH2ZkNImzgMBKLB+VrE+asE+nvTWKrsuyXCGEWAoSAAkh1rSpIgk+\nozIFqVqdsSD/+hM7+cj9GzBu6h10ZSDNH3/zBN97/QrF0sKmsWmahtsbIFfWuNQ7wPCoZIRWsnKp\nRLmQYX1rE+FQ6E4PRwgh1hQJgIQQAog0NrC+NUK5kK66ZLamKjy8q43f+sxu7uqKzNpmOw4vHe/n\ny08do+fy6ILHqWkabl+QfFmnt2+IkdFRyQitMIXsBF6XRUd7TLI+QghxB0gAJIQQk3RdZ31bjIBX\nIZ9NVx1YhANu/ukHtvHLH4rTGHTP2jaWKfJ3L5zl6983SaZr7x00RdM0PL4gecvFlesJRpNjEggt\nc7ZtU8iOE20O0hSJ3P4JQgghFoUEQEIIcZOpktlOaYJiMV/18+OdjXzx07t4z73r0NTZPYfO9Cb5\n8jeO8dO3rlO2Fj6FbSoQypZUevsSjKfHF3xMUX+lUgGlnKOjPYrX47nTwxFCiDVNAiAhhLgFTdNo\nb43S6HfVlA0ydI3H9nXwG5/aRVfb7DUeJcvmHw9d5Y+/dYJL/fUJWHRdx+0NkpqwuNafIJevPnAT\ni6OQnSDoUWlrbUGtsVmuEEKI+pFXYiGEeAfBYJCOtmYoZSkWclU/P9rg5Vc/toNPv3czfq9r1rZE\nMsdfPNfD0z85Tya3sN5BU1yGG90dYHA0Q9/AEKUqq9uJ+pmq8tbSFJCmpkIIsYzI6kshhLgNTdNo\na20hk5lgeGwcwxOo6k6+oijcu7WF7Z2NvHD4Kod6BpmZT3rz7DCnryT54P5O9m6PoirKnMeaL4/H\nh+M4XB9M4jFUWpoa0TRtwccV82NZFnYpS0dbs/y7CyHEMiMZICGEmKdAwM+GdTE0u0A+X31/H69b\n54mHu/i1J++mvdk/a1uuYPGdly7xZ8+con+kuuasc5lqpupoXq72j0jFuCVSKubRnSLr26IS/Agh\nxDIkAZAQQlRBURRi0SZikQDFXJpyuVz1MTqiAT7/5N187MGNuF2zPyBfTWT4yrdO8A+vXaZQXFjv\noJlj9vgC5C0XV/sSpNPpuhxXvF0+myHk04lFm1DqkMkTQghRfxIACSFEDbweT6Wil16uqYGqqio8\neHcrv/WZ3ezc1DRrm+3AKycG+NJTxzh5caRuWRtN0zC8QcayZa71J8hLoYS6sW2bfHactpawNDYV\nQohlTgIgIYSokaIoNEUitLWEKeXTlGsoOBDyG/yTR7fy2Y9sJxKa3TtofKLI//zhOb72fZPR8foF\nKy5XpVDCwGShhFqyWOKGYjGPUs6xYV0Mt9t9+ycIIYS4oyQAEkKIBXK73XS0x/AZTk3ZIICt6xv4\n4qd28749b+8ddPbqGF9+6hgvvnmtLr2Dpng8PhSXj2sDowwmRrDt+h17rchnM4R9Om2tLTLlTQgh\nVggJgIQQok4ijQ2sb41QLqQpFQtVP9+lqzy6t4MvfnoXW9bNLptcthx+eOQaX/7GMc5cHq3XkKfX\nB1mqm96+ISmUME/lcplibpz2aINMeRNCiBVGAiAhhKgjXddZ3xYj6FVraqAK0Bz28tmPbOcX3r+F\noG9276ChsTxf/t9H+d8/PEc6W6zXsFFVFY8vSK6s09uXIDVenwatq1EhO4FXL9O5rhXDMO70cIQQ\nQlRJ+gAJIcQiaAiHCfj9JIZHKSsuXK7q1oYoisKuzc1s62jgB0eu8fqpAWbGUkfPVXoHPbavg/07\nYqhqfaZf6bqOrgdJZ4uMZwZpagzh83rrcuzVwCnnaY81oKry9imEECuVZICEEGKR6LpOe2uUkFer\nORvkMXQ+/uBGPv9zO1nfMrt3UL5o8ewrl/nqMye5PlTb2qO56IaByxNkKDlB30CCYrF+2aaVbMum\nDsn6CCHECicBkBBCLLJwKERHWzOUshQLuZqOsa7Zz689cTdPPtKF1z07+3BtaII/+c5JnnvlMvli\nfSu6uT0+VCNAfyIlhRKEEEKsChIACSHEEtA0jbbWFiJBD/nseE2BhKoqPHB3K//xc/dz79bmWdsc\nB147NcCXvnGM4xeG617IwO3zTxdKGBoelUBICCHEiiUBkBBCLKFAwE9nexTVzlPIZ2s6Rjjg5hce\n3cqvfHQHzWHPrG3pbIn//aPz/M3zZxhO1ZZtmstUoYQShgRCQgghViwJgIQQYompqkprtJnmsI9C\nLl1zELF5XZh/86ldPLp3Pbo2uwjC+esp/vDp4/zwyFVK5foGKTcHQlI6WwghxEoiAZAQQtwhfr+P\njrYWlHKOYjFf0zF0TeV9e9bzm5/ezbaOhlnbypbDi29e5w+fPs65a2P1GPIsU4FQ3nJx5XqCkdGk\nBEJCCCGWPQmAhBDiDlJVlbbWFsI+nXy29kpukZCHX/5QnF98dCsh/+wqZSPjef7m+TP8rx+eY3yi\n/tXcNE2b7CGkSQ8hIYQQy540MhBCiGUgHArh9XjoHxpFN/xomlb1MRRF4e5NTWxd38AP37jKaycH\nsGckZE5cHOHs1TE+sG8993e31q130JSZPYRSmUGawkH8fl9dzyGEEEIslGSAhBBimTAMg872GLpT\npFBjuWwAt6Hx0Qc28q8/sZOOaGDWtkLJ4ruvXuFPvnOSq4n69g6aohsGhifIyHiO6wMJCoXCopxH\nCCGEqIUEQEIIsYwoikIs2kRzyFtz89QpbU1+/tUTd/Fzj3Thdc/OKPUNT/DV75zkmZcvkSvUt3fQ\nFMPtRTMC9A+nGRgcplxenPMIIYQQ1ZAASAghliG/30dne0uleWqNBRIAVEVh344Yv/WZe9iz7abe\nQcDBnkF+/xvHOHpuaNEKGHi8Phzdy7WBUYZHpGKcEEKIO2tFrAGKx+Nu4E+ATwBZ4PdM0/z9Ofb9\nKPCfgS3ABeB3TNN8bqnGKoQQ9TJVICGdTjOSSuP2BoDa1u0EvC4+9Z4t3BeP8szLl0gkb0yxm8iV\neOrHF3jDHOLxh7uINnjrdAU3KIqCxxegYFn09iVoDHkJBUN1P48QQghxOyslA/TfgD3Ae4DPA78b\nj8c/cfNO8Xh8F/BN4C+B3cCfA0/H4/GdSzdUIYSor2AwSEdbM05pglKptKBjdbWF+MIndvLB/R24\ntNlvARf7xvmjp4/zwqFeimVrQeeZi6ZpuL1Bxidseq8Pkk6nF+U8QgghxFyWfQYoHo/7gF8BPmia\n5jHgWDwe/6/AF4Bv3bT7PwF+ZJrmVya//5N4PP448BngxFKNWQgh6k3TNNpbo2Qm0uSzGRyn9gpu\nuqby7nvWsWtzM9999TKnrySnt1m2w0/e6uPYhREef2gj8c7Gegz/7WMwDMBgbKJAMj1IJBQgEPAv\nyrmEEEKImVZCBmg3lUDttRmPvQwcuMW+fwv8u1s8Hq7/sIQQYuk1hMNsWNeMXcxSLi6sp09j0M0v\nfTDOP3tsG+Gbegcl0wW+9n2T//HCWVKZxavi5jLcGJ4go5mCVIwTQgixJFZCANQGDJumObN80CDg\nicfjTTN3NCumMz3xePwu4P3AD5dkpEIIsQR0XWd9e5SAV1lQ89Qp3Rsj/NZndvOu3W2oyuzM0qnL\no3zpG8d4+Xg/lr14xQsMw1OpGDc0zkBiGMtanCl4QgghxEoIgHzAzbcEp753z/WkeDzeTGU90Eum\naT67SGMTQog7piEcpj3aQCmfXnCJacOl8aEDG/jCJ3eyoTU4a1uxbPP861f4yrdOcGVgcdfseHx+\nbNXDtYEREsOj2La9qOcTQgix9iz7NUBAnrcHOlPfZ2/1hHg8HgN+QKXK66erPaGmrYS4cOGmrnMt\nXO9aulaQ613Nbr5WXffQ1dnG8OgomWwOt9e3oOOva/Hza0/exRvmEM+/doVs/kZgNTCa5c+ePcW+\nHVE+fH8nfo9rQeeai6ZpuFxBbNvm2sAoux76aMv1Mz8bWpST1WCl/J6txL8LGfPiW2njBRnzUllp\nY17IOJXl3o8hHo8/APwU8JimaU8+9h7gu6ZpBm6x/zrgRcAC3mua5mCVp1ze/yBCCDGHXC5Pf2IU\n3e1H07TbP+E2MrkS3/7xeV453ve2bQGvi0+8dwsP7GxDUWovyDAfj33mN7ee+vFfnl/Uk8yfvEcI\nIcTyUdMb0ErIAL0FlID7gVcnH3sEOHzzjpMV474/uf97TdOs6Y7h+HgOy1r90y40TSUU8q6J611L\n1wpyvavZ7a61IRgiMTRCruTg9iwsGwTw+EMb2LWpkW//7BIDozeS7plcia8/f5qXjl7jyXdtojWy\n8HPdynK8E7lSfs9W4t+FjHnxrbTxgox5qay0MU+NtxbLPgAyTTMXj8e/Dnw1Ho//C2A98G+BX4bp\n6W4p0zTzwH8Auqj0C1IntwHkTNMcn+85LcumXF7+P/h6WUvXu5auFeR6V7N3utamSISJiSxDyRSG\nJ4CqLiyI6IgG+defuJtXTw7woyPXKM4476X+NH/wjeM8vKuV9+1Zj+FaeOZptuX381xpv2crbbwg\nY14KK228IGNeKitxzNVafrfWbu23gTeoTG37I+B3TNN8ZnJbP5U+PwCfALzAQaBvxteXl3S0Qghx\nh/n9Pjrbo6hWnmIht+DjaarKI7va+c3P7KZ74+zeQLbj8LNj/Xz5qWOcvjy64HMJIYQQi2nZZ4Cg\nkgUCPjv5dfM2dcb/71jKcQkhxHKmqiqtsWYymQmGx9K4vYEFr9dpCLj5Z4/FOdOb5LlXLpNM3yjS\nOZYp8t9fOMuODY18/KGNNATmLNQphBBC3DErIgASQghRu0DAj9frYXBolBIahuFZ8DG3dzayqT3E\nT968zks39Qg6fSXJ+esp3r9nPQ/takVb4BQ8IYQQop7kXUkIIdYATdNob20h7NPJZ9PUowKooWs8\ntr+T3/jkLrraQrO2lco23z/Uyx998wSX+ue9BFMIIYRYdBIACSHEGhIOhehoa8YqZigXi3U5ZrTR\ny69+bAeffs9m/J7ZEwsSyRx/8VwPT//kAplcqS7nE0IIIRZCAiAhhFhjNE1jfVsMnxvy2Uxdjqko\nCvdua+G3f/4e9u+Ivq0xw5tnh/jSN45x+EwCe5n3nxNCCLG6SQAkhBBrVKSxgbaWMIXcOOVyuS7H\n9Lp1nnxkE7/25F20N83uDZQrlPn2zy7y58+eon9koi7nE0IIIaolAZAQQqxhbrebzvYYhlomn8/e\n/gnz1BEN8us/t5OPPbgB9029gXoHM3zlWyd4/rUrFIpW3c4phBBCzIcEQEIIscYpikK0OUK00U8+\nO45t16cBnqYqPHh3G7/1md3s3BSZtc124OUT/XzpqWOcvDhSl6IMQgghxHxIACSEEAIAn9dLZ3sU\npZyjWMzX7bghv8E/eXQb//zD24mEZvcGGp8o8j9/eI6vf99kdLx+5xRCCCHmIgGQEEKIaaqq0tba\nQqPfVbdy2VO2dTTwxU/t5n171qGps8skmFfH+PJTx/jxm9cpW/XJQAkhhBC3IgGQEEKItwkGg6xv\nbaJcyFAu1a98tUtXeXRvB1/81C62rAvP2la2HH5w5Cp/+PRxLvSl6nZOIYQQYiYJgIQQQtySrut0\ntMfwGTaFbH2rtjU3ePnsR7bz8+/bQtDrmrVtOJXnr757mm+8eJ50tj69ioQQQogp+u13EUIIsZZF\nGhvxefMMjqTQDR+apt3+SfOgKAq7tzQT72zghcNXOdgzyMwZd2+dH+ZMb7Iu5xJCCCGmSAZICCHE\nbXk8Hjrbo2hOgUIdy2UDeAydxx/q4vNP3s26Fv+sbXkpky2EEKLOJAASQggxL4qi0Bptpun/b+/O\nw+Sq63yPvzsLSZolJCxJ2MwIzlcBh+WqwDAOijODjFfwojOg3CsKDgrjgw7OFVBARGYcNp0LCogj\n8cEF13FAFmcBRVknjAvD4ldFeIIQoiGQIJ1Alr5/nNNYNL1UJV1dp+q8X8+TJ12nf1X9/fWv6vz6\nU+ecX201a8IXSADYcbstOOHwPTnswIUv+OwgSZImigFIktSSLbbYnF122A7WDkzoctkAU6b0sf8e\n8zn5yL3Ya7dtJvSxJUkCA5AkaSO0c7lsgC37N+PIg1/Cqf973wl9XEmSDECSpI02tFz2+md/y7pn\nJ37Ftjlbzhi/kSRJLTAASZI2ybRp09hpwTz6Z8Cagd92uhxJksZkAJIkTYi5c7ZmwXazeWb1Ktav\nd/U2SVI1GYAkSRNmxowZ7LLDPKb3rWXNBC+XLUnSRDAASZImVF9fH9tvO5ftZvezZmAIHRdRAAAY\nHElEQVQVGzZs6HRJkiQ9xwAkSWqLzTfvZ5cdtqdv3eoJXy5bkqSNZQCSJLVNu5fLliSpVQYgSVLb\nPW+57LVrO12OJKnGDECSpEnx3HLZmw26XLYkqWMMQJKkSeVy2ZKkTjIASZImnctlS5I6xQAkSeqI\n5y+X7QIJkqTJYQCSJHVUsVz2dmx49mnWPftsp8uRJPU4A5AkqeOmTJnCjgu2p38GPDPwdKfLkST1\nMAOQJKky5s7Zmnnbbskzq59iw4YNnS5HktSDDECSpEqZOXMmOy/Yjr51qz0lTpI04QxAkqTKmTJl\nCgvmb8eW/VNY9etfdrocSVIPMQBJkipr69mz+dV9332g03VIknqHAUiSVGmDro8tSZpABiBJkiRJ\ntWEAkiRJklQbBiBJkiRJtWEAkiRJklQbBiBJkiRJtWEAkiRJklQbBiBJkiRJtWEAkiRJklQbBiBJ\nkiRJtWEAkiRJklQbBiBJkiRJtWEAkiRJklQbBiBJkiRJtWEAkiRJklQbBiBJkiRJtWEAkiRJklQb\nBiBJkiRJtWEAkiRJklQbBiBJkiRJtWEAkiRJklQbBiBJkiRJtWEAkiRJklQbBiBJkiRJtWEAkiRJ\nklQbBiBJkiRJtWEAkiRJklQbBiBJkiRJtTGt0wU0IyJmAJcARwADwIWZ+YlR2u4DXAq8HLgHOCEz\nfzhZtUqSJEmqrm45AnQBsC/wGuBE4CMRccTwRhHRD1wH3Fy2vx24LiJmTV6pkiRJkqqq8gGoDDXH\nASdl5k8y82rgPOC9IzQ/ChjIzFOy8H7gKeAvJq9iSZIkSVVV+QAE7EVxqt7tDdtuAfYboe1+5fca\n3Qoc0J7SJEmSJHWTbrgGaAGwPDPXNWxbBsyMiG0y8/Fhbe8Zdv9lwB5trrHrHPsPN71g2xWnHtyB\nSjTRHNve5diqWd34XPnbi25ixcDvbs/thwtOqnbNZy+6jYeWrXnu9sJ5MznznX/YwYrGNrBmLdfd\nuYTHHh9g/jb9vGG/XeifOb3TZY1p+ZOrufTqe1m+cjXbzp7FCYfvwbZbV/vKhm6see269fzoF8tZ\nObCW2f3T2XPhHKZPm9rpstqmG44A9QPPDNs2dHtGk22Ht6u1kSbGsbarezi2vcuxVbO68bkyPPwA\nrBgotlfV8PAD8NCyNZy96LYOVTS2gTVrOWvRYm6862Hue3AFN971MGctWszAmrWdLm1Uy59czamf\nuZ0Hl67iqYG1PLh0Fad+5naWP7m606WNqhtrXrtuPYtu+CnfvvVBbrv7Ub5964MsuuGnrF23vtOl\ntU03HAFawwsDzNDtgSbbDm83pqlTuyEXtse0ab3Z96ExdWx7U93Htw5jWyVVrKlZVX2uDA8/jdur\nWvPw8NO4vYo1X3fnElYNPPu8basGnuW6O5fw1te9pENVje3Sq+9lw+Dzt20YLLZ/9LhXdaaocXRj\nzT/6xXIeWzFAH30A9NHHYysGuOehJ3jlS7fvcHWj25R9cTcEoEeAbSNiSmZuKLfNB1Zn5pMjtJ0/\nbNt8YGkrP3Crrap9mLKd5szZvNMltJVj29vqOr51GNsq6ebnWTc+V6x5Yjz2+O/+wAWe+/qxFQOV\nrBdg+cqRj5osX7namifQyoG1TGsIE1On9gF9rBxYW9maN1U3BKAfA2uB/YGh48qvBhaP0PYO4JRh\n2w4EzmnlB65atZr16zeM37AHPfHE050uoS2mTp3CVlvNcmx7VN3Htw5jWyXd/DzrxueKNU+M+dv0\nc++DxWXTffQxSHGYYv7c/krWC7Dt7Fk8NfDCU/S2nT3LmifQ7P7prFu/gT76mDq1j/XrBxlkkNn9\n0ytbM2za/FD5AJSZqyPiSuCyiDgW2An4AHAMQETMA1Zm5hrgG8DHI+KTwOXAeyiuC/paKz9z/foN\nrFvXnZPbpur1fju2va2u41vHPndSNz/Pqlr33P6RT4Ob21/dmhfOmzniaXAL582sZM1v2G8XFt+3\n7HmnwW3Vvxlv2G+XStYLcMLhe3DqZ25/3illU/qK7dY8cfZcOIfF9y/jsRUDUIbj+XP72XPhnMrW\nvKn6BgcHx2/VYeUHmV4CvBlYCZyXmReX39sAvCMzryxvvwL4DPBS4G7g3Zl5dws/bvCJJ57u2QEf\n0o0rBG2KadOmMGfO5ji2vaku41vjse0bv+Wk6Yo5ohufK64C137PrQK3YoD5c10Frl26sea169Zz\nz0NPdNUqcJsyP3RFAJpkXTG5TYS6/NEI9eor2N9eVqe+ggFoU3Tjc8Wa26/b6gVrnizdVvOmzA/V\nW6ZEkiRJktrEACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJ\nkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrD\nACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJ\nkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxA\nkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSp\nNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJ\nkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrD\nACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJkmrDACRJkiSpNgxAkiRJ\nkmrDACRJkiSpNgxAkiRJkmpjWqcLaEZE/ANwLEVg+1xmnjJG2/2BC4E/AH4FXJCZn5uUQiVJkiRV\nWuWPAEXEB4CjgMOBNwNHR8TJo7SdB1wP3ATsDZwFXBwRh05OtZIkSZKqrBuOAJ0EnJ6ZtwNExCnA\nx4BPjND2TcDSzDyjvP1ARLwWeBtww2QUK0mSJKm6Kn0EKCIWADsDP2jYfAvwovJoz3A3AO8cYfvs\nNpQnSZIkqctU/QjQAmAQeLRh2zKgD9ip/Po5mbkEWDJ0OyK2pzh97sy2VypJkiSp8joegCJiJrDj\nKN/eAiAzn23Y9kz5/4wmHvebFOHp8lZqmjq10gfGJsxQP+vQ3zr1FexvL6tTX6Ga/axiTSPpxueK\nNbdft9UL1jxZuq3mTamzb3BwcAJLaV1EHAR8l+JIz3CnAOcCs4ZCUBlsBoB9M/PHozzm5sA1wO7A\ngZn5y3bULkmSJKm7dPwIUGbezCjXIpXXAJ0LzOd3p7bNpwhLS0e5z5bAd4AXA681/EiSJEkaUulj\nXJm5FHgY+KOGza8GlmTmsuHtI6IP+BawEPjjzPzpZNQpSZIkqTt0/AhQEy4Fzo2IRygWP/g4cP7Q\nNyNiW2B1Zj4NvAt4DfBGYFXDSnHPZuYTk1q1JEmSpMrphgB0PrAd8M/AOuCfMvP/NXx/MbAIOBs4\ngiIkXTvsMW4GDm5/qZIkSZKqrOOLIEiSJEnSZKn0NUCSJEmSNJEMQJIkSZJqwwAkSZIkqTYMQJIk\nSZJqoxtWgZtQETEDuIRixbgB4MLM/MQoba+mWFJ7kGJ1uUHgjZl5/SSVO2HKft8F/HVmfn+UNvtQ\nLDv+cuAe4ITM/OHkVTkxmuxr149tROwAXAS8luK5/DXgtMx8doS2XT+2Lfa3q8c3InYFPg0cCDwO\nfCozLxilbS+MbSv9rczYRsS/Al/KzCsn+2ePp5W5rmqa2YdXQSv7pKpo5bVWNRFxHbAsM4/tdC3j\niYg3Uaxe3Lif+mZm/mVHCxtFRGwGfBJ4K/AMcEVmfrizVY0uIo6hWAG68ffbB2zIzKayTR2PAF0A\n7EvxeUEnAh+JiCNGafsy4G3AAmB++f+/T0KNE6qcTK4Cdh+jTT9wHcWS4fsCtwPXRcSsSSlygjTT\n11IvjO03gZkUE9lRFH8Ufmx4o14ZW5rsb6lrx7f8QOfrgGXA3sB7gNMj4qgR2nb92LbS31LHxzYi\n+iLiYuBPJvPntqiVua4yWtiHV0Er+6SO24jXWmWUNR7a6TpasDtwDcU+amg/9a6OVjS2i4DXAX9K\nsX/9q4j4q86WNKav8Lvf63zgRcAvgH9s9gFqdQSo/GPhOOCQzPwJ8JOIOA94L0VSb2y7GfB7wF2Z\n+etJL3aCRMTLgC830fQoYCAzTylvvz8i/hz4C6By726OpNm+9sLYRkQArwLmZebyctuZFJ+bdcqw\n5r0wtk33twfGdx7wI+DE8gOeH4iIG4E/otjpN+r6saWF/lZhbMt3/b9Y1vFkJ2oYTytzXZW0MF91\nXIv74KpoZd9SGRExBzgP+M9O19KClwH3ZOZvOl3IeMrf77HAwZn5X+W2C4D9gM92srbRZOYzwHNz\nQEScVn552sj3eKFaBSBgL4o+396w7RbgQyO0DWAD8MtJqKudDgJuBE6nOEQ/mv0ofheNbgUOoHv+\nkGq2r70wto8Brx+aeEt9wOwR2vbC2LbS364e38x8jOI0BAAi4kDgjynerR2u68e2xf5WYWz3BZYA\nbwH+q4N1jKWVua5Kmt2HV0Er+6RKaPG1ViUXUOzPdux0IS3YnS4564AiAD+Zmc/NJZl5XgfraUkZ\n4D4IHJuZa5u9X90C0AJgeWaua9i2DJgZEdtk5uMN218GrAK+GBGvAR4GPpKZ35m0aidAZl429HXx\nhtWoFlBcP9BoGbBHG8pqixb62vVjm5kradi5lqc2vBf4jxGa98LYttLfrh/fIRHxELAzcC0jv3Pf\n9WPbqIn+dnxsM/Pasr7x9jOd1MpcVxkt7MM7rsV9UuU08VqrhIg4GHg1xTWOl43TvEoCeH1EfBiY\nCnwdOLOVP9An0YuBhyLi/1C8SbIZxfU1f5eZgx2trDknAo9k5rdauVPdrgHqp7i4q9HQ7RnDtr8U\nmAXcABwCXA98OyL2bWuFnTPa72b476UX9OLYnk9xTvdIFy324tiO1d9eGt8jKK4r2IeRz23utbEd\nr79tH9uImBkRu47yr3+ifk6btTLXaWKMtU+qovFeax1XXg92GcUpe8Ofz5UVEbtQ7KdWU5yO/AHg\naIrT+KpoC+D3geOBd1DUexLw/g7W1IrjKK5hakndAtAaXrjzH7r9vMPtmXk2sGNmfiEz/zszP0ox\n6R7f/jI7YrTfTdVPQ2hZr41tRJxLsbM6OjPvH6FJT43teP3tpfHNzB+Wq5v9DXB8RAw/at9TYzte\nfydpbPcDfg78bIR/VV70oFHTc502XRP74MppYt9SBWcBizOzK46qDcnMJcA2mXlcZt6dmVdThInj\nyyOFVbMO2BJ4a2bemZn/Avwd8O7OljW+iHglxamRX231vlV8wrfTI8C2ETElMzeU2+YDqzPzBRez\nloe4G91Pd6xMszEeofhdNJoPLO1ALW3XK2NbrkT1boqJ919GadYzY9tkf7t6fCNie+CActIcch/F\naQlbASsatnf92LbY37aPbWbeTPe/OdjSXKeN1+w+qQpafa1VwJHAvIh4qrw9AyAi3pKZW3WurPGN\n8Dq7n2LFwLkUy49XyVJgTWb+qmFbUpwiWXWHAN8fYV4YV7fv5Fv1Y2AtsH/DtlcDi4c3jIhFEfG5\nYZv3Bn7avvI66g7gD4dtO7Dc3lN6ZWwj4iMU73wfmZlfH6NpT4xts/3tgfH9PeCfI2JBw7ZXAL/J\nzOF/oPTC2Dbd3x4Y28nS9FynjdfCPrgqWtm3VMFBFNf+7FX+uwa4uvy6siLizyJieUTMbNi8D/B4\nRa+/u4Pi+sDdGrbtDjzUmXJash/Fwj8tq9URoMxcHRFXApdFxLHAThTnOh4DEBHzgJWZuYbihXZV\nRHwPuI3i/M0DgSqvi96SYf39BvDxiPgkcDnFqjD9FB/s1vV6bWzL5WJPB/4euK3sHwCZuazXxrbF\n/nb7+C6m+BDIKyLiZIo/Ws4DzoGefN220t9uH9tJMd5cp0033j6pY4WNbczXWtVk5sONt8sjQYOZ\n+WCHSmrWbRSnmv5TRJwN7Erxez63o1WNIjN/FsWHzH4+Ik6kWETlFODszlbWlD2BL2zMHet2BAjg\nZIqlS28CLgbOaDgcvBT4S4ByNYkTKXZw/01xseAh5bmd3Wr4ah6N/X0K+J8US2LeRfH5Bodm5upJ\nrXDijNXXXhjbwyhev6cDj5b/lpb/Q++NbSv97erxLU9ZOhx4mmIivRz4x8z8VNmkp8a2xf5WbWyr\nvELSWHNdN6jy7xbG3ydVThOvNU2AzPwtxalZ21GEzs8Cl2XmhR0tbGxHU3yQ6A+AzwMXZeanO1pR\nc7YHntiYO/YNDlZ9HyNJkiRJE6OOR4AkSZIk1ZQBSJIkSVJtGIAkSZIk1YYBSJIkSVJtGIAkSZIk\n1YYBSJIkSVJtGIAkSZIk1YYBSJIkSVJtGIAkSZIk1ca0ThcgCSLiIWCXhk2DwG+BHwFnZOYPxrn/\nQcB3gYWZuaRNZUqSOmhT54pN+LmLgBdl5sHteHxpsnkESKqGQeB8YH75bwfgAGAl8J2I2KnJx5Ak\n9a6JmCuk2vMIkFQdT2fmrxtuL4uI9wCPAP8LuLgzZUmSKsS5QtpEBiCp2taX/6+JiGnAmcDbge2A\n+4DTMvM/ht8pIrameJfwUGB74AngauCkzFxTtvlb4D3ATsCjwBWZeU75vVkUk+gbgK2B+4GPZea3\n2tRPSdLGG5ornomInSn2/68F5gDLgC9l5qkAEXEMcDpwHfAO4KbMPCIidgMuBA4C1gH/BrwvM39T\nPvb0iDivvE8/8O/A8Q3fl7qGp8BJFRUROwKfoji/+wbgIuB44G+APYF/Ba6JiJeMcPfPA3sBbwJ2\nA95PEZyOLx/7jcBp5e3dgFOAD0fE28r7n1P+jNcDLy1//lciovHcc0lShw2bK64HrgG2BF4H/D5F\nGPpgRBzWcLddgQXA3hT7/tnA94HpwGvK++4KfLXhPgdSvCF2IPDnFKfend+ufknt5BEgqTo+FBH/\nt/x6GrAZxZGXtwBPAscCf91wFOb0iADYaoTH+jfg5sy8t7y9JCJOAl5e3n4xsAZYkpm/Ar4eEY8A\nSxq+/xTwUGaujIgzgO9RHEmSJHXOWHPFcuBK4GuZ+UjZ5qKIOI1i/39NuW0QODszHwKIiHcDWwBH\nZeaqcttxwFsjYnp5n0cz8/jy659HxFeAP2lTH6W2MgBJ1XEZxVEeKE5nWJGZTwFExP+geGfuzsY7\nZObp5fcPGvZYlwKHRcQ7gZcAewALKSZJgC8C7wR+FhH3UZzK8I0yDAGcSzFR/iYi7qQIVF8eqkeS\n1DGjzhUAEfFp4C0RsR/FEf4/oDgVeuqwx/lFw9d7Aj8bCj8AmXkP8OHyMQEeGHb/J4BZm9oZqRMM\nQFJ1rMjMX47yvbVAXzMPEhF9FOd27w58GfgK8EPgs0NtMvNxYO+IOAD4M+AQ4H0RcWZmnpOZd5Tn\nkf8pxTt8bwfOiIhDMvO7G9c9SdIEGHWuiIh+4AfADODrwCLgP4FbhrfNzGcabq5t4ueuH2FbU/OS\nVDUGIKk7/JxignolcM/Qxoi4A7gK+HFD270prt15VWbeVbabTvFO4APl7bcBW2fmJcDtwEcj4nLg\nKOCciDgLuCUzrwWujYiTgXuBN1N83pAkqXoOoZgD5mXmcoCImAvMY+ywch/wrojYsuHMg30prv/c\np70lS5PPACR1gcxcHREXU4ST5RRh5F0Up7ZdT/FZEEOT22MUYenIsu22wIcoJsAZZZuZwAURsYri\n3cKdKVb++V75/RcDR0fE8RShaX+KD9+7tY3dlCRtmqHTmN8eEd+g2G//PcXfezNGvRd8iWJluC+U\n13xuBlwC/CQzHy1PgZN6hqvASdXQzIeYnkpxceulwN0UgeXQzPx542Nk5lLgGOAwinf1vkYxKX4S\neEXZ5gqKJbXPoLgu6KsU7/S9r3ysE4EbgS8ACXwU+GBmXrUpnZQkbZIx54rMXAycDJxEsW+/guKN\nrasoziAY7X6rKY4eTQduo3hj7R7gyIkoWqqavsFBPzxekiRJUj14BEiSJElSbRiAJEmSJNWGAUiS\nJElSbRiAJEmSJNWGAUiSJElSbRiAJEmSJNWGAUiSJElSbRiAJEmSJNWGAUiSJElSbRiAJEmSJNWG\nAUiSJElSbRiAJEmSJNXG/wfgf+XzPFWa4QAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "sns.pairplot(data, x_vars=['Pclass','Parch'], y_vars='Survived', size=6, aspect=0.7, kind='reg')" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[0, 3],\n", + " [0, 1],\n", + " [0, 3],\n", + " ..., \n", + " [2, 3],\n", + " [0, 1],\n", + " [0, 3]], dtype=int64)" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn.cross_validation import train_test_split\n", + "features = np.array([data.Parch, data.Pclass]).T\n", + "features # 2D array" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0]], dtype=int64)" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "response = np.array([data.Survived]).T \n", + "response # 1D array" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "# step 1: split data into training set and test set\n", + "features_train, features_test, response_train, response_test = train_test_split(features, response, random_state=4)\n", + "# the random_state allows us all to get the same random numbers" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[0, 2],\n", + " [0, 3],\n", + " [0, 3],\n", + " ..., \n", + " [0, 2],\n", + " [0, 1],\n", + " [0, 2]], dtype=int64)" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "features_train" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\Eugene\\Anaconda2\\envs\\bersonenv\\lib\\site-packages\\ipykernel\\__main__.py:2: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n", + " from ipykernel import kernelapp as app\n" + ] + }, + { + "data": { + "text/plain": [ + "0.63228699551569512" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "knn = KNeighborsClassifier(n_neighbors=5)\n", + "knn.fit(features_train, response_train) # Note that I fit to the training\n", + "knn.score(features_test, response_test) # and scored on the test set" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "X = data[['Parch', 'Pclass']]\n", + "y = data['Survived']\n", + "from sklearn.cross_validation import cross_val_score\n", + "knn = KNeighborsClassifier(n_neighbors=5)\n", + "scores = cross_val_score(knn, X, y, cv=5, scoring='accuracy')" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([ 0.61452514, 0.68156425, 0.70786517, 0.75280899, 0.70621469])" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "scores" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python [bersonenv]", + "language": "python", + "name": "Python [bersonenv]" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.12" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} diff --git a/labs/Titanic_Eugene.ipynb b/labs/Titanic_Eugene.ipynb new file mode 100644 index 0000000..2dc8b4a --- /dev/null +++ b/labs/Titanic_Eugene.ipynb @@ -0,0 +1,1620 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked
0103Braund, Mr. Owen Harrismale22.010A/5 211717.2500NaNS
1211Cumings, Mrs. John Bradley (Florence Briggs Th...female38.010PC 1759971.2833C85C
2313Heikkinen, Miss. Lainafemale26.000STON/O2. 31012827.9250NaNS
3411Futrelle, Mrs. Jacques Heath (Lily May Peel)female35.01011380353.1000C123S
4503Allen, Mr. William Henrymale35.0003734508.0500NaNS
\n", + "
" + ], + "text/plain": [ + " PassengerId Survived Pclass \\\n", + "0 1 0 3 \n", + "1 2 1 1 \n", + "2 3 1 3 \n", + "3 4 1 1 \n", + "4 5 0 3 \n", + "\n", + " Name Sex Age SibSp \\\n", + "0 Braund, Mr. Owen Harris male 22.0 1 \n", + "1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 \n", + "2 Heikkinen, Miss. Laina female 26.0 0 \n", + "3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 \n", + "4 Allen, Mr. William Henry male 35.0 0 \n", + "\n", + " Parch Ticket Fare Cabin Embarked \n", + "0 0 A/5 21171 7.2500 NaN S \n", + "1 0 PC 17599 71.2833 C85 C \n", + "2 0 STON/O2. 3101282 7.9250 NaN S \n", + "3 0 113803 53.1000 C123 S \n", + "4 0 373450 8.0500 NaN S " + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "from sklearn.linear_model import LinearRegression\n", + "from sklearn.cross_validation import cross_val_score\n", + "from sklearn import metrics\n", + "import statsmodels.formula.api as smf\n", + "from sklearn.neighbors import KNeighborsClassifier\n", + "\n", + "# visualization\n", + "import seaborn as sns\n", + "import matplotlib.pyplot as plt\n", + "%matplotlib inline\n", + "\n", + "data = pd.read_csv('http://localhost:8888/files/data/titanic.csv')\n", + "data.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\Eugene\\Anaconda2\\envs\\bersonenv\\lib\\site-packages\\numpy\\lib\\function_base.py:3834: RuntimeWarning: Invalid value encountered in percentile\n", + " RuntimeWarning)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PassengerIdSurvivedPclassAgeSibSpParchFare
count891.000000891.000000891.000000714.000000891.000000891.000000891.000000
mean446.0000000.3838382.30864229.6991180.5230080.38159432.204208
std257.3538420.4865920.83607114.5264971.1027430.80605749.693429
min1.0000000.0000001.0000000.4200000.0000000.0000000.000000
25%223.5000000.0000002.000000NaN0.0000000.0000007.910400
50%446.0000000.0000003.000000NaN0.0000000.00000014.454200
75%668.5000001.0000003.000000NaN1.0000000.00000031.000000
max891.0000001.0000003.00000080.0000008.0000006.000000512.329200
\n", + "
" + ], + "text/plain": [ + " PassengerId Survived Pclass Age SibSp \\\n", + "count 891.000000 891.000000 891.000000 714.000000 891.000000 \n", + "mean 446.000000 0.383838 2.308642 29.699118 0.523008 \n", + "std 257.353842 0.486592 0.836071 14.526497 1.102743 \n", + "min 1.000000 0.000000 1.000000 0.420000 0.000000 \n", + "25% 223.500000 0.000000 2.000000 NaN 0.000000 \n", + "50% 446.000000 0.000000 3.000000 NaN 0.000000 \n", + "75% 668.500000 1.000000 3.000000 NaN 1.000000 \n", + "max 891.000000 1.000000 3.000000 80.000000 8.000000 \n", + "\n", + " Parch Fare \n", + "count 891.000000 891.000000 \n", + "mean 0.381594 32.204208 \n", + "std 0.806057 49.693429 \n", + "min 0.000000 0.000000 \n", + "25% 0.000000 7.910400 \n", + "50% 0.000000 14.454200 \n", + "75% 0.000000 31.000000 \n", + "max 6.000000 512.329200 " + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 0.616162\n", + "1 0.383838\n", + "Name: Survived, dtype: float64" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.Survived.value_counts(normalize=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "PassengerId 0\n", + "Survived 0\n", + "Pclass 0\n", + "Name 0\n", + "Sex 0\n", + "Age 177\n", + "SibSp 0\n", + "Parch 0\n", + "Ticket 0\n", + "Fare 0\n", + "Cabin 687\n", + "Embarked 2\n", + "dtype: int64" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.isnull().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PassengerIdSurvivedPclassAgeSibSpParchFare
count183.000000183.000000183.000000183.000000183.000000183.000000183.000000
mean455.3661200.6721311.19125735.6744260.4644810.47541078.682469
std247.0524760.4707250.51518715.6438660.6441590.75461776.347843
min2.0000000.0000001.0000000.9200000.0000000.0000000.000000
25%263.5000000.0000001.00000024.0000000.0000000.00000029.700000
50%457.0000001.0000001.00000036.0000000.0000000.00000057.000000
75%676.0000001.0000001.00000047.5000001.0000001.00000090.000000
max890.0000001.0000003.00000080.0000003.0000004.000000512.329200
\n", + "
" + ], + "text/plain": [ + " PassengerId Survived Pclass Age SibSp \\\n", + "count 183.000000 183.000000 183.000000 183.000000 183.000000 \n", + "mean 455.366120 0.672131 1.191257 35.674426 0.464481 \n", + "std 247.052476 0.470725 0.515187 15.643866 0.644159 \n", + "min 2.000000 0.000000 1.000000 0.920000 0.000000 \n", + "25% 263.500000 0.000000 1.000000 24.000000 0.000000 \n", + "50% 457.000000 1.000000 1.000000 36.000000 0.000000 \n", + "75% 676.000000 1.000000 1.000000 47.500000 1.000000 \n", + "max 890.000000 1.000000 3.000000 80.000000 3.000000 \n", + "\n", + " Parch Fare \n", + "count 183.000000 183.000000 \n", + "mean 0.475410 78.682469 \n", + "std 0.754617 76.347843 \n", + "min 0.000000 0.000000 \n", + "25% 0.000000 29.700000 \n", + "50% 0.000000 57.000000 \n", + "75% 1.000000 90.000000 \n", + "max 4.000000 512.329200 " + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.dropna().describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0AAAAJQCAYAAACnwgRtAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAUiSJElSbRiAJEmSJNXG/wfgf+XzPFWa4QAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "sns.pairplot(data, x_vars=['Pclass','Parch'], y_vars='Survived', size=6, aspect=0.7, kind='reg')" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[0, 3],\n", + " [0, 1],\n", + " [0, 3],\n", + " ..., \n", + " [2, 3],\n", + " [0, 1],\n", + " [0, 3]], dtype=int64)" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn.cross_validation import train_test_split\n", + "features = np.array([data.Parch, data.Pclass]).T\n", + "features # 2D array" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [1],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [0],\n", + " [1],\n", + " [0],\n", + " [1],\n", + " [0]], dtype=int64)" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "response = np.array([data.Survived]).T \n", + "response # 1D array" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "# step 1: split data into training set and test set\n", + "features_train, features_test, response_train, response_test = train_test_split(features, response, random_state=4)\n", + "# the random_state allows us all to get the same random numbers" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[0, 2],\n", + " [0, 3],\n", + " [0, 3],\n", + " ..., \n", + " [0, 2],\n", + " [0, 1],\n", + " [0, 2]], dtype=int64)" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "features_train" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\Eugene\\Anaconda2\\envs\\bersonenv\\lib\\site-packages\\ipykernel\\__main__.py:2: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n", + " from ipykernel import kernelapp as app\n" + ] + }, + { + "data": { + "text/plain": [ + "0.63228699551569512" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "knn = KNeighborsClassifier(n_neighbors=5)\n", + "knn.fit(features_train, response_train) # Note that I fit to the training\n", + "knn.score(features_test, response_test) # and scored on the test set" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "X = data[['Parch', 'Pclass']]\n", + "y = data['Survived']\n", + "from sklearn.cross_validation import cross_val_score\n", + "knn = KNeighborsClassifier(n_neighbors=5)\n", + "scores = cross_val_score(knn, X, y, cv=5, scoring='accuracy')" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([ 0.61452514, 0.68156425, 0.70786517, 0.75280899, 0.70621469])" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "scores" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python [bersonenv]", + "language": "python", + "name": "Python [bersonenv]" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.12" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} diff --git a/labs/untitled b/labs/untitled new file mode 100644 index 0000000..e69de29 diff --git a/notebooks/.ipynb_checkpoints/02_pandas-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/02_pandas-checkpoint.ipynb new file mode 100644 index 0000000..b826e3f --- /dev/null +++ b/notebooks/.ipynb_checkpoints/02_pandas-checkpoint.ipynb @@ -0,0 +1,7213 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "\"\\nCLASS: Pandas for Data Exploration, Analysis, and Visualization\\n\\nWHO alcohol consumption data:\\n article: http://fivethirtyeight.com/datalab/dear-mona-followup-where-do-people-drink-the-most-beer-wine-and-spirits/ \\n original data: https://github.com/fivethirtyeight/data/tree/master/alcohol-consumption\\n files: drinks.csv (with additional 'continent' column)\\n\"" + ] + }, + "execution_count": 1, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "'''\n", + "CLASS: Pandas for Data Exploration, Analysis, and Visualization\n", + "\n", + "WHO alcohol consumption data:\n", + " article: http://fivethirtyeight.com/datalab/dear-mona-followup-where-do-people-drink-the-most-beer-wine-and-spirits/ \n", + " original data: https://github.com/fivethirtyeight/data/tree/master/alcohol-consumption\n", + " files: drinks.csv (with additional 'continent' column)\n", + "'''" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/sinanozdemir/anaconda/envs/sfdat26-env/lib/python2.7/site-packages/matplotlib/font_manager.py:273: UserWarning: Matplotlib is building the font cache using fc-list. This may take a moment.\n", + " warnings.warn('Matplotlib is building the font cache using fc-list. This may take a moment.')\n" + ] + } + ], + "source": [ + "# imports\n", + "import pandas as pd\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "%matplotlib inline" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "pandas.core.frame.DataFrame" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "'''\n", + "Pandas Basics: Reading Files, Summarizing, Handling Missing Values, Filtering, Sorting\n", + "'''\n", + "\n", + "# read in the CSV file from a URL\n", + "drinks = pd.read_csv('../data/drinks.csv')\n", + "\n", + "type(drinks) # Use the type method to check python type\n" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servingsspirit_servingswine_servingstotal_litres_of_pure_alcoholcontinent
0Afghanistan0000.0AS
1Albania89132544.9EU
2Algeria250140.7AF
3Andorra24513831212.4EU
4Angola21757455.9AF
5Antigua & Barbuda102128454.9NaN
6Argentina193252218.3SA
7Armenia21179113.8EU
8Australia2617221210.4OC
9Austria279751919.7EU
10Azerbaijan214651.3EU
11Bahamas122176516.3NaN
12Bahrain426372.0AS
13Bangladesh0000.0AS
14Barbados143173366.3NaN
15Belarus1423734214.4EU
16Belgium2958421210.5EU
17Belize26311486.8NaN
18Benin344131.1AF
19Bhutan23000.4AS
20Bolivia1674183.8SA
21Bosnia-Herzegovina7617384.6EU
22Botswana17335355.4AF
23Brazil245145167.2SA
24Brunei31210.6AS
25Bulgaria2312529410.3EU
26Burkina Faso25774.3AF
27Burundi88006.3AF
28Cote d'Ivoire37174.0AF
29Cabo Verde14456164.0AF
.....................
163Suriname12817875.6SA
164Swaziland90224.7AF
165Sweden152601867.2EU
166Switzerland18510028010.2EU
167Syria535161.0AS
168Tajikistan21500.3AS
169Thailand9925816.4AS
170Macedonia10627863.9EU
171Timor-Leste1140.1AS
172Togo362191.3AF
173Tonga362151.1OC
174Trinidad & Tobago19715676.4NaN
175Tunisia513201.3AF
176Turkey512271.4AS
177Turkmenistan1971322.2AS
178Tuvalu64191.0OC
179Uganda45908.3AF
180Ukraine206237458.9EU
181United Arab Emirates1613552.8AS
182United Kingdom21912619510.4EU
183Tanzania36615.7AF
184USA249158848.7NaN
185Uruguay115352206.6SA
186Uzbekistan2510182.4AS
187Vanuatu2118110.9OC
188Venezuela33310037.7SA
189Vietnam111212.0AS
190Yemen6000.1AS
191Zambia321942.5AF
192Zimbabwe641844.7AF
\n", + "

193 rows × 6 columns

\n", + "
" + ], + "text/plain": [ + " country beer_servings spirit_servings wine_servings \\\n", + "0 Afghanistan 0 0 0 \n", + "1 Albania 89 132 54 \n", + "2 Algeria 25 0 14 \n", + "3 Andorra 245 138 312 \n", + "4 Angola 217 57 45 \n", + "5 Antigua & Barbuda 102 128 45 \n", + "6 Argentina 193 25 221 \n", + "7 Armenia 21 179 11 \n", + "8 Australia 261 72 212 \n", + "9 Austria 279 75 191 \n", + "10 Azerbaijan 21 46 5 \n", + "11 Bahamas 122 176 51 \n", + "12 Bahrain 42 63 7 \n", + "13 Bangladesh 0 0 0 \n", + "14 Barbados 143 173 36 \n", + "15 Belarus 142 373 42 \n", + "16 Belgium 295 84 212 \n", + "17 Belize 263 114 8 \n", + "18 Benin 34 4 13 \n", + "19 Bhutan 23 0 0 \n", + "20 Bolivia 167 41 8 \n", + "21 Bosnia-Herzegovina 76 173 8 \n", + "22 Botswana 173 35 35 \n", + "23 Brazil 245 145 16 \n", + "24 Brunei 31 2 1 \n", + "25 Bulgaria 231 252 94 \n", + "26 Burkina Faso 25 7 7 \n", + "27 Burundi 88 0 0 \n", + "28 Cote d'Ivoire 37 1 7 \n", + "29 Cabo Verde 144 56 16 \n", + ".. ... ... ... ... \n", + "163 Suriname 128 178 7 \n", + "164 Swaziland 90 2 2 \n", + "165 Sweden 152 60 186 \n", + "166 Switzerland 185 100 280 \n", + "167 Syria 5 35 16 \n", + "168 Tajikistan 2 15 0 \n", + "169 Thailand 99 258 1 \n", + "170 Macedonia 106 27 86 \n", + "171 Timor-Leste 1 1 4 \n", + "172 Togo 36 2 19 \n", + "173 Tonga 36 21 5 \n", + "174 Trinidad & Tobago 197 156 7 \n", + "175 Tunisia 51 3 20 \n", + "176 Turkey 51 22 7 \n", + "177 Turkmenistan 19 71 32 \n", + "178 Tuvalu 6 41 9 \n", + "179 Uganda 45 9 0 \n", + "180 Ukraine 206 237 45 \n", + "181 United Arab Emirates 16 135 5 \n", + "182 United Kingdom 219 126 195 \n", + "183 Tanzania 36 6 1 \n", + "184 USA 249 158 84 \n", + "185 Uruguay 115 35 220 \n", + "186 Uzbekistan 25 101 8 \n", + "187 Vanuatu 21 18 11 \n", + "188 Venezuela 333 100 3 \n", + "189 Vietnam 111 2 1 \n", + "190 Yemen 6 0 0 \n", + "191 Zambia 32 19 4 \n", + "192 Zimbabwe 64 18 4 \n", + "\n", + " total_litres_of_pure_alcohol continent \n", + "0 0.0 AS \n", + "1 4.9 EU \n", + "2 0.7 AF \n", + "3 12.4 EU \n", + "4 5.9 AF \n", + "5 4.9 NaN \n", + "6 8.3 SA \n", + "7 3.8 EU \n", + "8 10.4 OC \n", + "9 9.7 EU \n", + "10 1.3 EU \n", + "11 6.3 NaN \n", + "12 2.0 AS \n", + "13 0.0 AS \n", + "14 6.3 NaN \n", + "15 14.4 EU \n", + "16 10.5 EU \n", + "17 6.8 NaN \n", + "18 1.1 AF \n", + "19 0.4 AS \n", + "20 3.8 SA \n", + "21 4.6 EU \n", + "22 5.4 AF \n", + "23 7.2 SA \n", + "24 0.6 AS \n", + "25 10.3 EU \n", + "26 4.3 AF \n", + "27 6.3 AF \n", + "28 4.0 AF \n", + "29 4.0 AF \n", + ".. ... ... \n", + "163 5.6 SA \n", + "164 4.7 AF \n", + "165 7.2 EU \n", + "166 10.2 EU \n", + "167 1.0 AS \n", + "168 0.3 AS \n", + "169 6.4 AS \n", + "170 3.9 EU \n", + "171 0.1 AS \n", + "172 1.3 AF \n", + "173 1.1 OC \n", + "174 6.4 NaN \n", + "175 1.3 AF \n", + "176 1.4 AS \n", + "177 2.2 AS \n", + "178 1.0 OC \n", + "179 8.3 AF \n", + "180 8.9 EU \n", + "181 2.8 AS \n", + "182 10.4 EU \n", + "183 5.7 AF \n", + "184 8.7 NaN \n", + "185 6.6 SA \n", + "186 2.4 AS \n", + "187 0.9 OC \n", + "188 7.7 SA \n", + "189 2.0 AS \n", + "190 0.1 AS \n", + "191 2.5 AF \n", + "192 4.7 AF \n", + "\n", + "[193 rows x 6 columns]" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# examine the data\n", + "drinks # print the first 30 and last 30 rows" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servingsspirit_servingswine_servingstotal_litres_of_pure_alcoholcontinent
0Afghanistan0000.0AS
1Albania89132544.9EU
2Algeria250140.7AF
3Andorra24513831212.4EU
4Angola21757455.9AF
\n", + "
" + ], + "text/plain": [ + " country beer_servings spirit_servings wine_servings \\\n", + "0 Afghanistan 0 0 0 \n", + "1 Albania 89 132 54 \n", + "2 Algeria 25 0 14 \n", + "3 Andorra 245 138 312 \n", + "4 Angola 217 57 45 \n", + "\n", + " total_litres_of_pure_alcohol continent \n", + "0 0.0 AS \n", + "1 4.9 EU \n", + "2 0.7 AF \n", + "3 12.4 EU \n", + "4 5.9 AF " + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "drinks.head() # print the first 5 rows" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servingsspirit_servingswine_servingstotal_litres_of_pure_alcoholcontinent
188Venezuela33310037.7SA
189Vietnam111212.0AS
190Yemen6000.1AS
191Zambia321942.5AF
192Zimbabwe641844.7AF
\n", + "
" + ], + "text/plain": [ + " country beer_servings spirit_servings wine_servings \\\n", + "188 Venezuela 333 100 3 \n", + "189 Vietnam 111 2 1 \n", + "190 Yemen 6 0 0 \n", + "191 Zambia 32 19 4 \n", + "192 Zimbabwe 64 18 4 \n", + "\n", + " total_litres_of_pure_alcohol continent \n", + "188 7.7 SA \n", + "189 2.0 AS \n", + "190 0.1 AS \n", + "191 2.5 AF \n", + "192 4.7 AF " + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "drinks.tail() # print the last 5 rows" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
beer_servingsspirit_servingswine_servingstotal_litres_of_pure_alcohol
count193.000000193.000000193.000000193.000000
mean106.16062280.99481949.4507774.717098
std101.14310388.28431279.6975983.773298
min0.0000000.0000000.0000000.000000
25%20.0000004.0000001.0000001.300000
50%76.00000056.0000008.0000004.200000
75%188.000000128.00000059.0000007.200000
max376.000000438.000000370.00000014.400000
\n", + "
" + ], + "text/plain": [ + " beer_servings spirit_servings wine_servings \\\n", + "count 193.000000 193.000000 193.000000 \n", + "mean 106.160622 80.994819 49.450777 \n", + "std 101.143103 88.284312 79.697598 \n", + "min 0.000000 0.000000 0.000000 \n", + "25% 20.000000 4.000000 1.000000 \n", + "50% 76.000000 56.000000 8.000000 \n", + "75% 188.000000 128.000000 59.000000 \n", + "max 376.000000 438.000000 370.000000 \n", + "\n", + " total_litres_of_pure_alcohol \n", + "count 193.000000 \n", + "mean 4.717098 \n", + "std 3.773298 \n", + "min 0.000000 \n", + "25% 1.300000 \n", + "50% 4.200000 \n", + "75% 7.200000 \n", + "max 14.400000 " + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "drinks.describe() # describe any numeric columns" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Index([u'country', u'beer_servings', u'spirit_servings', u'wine_servings',\n", + " u'total_litres_of_pure_alcohol', u'continent'],\n", + " dtype='object')" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "drinks.columns # get series of column names" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ab
013
124
\n", + "
" + ], + "text/plain": [ + " a b\n", + "0 1 3\n", + "1 2 4" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Note: the dataframe is like a more complicated dictionary where the \n", + "# column names are the keys and the column itself is the value\n", + "\n", + "d = {'a':[1,2], 'b':[3,4]}\n", + "pd.DataFrame(d)" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(193, 6)" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "drinks.shape # tuple of (#rows, #cols)" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "country 0\n", + "beer_servings 0\n", + "spirit_servings 0\n", + "wine_servings 0\n", + "total_litres_of_pure_alcohol 0\n", + "continent 23\n", + "dtype: int64" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# find missing values in a DataFrame\n", + "drinks.isnull() # DataFrame of booleans\n", + "drinks.isnull().sum() # convert booleans to integers and add" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servingsspirit_servingswine_servingstotal_litres_of_pure_alcoholcontinent
5Antigua & Barbuda102128454.9NaN
11Bahamas122176516.3NaN
14Barbados143173366.3NaN
17Belize26311486.8NaN
32Canada2401221008.2NaN
41Costa Rica14987114.4NaN
43Cuba9313754.2NaN
50Dominica52286266.6NaN
51Dominican Republic19314796.2NaN
54El Salvador526922.2NaN
68Grenada1994382811.9NaN
69Guatemala536922.2NaN
73Haiti132615.9NaN
74Honduras699823.0NaN
84Jamaica829793.4NaN
109Mexico2386855.5NaN
122Nicaragua7811813.5NaN
130Panama285104187.2NaN
143St. Kitts & Nevis194205327.7NaN
144St. Lucia1713157110.1NaN
145St. Vincent & the Grenadines120221116.3NaN
174Trinidad & Tobago19715676.4NaN
184USA249158848.7NaN
\n", + "
" + ], + "text/plain": [ + " country beer_servings spirit_servings \\\n", + "5 Antigua & Barbuda 102 128 \n", + "11 Bahamas 122 176 \n", + "14 Barbados 143 173 \n", + "17 Belize 263 114 \n", + "32 Canada 240 122 \n", + "41 Costa Rica 149 87 \n", + "43 Cuba 93 137 \n", + "50 Dominica 52 286 \n", + "51 Dominican Republic 193 147 \n", + "54 El Salvador 52 69 \n", + "68 Grenada 199 438 \n", + "69 Guatemala 53 69 \n", + "73 Haiti 1 326 \n", + "74 Honduras 69 98 \n", + "84 Jamaica 82 97 \n", + "109 Mexico 238 68 \n", + "122 Nicaragua 78 118 \n", + "130 Panama 285 104 \n", + "143 St. Kitts & Nevis 194 205 \n", + "144 St. Lucia 171 315 \n", + "145 St. Vincent & the Grenadines 120 221 \n", + "174 Trinidad & Tobago 197 156 \n", + "184 USA 249 158 \n", + "\n", + " wine_servings total_litres_of_pure_alcohol continent \n", + "5 45 4.9 NaN \n", + "11 51 6.3 NaN \n", + "14 36 6.3 NaN \n", + "17 8 6.8 NaN \n", + "32 100 8.2 NaN \n", + "41 11 4.4 NaN \n", + "43 5 4.2 NaN \n", + "50 26 6.6 NaN \n", + "51 9 6.2 NaN \n", + "54 2 2.2 NaN \n", + "68 28 11.9 NaN \n", + "69 2 2.2 NaN \n", + "73 1 5.9 NaN \n", + "74 2 3.0 NaN \n", + "84 9 3.4 NaN \n", + "109 5 5.5 NaN \n", + "122 1 3.5 NaN \n", + "130 18 7.2 NaN \n", + "143 32 7.7 NaN \n", + "144 71 10.1 NaN \n", + "145 11 6.3 NaN \n", + "174 7 6.4 NaN \n", + "184 84 8.7 NaN " + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# So we have 23 missing continent values, that's a no bueno situation\n", + "\n", + "''' SELECT * from drinks where continent is NULL '''\n", + "drinks[drinks['continent'].isnull()] # DataFrame of values with null continent value\n", + "\n", + "# Anyone have any thoughts?\n" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servingsspirit_servingswine_servingstotal_litres_of_pure_alcoholcontinent
0Afghanistan0000.0AS
1Albania89132544.9EU
2Algeria250140.7AF
3Andorra24513831212.4EU
4Angola21757455.9AF
5Antigua & Barbuda102128454.9NA
6Argentina193252218.3SA
7Armenia21179113.8EU
8Australia2617221210.4OC
9Austria279751919.7EU
10Azerbaijan214651.3EU
11Bahamas122176516.3NA
12Bahrain426372.0AS
13Bangladesh0000.0AS
14Barbados143173366.3NA
15Belarus1423734214.4EU
16Belgium2958421210.5EU
17Belize26311486.8NA
18Benin344131.1AF
19Bhutan23000.4AS
20Bolivia1674183.8SA
21Bosnia-Herzegovina7617384.6EU
22Botswana17335355.4AF
23Brazil245145167.2SA
24Brunei31210.6AS
25Bulgaria2312529410.3EU
26Burkina Faso25774.3AF
27Burundi88006.3AF
28Cote d'Ivoire37174.0AF
29Cabo Verde14456164.0AF
.....................
163Suriname12817875.6SA
164Swaziland90224.7AF
165Sweden152601867.2EU
166Switzerland18510028010.2EU
167Syria535161.0AS
168Tajikistan21500.3AS
169Thailand9925816.4AS
170Macedonia10627863.9EU
171Timor-Leste1140.1AS
172Togo362191.3AF
173Tonga362151.1OC
174Trinidad & Tobago19715676.4NA
175Tunisia513201.3AF
176Turkey512271.4AS
177Turkmenistan1971322.2AS
178Tuvalu64191.0OC
179Uganda45908.3AF
180Ukraine206237458.9EU
181United Arab Emirates1613552.8AS
182United Kingdom21912619510.4EU
183Tanzania36615.7AF
184USA249158848.7NA
185Uruguay115352206.6SA
186Uzbekistan2510182.4AS
187Vanuatu2118110.9OC
188Venezuela33310037.7SA
189Vietnam111212.0AS
190Yemen6000.1AS
191Zambia321942.5AF
192Zimbabwe641844.7AF
\n", + "

193 rows × 6 columns

\n", + "
" + ], + "text/plain": [ + " country beer_servings spirit_servings wine_servings \\\n", + "0 Afghanistan 0 0 0 \n", + "1 Albania 89 132 54 \n", + "2 Algeria 25 0 14 \n", + "3 Andorra 245 138 312 \n", + "4 Angola 217 57 45 \n", + "5 Antigua & Barbuda 102 128 45 \n", + "6 Argentina 193 25 221 \n", + "7 Armenia 21 179 11 \n", + "8 Australia 261 72 212 \n", + "9 Austria 279 75 191 \n", + "10 Azerbaijan 21 46 5 \n", + "11 Bahamas 122 176 51 \n", + "12 Bahrain 42 63 7 \n", + "13 Bangladesh 0 0 0 \n", + "14 Barbados 143 173 36 \n", + "15 Belarus 142 373 42 \n", + "16 Belgium 295 84 212 \n", + "17 Belize 263 114 8 \n", + "18 Benin 34 4 13 \n", + "19 Bhutan 23 0 0 \n", + "20 Bolivia 167 41 8 \n", + "21 Bosnia-Herzegovina 76 173 8 \n", + "22 Botswana 173 35 35 \n", + "23 Brazil 245 145 16 \n", + "24 Brunei 31 2 1 \n", + "25 Bulgaria 231 252 94 \n", + "26 Burkina Faso 25 7 7 \n", + "27 Burundi 88 0 0 \n", + "28 Cote d'Ivoire 37 1 7 \n", + "29 Cabo Verde 144 56 16 \n", + ".. ... ... ... ... \n", + "163 Suriname 128 178 7 \n", + "164 Swaziland 90 2 2 \n", + "165 Sweden 152 60 186 \n", + "166 Switzerland 185 100 280 \n", + "167 Syria 5 35 16 \n", + "168 Tajikistan 2 15 0 \n", + "169 Thailand 99 258 1 \n", + "170 Macedonia 106 27 86 \n", + "171 Timor-Leste 1 1 4 \n", + "172 Togo 36 2 19 \n", + "173 Tonga 36 21 5 \n", + "174 Trinidad & Tobago 197 156 7 \n", + "175 Tunisia 51 3 20 \n", + "176 Turkey 51 22 7 \n", + "177 Turkmenistan 19 71 32 \n", + "178 Tuvalu 6 41 9 \n", + "179 Uganda 45 9 0 \n", + "180 Ukraine 206 237 45 \n", + "181 United Arab Emirates 16 135 5 \n", + "182 United Kingdom 219 126 195 \n", + "183 Tanzania 36 6 1 \n", + "184 USA 249 158 84 \n", + "185 Uruguay 115 35 220 \n", + "186 Uzbekistan 25 101 8 \n", + "187 Vanuatu 21 18 11 \n", + "188 Venezuela 333 100 3 \n", + "189 Vietnam 111 2 1 \n", + "190 Yemen 6 0 0 \n", + "191 Zambia 32 19 4 \n", + "192 Zimbabwe 64 18 4 \n", + "\n", + " total_litres_of_pure_alcohol continent \n", + "0 0.0 AS \n", + "1 4.9 EU \n", + "2 0.7 AF \n", + "3 12.4 EU \n", + "4 5.9 AF \n", + "5 4.9 NA \n", + "6 8.3 SA \n", + "7 3.8 EU \n", + "8 10.4 OC \n", + "9 9.7 EU \n", + "10 1.3 EU \n", + "11 6.3 NA \n", + "12 2.0 AS \n", + "13 0.0 AS \n", + "14 6.3 NA \n", + "15 14.4 EU \n", + "16 10.5 EU \n", + "17 6.8 NA \n", + "18 1.1 AF \n", + "19 0.4 AS \n", + "20 3.8 SA \n", + "21 4.6 EU \n", + "22 5.4 AF \n", + "23 7.2 SA \n", + "24 0.6 AS \n", + "25 10.3 EU \n", + "26 4.3 AF \n", + "27 6.3 AF \n", + "28 4.0 AF \n", + "29 4.0 AF \n", + ".. ... ... \n", + "163 5.6 SA \n", + "164 4.7 AF \n", + "165 7.2 EU \n", + "166 10.2 EU \n", + "167 1.0 AS \n", + "168 0.3 AS \n", + "169 6.4 AS \n", + "170 3.9 EU \n", + "171 0.1 AS \n", + "172 1.3 AF \n", + "173 1.1 OC \n", + "174 6.4 NA \n", + "175 1.3 AF \n", + "176 1.4 AS \n", + "177 2.2 AS \n", + "178 1.0 OC \n", + "179 8.3 AF \n", + "180 8.9 EU \n", + "181 2.8 AS \n", + "182 10.4 EU \n", + "183 5.7 AF \n", + "184 8.7 NA \n", + "185 6.6 SA \n", + "186 2.4 AS \n", + "187 0.9 OC \n", + "188 7.7 SA \n", + "189 2.0 AS \n", + "190 0.1 AS \n", + "191 2.5 AF \n", + "192 4.7 AF \n", + "\n", + "[193 rows x 6 columns]" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Pandas isn't brilliant, it saw the \"NA\" string and assumed it meant a null value\n", + "\n", + "# handling missing values\n", + "drinks.dropna() # drop a row if ANY values are missing\n", + "drinks.fillna(value='NA') # fill in missing values" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "country 0\n", + "beer_servings 0\n", + "spirit_servings 0\n", + "wine_servings 0\n", + "total_litres_of_pure_alcohol 0\n", + "continent 0\n", + "dtype: int64" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# fix the original import, this time using a live url!\n", + "drinks = pd.read_csv('https://raw.githubusercontent.com/sinanuozdemir/sfdat28/master/data/drinks.csv', na_filter=False)\n", + "drinks.isnull().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 AS\n", + "1 EU\n", + "2 AF\n", + "3 EU\n", + "4 AF\n", + "5 NA\n", + "6 SA\n", + "7 EU\n", + "8 OC\n", + "9 EU\n", + "10 EU\n", + "11 NA\n", + "12 AS\n", + "13 AS\n", + "14 NA\n", + "15 EU\n", + "16 EU\n", + "17 NA\n", + "18 AF\n", + "19 AS\n", + "20 SA\n", + "21 EU\n", + "22 AF\n", + "23 SA\n", + "24 AS\n", + "25 EU\n", + "26 AF\n", + "27 AF\n", + "28 AF\n", + "29 AF\n", + " ..\n", + "163 SA\n", + "164 AF\n", + "165 EU\n", + "166 EU\n", + "167 AS\n", + "168 AS\n", + "169 AS\n", + "170 EU\n", + "171 AS\n", + "172 AF\n", + "173 OC\n", + "174 NA\n", + "175 AF\n", + "176 AS\n", + "177 AS\n", + "178 OC\n", + "179 AF\n", + "180 EU\n", + "181 AS\n", + "182 EU\n", + "183 AF\n", + "184 NA\n", + "185 SA\n", + "186 AS\n", + "187 OC\n", + "188 SA\n", + "189 AS\n", + "190 AS\n", + "191 AF\n", + "192 AF\n", + "Name: continent, dtype: object" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# selecting a column ('Series')\n", + "drinks['continent']\n", + "drinks.continent # equivalent\n", + "\n", + "# Note the dictionary like selection" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "pandas.core.series.Series" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "type(drinks.continent) # Series if pandas equivalent to list" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "count 193\n", + "unique 6\n", + "top AF\n", + "freq 53\n", + "Name: continent, dtype: object" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# summarizing a non-numeric column\n", + "drinks.continent.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "AF 53\n", + "EU 45\n", + "AS 44\n", + "NA 23\n", + "OC 16\n", + "SA 12\n", + "Name: continent, dtype: int64" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "drinks.continent.value_counts()" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servings
0Afghanistan0
1Albania89
2Algeria25
3Andorra245
4Angola217
\n", + "
" + ], + "text/plain": [ + " country beer_servings\n", + "0 Afghanistan 0\n", + "1 Albania 89\n", + "2 Algeria 25\n", + "3 Andorra 245\n", + "4 Angola 217" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "\n", + "'''\n", + "note the double square bracket\n", + "the outer pair is used like in a python dictionary\n", + " to select\n", + "the inner pair is a list!\n", + "\n", + "so in all, the double use of square brackets is telling\n", + "the dataframe to select a list!\n", + "'''\n", + "# selecting multiple columns\n", + "''' SELECT country,beer_servings from drinks '''\n", + "drinks[['country', 'beer_servings']].head()\n", + "\n", + "\n", + "# remember the .head() just shows us the first 5 rows" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servings
0Afghanistan0
1Albania89
2Algeria25
3Andorra245
4Angola217
\n", + "
" + ], + "text/plain": [ + " country beer_servings\n", + "0 Afghanistan 0\n", + "1 Albania 89\n", + "2 Algeria 25\n", + "3 Andorra 245\n", + "4 Angola 217" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "my_cols = ['country', 'beer_servings']\n", + "drinks[my_cols].head()" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servingsspirit_servingswine_servingstotal_litres_of_pure_alcoholcontinenttotal_servings
0Afghanistan0000.0AS0
1Albania89132544.9EU275
2Algeria250140.7AF39
3Andorra24513831212.4EU695
4Angola21757455.9AF319
\n", + "
" + ], + "text/plain": [ + " country beer_servings spirit_servings wine_servings \\\n", + "0 Afghanistan 0 0 0 \n", + "1 Albania 89 132 54 \n", + "2 Algeria 25 0 14 \n", + "3 Andorra 245 138 312 \n", + "4 Angola 217 57 45 \n", + "\n", + " total_litres_of_pure_alcohol continent total_servings \n", + "0 0.0 AS 0 \n", + "1 4.9 EU 275 \n", + "2 0.7 AF 39 \n", + "3 12.4 EU 695 \n", + "4 5.9 AF 319 " + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# add a new column as a function of existing columns\n", + "drinks['total_servings'] = drinks.beer_servings + drinks.spirit_servings + drinks.wine_servings\n", + "drinks.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servingsspirit_servingswine_servingstotal_litres_of_pure_alcoholcontinenttotal_servings
1Albania89132544.9EU275
3Andorra24513831212.4EU695
7Armenia21179113.8EU211
9Austria279751919.7EU545
10Azerbaijan214651.3EU72
\n", + "
" + ], + "text/plain": [ + " country beer_servings spirit_servings wine_servings \\\n", + "1 Albania 89 132 54 \n", + "3 Andorra 245 138 312 \n", + "7 Armenia 21 179 11 \n", + "9 Austria 279 75 191 \n", + "10 Azerbaijan 21 46 5 \n", + "\n", + " total_litres_of_pure_alcohol continent total_servings \n", + "1 4.9 EU 275 \n", + "3 12.4 EU 695 \n", + "7 3.8 EU 211 \n", + "9 9.7 EU 545 \n", + "10 1.3 EU 72 " + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# logical filtering and sorting\n", + "\n", + "'''\n", + "How it works:\n", + " drinks.continent=='EU' by itself returns a bunch\n", + " of Trues and Falses\n", + " \n", + "drinks.continent=='EU'\n", + "\n", + "See?\n", + "\n", + "\n", + "when you wrap drinks around it with square brackets\n", + "you're telling the drinks dataframe to select\n", + "only those that are True, and not the False ones\n", + "\n", + "drinks[drinks.continent=='EU']\n", + "'''\n", + "drinks.continent=='EU' # this is a series of T and F\n", + "\n", + "# we put tht series of Trues and Falses directly into the square brackets of justice\n", + "drinks[drinks.continent=='EU'] .head()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrytotal_servings
5Antigua & Barbuda275
11Bahamas349
14Barbados352
17Belize385
32Canada462
41Costa Rica247
43Cuba235
50Dominica364
51Dominican Republic349
54El Salvador123
68Grenada665
69Guatemala124
73Haiti328
74Honduras169
84Jamaica188
109Mexico311
122Nicaragua197
130Panama407
143St. Kitts & Nevis431
144St. Lucia557
145St. Vincent & the Grenadines352
174Trinidad & Tobago360
184USA491
\n", + "
" + ], + "text/plain": [ + " country total_servings\n", + "5 Antigua & Barbuda 275\n", + "11 Bahamas 349\n", + "14 Barbados 352\n", + "17 Belize 385\n", + "32 Canada 462\n", + "41 Costa Rica 247\n", + "43 Cuba 235\n", + "50 Dominica 364\n", + "51 Dominican Republic 349\n", + "54 El Salvador 123\n", + "68 Grenada 665\n", + "69 Guatemala 124\n", + "73 Haiti 328\n", + "74 Honduras 169\n", + "84 Jamaica 188\n", + "109 Mexico 311\n", + "122 Nicaragua 197\n", + "130 Panama 407\n", + "143 St. Kitts & Nevis 431\n", + "144 St. Lucia 557\n", + "145 St. Vincent & the Grenadines 352\n", + "174 Trinidad & Tobago 360\n", + "184 USA 491" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# North American countries with total servings\n", + "# drinks[['country', 'total_servings']][drinks.continent=='NA']\n", + "\n", + "new_df = drinks[['country', 'total_servings']] # selection of two columns\n", + "new_df[drinks.continent=='NA']" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/sinanozdemir/anaconda/envs/sfdat26-env/lib/python2.7/site-packages/ipykernel/__main__.py:2: FutureWarning: by argument to sort_index is deprecated, pls use .sort_values(by=...)\n", + " from ipykernel import kernelapp as app\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrytotal_servings
54El Salvador123
69Guatemala124
74Honduras169
84Jamaica188
122Nicaragua197
43Cuba235
41Costa Rica247
5Antigua & Barbuda275
109Mexico311
73Haiti328
51Dominican Republic349
11Bahamas349
14Barbados352
145St. Vincent & the Grenadines352
174Trinidad & Tobago360
50Dominica364
17Belize385
130Panama407
143St. Kitts & Nevis431
32Canada462
184USA491
144St. Lucia557
68Grenada665
\n", + "
" + ], + "text/plain": [ + " country total_servings\n", + "54 El Salvador 123\n", + "69 Guatemala 124\n", + "74 Honduras 169\n", + "84 Jamaica 188\n", + "122 Nicaragua 197\n", + "43 Cuba 235\n", + "41 Costa Rica 247\n", + "5 Antigua & Barbuda 275\n", + "109 Mexico 311\n", + "73 Haiti 328\n", + "51 Dominican Republic 349\n", + "11 Bahamas 349\n", + "14 Barbados 352\n", + "145 St. Vincent & the Grenadines 352\n", + "174 Trinidad & Tobago 360\n", + "50 Dominica 364\n", + "17 Belize 385\n", + "130 Panama 407\n", + "143 St. Kitts & Nevis 431\n", + "32 Canada 462\n", + "184 USA 491\n", + "144 St. Lucia 557\n", + "68 Grenada 665" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# same thing, sorted by total_servings\n", + "drinks[['country', 'total_servings']][drinks.continent=='NA'].sort_index(by='total_servings')" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrytotal_servings
68 Grenada 665
144 St. Lucia 557
184 USA 491
32 Canada 462
143 St. Kitts & Nevis 431
130 Panama 407
17 Belize 385
50 Dominica 364
174 Trinidad & Tobago 360
14 Barbados 352
145 St. Vincent & the Grenadines 352
51 Dominican Republic 349
11 Bahamas 349
73 Haiti 328
109 Mexico 311
5 Antigua & Barbuda 275
41 Costa Rica 247
43 Cuba 235
122 Nicaragua 197
84 Jamaica 188
74 Honduras 169
69 Guatemala 124
54 El Salvador 123
\n", + "
" + ], + "text/plain": [ + " country total_servings\n", + "68 Grenada 665\n", + "144 St. Lucia 557\n", + "184 USA 491\n", + "32 Canada 462\n", + "143 St. Kitts & Nevis 431\n", + "130 Panama 407\n", + "17 Belize 385\n", + "50 Dominica 364\n", + "174 Trinidad & Tobago 360\n", + "14 Barbados 352\n", + "145 St. Vincent & the Grenadines 352\n", + "51 Dominican Republic 349\n", + "11 Bahamas 349\n", + "73 Haiti 328\n", + "109 Mexico 311\n", + "5 Antigua & Barbuda 275\n", + "41 Costa Rica 247\n", + "43 Cuba 235\n", + "122 Nicaragua 197\n", + "84 Jamaica 188\n", + "74 Honduras 169\n", + "69 Guatemala 124\n", + "54 El Salvador 123" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#sorted in reverse order\n", + "drinks[['country', 'total_servings']][drinks.continent=='NA'].sort_index(by='total_servings', ascending = False)" + ] + }, + { + "cell_type": "code", + "execution_count": 97, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/sinanozdemir/anaconda/envs/sfdat26-env/lib/python2.7/site-packages/ipykernel/__main__.py:2: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n", + " from ipykernel import kernelapp as app\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servingsspirit_servingswine_servingstotal_litres_of_pure_alcoholcontinenttotal_servings
3Andorra24513831212.4EU695
\n", + "
" + ], + "text/plain": [ + " country beer_servings spirit_servings wine_servings \\\n", + "3 Andorra 245 138 312 \n", + "\n", + " total_litres_of_pure_alcohol continent total_servings \n", + "3 12.4 EU 695 " + ] + }, + "execution_count": 97, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# contries with wine servings over 300 and total liters over 12\n", + "drinks[drinks.wine_servings > 300][drinks.total_litres_of_pure_alcohol > 12]" + ] + }, + { + "cell_type": "code", + "execution_count": 98, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servingsspirit_servingswine_servingstotal_litres_of_pure_alcoholcontinenttotal_servings
3Andorra24513831212.4EU695
\n", + "
" + ], + "text/plain": [ + " country beer_servings spirit_servings wine_servings \\\n", + "3 Andorra 245 138 312 \n", + "\n", + " total_litres_of_pure_alcohol continent total_servings \n", + "3 12.4 EU 695 " + ] + }, + "execution_count": 98, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Same result but using python logic operators\n", + "# Note the paranthesis around each filter when using logical operators\n", + "drinks[(drinks.wine_servings > 300) & (drinks.total_litres_of_pure_alcohol > 12)]" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servingsspirit_servingswine_servingstotal_litres_of_pure_alcoholcontinenttotal_servings
3Andorra24513831212.4EU695
6Argentina193252218.3SA439
35Chile1301241727.6SA426
40Cook Islands0254745.9OC328
42Croatia2308725410.2EU571
48Denmark2248127810.4EU583
55Equatorial Guinea9202335.8AF325
61France12715137011.8EU648
64Georgia521001495.4EU301
67Greece1331122188.3EU463
83Italy85422376.5EU364
92Laos6201236.2AS185
94Lebanon2055311.9AS106
99Luxembourg23613327111.4EU640
113Montenegro311141284.9EU273
136Portugal1946733911.0EU600
137Qatar14270.9AS50
148Sao Tome & Principe56381404.2AF234
156Slovenia2705127610.6EU597
165Sweden152601867.2EU398
166Switzerland18510028010.2EU565
167Syria535161.0AS56
171Timor-Leste1140.1AS6
177Turkmenistan1971322.2AS122
178Tuvalu64191.0OC56
185Uruguay115352206.6SA370
\n", + "
" + ], + "text/plain": [ + " country beer_servings spirit_servings wine_servings \\\n", + "3 Andorra 245 138 312 \n", + "6 Argentina 193 25 221 \n", + "35 Chile 130 124 172 \n", + "40 Cook Islands 0 254 74 \n", + "42 Croatia 230 87 254 \n", + "48 Denmark 224 81 278 \n", + "55 Equatorial Guinea 92 0 233 \n", + "61 France 127 151 370 \n", + "64 Georgia 52 100 149 \n", + "67 Greece 133 112 218 \n", + "83 Italy 85 42 237 \n", + "92 Laos 62 0 123 \n", + "94 Lebanon 20 55 31 \n", + "99 Luxembourg 236 133 271 \n", + "113 Montenegro 31 114 128 \n", + "136 Portugal 194 67 339 \n", + "137 Qatar 1 42 7 \n", + "148 Sao Tome & Principe 56 38 140 \n", + "156 Slovenia 270 51 276 \n", + "165 Sweden 152 60 186 \n", + "166 Switzerland 185 100 280 \n", + "167 Syria 5 35 16 \n", + "171 Timor-Leste 1 1 4 \n", + "177 Turkmenistan 19 71 32 \n", + "178 Tuvalu 6 41 9 \n", + "185 Uruguay 115 35 220 \n", + "\n", + " total_litres_of_pure_alcohol continent total_servings \n", + "3 12.4 EU 695 \n", + "6 8.3 SA 439 \n", + "35 7.6 SA 426 \n", + "40 5.9 OC 328 \n", + "42 10.2 EU 571 \n", + "48 10.4 EU 583 \n", + "55 5.8 AF 325 \n", + "61 11.8 EU 648 \n", + "64 5.4 EU 301 \n", + "67 8.3 EU 463 \n", + "83 6.5 EU 364 \n", + "92 6.2 AS 185 \n", + "94 1.9 AS 106 \n", + "99 11.4 EU 640 \n", + "113 4.9 EU 273 \n", + "136 11.0 EU 600 \n", + "137 0.9 AS 50 \n", + "148 4.2 AF 234 \n", + "156 10.6 EU 597 \n", + "165 7.2 EU 398 \n", + "166 10.2 EU 565 \n", + "167 1.0 AS 56 \n", + "171 0.1 AS 6 \n", + "177 2.2 AS 122 \n", + "178 1.0 OC 56 \n", + "185 6.6 SA 370 " + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# contries with more wine servings than beer servings\n", + "drinks[drinks.wine_servings > drinks.beer_servings]" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 False\n", + "1 False\n", + "2 False\n", + "3 True\n", + "4 False\n", + "5 False\n", + "6 True\n", + "7 False\n", + "8 False\n", + "9 False\n", + "10 False\n", + "11 False\n", + "12 False\n", + "13 False\n", + "14 False\n", + "15 False\n", + "16 False\n", + "17 False\n", + "18 False\n", + "19 False\n", + "20 False\n", + "21 False\n", + "22 False\n", + "23 False\n", + "24 False\n", + "25 False\n", + "26 False\n", + "27 False\n", + "28 False\n", + "29 False\n", + " ... \n", + "163 False\n", + "164 False\n", + "165 True\n", + "166 True\n", + "167 True\n", + "168 False\n", + "169 False\n", + "170 False\n", + "171 True\n", + "172 False\n", + "173 False\n", + "174 False\n", + "175 False\n", + "176 False\n", + "177 True\n", + "178 True\n", + "179 False\n", + "180 False\n", + "181 False\n", + "182 False\n", + "183 False\n", + "184 False\n", + "185 True\n", + "186 False\n", + "187 False\n", + "188 False\n", + "189 False\n", + "190 False\n", + "191 False\n", + "192 False\n", + "dtype: bool" + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# to reiterate how the filter works:\n", + "drinks.wine_servings > drinks.beer_servings # is a series of T and F" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servingsspirit_servingswine_servingstotal_litres_of_pure_alcoholcontinenttotal_servings
98 Lithuania 343 244 56 12.9 EU 643
135 Poland 343 215 56 10.9 EU 614
65 Germany 346 117 175 11.3 EU 638
62 Gabon 347 98 59 8.9 AF 504
45 Czech Republic 361 170 134 11.8 EU 665
117 Namibia 376 3 1 6.8 AF 380
\n", + "
" + ], + "text/plain": [ + " country beer_servings spirit_servings wine_servings \\\n", + "98 Lithuania 343 244 56 \n", + "135 Poland 343 215 56 \n", + "65 Germany 346 117 175 \n", + "62 Gabon 347 98 59 \n", + "45 Czech Republic 361 170 134 \n", + "117 Namibia 376 3 1 \n", + "\n", + " total_litres_of_pure_alcohol continent total_servings \n", + "98 12.9 EU 643 \n", + "135 10.9 EU 614 \n", + "65 11.3 EU 638 \n", + "62 8.9 AF 504 \n", + "45 11.8 EU 665 \n", + "117 6.8 AF 380 " + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# last 5 elements of the dataframe sorted by beer servings\n", + "drinks.sort_index(by='beer_servings').tail(6)\n", + "# note tail took in an optional input of 6, showing us the last 6 rows" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "# Quiz\n", + "\n", + "# 1. List countries that drink more spirits than beer on average\n", + "\n", + "# 2. What are the top three beer drinking countries?\n", + "\n", + "# 3. What are the top three beer drinking countries in Europe?" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "# Answers below don't peak!\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "1 Albania\n", + "5 Antigua & Barbuda\n", + "7 Armenia\n", + "10 Azerbaijan\n", + "11 Bahamas\n", + "12 Bahrain\n", + "14 Barbados\n", + "15 Belarus\n", + "21 Bosnia-Herzegovina\n", + "25 Bulgaria\n", + "30 Cambodia\n", + "36 China\n", + "38 Comoros\n", + "40 Cook Islands\n", + "43 Cuba\n", + "49 Djibouti\n", + "50 Dominica\n", + "54 El Salvador\n", + "61 France\n", + "64 Georgia\n", + "68 Grenada\n", + "69 Guatemala\n", + "71 Guinea-Bissau\n", + "72 Guyana\n", + "73 Haiti\n", + "74 Honduras\n", + "77 India\n", + "82 Israel\n", + "84 Jamaica\n", + "85 Japan\n", + " ... \n", + "89 Kiribati\n", + "91 Kyrgyzstan\n", + "94 Lebanon\n", + "96 Liberia\n", + "101 Malawi\n", + "112 Mongolia\n", + "113 Montenegro\n", + "119 Nepal\n", + "122 Nicaragua\n", + "125 Niue\n", + "134 Philippines\n", + "137 Qatar\n", + "139 Moldova\n", + "141 Russian Federation\n", + "143 St. Kitts & Nevis\n", + "144 St. Lucia\n", + "145 St. Vincent & the Grenadines\n", + "149 Saudi Arabia\n", + "155 Slovakia\n", + "161 Sri Lanka\n", + "162 Sudan\n", + "163 Suriname\n", + "167 Syria\n", + "168 Tajikistan\n", + "169 Thailand\n", + "177 Turkmenistan\n", + "178 Tuvalu\n", + "180 Ukraine\n", + "181 United Arab Emirates\n", + "186 Uzbekistan\n", + "Name: country, dtype: object" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 1. \n", + "drinks['country'][drinks.spirit_servings>drinks.beer_servings]" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/sinanozdemir/anaconda/envs/sfdat26-env/lib/python2.7/site-packages/ipykernel/__main__.py:2: FutureWarning: by argument to sort_index is deprecated, pls use .sort_values(by=...)\n", + " from ipykernel import kernelapp as app\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servings
62Gabon347
45Czech Republic361
117Namibia376
\n", + "
" + ], + "text/plain": [ + " country beer_servings\n", + "62 Gabon 347\n", + "45 Czech Republic 361\n", + "117 Namibia 376" + ] + }, + "execution_count": 39, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 2. \n", + "drinks[['country', 'beer_servings']].sort_index(by='beer_servings').tail(3)" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/sinanozdemir/anaconda/envs/sfdat26-env/lib/python2.7/site-packages/ipykernel/__main__.py:2: FutureWarning: by argument to sort_index is deprecated, pls use .sort_values(by=...)\n", + " from ipykernel import kernelapp as app\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
countrybeer_servings
45Czech Republic361
65Germany346
135Poland343
\n", + "
" + ], + "text/plain": [ + " country beer_servings\n", + "45 Czech Republic 361\n", + "65 Germany 346\n", + "135 Poland 343" + ] + }, + "execution_count": 40, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 3. \n", + "drinks[drinks.continent=='EU'][['country', 'beer_servings']].sort_index(by='beer_servings', ascending=False).head(3)" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "145.434782609\n" + ] + } + ], + "source": [ + "# average North American beer consumption\n", + "'''\n", + "Note the procedure:\n", + "drinks Dataframe\n", + "drinks.beer_servings one column (Series)\n", + "drinks.beer_servings[drinks.continent=='NA'] logical filtering\n", + "drinks.beer_servings[drinks.continent=='NA'].mean() mean of that filtered column\n", + "'''\n", + "\n", + "print drinks.beer_servings[drinks.continent=='NA'].mean()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "# average European beer consumption\n", + "drinks.beer_servings[drinks.continent=='EU'].mean()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "collapsed": true + }, + "source": [ + "**Split Apply Combine**\n", + "\n", + "\n", + "\n", + "Pandas uses the \"groupby\" command to split apply and combine" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "continent\n", + "AF 61.471698\n", + "AS 37.045455\n", + "EU 193.777778\n", + "NA 145.434783\n", + "OC 89.687500\n", + "SA 175.083333\n", + "Name: beer_servings, dtype: float64" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# for each continent, calculate mean beer servings\n", + "drinks.groupby('continent').beer_servings.mean()" + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "AF 53\n", + "EU 45\n", + "AS 44\n", + "NA 23\n", + "OC 16\n", + "SA 12\n", + "Name: continent, dtype: int64" + ] + }, + "execution_count": 47, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# for each continent, count number of occurrences\n", + "drinks.groupby('continent').continent.count()\n", + "drinks.continent.value_counts() #same thing" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "continent\n", + "AF 94.075472\n", + "AS 106.954545\n", + "EU 468.555556\n", + "NA 335.695652\n", + "OC 183.750000\n", + "SA 352.250000\n", + "Name: total_servings, dtype: float64" + ] + }, + "execution_count": 48, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# We can apply any function using .apply\n", + "drinks.groupby('continent').total_servings.apply(lambda x: x.mean()) # mean" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "# on lambda functions:\n", + "\n", + "'''\n", + "Lamda Functions are ananonymous functions\n", + "\n", + "f = lambda x: x + 1 IS THE SAME AS \n", + "def f(x): return x + 1\n", + "'''" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "continent\n", + "AF 114.040622\n", + "AS 132.630446\n", + "EU 176.921857\n", + "NA 134.437696\n", + "OC 175.450848\n", + "SA 81.923606\n", + "Name: total_servings, dtype: float64" + ] + }, + "execution_count": 49, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# note x here is an entire series\n", + "drinks.groupby('continent').total_servings.apply(lambda x: x.std()) # standard deviation" + ] + }, + { + "cell_type": "code", + "execution_count": 50, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "continent\n", + "AF 0\n", + "AS 0\n", + "EU 0\n", + "NA 123\n", + "OC 0\n", + "SA 216\n", + "Name: total_servings, dtype: int64\n", + "continent\n", + "AF 504\n", + "AS 646\n", + "EU 695\n", + "NA 665\n", + "OC 545\n", + "SA 439\n", + "Name: total_servings, dtype: int64\n" + ] + } + ], + "source": [ + "# for each continent, calculate the min, max, and range for total servings\n", + "print drinks.groupby('continent').total_servings.min()\n", + "print drinks.groupby('continent').total_servings.max()" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "continent\n", + "AF 504\n", + "AS 646\n", + "EU 695\n", + "NA 542\n", + "OC 545\n", + "SA 223\n", + "Name: total_servings, dtype: int64" + ] + }, + "execution_count": 51, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# What does this do?\n", + "drinks.groupby('continent').total_servings.apply(lambda x: x.max() - x.min())" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 52, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXwAAAEeCAYAAACJ266bAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nEAn8iIhC/H/nV+EatLvFiAAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "'''\n", + "Plotting\n", + "'''\n", + "\n", + "# bar plot of number of countries in each continent\n", + "drinks.continent.value_counts().plot(kind='bar', title='Countries per Continent')\n", + "plt.xlabel('Continent')\n", + "plt.ylabel('Count')" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 53, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAEUCAYAAAA7l80JAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nMa4vzVaOAAAAAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# bar plot of average number of beer servings by continent\n", + "drinks.groupby('continent').beer_servings.mean().plot(kind='bar')" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 54, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAEACAYAAABI5zaHAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# histogram of beer servings\n", + "drinks.beer_servings.hist(bins=20)" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[,\n", + " ],\n", + " [,\n", + " ],\n", + " [,\n", + " ]], dtype=object)" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAEMCAYAAAAoB2Y1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# grouped histogram of beer servings\n", + "drinks.beer_servings.hist(by=drinks.continent)\n", + "\n", + "# stop and think, does this make sense\n" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[,\n", + " ],\n", + " [,\n", + " ],\n", + " [,\n", + " ]], dtype=object)" + ] + }, + "execution_count": 56, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAEMCAYAAAAoB2Y1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3X20XHV97/H3J0FjAgTDUw7lIUfsEiilDVjRFu/NxNYH\nSluptVrsklCEUlseCiwVuO2lsbaFPuRer8pavYAKVK4gvTx5EYELh161CBXSaA1PxRPUJgeQYBJC\nApjv/WPvw0wmc87Ze+Y3M3vOfF5rzTpz9uz5nu+Z2b/f7Pnt7/5tRQRmZjYc5vQ7ATMz6x13+mZm\nQ8SdvpnZEHGnb2Y2RNzpm5kNEXf6ZmZDxJ2+mdkQcaffR5LGJD0r6VUNyz4nabukTZI25z9/u595\nmnXbFG3hQEk3SHpa0kZJaySd3M88ZwN3+n0iaQnwVmAH8BtND18aEQsjYs/855d6n6FZb0zTFq4B\n1gEHA/sAHwQmep7gLONOv39OBv4Z+DxwSl8zMeuvqdrCm4CrImJbROyIiH+NiK/2Ib9ZxZ1+/5wM\n/ANwLfBOSfv1OR+zfpmqLfwzcJmk90s6uG/ZzTLu9PtA0luBQ4DrI+JB4HHgAw2rfCQf39wo6am+\nJGnWAzO0hd8G/gn4E+AJSQ9K+oX+ZDp7uNPvj5OBOyJiY/77/wJWNDz+NxGxd0Qsioj9e5+eWc9M\n2RYi4scRcVFEHAUsBv4VuLE/ac4e8iybvSXpNcAGsg/c5/PF84C9gKOBc4HvR8R/7U+GZr0xRVt4\nNfBaYGlEfLtp/SOBNcC+DR8SVtJu/U5gCP0m8DLw88BLDcuvJ9vrMRsW07WFFZJeJqvgeRhYAPwh\n8Lg7/M54eKf3TgY+GxE/jIinJm/AZ8jGMuf2Nz2znpmpLexJNpyzkWys/2B2LW+2kmYc3pE0j+xg\nyqvJvhncEBErJV0MnA5MHmi8KCJu72ayZmbWmUJj+pIWRMRWSXOBrwNnA8cDmyNiVZdzNDOzRAoN\n70TE1vzuPLK9/clPCnUjKTMz645Cnb6kOZIeIjvSfmdEPJA/dKak1ZKukLRX17I0M7MkSpVsSlpI\ndmDlLOBp4JmICEmfAA6IiA91J00zM0uhdJ2+pD8Fnm8cy88nTLo1In6uxfo+EcC6IiIGanjRbcG6\nqWh7mHF4R9K+k0M3kuYDbwceljTSsNp7gO9Mk0yS27JlyyoXq4o5VTVWypwGVdXek6rGqmJOVY5V\nRpGTsw4ArpI0h+xD4rqIuE3S1ZKWkk2HOg6cUXL7L210dLRysaqYU1Vjpcxp2FXx/U0Zq4o5VTlW\nGUUO5D5KdrZckFXrTH5QnEN2YHd+ftvWjQQbVfEFr2JOVY3lTj+dKr6/KWNVMacqxypjxk4/IrYD\nyyPiaGApcLykY4ELgLsi4jDgbuDCrmYK1Gq1ysWqYk5VjZUyp2FXxfc3Zawq5lTlWGWUrd5ZQHZ2\n7ofJ5sRYFhET+fj+WEQc3uI58au/+julEzv//DN429tqpZ9nw0ESMYAHcsuOv5oVUaY9FJpwLR/P\n/xbweuAzEfGApMURMQEQERskTTkF8G23lZ0u43Z+6qf+0Z2+mVlihTr9iNgBHD1Zp59Pcdq8yzLN\nLszfA6P5rZbfpvMM2aEEs8zY2BhjY2OMj48zPj7e73TaVqvVGB0dZXR0lFqt5iEva0sn7aHdOv2t\nwGlArWF4556IOKLF+jHt50FLn+K00x7l8ss/VfJ5Niw8vGNWV6Y9tFunvxa4hfpFjFcAN7eVrZmZ\n9Uwndfr3AddLOhVYB7yvi3mamVkCRer0NwLPAa8iq9PflC8/Czic7DJn+wJv6UaCZmaWTpE9/ZeB\n8yJitaQ9gG9JujN/bFV4Pn0zs4ExY6cfERvIzrwlIrZIWgscmD88UAfSzPpt/vzXTvv4fvuN8Mgj\nDzF//vweZWTDptSF0SWNkp2V+03grWTz6X8Q+Bfg/Ij4ceoEzWaTbdvGp318YmIJ27Ztc6dvXVO4\n08+Hdm4Azsn3+C8DPh7xynz6q4Ap5tOvUa5O32xns6VOH05kuraQ1UuYTa/rdfqSdgO+DHwlIj7Z\n4vEZ5tN3nb6lNah1+jO1hXnzFrF+/RMsWrSoR1nZbJC0Tj/3WeC7jR1+mfn0zcysGmYc3pF0IvBB\nYJukD5PNkXA6cIqkE8hKOX8MHNfNRM3MrHNF9vTvA46OiPnAfmRTMIyTnZD15xHxGrLx/NO6laSZ\nmaVRZD79DRGxOr+/hWwKhoOAdwNX5atdRXaEyszMKqxUqUBDyeZ9wE5TKwNTTq1sZmbVULjTby7Z\npNTUymZmVgVFL6KyG1mHf01ETM6mOTF5IZW8kuepqSPUcJ2+dWL21OnXcFuwTvWiTv9q4JmIOK9h\n2aXAsxFxqaSPAYsi4oIWz3WdviXnOn2zuqSXS5R0HPC7wLclPUS21V4EXIqnVjYzGyhFxvRPJavN\nnxMRR0fEMcCbgTXA3mRTK6+KiOe6l6aZmaVQpNP/HPDOFstXRcQx+e32xHmZmVkXFKnT/xrZhVSa\nDdR4qpmZlazTb3KmpNWSrpi8hq6ZmVVbu53+ZcChEbGU7AIrvnqWmdkAKHURlUkR8XTDr5cDt07/\njBquTbZOuE7frK6T9lC00xcNY/iSRvKpF6DQtMpjpZIya1ar1ajVaq/8Lg3qIaWxfidgs0An7aFI\nnf61ZLsj+0h6ErgYWC5pKbCDbMbNM8okbGZm/VFkT/8FYC7wyOSVsSTdBFwHLAHmA9u6lqGZmSXT\nbp3+BcBdEXEYcDdwYerEzMwsvXbr9D2XvpnZAGq3ZHN/z6VvZjZ42irZbGGGaTRruEzNOuGSTbO6\nXpRsNisxlz64TM065ZJNs7pO2kPR4Z2d6vSBW4BT8vsrgJubn2BmZtUzY6ef1+l/A3iDpCcl/R5w\nCfB2SS8BfwL8qqT7Uyb2hS98AUmlbyMjoynTMDObVWYc3omID0zx0K9IegJ4Y0S0moWzIy+8sJF2\nLrs7MTGoX/vNzLqvk1k2IRvy6TSGmZn1SKcddgB3SnpA0ukpEurcPA8L2aw3MjLqbdra0mnJ5nER\nsV7SfmSd/9r8ZK4+2o6HhWy2m5hYx0zbubdpa6WjTj8i1uc/n5Z0I3As0KLTr+HaZOuE6/TN6jpp\nD4oov1cMIGkB2cXSt0jaHbgDWBkRdzStF+X3vD8FnE07e+zZYYb2ntfua2G9J4mIGKhd2SJtYd68\nRaxf/wSLFi2aKRYzb+fepodFmfbQyZ7+YuDGbENmN+ALzR2+mZV3+OFLeeqpJ/udhs1SbR/IjYjv\nkc22OR+YR3u712bWJOvwY4ZbETMXNfhg7/Bpu9OXNAf4NNm0y0cCJ0k6PFVirY1VLtbYWJo4wxAr\nZU5WxGRRw9S3iYl1s35bGYZYZXRSsnks8FhErIuIl4Avkk253EVjXYzVXqnn8uVvb+t5kpg7d/em\nWMuTlZdWYeNsLitM+f9ZKvMKvS/N2+pU75s7/f7EKqOTTv9A4PsNv/8gX9ZF412MNfNeUevby20+\nL9ixY2vTshWFnpeV683w3yWscGk3Vr2sMP3/Z6lsp8j7suu22vp9S7XdFYlT9FyFKrSFbscqI9XU\nytNauPCoUutv3/4M27e3emQ8RTpdiJXKeLpIldw4U8UZXDO1hW3bXuxRJo3G00XqYadf9FyFaraF\n/nX6nZRsvgX4s4h4V/77BUBExKVN6/kAr3XFYJZsmnVH0fbQSac/F3gE+GVgPXA/cFJErG0roJmZ\ndV3bwzsR8RNJZ5KdlDUHuNIdvplZtbW9p29mZoPH0yKbmQ0Rd/pmZkPEnb6Z2RBxp29mNkTc6ZuZ\nDRF3+mZmQ8SdvpnZEHGnb2Y2RNzpm5kNEXf6PSZpXNJWSZskbc5//g9JF0u6psX6OyQd2o9czbop\nbwsTkuY3LPuQpHua1ntC0nd6n+Hs5E6/9wI4ISIWRsSe+c+zGx5rtb7ZbBRkfdAft1gOgKT/DOwH\nHCrpjT3MbdZyp98fZaYEHqjpg81K+hvgfEkLp3h8BXATcFt+3zrkTt/M+ulfyK5d+pHmB/Jhn/cC\nXwCuJbsOd08u/DSbudPvj5skPStpY/7zQ/1OyKyPLgbOlLRP0/LfArYBXwX+D9lU8Cf0OLdZx51+\nf7w7IvaOiEX5zyvJLrb7qsaVGvZqXup5hmY9EhH/BnwZuLDpoZOB6yOzHfjfeIinY/6q1B+txumf\nBH6tadmhZB3+D7uekVl//RnwIPB3AJIOBN4GvEnSe/N15gOvkbR3RDzblyxnAe/pV8ftwOGSflfS\nbpL2Bv4CuCEidvQ5N7Ouioh/B64DJivZPkh2OdY3AD+f394A/AA4qR85zhbu9Pvj1rw+f/L2jxHx\nNHA88AfAU8Aa4FngD/uZqFkXNZcjfxxYkN8/GfhMRDwdEU9N3oC/x0M8HZnxcomS5gH/BLyabDjo\nhohYKeli4HSyDgrgooi4vZvJmplZZwpdI1fSgojYKmku8HWyr2DHA5sjYlWXczQzs0QKDe9ExNb8\n7jyyvf3JTwqfOGRmNkAKdfqS5kh6CNgA3BkRD+QPnSlptaQrJO3VtSzNzCyJQsM7r6ycnSp9I3AW\n8DTwTESEpE8AB0SETzIyM6uwUp0+gKQ/BZ5vHMuXtAS4NSJ+rsX6njDMuiIiBmp40W3Buqloe5hx\neEfSvpNDN/lcGG8HHpY00rDae4Appz6NiCS3ZcuWVS5WFXOqaqyUOQ2qqr0nVY1VxZyqHKuMImfk\nHgBcJWkO2YfEdRFxm6SrJS0FdgDjwBklt//SRkdHKxerijlVNVbKnIZdFd/flLGqmFOVY5VR5EDu\no2RTAQRZtc7kB8U5ZAd25+e3bd1IsFEVX/Aq5lTVWO7006ni+5syVhVzqnKsMmbs9COb6Gh5RBwN\nLAWOl3QscAFwV0QcBtzNrpMlJVer1SoXq4o5VTVWypyGXRXf35SxqphTlWOVUbZ6ZwHZ2bkfBq4B\nlkXERD6+PxYRh7d4TpQdczKbiSRiAA/kui1YN5RpD53U6S+OiAmAiNgA7N9uwmZm1huFplaObJbH\noyfr9CUdya6TJU25C1Or1RgdHWV0dJRareav+Vba2NgYY2NjjI+PMz4+3u902ua2YCl00h7ardPf\nCpwG1BqGd+6JiCNarO+vtJach3fM6pIO70xRp78WuAU4JV9tBXBzW9mamVnPdFKnfx9wvaRTgXXA\n+7qYp5mZJVDkQO5G4Dmy67cK2JQvPws4HHge2Bd4SzcSNDOzdIpcRGUEGImI1ZL2AL4FvBt4PwXm\n0/c4pnWDx/TN6sq0hxmHd/JyzA35/S2S1gIHTv6ttrM0M7OeK3WNXEmjZGflfjNf5Pn0zcwGSKE6\nfYB8aOcG4Jx8j/8y4OMRr8ynvwpoOZ++a5OtU67TN6vrep2+pN2ALwNfiYhPtnh82vn0PY5pqXlM\n36wu+TQMwGeB7zZ2+GXm0zczs2ooUr1zItklEienTn4GOJ3sxKwTyEo5fwwcFxGPt3i+924sOe/p\nm9Wl3tO/Dzg6IuYD+5FNwTBOdkLWn0fEa8jG809rL10zM+uVIvPpb4iI1fn9LWRTMBxEVqt/Vb7a\nVcCJ3UrSzMzSaLdk8z48tbKZ2cAp3Ok3l2xSYmplMzOrhkJ1+nnJ5g3ANRExOZvmhKTFDVMrPzXV\n812bbJ1ynb5ZXS/q9K8GnomI8xqWXQo8GxGXSvoYsCgiLmjxXFcsWHKu3jGrK9MeipRsHkd2Xdxv\nkw3hBHARcD9wPXAw+dTKEfFci+d7Q7fk3Omb1aUu2TyVrDZ/TkQcHRHHAG8G1gB7k02tvKpVh29m\nZtVSpNP/HPDOFstXRcQx+e32xHmZmVkXFKnT/xrZhVSaDdRXazMzK1mn38TTKpuZDZh2O/3LgEMj\nYinZBVamvXqWmZlVQ+H59BtFxNMNv14O3Drd+q5Ntk65Tt+srhd1+qNk8+Uflf8+kk+9gKRzgTdF\nxAemeK7L1Cw5l2ya1SW9Rq6ka4EasI+kJ4GLgeWSlgI7yGbcPKPtbM3MrGeKDO+8AMwFHpm8Mpak\nm4DrgCXAfOpz7ZuZWYW1W6d/AXBXRBwG3A1cmDoxMzNLr906fc+lb2Y2gNot2dzfc+mbmQ2etko2\nW5i2JMFlap0ZGRllYmJd6ectXryEDRvG0yfUBy7ZNKvrRcnmErKSzckDuWuBWsNc+vdExBFTPNdl\nah2SRHvXqBGz9bV3yaZZXepZNiGbZ6cx4C3AKfn9FcDNzU8wM7PqKTKf/it1+sAEWZ3+TcCXgGVk\n5ZrfA7ZFxLEtnu+9mw55T39X3tM3q0t6EZUZ/tATwBsjotUsnJPreEPvkDv9XbnTN6vrxvDOlH8r\nQQwzM+uRTjvsAO6U9ICk01MkZCnNQ1Kp28jIaL+TNrMu6rRk87iIWC9pP7LOf21+MtdOzj33o6WC\njo4ewtln/1E+rGHt207ZYaGJCb/mZrNZR2P6OwWSLgY2R8SqpuUBrwMWkV1S91Dg9TNE+xgvv/wy\nc+fOTZJblbRbc9/umH7551XzOEBzXfK99947kGP6y5Ytc52+dayT9tB2py9pAdnF0rdI2h24A1gZ\nEXc0rRdlOx5pLi+99OKs7PTbOyjb/oHc2dLpN/OBXLO6Xh3IXQx8TdJDwH1kJ2/dMcNzumpkZLT0\nGLYk5s7d3WPfHWr3tffrOFyKbifeLrqn7U4/Ir5HNtvmfGAe7e2KJpUNm0Tp244dW0s/Z2JiQ1ud\nXPWVP/grqe3Xvr2hrtmvzIdomZ2WbnSmZXItup2U2S7K/H1/mHTQ6UuaA3yabNrlI4GTJB2eKrFW\nxsbGUkbr8PmTB0nvoVxH182cUsSa/L8ab0X+x27mNHxm7hzr70mZnZZWnWmn7WrnXGfaVtIr81p1\nupORsg9K258V10n1zrHAYxGxDkDSF8mmXH44RWKtjI2NJTzwNUZ2onFV4nQjVipjVO+1GkxXX311\nokhjtPdaziv0jXPOnAX5h0lZY1TvPR6jnlOx/3+qyQpT9kFp+7PiOun0DwS+3/D7D8g+CJI48MDX\nt/xUXrlyZaK/MF6xOMMQK1WcwfXhD9/AnDmvnXadHTueKxBpvM0MWpXxngJ8vimHMkUAjZ3oeHtp\nddV4w/1iZcxTlS6nnOG1X7PFpppaeVoLFx5Vav0XX1zQ8JWtUY3p92DLjJmPl8qp+3GGIVaqOINL\nWsucOa+Zdp2IIlcfHU+ST7VjpTKeLtKQd/o/BA5p+P2gfNkuNm36Tpt/olUnPlPHXqbj1xT3yz6/\n7HOnW3+qx9o9CNzJ/1U2TnvrDMYB7jSef/7xEmuX2dbb3e7LLkuRS7G45baL9K/VVH8/5fbaj22/\nkzr9ucAjwC8D64H7gZMiYm269MzMLKW29/Qj4ieSziQ7KWsOcKU7fDOzaks2DYOZmVWfp0U2Mxsi\n7vTNzIaIO30zsyHiTt/MbIi40zczGyLu9M3Mhog7fTOzIeJO38xsiLjTNzMbIu70+0DSKZLWSHpe\n0n9IukzSXg2Pv0HS9ZKelrRR0mpJ52qYZiazoSDprZK+Luk5Sc9I+n+S3tjweE3SDkkf6Wees4k7\n/R6TdD7wV8D5wELgLcAS4E5Ju0l6Pdk1h9cBPxsRi4DfBo4B9uxP1mbpSdoTuBX4JLCI7BodK8km\nvZ90MvCj/Kcl4Ll3eijfyP8DOCUi/rFh+e7AE2TXHH4b8NqI+PX+ZGnWG/ke/Z0RsfcUjy8ANgCn\nAVcDvxQRD/YwxVnJe/q99UtkF5G/sXFhRDwPfAV4O/ArwA29T82s5x4FfiLp85LeJan5kmK/BWwG\nvkQ2m++KXic4G7nT7619gWciYkeLx9bnj++d3zeb1SJiM/BWYAfwP4GnJN0sab98lZOBL0Y2HHEt\n8Dv5dTysA+70e+sZYF9JrV73A/LHf5TfN5v1IuKRiDg1Ig4Bfhb4KeC/SzoIWE7W2QPcAswHTuhP\nprOHO/3e+meyg1TvaVwoaQ/geOCu/Pbe3qdm1l8R8SjZFdp/FvggWf90q6T1wL+TDY16iKdD7vR7\nKCI2AR8HPiXpnXm1zihwHfAkcA3wZ8AvSrpU0mIAST8t6RpJC/uTuVl6kg6TdJ6kA/PfDwZOIqte\nWwFcDCwFfj6/vRc4QdKiPqU8K7jT77GI+BvgIuBvgR+T7f2vA34lIl6KiCeAXwReB/ybpI1kB7Ie\nIDuoZTZbbAbeDHxT0mbgG8Aa4B+AQ4DLIuKphtutwGNkHwzWphlLNiXNA/4JeDXZNXVviIiVki4G\nTgeeyle9KCJu72ayZmbWmUJ1+pIWRMTW/Mj514GzycagN0fEqi7naGZmiRQa3omIrfndeWR7+5Of\nFJ4WwMxsgBTq9CXNkfQQ2dlxd0bEA/lDZ+bzwlzROHeMmZlVU6lpGPLqkRuBs4CnyU40CkmfAA6I\niA91J00zM0uh9Nw7kv4UeL5xLF/SEuDWiPi5Fut7ch/riogYqOFFtwXrpqLtYcbhHUn7Tg7dSJpP\nNj/Mw5JGGlZ7D/CdaZJJclu2bFnlYlUxp6rGSpnToKrae1LVWFXMqcqxytitwDoHAFflUwfMAa6L\niNskXS1pKdm8GePAGSW3/9JGR0crF6uKOVU1Vsqchl0V39+UsaqYU5VjlVHkQO6jwEtkFTui/kFx\nDtmB3fn5bVs3EmxUxRe8ijlVNZY7/XSq+P6mjFXFnKocq4wZO/2I2A4sj4ijyU6JPl7SsWRzv98V\nEYcBdwMXdjVToFarVS5WFXOqaqyUOQ27Kr6/KWNVMacqxyqjbPXOArKzcz9MNk/MsoiYyMf3xyLi\n8BbPibJjTmYzkUQM4IFctwXrhjLtoZM6/cURMQEQERuA/dtN2MzMeqPIgVwiu+jH0ZN1+pKOpH5W\n7iurTfX8Wq3G6Ogoo6Oj1Go1f8230sbGxhgbG2N8fJzx8fF+p9M2twVLoZP20G6d/lay61bWGoZ3\n7omII1qs76+0lpyHd8zqkg7vTFGnv5bsSjan5KutAG5uK1szM+uZTur07wOul3Qq2Xzw7+tinmZm\nlkCRA7kbgeeAV5HV6W/Kl58FHA48T3ZB77d0I0EzM0unyEVURoCRiFidX8v1W8C7gfdTYD59j2Na\nN3hM36yuTHuYcXgnL8fckN/fImktcODk32o7SzMz67lS18jNL+K9FPhmvsjz6ZuZDZBCdfoA+dDO\nDcA5+R7/ZcDHI16ZT38V0HI+fdcmW6dcp29W1/U6fUm7AV8GvhIRn2zx+LTz6Xsc01LzmL5ZXfJp\nGIDPAt9t7PDLzKdvZmbVUKR650SySyROTp38DHA62YlZJ5CVcv4YOC4iHm/xfO/dWHLe0zerS72n\nfx9wdETMB/Yjm4JhnOyErD+PiNeQjeef1l66ZmbWK0Xm098QEavz+1vIpmA4iKxW/6p8tauAE7uV\npJmZpdFuyeZ9eGplM7OBU7jTby7ZpMTUymZmVg2F6vTzks0bgGsiYnI2zQlJixumVn5qque7Ntk6\n5Tp9s7pe1OlfDTwTEec1LLsUeDYiLpX0MWBRRFzQ4rmuWLDkXL1jVlemPRQp2TyO7Lq43yYbwgng\nIuB+4HrgYPKplSPiuRbP94ZuybnTN6tLXbJ5Kllt/pyIODoijgHeDKwB9iabWnlVqw7fzMyqpUin\n/zngnS2Wr4qIY/Lb7YnzMjOzLihSp/81sgupNBuor9ZmZlayTr+Jp1U2Mxsw7Xb6lwGHRsRSsgus\nTHv1LDMzq4bC8+k3ioinG369HLh1uvVdm2ydcp2+WV0v6vRHyebLPyr/fSSfegFJ5wJviogPTPFc\nl6lZci7ZNKtLeo1cSdcCNWAfSU8CFwPLJS0FdpDNuHlG29mamVnPFBneeQGYCzwyeWUsSTcB1wFL\ngPnU59o3M7MKa7dO/wLgrog4DLgbuDB1YmZmll67dfqeS9/MbAC1W7K5v+fSNzMbPG2VbLYwbUmC\ny9SsUy7ZNKvrRcnmErKSzckDuWuBWsNc+vdExBFTPNdlapacSzbN6lLPsgnZPDuNAW8BTsnvrwBu\nbn6CmZlVT5H59F+p0wcmyOr0bwK+BCwjK9f8HrAtIo5t8Xzv3Vhy3tM3q0t6EZUZ/tATwBsjotUs\nnJPreEO35Nzpm9V1Y3hnyr+VIIaZmfVIpx12AHdKekDS6SkSMjOz7um0ZPO4iFgvaT+yzn9tfjLX\nTs4996OFgh1xxGH8/u9/qMOUzMxsKh2N6e8USLoY2BwRq5qWB7wOWER2Sd1Dgde3iLCNefP+lm3b\nNiXJx2aX5rrke++9dyDH9JctW+Y6fetYJ+2h7U5f0gKyi6VvkbQ7cAewMiLuaFovZjh3K7eJefMO\ncqdvhfhArlld0qmVp7EYuDHr1NkN+EJzh1/W9u0vIxVvx4sXL2HDhvFO/qSZ2VBp+0BuRHyPbLbN\n+cA8iu3Oz+CFPEyx28TEus7/pJm1bWRkFEnT3kZGRvudpjVou9OXNAf4NNm0y0cCJ0k6PFVirY2l\nizSWJlaqOMMQK2VOw66T1/KRRx5h330PZuHCxSxcuJgFCxa9cr/x9gd/cP6MsbIdr8adsXtIsXNW\nxe23yrHK6KRk81jgsYhYFxEvAV8km3K5i8aafp83417GVHsb/ezIpto7Wr58ebK9pCpunO700+nk\ntVy3bh0vvngomzevYfPmNbzwwodeuV+/fYYrr7x8xnbVIrO289opSgW33yrHKqOTTv9A4PsNv/8g\nX9ZF402/b6f4UNCGnTbWlStXJvlK2s6Mj7vuHU3eVrTIu9xe0uQHykz/nyTmzt290AfmZKxOv6YP\n8uyYVdPpazlnzjyyw3KLgWca7k/e9ubllzczc9vaJbMWy2beOWveFlttv0W211brNMfqZDtufN07\nHdrqV3tINbXytBYuPGrGdSJ+wubNM6013kEWkx8Qk2pMt1cyMVHsgHLaN67zWPUPlBoz7XXt2CGK\nHYrJYhV9TabiTj+dTl7LPffck61bv/FKu9yy5Qn22ONbO63z8stb2Lq1rcxaLGtue7vadVus0bz9\nFtleW6+zc6xOtuPG173e1qY23d8axE7/h8AhDb8flC/bxaZN3ykRdqY3pPnxMm9guecWrSQqU3E0\n89/edXkgwyD+AAAGZUlEQVT5+Gr62U4erddr739tiNLh8wddyv+/01gvvVRvl1O30Xa2oVbP6Wec\nXZd18trt/NyZ40z3t/rRHjqp058LPAL8MrAeuB84KSLWpkvPzMxSantPPyJ+IulMspOy5gBXusM3\nM6u2ZNMwmJlZ9XlaZDOzIeJO38xsiCQv2czPyn039Zr9HwK3eLx/V8oO3R/Lzq/V/e3MypUqVhVz\nSh2rV9wWiqvqtlLFWJ3GSTqmL+ljwElkZ+f+IF98EPA7wBcj4pISsfYCLgROBPYnK4h9iuwi7JdE\nxHMlc6vEC94Q5x3AZcBj1EtdDwJ+GvjDMpPXpYpVxZxSx+qVYWgLqWJVdVupYqwkcSIi2Q14FHhV\ni+WvJpuyoUysrwIfA0Yalo3ky+4oGesdwOPAV4Ar8tvt+bJ39DpOHmstMNpi+euAtf2IVcWcUsfq\n1W22t4WUsaq6rVQxVoo4yTby/A8/DCxpsXwJ8EjJWFOu30asyrzgDc95DNitxfJXA4/3I1YVc0od\nq1e32d4WUsaq6rZSxVgp4qQe0/9j4P9Keoz6vDyHkH31OLNkrHWSPgpcFRETAJIWA6ew85w/RexG\n/St2ox8Cr+pDHIDPAg9I+iL1/+dgsq//V/YpVhVzSh2rV2Z7W0gZq6rbShVjdRwneZ2+simXm8f4\nHoiIn5SMs4hsvv53k80AFcAEcAtwaUQ8WyLWhcD7yMZXm1+o6yPir3oZpyHezwC/wa4H+r5bJk4e\n6whaHzQsFauKOaXOq1dmc1voQqxZv91VpY0OzMlZkv4TWQP6drRx4C7Vm5dygzJrR1XaQh7L7WHQ\nlBmX6uWNrAJg8v5pwEPAxcDXgQv6nV+C/28v4BKysd9ngR+RjZFeAry2ZKx3NcW9AlgDXAssHuSc\nUuc1iDe3hcHf7qrURqt8clbjmOAZZNUAK8kqBn63TCBJe0m6RNLDkp6V9CNJa/Nlry0R511NMa+Q\ntEbStfkYaxnXAxuBWkTsHRH7AMvzZdeXjPWXDff/DtgA/DrwAPD3A55T6rwGUeXaQh4rVXsYhu2u\nOm2035/y03yi/SuwCNgHeLDpsYdKxkpS8taYB9kn9SfIqjHOBW4qmVPKiozGvFY3PbZ6kHNKndcg\n3qrYFlq8x223h2HY7qrURntyEZU27QV8i2zC6pB0QESsl7QH5SbRh6ys7NLGBRGxAbhU0qlt5vcL\nEbE0v//fJK0o+fyUFRn7SzqP7HXZS5Ii3wooN9VGFXNKndcgqnpbgM7awzBsd5Vpo5Ud3omI0Yg4\nNCJel/9cnz+0A/jNkuHWSfpo41dOSYvzsybLvHn7SzpP0vnkb1zDY2Vfy/eT7bndK2mjpGfJLu+z\nN1lFRBmXA3sCewCfB/YFkDQCrB7wnFrltTHPa5828ho4FW0LkK49DMp2V4W8Om4LA1O904mmkrf9\n88WTJW+XRMTGgnEublp0WUQ8nb9xfx0RJ5fM63CyU6jvi4gtDcvfFRG3txHrQOCbncSSdCwQEfGA\npCOBd5GdaHNbmXxaxPqZPNbD7cRqEfuaiPhgp3GGTaq2kMdK1h6q2Bby51S+PZRtC0PR6U9H0u9F\nxOd6HUfS2cAfkR15XwqcExE35489GBHHlIh1FtkJPx3Fyhvx8WQn3dxJVhY4Brwd+GpE/EWJnFLG\nuqXF4rcBdwNExG8UjWVTS9UWysaqYlvI169ce0jSFsocjJiNN+DJfsQBvg3skd8fBf6FbAOF8gfn\nksTK48wFFgCbgIX58vnAmjZyShXrQeAfyK5wvSz/uT6/v6zf29BsuaVqC2VjVbEtNMSqVHtI0Raq\nfCA3GUlrpnqI7AzHnsbJzYn8q2dEjEuqATdIWkL5g3OpYr0c2dmiWyX9e0RsymO+IGlHyZxSxvoF\n4BzgvwAfiYjVkl6IiHtLxhl6KbfhhLGq2Bagmu2h47YwFJ0+2Qb4TrJa1kYCvtGHOAATkpZGxGqA\niNgi6dfI5tY4qk+xXpS0ICK2Am+cXKhsat+yG3myWBGxg6wi5Ev5zwmGZ9tNLeU2nCpWFdsCVLA9\nJGkLqb7OVflGNhHRW6d47Npex8nXP4iGWummx47rRyxg3hTL9wWOKplTslgtYpwA/GW/tqdBviXe\nhlO1q8q1hXz9yreHdtrC0B/INTMbJpWt0zczs/Tc6ZuZDRF3+mZmQ8SdvpnZEHGnb2Y2RP4/WpMu\ngMiiD48AAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# same charts with the same scale for x and y axis\n", + "drinks.beer_servings.hist(by=drinks.continent, sharex=True, sharey=True)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 57, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEaCAYAAAD5fVeOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nziXIG3/nnEuQN/7OOZeg/w9o59RUDHomSgAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# boxplot of beer servings by continent\n", + "drinks.boxplot(column='beer_servings', by='continent')" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 58, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY8AAAEQCAYAAABIqvhxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# scatterplot of beer servings versus wine servings\n", + "drinks.plot(x='beer_servings', y='wine_servings', kind='scatter', alpha=0.3)" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array(['b', 'r', 'b', 'r', 'b', 'b', 'b', 'r', 'b', 'r', 'r', 'b', 'b',\n", + " 'b', 'b', 'r', 'r', 'b', 'b', 'b', 'b', 'r', 'b', 'b', 'b', 'r',\n", + " 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b',\n", + " 'b', 'b', 'b', 'r', 'b', 'r', 'r', 'b', 'b', 'r', 'b', 'b', 'b',\n", + " 'b', 'b', 'b', 'b', 'b', 'r', 'b', 'b', 'r', 'r', 'b', 'b', 'r',\n", + " 'r', 'b', 'r', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'r', 'r', 'b',\n", + " 'b', 'b', 'b', 'r', 'b', 'r', 'b', 'b', 'b', 'b', 'b', 'b', 'b',\n", + " 'b', 'b', 'r', 'b', 'b', 'b', 'b', 'r', 'r', 'b', 'b', 'b', 'b',\n", + " 'b', 'r', 'b', 'b', 'b', 'b', 'b', 'r', 'b', 'r', 'b', 'b', 'b',\n", + " 'b', 'b', 'b', 'r', 'b', 'b', 'b', 'b', 'b', 'r', 'b', 'b', 'b',\n", + " 'b', 'b', 'b', 'b', 'b', 'r', 'r', 'b', 'b', 'r', 'r', 'b', 'b',\n", + " 'b', 'b', 'b', 'b', 'r', 'b', 'b', 'b', 'r', 'b', 'b', 'b', 'r',\n", + " 'r', 'b', 'b', 'b', 'r', 'b', 'b', 'b', 'b', 'r', 'r', 'b', 'b',\n", + " 'b', 'r', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'r', 'b',\n", + " 'r', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b', 'b'], \n", + " dtype='|S1')" + ] + }, + "execution_count": 60, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# same scatterplot, except all European countries are colored red\n", + "colors = np.where(drinks.continent=='EU', 'r', 'b')\n", + "colors # is a series of 'r' and 'b' that \n", + " # correspond to countries" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array(['a', 'b', 'b'], \n", + " dtype='|S1')" + ] + }, + "execution_count": 61, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "'''\n", + "np.where is like a condensed if statement\n", + "it's like a list comprehension for pandas!\n", + "\n", + "it will loop through drinks.continent which is a series\n", + "for each element:\n", + " if it is \"EU\":\n", + " make it 'r'\n", + " else:\n", + " make it 'b'\n", + "\n", + "More in depth:\n", + " drinks.continent=='EU' is a logical statement\n", + " It will return a bunch of Trues and Falses\n", + " and np.where makes the True ones 'r' and\n", + " the False ones 'b'\n", + " \n", + " Recall logical filtering!\n", + "\n", + "'''\n", + "\n", + "# Side quest\n", + "np.where([True, False, False], 'a', 'b')\n", + "\n", + "# 10 gold coins earned" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 62, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY8AAAEQCAYAAABIqvhxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nJYEAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "drinks.plot(x='beer_servings', y='wine_servings', kind='scatter', c=colors)\n", + "# passing colors into the chart makes the european dots, red!" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 81, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "'\\n----UFO data----\\nScraped from: http://www.nuforc.org/webreports.html\\n'" + ] + }, + "execution_count": 81, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "'''\n", + "----UFO data----\n", + "Scraped from: http://www.nuforc.org/webreports.html\n", + "'''" + ] + }, + { + "cell_type": "code", + "execution_count": 82, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "ufo = pd.read_csv('../data/ufo.csv') " + ] + }, + { + "cell_type": "code", + "execution_count": 83, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
CityColors ReportedShape ReportedStateTime
0IthacaNaNTRIANGLENY6/1/1930 22:00
1WillingboroNaNOTHERNJ6/30/1930 20:00
2HolyokeNaNOVALCO2/15/1931 14:00
3AbileneNaNDISKKS6/1/1931 13:00
4New York Worlds FairNaNLIGHTNY4/18/1933 19:00
\n", + "
" + ], + "text/plain": [ + " City Colors Reported Shape Reported State Time\n", + "0 Ithaca NaN TRIANGLE NY 6/1/1930 22:00\n", + "1 Willingboro NaN OTHER NJ 6/30/1930 20:00\n", + "2 Holyoke NaN OVAL CO 2/15/1931 14:00\n", + "3 Abilene NaN DISK KS 6/1/1931 13:00\n", + "4 New York Worlds Fair NaN LIGHT NY 4/18/1933 19:00" + ] + }, + "execution_count": 83, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ufo.head() # Look at the top 5 observations" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
CityColors ReportedShape ReportedStateTime
80538NelighNaNCIRCLENE9/4/2014 23:20
80539UhrichsvilleNaNLIGHTOH9/5/2014 1:14
80540TucsonRED BLUENaNAZ9/5/2014 2:40
80541Orland parkREDLIGHTIL9/5/2014 3:43
80542LoughmanNaNLIGHTFL9/5/2014 5:30
\n", + "
" + ], + "text/plain": [ + " City Colors Reported Shape Reported State Time\n", + "80538 Neligh NaN CIRCLE NE 9/4/2014 23:20\n", + "80539 Uhrichsville NaN LIGHT OH 9/5/2014 1:14\n", + "80540 Tucson RED BLUE NaN AZ 9/5/2014 2:40\n", + "80541 Orland park RED LIGHT IL 9/5/2014 3:43\n", + "80542 Loughman NaN LIGHT FL 9/5/2014 5:30" + ] + }, + "execution_count": 84, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ufo.tail() # Look at the bottom 5 observations" + ] + }, + { + "cell_type": "code", + "execution_count": 85, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "ufo['Location'] = ufo['City'] + ', ' + ufo['State']" + ] + }, + { + "cell_type": "code", + "execution_count": 86, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
CityColors ReportedShape ReportedStateTimeLocation
0IthacaNaNTRIANGLENY6/1/1930 22:00Ithaca, NY
1WillingboroNaNOTHERNJ6/30/1930 20:00Willingboro, NJ
2HolyokeNaNOVALCO2/15/1931 14:00Holyoke, CO
3AbileneNaNDISKKS6/1/1931 13:00Abilene, KS
4New York Worlds FairNaNLIGHTNY4/18/1933 19:00New York Worlds Fair, NY
\n", + "
" + ], + "text/plain": [ + " City Colors Reported Shape Reported State Time \\\n", + "0 Ithaca NaN TRIANGLE NY 6/1/1930 22:00 \n", + "1 Willingboro NaN OTHER NJ 6/30/1930 20:00 \n", + "2 Holyoke NaN OVAL CO 2/15/1931 14:00 \n", + "3 Abilene NaN DISK KS 6/1/1931 13:00 \n", + "4 New York Worlds Fair NaN LIGHT NY 4/18/1933 19:00 \n", + "\n", + " Location \n", + "0 Ithaca, NY \n", + "1 Willingboro, NJ \n", + "2 Holyoke, CO \n", + "3 Abilene, KS \n", + "4 New York Worlds Fair, NY " + ] + }, + "execution_count": 86, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ufo.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 87, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "# rename some columns\n", + "ufo.rename(columns={'Colors Reported':'Colors', 'Shape Reported':'Shape'}, inplace=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 88, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
CityColorsShapeStateTimeLocation
0IthacaNaNTRIANGLENY6/1/1930 22:00Ithaca, NY
1WillingboroNaNOTHERNJ6/30/1930 20:00Willingboro, NJ
2HolyokeNaNOVALCO2/15/1931 14:00Holyoke, CO
3AbileneNaNDISKKS6/1/1931 13:00Abilene, KS
4New York Worlds FairNaNLIGHTNY4/18/1933 19:00New York Worlds Fair, NY
\n", + "
" + ], + "text/plain": [ + " City Colors Shape State Time \\\n", + "0 Ithaca NaN TRIANGLE NY 6/1/1930 22:00 \n", + "1 Willingboro NaN OTHER NJ 6/30/1930 20:00 \n", + "2 Holyoke NaN OVAL CO 2/15/1931 14:00 \n", + "3 Abilene NaN DISK KS 6/1/1931 13:00 \n", + "4 New York Worlds Fair NaN LIGHT NY 4/18/1933 19:00 \n", + "\n", + " Location \n", + "0 Ithaca, NY \n", + "1 Willingboro, NJ \n", + "2 Holyoke, CO \n", + "3 Abilene, KS \n", + "4 New York Worlds Fair, NY " + ] + }, + "execution_count": 88, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ufo.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 89, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "del ufo['City'] # delete a column (permanently)\n", + "del ufo['State'] # delete a column (permanently)" + ] + }, + { + "cell_type": "code", + "execution_count": 90, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "LIGHT 16332\n", + "TRIANGLE 7816\n", + "CIRCLE 7725\n", + "FIREBALL 6249\n", + "OTHER 5506\n", + "SPHERE 5231\n", + "DISK 5226\n", + "OVAL 3721\n", + "FORMATION 2405\n", + "CIGAR 1983\n", + "VARIOUS 1957\n", + "FLASH 1329\n", + "RECTANGLE 1295\n", + "CYLINDER 1252\n", + "DIAMOND 1152\n", + "CHEVRON 940\n", + "EGG 733\n", + "TEARDROP 723\n", + "CONE 310\n", + "CROSS 241\n", + "DELTA 7\n", + "CRESCENT 2\n", + "ROUND 2\n", + "HEXAGON 1\n", + "FLARE 1\n", + "PYRAMID 1\n", + "DOME 1\n", + "Name: Shape, dtype: int64" + ] + }, + "execution_count": 90, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ufo.Shape.value_counts() # excludes missing values" + ] + }, + { + "cell_type": "code", + "execution_count": 91, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "LIGHT 16332\n", + "NaN 8402\n", + "TRIANGLE 7816\n", + "CIRCLE 7725\n", + "FIREBALL 6249\n", + "OTHER 5506\n", + "SPHERE 5231\n", + "DISK 5226\n", + "OVAL 3721\n", + "FORMATION 2405\n", + "CIGAR 1983\n", + "VARIOUS 1957\n", + "FLASH 1329\n", + "RECTANGLE 1295\n", + "CYLINDER 1252\n", + "DIAMOND 1152\n", + "CHEVRON 940\n", + "EGG 733\n", + "TEARDROP 723\n", + "CONE 310\n", + "CROSS 241\n", + "DELTA 7\n", + "CRESCENT 2\n", + "ROUND 2\n", + "HEXAGON 1\n", + "PYRAMID 1\n", + "DOME 1\n", + "FLARE 1\n", + "Name: Shape, dtype: int64" + ] + }, + "execution_count": 91, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ufo.Shape.value_counts(dropna=False) # includes missing values" + ] + }, + { + "cell_type": "code", + "execution_count": 92, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "8402" + ] + }, + "execution_count": 92, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ufo.Shape.isnull().sum() # count the missing values in the shape column" + ] + }, + { + "cell_type": "code", + "execution_count": 93, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Colors 63509\n", + "Shape 8402\n", + "Time 0\n", + "Location 47\n", + "dtype: int64" + ] + }, + "execution_count": 93, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ufo.isnull().sum() # returns a count of missing values in all columns" + ] + }, + { + "cell_type": "code", + "execution_count": 99, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ColorsShapeTimeLocation
12REDSPHERE6/30/1939 20:00Belton, SC
19REDOTHER4/30/1943 23:00Bering Sea, AK
36REDFORMATION7/10/1945 1:30Portsmouth, VA
44GREENSPHERE6/30/1946 19:00Blairsden, CA
82BLUECHEVRON7/15/1947 21:00San Jose, CA
84BLUEDISK8/8/1947 22:00Modesto, CA
91REDSPHERE5/10/1948 19:00Scipio, IN
111ORANGECIRCLE8/15/1949 22:00Tarrant City, AL
129GREENDISK6/10/1950 0:00Napa, CA
138ORANGECIGAR7/2/1950 13:00Coeur d'Alene, ID
152BLUEDISK4/15/1951 0:30Irving, KS
157GREENDISK6/15/1951 20:30Greenville, MS
163GREENSPHERE7/3/1951 12:00Green River, WY
164BLUEDISK7/10/1951 23:30Provo, UT
174ORANGETRIANGLE4/15/1952 16:00Greenville, TX
178REDFIREBALL6/1/1952 22:00Norfolk, VA
202GREENOVAL7/13/1952 21:00Arlington, VA
226REDSPHERE4/1/1953 18:00Cambridge, MA
229YELLOWFIREBALL4/15/1953 16:00Midwest City, OK
238REDFIREBALL6/30/1953 0:00Cleveland, OH
241BLUEDISK7/4/1953 14:00NaN
249ORANGEOTHER8/15/1953 19:00Artesia, NM
256GREENDISK11/21/1953 22:30Pendleton, IN
288REDOVAL7/1/1954 21:00St. Louis Airport, MO
289REDCIRCLE7/1/1954 22:00Los Angeles, CA
304REDDISK9/9/1954 12:30Beaumont, TX
311ORANGECIRCLE12/15/1954 23:10Red Bank, NJ
314YELLOWEGG5/1/1955 15:00Holbrook, MA
323ORANGECIRCLE6/15/1955 0:00Terre Haute, IN
354ORANGECYLINDER6/1/1956 20:00Memphis, TN
...............
80429REDCIRCLE8/31/2014 20:50Bettendorf, IA
80430REDSPHERE8/31/2014 21:00Pompton Lakes, NJ
80436ORANGESPHERE8/31/2014 21:45Montrose, MI
80438ORANGECYLINDER8/31/2014 22:00Brunswick, OH
80441REDTEARDROP8/31/2014 22:30Scribner, NE
80453RED ORANGE GREEN BLUETRIANGLE9/1/2014 11:56Minersville, PA
80457ORANGECIRCLE9/1/2014 16:05Syracuse, NY
80458ORANGEFIREBALL9/1/2014 20:00Parma, OH
80459ORANGECIRCLE9/1/2014 20:00Roswell, NM
80465GREENVARIOUS9/1/2014 21:30South Londonderry, VT
80467ORANGELIGHT9/1/2014 22:00Gold Hill, NC
80469ORANGECIRCLE9/1/2014 22:19Milford, DE
80473BLUETRIANGLE9/2/2014 5:50Trevose, PA
80482ORANGEFIREBALL9/2/2014 22:30Spearfish, SD
80489ORANGESPHERE9/3/2014 5:00Pleasure Island, NC
80494RED GREENCIRCLE9/3/2014 19:00Boca Raton, FL
80495YELLOWFLASH9/3/2014 19:00Kingston, NH
80496REDFLASH9/3/2014 19:00New York City, NY
80500RED BLUELIGHT9/3/2014 21:00Johnsburg, IL
80503ORANGEVARIOUS9/3/2014 21:15Bethel Park, PA
80505YELLOWTRIANGLE9/3/2014 21:30Clarence, NY
80509RED BLUECIRCLE9/3/2014 23:30Chesapeake Beach, MD
80510REDOVAL9/4/2014 0:00Rogersville, TN
80519REDCIRCLE9/4/2014 20:20Glen Ellyn, IL
80522ORANGELIGHT9/4/2014 20:30Lawrence, MA
80524REDLIGHT9/4/2014 21:10Olympia, WA
80525BLUELIGHT9/4/2014 21:11Iowa City, IA
80528REDTRIANGLE9/4/2014 21:30North Royalton, OH
80536REDDISK9/4/2014 23:00Wyoming, PA
80541REDLIGHT9/5/2014 3:43Orland park, IL
\n", + "

15516 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " Colors Shape Time \\\n", + "12 RED SPHERE 6/30/1939 20:00 \n", + "19 RED OTHER 4/30/1943 23:00 \n", + "36 RED FORMATION 7/10/1945 1:30 \n", + "44 GREEN SPHERE 6/30/1946 19:00 \n", + "82 BLUE CHEVRON 7/15/1947 21:00 \n", + "84 BLUE DISK 8/8/1947 22:00 \n", + "91 RED SPHERE 5/10/1948 19:00 \n", + "111 ORANGE CIRCLE 8/15/1949 22:00 \n", + "129 GREEN DISK 6/10/1950 0:00 \n", + "138 ORANGE CIGAR 7/2/1950 13:00 \n", + "152 BLUE DISK 4/15/1951 0:30 \n", + "157 GREEN DISK 6/15/1951 20:30 \n", + "163 GREEN SPHERE 7/3/1951 12:00 \n", + "164 BLUE DISK 7/10/1951 23:30 \n", + "174 ORANGE TRIANGLE 4/15/1952 16:00 \n", + "178 RED FIREBALL 6/1/1952 22:00 \n", + "202 GREEN OVAL 7/13/1952 21:00 \n", + "226 RED SPHERE 4/1/1953 18:00 \n", + "229 YELLOW FIREBALL 4/15/1953 16:00 \n", + "238 RED FIREBALL 6/30/1953 0:00 \n", + "241 BLUE DISK 7/4/1953 14:00 \n", + "249 ORANGE OTHER 8/15/1953 19:00 \n", + "256 GREEN DISK 11/21/1953 22:30 \n", + "288 RED OVAL 7/1/1954 21:00 \n", + "289 RED CIRCLE 7/1/1954 22:00 \n", + "304 RED DISK 9/9/1954 12:30 \n", + "311 ORANGE CIRCLE 12/15/1954 23:10 \n", + "314 YELLOW EGG 5/1/1955 15:00 \n", + "323 ORANGE CIRCLE 6/15/1955 0:00 \n", + "354 ORANGE CYLINDER 6/1/1956 20:00 \n", + "... ... ... ... \n", + "80429 RED CIRCLE 8/31/2014 20:50 \n", + "80430 RED SPHERE 8/31/2014 21:00 \n", + "80436 ORANGE SPHERE 8/31/2014 21:45 \n", + "80438 ORANGE CYLINDER 8/31/2014 22:00 \n", + "80441 RED TEARDROP 8/31/2014 22:30 \n", + "80453 RED ORANGE GREEN BLUE TRIANGLE 9/1/2014 11:56 \n", + "80457 ORANGE CIRCLE 9/1/2014 16:05 \n", + "80458 ORANGE FIREBALL 9/1/2014 20:00 \n", + "80459 ORANGE CIRCLE 9/1/2014 20:00 \n", + "80465 GREEN VARIOUS 9/1/2014 21:30 \n", + "80467 ORANGE LIGHT 9/1/2014 22:00 \n", + "80469 ORANGE CIRCLE 9/1/2014 22:19 \n", + "80473 BLUE TRIANGLE 9/2/2014 5:50 \n", + "80482 ORANGE FIREBALL 9/2/2014 22:30 \n", + "80489 ORANGE SPHERE 9/3/2014 5:00 \n", + "80494 RED GREEN CIRCLE 9/3/2014 19:00 \n", + "80495 YELLOW FLASH 9/3/2014 19:00 \n", + "80496 RED FLASH 9/3/2014 19:00 \n", + "80500 RED BLUE LIGHT 9/3/2014 21:00 \n", + "80503 ORANGE VARIOUS 9/3/2014 21:15 \n", + "80505 YELLOW TRIANGLE 9/3/2014 21:30 \n", + "80509 RED BLUE CIRCLE 9/3/2014 23:30 \n", + "80510 RED OVAL 9/4/2014 0:00 \n", + "80519 RED CIRCLE 9/4/2014 20:20 \n", + "80522 ORANGE LIGHT 9/4/2014 20:30 \n", + "80524 RED LIGHT 9/4/2014 21:10 \n", + "80525 BLUE LIGHT 9/4/2014 21:11 \n", + "80528 RED TRIANGLE 9/4/2014 21:30 \n", + "80536 RED DISK 9/4/2014 23:00 \n", + "80541 RED LIGHT 9/5/2014 3:43 \n", + "\n", + " Location \n", + "12 Belton, SC \n", + "19 Bering Sea, AK \n", + "36 Portsmouth, VA \n", + "44 Blairsden, CA \n", + "82 San Jose, CA \n", + "84 Modesto, CA \n", + "91 Scipio, IN \n", + "111 Tarrant City, AL \n", + "129 Napa, CA \n", + "138 Coeur d'Alene, ID \n", + "152 Irving, KS \n", + "157 Greenville, MS \n", + "163 Green River, WY \n", + "164 Provo, UT \n", + "174 Greenville, TX \n", + "178 Norfolk, VA \n", + "202 Arlington, VA \n", + "226 Cambridge, MA \n", + "229 Midwest City, OK \n", + "238 Cleveland, OH \n", + "241 NaN \n", + "249 Artesia, NM \n", + "256 Pendleton, IN \n", + "288 St. Louis Airport, MO \n", + "289 Los Angeles, CA \n", + "304 Beaumont, TX \n", + "311 Red Bank, NJ \n", + "314 Holbrook, MA \n", + "323 Terre Haute, IN \n", + "354 Memphis, TN \n", + "... ... \n", + "80429 Bettendorf, IA \n", + "80430 Pompton Lakes, NJ \n", + "80436 Montrose, MI \n", + "80438 Brunswick, OH \n", + "80441 Scribner, NE \n", + "80453 Minersville, PA \n", + "80457 Syracuse, NY \n", + "80458 Parma, OH \n", + "80459 Roswell, NM \n", + "80465 South Londonderry, VT \n", + "80467 Gold Hill, NC \n", + "80469 Milford, DE \n", + "80473 Trevose, PA \n", + "80482 Spearfish, SD \n", + "80489 Pleasure Island, NC \n", + "80494 Boca Raton, FL \n", + "80495 Kingston, NH \n", + "80496 New York City, NY \n", + "80500 Johnsburg, IL \n", + "80503 Bethel Park, PA \n", + "80505 Clarence, NY \n", + "80509 Chesapeake Beach, MD \n", + "80510 Rogersville, TN \n", + "80519 Glen Ellyn, IL \n", + "80522 Lawrence, MA \n", + "80524 Olympia, WA \n", + "80525 Iowa City, IA \n", + "80528 North Royalton, OH \n", + "80536 Wyoming, PA \n", + "80541 Orland park, IL \n", + "\n", + "[15516 rows x 4 columns]" + ] + }, + "execution_count": 99, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Shows how many rows has a not null shape AND a not null color\n", + "ufo[(ufo.Shape.notnull()) & (ufo.Colors.notnull())]" + ] + }, + { + "cell_type": "code", + "execution_count": 100, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(15510, 4)\n", + "(80543, 4)\n" + ] + } + ], + "source": [ + "ufo.dropna() # drop a row if ANY values are missing\n", + "print ufo.dropna().shape\n", + "ufo.dropna(how='all') # drop a row only if ALL values are missing\n", + "print ufo.dropna(how='all').shape" + ] + }, + { + "cell_type": "code", + "execution_count": 101, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ColorsShapeTimeLocation
0NaNTRIANGLE6/1/1930 22:00Ithaca, NY
1NaNOTHER6/30/1930 20:00Willingboro, NJ
2NaNOVAL2/15/1931 14:00Holyoke, CO
3NaNDISK6/1/1931 13:00Abilene, KS
4NaNLIGHT4/18/1933 19:00New York Worlds Fair, NY
\n", + "
" + ], + "text/plain": [ + " Colors Shape Time Location\n", + "0 NaN TRIANGLE 6/1/1930 22:00 Ithaca, NY\n", + "1 NaN OTHER 6/30/1930 20:00 Willingboro, NJ\n", + "2 NaN OVAL 2/15/1931 14:00 Holyoke, CO\n", + "3 NaN DISK 6/1/1931 13:00 Abilene, KS\n", + "4 NaN LIGHT 4/18/1933 19:00 New York Worlds Fair, NY" + ] + }, + "execution_count": 101, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ufo.head() # Without an inplace=True, the dataframe is unaffected!" + ] + }, + { + "cell_type": "code", + "execution_count": 109, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "ufo.Colors.fillna(value='Unknown', inplace=True) # Permanent" + ] + }, + { + "cell_type": "code", + "execution_count": 110, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ColorsShapeTimeLocation
0UnknownTRIANGLE6/1/1930 22:00Ithaca, NY
1UnknownOTHER6/30/1930 20:00Willingboro, NJ
2UnknownOVAL2/15/1931 14:00Holyoke, CO
3UnknownDISK6/1/1931 13:00Abilene, KS
4UnknownLIGHT4/18/1933 19:00New York Worlds Fair, NY
5UnknownDISK9/15/1934 15:30Valley City, ND
6UnknownCIRCLE6/15/1935 0:00Crater Lake, CA
7UnknownDISK7/15/1936 0:00Alma, MI
8UnknownCIGAR10/15/1936 17:00Eklutna, AK
9UnknownCYLINDER6/15/1937 0:00Hubbard, OR
\n", + "
" + ], + "text/plain": [ + " Colors Shape Time Location\n", + "0 Unknown TRIANGLE 6/1/1930 22:00 Ithaca, NY\n", + "1 Unknown OTHER 6/30/1930 20:00 Willingboro, NJ\n", + "2 Unknown OVAL 2/15/1931 14:00 Holyoke, CO\n", + "3 Unknown DISK 6/1/1931 13:00 Abilene, KS\n", + "4 Unknown LIGHT 4/18/1933 19:00 New York Worlds Fair, NY\n", + "5 Unknown DISK 9/15/1934 15:30 Valley City, ND\n", + "6 Unknown CIRCLE 6/15/1935 0:00 Crater Lake, CA\n", + "7 Unknown DISK 7/15/1936 0:00 Alma, MI\n", + "8 Unknown CIGAR 10/15/1936 17:00 Eklutna, AK\n", + "9 Unknown CYLINDER 6/15/1937 0:00 Hubbard, OR" + ] + }, + "execution_count": 110, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ufo.head(10)" + ] + }, + { + "cell_type": "code", + "execution_count": 111, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "ufo.fillna(value = 'Unknown', inplace = True) # Permanent for the entire dataframe" + ] + }, + { + "cell_type": "code", + "execution_count": 114, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
CityColors ReportedShape ReportedStateTimeMonthDayYear
0IthacaNaNTRIANGLENY6/1/1930 22:00611930
1WillingboroNaNOTHERNJ6/30/1930 20:006301930
2HolyokeNaNOVALCO2/15/1931 14:002151931
3AbileneNaNDISKKS6/1/1931 13:00611931
4New York Worlds FairNaNLIGHTNY4/18/1933 19:004181933
\n", + "
" + ], + "text/plain": [ + " City Colors Reported Shape Reported State Time \\\n", + "0 Ithaca NaN TRIANGLE NY 6/1/1930 22:00 \n", + "1 Willingboro NaN OTHER NJ 6/30/1930 20:00 \n", + "2 Holyoke NaN OVAL CO 2/15/1931 14:00 \n", + "3 Abilene NaN DISK KS 6/1/1931 13:00 \n", + "4 New York Worlds Fair NaN LIGHT NY 4/18/1933 19:00 \n", + "\n", + " Month Day Year \n", + "0 6 1 1930 \n", + "1 6 30 1930 \n", + "2 2 15 1931 \n", + "3 6 1 1931 \n", + "4 4 18 1933 " + ] + }, + "execution_count": 114, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "''' Fun Stuff '''\n", + "\n", + "ufo = pd.read_csv('../data/ufo.csv')\n", + "\n", + "# Make a new month column\n", + "ufo['Month'] = ufo['Time'].apply(lambda x:int(x.split('/')[0]))\n", + "\n", + "'''\n", + "the apply function applys the lambda funciton to every element in the Series\n", + "lambda x:x.split('/')[0] will take in x and split it by '/' and return the first element\n", + "so if we pass in say 9/3/2014 01:22 into the function we would get:\n", + "9 i.e. the month\n", + "'''\n", + "\n", + "# similar for day\n", + "ufo['Day'] = ufo['Time'].apply(lambda x:int(x.split('/')[1]))\n", + "\n", + "# for year, I need the [:4] at the end to remove the time\n", + "ufo['Year'] = ufo['Time'].apply(lambda x:int(x.split('/')[2][:4]))\n", + "ufo.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 115, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 115, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEZCAYAAACZwO5kAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nUSnRC3mjAAAAAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "sightings_per_year = ufo.groupby('Year').City.count()\n", + "\n", + "sightings_per_year.plot(kind='line', \n", + " color='r', \n", + " linewidth=1, \n", + " title='UFO Sightings by year')" + ] + }, + { + "cell_type": "code", + "execution_count": 116, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 116, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYMAAAEPCAYAAACgFqixAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# -----Analysis-----\n", + "# Clearly, Aliens love the X-Files (which came out in 1993).\n", + "# Aliens are a natural extension of the target demographic so it makes sense.\n", + "\n", + "# Well hold on Sinan, the US population is always increasing\n", + "# So maybe there's a jump in population which would make sense!\n", + "# US Population data from 1930 as taken from the Census\n", + "\n", + "us_population = pd.read_csv('../data/us_population.csv')\n", + "us_population.plot(x = 'Date', y = 'Population', legend = False)\n", + "# Seems like a steady increase to me..\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 117, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 117, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAEcCAYAAADXxE9kAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nA29USNyQpbAIAAAAAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plot the sightings in in July \n", + "ufo[(ufo.Year==2014) & (ufo.Month == 7)].groupby('Day').City.count().plot( kind='bar',\n", + " color='b', \n", + " title='UFO Sightings in July 2014')\n", + " \n", + "\n", + "# -----Analysis-----\n", + "# Aliens are love the 4th of July. The White House is still standing. Therefore\n", + "# it follows that Aliens are just here for the party.\n", + "\n", + "# Well maybe it's just 2014?" + ] + }, + { + "cell_type": "code", + "execution_count": 118, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([,\n", + " ,\n", + " ,\n", + " ], dtype=object)" + ] + }, + "execution_count": 118, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAawAAAIzCAYAAABcEC2nAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzs3X2cXGV9///XOwmJbO6IILstIVkQInHVBFoCv6rNJrGC\ngtz2FwWjRG4qUpXeWYM3ZOOvPxX7sNbS8qPKjVFERJESxIaYwCpUbhSJQBIghe4m8DWLEQ0klCRL\nPr8/5uwy2cxs5nZnzsz7+XjMIzPXOde5rrOTmc9c51zncxQRmJmZ1btRte6AmZlZIRywzMwsFRyw\nzMwsFRywzMwsFRywzMwsFRywzMwsFRywzMwsFRywzCpE0lhJ10jqkbRN0i8lnZy1fIGkDZK2S1oj\naVrWsk5Jd0n6vaSnc2z7c5IekbRb0uUjtU9m9cQBy6xyxgCbgLdHxGTgs8DNkqZJOhi4Bfg08Frg\nIeC7WXV3ANcCf5dn2xuBTwA/rFLfzeqenOnCrHok/QroAg4BzouItyXlLcBWYHZEPJm1/gLg6xFx\nZJ7tfQvYGBGfq3bfzeqNR1hmVSKpFTgaWAd0AL8aWBYRLwH/nZSbWQEcsMyqQNIY4AbgG8kIagKw\nbchqLwATR7pvZmnlgGVWYZJEJljtBD6WFG8HJg1ZdTLw4gh2zSzVHLDMKu9aMueszoqIV5KydcDs\ngRUkjQden5SbWQEcsMwqSNLVwDHAaRGxK2vRrUCHpDMljQOWAmsHJlwoYxwwFhglaZykA7K2O0bS\na8h8Zg9Ilvvza03FswTNKiS5rqoHeBkYGFkF8OGI+I6k+cC/AdOAB4DFEbEpqTsXuDtZf8BPImJ+\nsvx64Lwhyz8UEd+s3h6Z1Zf9BixJ1wKnAn0R8Zas8o8BlwD9wB0RsSQpvww4Pym/NCJWVanvZmbW\nRMYUsM71wJXA4C85SZ3Ae4A3R0S/pEOS8pnAQmAmMBVYLeno8DDOzMzKtN9j4BFxL/C7IcUfAb4Y\nEf3JOluT8tOBmyKiPyJ6yFydP6dy3TUzs2ZV6knbGcCfSrpf0t2S/igpPwzYnLXes0mZmZlZWQo5\nJJiv3pSIOFHS8cD3gJypZMzMzCqh1IC1GfgBQET8XNIrSXLPZ8nMgBowNSnbhySf1zIzs31EhHKV\nF3pIUMljwH8AA9NtZwBjI+K3wArgvcltFo4AjgIeHKZTOR9z587NuyzXY+nSpUWtX0qdkWjD++59\nr6d+ed+977XY9+Hsd4Ql6UagEzhY0iYyFzxeB1wv6VEy6Wc+mASg9ZJuBtYDu4FLYn89yKG9vb3Y\nKg3D+96cvO/NyftenP0GrIg4N8+iD+RZ/wvAF4ruSRa/ic3J+96cvO/NqZR9H93V1VXxjhRi2bJl\nXcO1XezOlLLz9dhGKXUapY1S6jRKG6XUaZQ2SqnTKG2UUqdR2shXZ9myZXR1dS3LtX7NUjNJKuVo\noZmZNTBJRJmTLppSW1s7knI+2traa909M6tD7e35vzf8ePVRyojMI6xhZG5rlK+P2u+MFjNrPskI\nodbdqHv5/k4eYZmZWertN2BJulZSn6RHciz7W0l7JL02q+wySRslbZD0zkp32MzMmlMhI6zrgZOG\nFkqaCvwZ0JtVlp2t/V3AVcocVzMzMytLqdnaAb4CfGJImbO1m5lZVZR0DkvSacDmiHh0yCJnazcz\nG2K4GceVeBQza3nXrl1ceOGFtLe3M3nyZI477jhWrlw5uHzNmjXMnDmTCRMmsGDBAjZt2jS4rLu7\nm/nz53PQQQdx5JH75ju//PLLectb3sIBBxzA5z73ubL+ZrkUnfxW0oHAp8gcDixL9oXDnZ2ddHZ2\nlrtJM7O609fXS/4Zx5XYfuFnXvr7+5k2bRr33HMPhx9+OHfccQcLFy7kscceY/z48Zx99tlcd911\nnHrqqXzmM5/hve99L/fddx8A48eP54ILLuDcc8/l85///D7bPvroo/nHf/xHrr766oL7093dTXd3\nd0HrFjStXdJ04PaIeIukNwGrgZfIJMQdyMg+BzgfICK+mNRbCSyNiAdybNPT2s2s4eSarj38d0lF\nWi3r+2jWrFl0dXWxdetWli9fzr333gvASy+9xCGHHMLatWuZMWPG4Ppr1qzhoosu4umnn865vQ98\n4AMcffTRXH755fl7XMVp7YPZ2iPisYhoi4gjI+II4Bng2Ih4jiKztZuZWW319fWxceNGOjo6WLdu\nHbNmzRpc1tLSwlFHHcW6detq2MNXFTKt/UbgZ8AMSZskfWjIKsGrwWw9MJCt/UeUmK3dzMyqr7+/\nn0WLFrF48WJmzJjB9u3bmTx58l7rTJo0iRdffLFGPdxbOdnaB5YfOeR12dnazcysuiKCRYsWMW7c\nOK688koAJkyYwAsvvLDXetu2bWPixIm16OI+nOnCzKwJXXDBBWzdupUf/OAHjB49GoCOjg7Wrl07\nuM6OHTt46qmn6OjoqFU39+KAZWbWZC6++GIef/xxVqxYwdixYwfLzzzzTNatW8ett97Kzp07WbZs\nGbNnzx6ccBER7Ny5k127drFnzx527tzJ7t27B+v39/fz8ssvs2fPHnbv3s3OnTvZs2dP5Tpe7G2N\nK/XINF3fgIDI86j//pvZyMv13TD8d0klHoV/H/X29oakOPDAA2PChAkxYcKEmDhxYtx4440REbFm\nzZo45phjoqWlJebNmxe9vb2Ddbu7u0NSjBo1avAxb968weWLFy/eZ/ny5csL/jtlleeMG87WPgxP\nazezYuWart3W1p5ci1Udra3T2bKlp2rbr4aqTGvPlfxW0peS5LZrJd0iaVLWMie/NTPLsmVLT1WP\nWKUtWJWq1OS3q4COiJhNJl/gZQCS3oiT35qZWRWUlPw2IlZHxMCZtPvJZLsAOA0nvzUzsyqoxCzB\n88lcJAxOfmtmZlVSVsCS9Glgd0R8p0L9MTMzy6nobO0DJC0G3g3Mzyp+Fjg86/VAYtycnK3dzKy5\nVSNbezuZbO1vTl6fDHwZ+NOI+G3Wem8Evg2cQOZQ4I+Bo3PNX/e0djNrRO3t7fT2Vm8Ke6OYPn06\nPT09+5QPN619vwErSX7bCRwM9AFLydwPaywwEKzuj4hLkvUvAy4AdgOXRsSqPNt1wDIzs72UFbCq\nxQHLzMyGqsT9sMzMzGrKAcvMzFLBAcvMzFLBAcvMzFLBAcvMzFKh1GztUyStkvSEpDslTc5a5mzt\nZmZWcaVma18CrI6INwB34WztZmZWZSVlawdOB5Ynz5cDZyTPna3dzMyqotRzWIdGRB9ARGwBDk3K\nna3dzMyqolKTLpzywczMqqrUbO19klojok9SG/BcUu5s7WZmVrCRyNZ+BfB8RFwh6ZPAlIhY4mzt\nZmZWjuFyCe53hJWdrV3SJjLZ2r8IfE/S+UAvmZmBRMR6STcD68lka7+k7qOSmZmlgrO1D8MjLDOz\nkeVs7WZmlnoOWGZmlgoOWGZmlgoOWGZmlgoOWGZmlgplBSxJfy3pMUmPSPq2pLHDZXI3MzMrVckB\nS9IfAh8DjouIt5C5pusc8mRyNzMzK0e5hwRHA+MljQEOJJOGKV8mdzMzs5KVHLAi4v8AXwY2kQlU\n2yJiNdCaJ5O7mZlZyUpNfoukg8iMpqYD28ikano/+6aGyJsOwslvzcyaW8WT3+asKP05cFJEXJS8\n/gBwIjAf6MzK5H53RMzMUd+pmczMbC/VSs20CThR0muU+WZfQCbp7QpgcbLOecBtZbRhZmYGlJn8\nVtJS4H1kMrM/DFwITARuJnNfrF5gYUT8Pkddj7DMzGwvw42wnK19GA5YZmYjy9nazcws9RywzMws\nFRywzMwsFZoqYLW1tSNpn0dbW3utu2ZmZvtR7izBycA1wJuAPcD5wJPAd8lcUNxDZpbgthx1R3zS\nRf5JFLknUHjShZnZyKrmpIuvAj9KLgyeBTyOk9+amVkVlJPpYhLwcES8fkj548DcrEwX3RFxTI76\nHmGZmdleqjXCOgLYKul6Sb+U9DVJLTj5rZmZVUE5AWsMcBzwbxFxHLCDzOHAgpPfmpmZFarkbO3A\nM8DmiPhF8voWMgGrT1Jr1iHB5/JtwNnazcya24hkaweQ9BPgooh4Mskr2JIsej4irpD0SWBKRCzJ\nUdfnsMzMbC9VyyUoaRaZae0HAE8DHyJzF+K6TH7rgGVmVt+c/PbVNnHAMjOrX05+a2ZmqeeAZWZm\nqeCAZWZmqeCAZWZmqeCAZWZmqVB2wJI0KknNtCJ5PUXSKklPSLozyehuZmZWlkqMsC4F1me9drZ2\nMzOruLIClqSpwLvJXDw84HRgefJ8OXBGOW2YmZlB+SOsrwCfYO+ra52t3czMKq7kgCXpFKAvItYC\nOa9KTjgdhJlZg2lra0fSPo+2tvaqtVlOtva3AqdJejdwIDBR0reALc7WbmbW2Pr6esk1HunrG278\nsq8Ry9Y+uBFpLvC3EXGapC8Bv3W2djOzxlXs92kx2x3JXIJfBP5M0hPAguS1mZlZWZytPbPEIywz\nsyI0ygjLzMys4hywzMwsFVIbsGoxpdLMzGqnLgJWvuAzXAB6dUrl3o9MuZmZNZq6mHRRyuSGUk74\nedKFmVllpGrShaSpku6StE7So5I+npQ7W7uZ1ZxPGzSekkdYSRaLtohYK2kC8BCZxLcfInPh8JcK\nvXDYIywzq7RqjQAsI1UjrIjYkuQRJCK2AxuAqThbuzUh/5o3q76KTLqQ1A7MBu7H2dqtCRU7CaiU\niUZmza6c5LcAJIcDvw9cGhHbJQ0dC+YdG2Ynv4VuoLPc7tRcW1t7zi+p1tbpbNnSM/IdsrqUL3Fo\nZllxyUPN0mzEkt9KGgP8EPjPiPhqUrYB6MzK1n53RMzMUbchz2H5uHn9GYkfET4/Wl2lvIeN8lms\n1x/BqTqHlbgOWD8QrBIrgMXJ8/OA28psw2qglENW9Xoep1Gu2avXv+9IaJT3sBTNvO9DlTNL8K3A\nT4FHefWv+CngQeBm4HCgF1gYEb/PUd8jrDrWSPs+Ev3y/63C5RsxQP5Rw0h83kvp10io1/e9Wn/f\n4UZYvnC4pDYq269i1fYQF1Rq30fqC8IBq7400ud9JNTyOwUq9yOi0L+vA1aJder1S6W2beRvp16/\nIOrxPanX/1ulKPYHVCN93kdCs33eq3kOy6zheMp5cXyOxUaKA5bZEPm+gNP4JVzsRA0H6+LU60SY\neu1XuXxIsKQ2KtevkToBXax6OkRQrnp835v5/3wz73spGmXf6/qQoKSTJT0u6UllcgpaDiP1a75R\nf3GZpYlHsOWpSsCSNAr4V+AkoAM4R9IxhW+hu8gWi12/XtsopU5h6+8dGO+muKBYbJ+qV6f8wFts\nv4pdf6TqNEobpdRJbxv7/kCtx8/iSLRRWp1qjbDmABsjojcidgM3kUmKW6DuIpsrdv16baOUOo3S\nRmF19v7AL6X40Wix/Sp2/ZGq0yhtlFKnUdoopU6jtFFanWoFrMOAzVmvn0nKCtRT2d6kSk+tO1BD\nPbXuQA311LoDNdRT6w7UUE+tO1BDPUXXqNNZgj217kAN9dS6AzXUU+sO1FBPrTtQQz217kAN9dS6\nAzXUU3SNqswSlHQi0BURJyevlwAREVdkrVO7Kx3NzKxujWimC0mjgSeABcCvyeQXPCciNlS8MTMz\nawpl3w8rl4h4RdJHgVVkDjte62BlZmblqNmFw2ZmZsWo00kXZmZme3PAMjOzVHDAMjOzVHDAMjOz\nVHDAMqsQSWMlXSOpR9I2Sb+UdHLW8gWSNkjaLmmNpGlZyzol3SXp95KeHrLd10m6UdKzkn4n6R5J\nc0Zy38zqgQOWWeWMATYBb4+IycBngZslTZN0MHAL8GngtcBDwHez6u4ArgX+Lsd2J5C5lvHYpO43\ngTsktVRrR8zqkae1m1WRpF8BXcAhwHkR8bakvAXYCsyOiCez1l8AfD0ijtzPdrcBnRHxcLX6blZv\nPMIyqxJJrcDRwDoyt9n51cCyiHgJ+O+kvNjtzgYOSOqbNQ0HLLMqkDQGuAH4RjKCmgBsG7LaC8DE\nIrc7icwhwa6IeLESfTVLCwcsswpT5l7gNwA7gY8lxduBSUNWnQwUHHQkvQZYAfwsIr5Uga6apYoD\nllnlXUvmnNVZEfFKUrYOmD2wgqTxwOuT8v2SNBb4D2BTRFxc2e6apYMDllkFSboaOAY4LSJ2ZS26\nFeiQdKakcWRul7x2YMKFMsYBY4FRksZJOiBZNobMDMOXgMUjtzdm9cWzBM0qJLmuqgd4GRgYWQXw\n4Yj4jqT5wL8B04AHgMURsSmpOxe4O1l/wE8iYr6kP02W/W/W8gDeFRH/Vd29Mqsf+w1YkqaSOcnb\nCuwhM+X2XyRNIXMdyXQyH9KFEbEtqXMZcD7QD1waEauqtgdmZtYUCglYbUBbRKyVNIHMBY+nAx8C\nfhsRX5L0SWBKRCyR9Ebg28DxwFRgNXB0eChnZmZl2O85rIjYEhFrk+fbgQ1kAtHpwPJkteXAGcnz\n04CbIqI/InqAjYDTyJiZWVmKmnQhqZ3MTKf7gdaI6INMUAMOTVY7DNicVe3ZpMzMzKxkBQes5HDg\n98mck9rO3ieHyfHazMysYsYUslIyrfb7wLci4rakuE9Sa0T0Jee5nkvKnwUOz6o+NSkbuk0HODMz\n20dEKFd5oSOs64D1EfHVrLIVvHpNyHnAbVnl70tutXAEcBSZTNO5OpXzMXfu3LzLcj2WLl1a1Pql\n1BmJNrzv3vd66pf33ftei30fzn5HWJLeCrwfeFTSw2QO/X0KuILMrRPOB3qBhUkQWi/pZmA9sBu4\nJPbXiyHa29uLWb2heN+bk/e9OXnfi7PfgBWZCxNH51n8jjx1vgB8oejeJPwmNifve3PyvjenUvZ9\ndFdXV8U7Uohly5Z1Ddd2sTtTys7XYxul1GmUNkqp0yhtlFKnUdoopU6jtFFKnUZpI1+dZcuW0dXV\ntSzX+jVLzSSp2COFZmbW4CQRZU66aEptU9uQlPPRNrWt1t0zszrU3t6e93vDj1cfpYzIPMIahqTM\nzc1z6WK/M1rMrPkkI4Rad6Pu5fs7eYRlZmap54BlZmap4IBlZmap4IBlZmap4IBlZlZlw804rsSj\nmFnLu3bt4sILL6S9vZ3Jkydz3HHHsXLlysHla9asYebMmUyYMIEFCxawadOmwWXd3d3Mnz+fgw46\niCOPPHKv7f7mN7/h3HPP5bDDDmPKlCm8/e1v58EHc2blK1lByW/NzKx0fc/25Z9xXIntd/UVvG5/\nfz/Tpk3jnnvu4fDDD+eOO+5g4cKFPPbYY4wfP56zzz6b6667jlNPPZXPfOYzvPe97+W+++4DYPz4\n8VxwwQWce+65fP7zn99ru9u3b2fOnDn88z//M6973eu45pprOOWUU+jt7aWlpaUi++lp7cPwtHYz\nK1au6drDfpdUQld530ezZs2iq6uLrVu3snz5cu69914AXnrpJQ455BDWrl3LjBkzBtdfs2YNF110\nEU8//fSw2508eTLd3d0ce+yx+yzztHYzMytKX18fGzdupKOjg3Xr1jFr1qzBZS0tLRx11FGsW7eu\n6O2uXbuW3bt3c9RRR1Wsrw5YZmZNqr+/n0WLFrF48WJmzJjB9u3bmTx58l7rTJo0iRdffLGo7b7w\nwgt88IMfpKuri4kTJ1asvw5YZmZNKCJYtGgR48aN48orrwRgwoQJvPDCC3utt23btqKCzssvv8xp\np53Gn/zJn/D3f//3Fe2zA5aZWRO64IIL2Lp1Kz/4wQ8YPTpzB6mOjg7Wrl07uM6OHTt46qmn6Ojo\nKGibu3bt4owzzmDatGlcffXVFe+zA5aZWZO5+OKLefzxx1mxYgVjx44dLD/zzDNZt24dt956Kzt3\n7mTZsmXMnj17cMJFRLBz50527drFnj172LlzJ7t37wYyhxfPPvtsWlpa+MY3vlGVfjtgmZk1kU2b\nNvG1r32NtWvX0traysSJE5k0aRLf+c53OOSQQ7jlllv41Kc+xWtf+1p+8YtfcNNNNw3W/elPf8qB\nBx7IqaeeyubNm2lpaeGkk04C4Gc/+xk/+tGPWLVqFZMnTx7c7n/9139VrO+e1j4MT2s3s2Llmq7d\nNrUtcy1WlbQe1sqWZ7ZUbfvVUMq0dl84bGZWZWkLJvVqv4cEJV0rqU/SI1llSyU9I+mXyePkrGWX\nSdooaYOkd1ar42Zm1lwKOYd1PXBSjvJ/iojjksdKAEkzgYXATOBdwFWScg7tzMzMirHfgBUR9wK/\ny7EoVyA6HbgpIvojogfYCMwpq4dmZmaUN0vwo5LWSrpG0sCl0YcBm7PWeTYpMzMzK0upky6uAj4X\nESHpH4AvAxcWu5Gurq7B552dnXR2dpbYHTMzS6Pu7m66u7sLWregae2SpgO3R8RbhlsmaQkQEXFF\nsmwlsDQiHshRz9PazazhtLe309vbW+tu1L3p06fT09OzT3klprWLrHNWktoiYmCe5lnAY8nzFcC3\nJX2FzKHAo4DK3sHLzKyO5foStsrYb8CSdCPQCRwsaROwFJgnaTawB+gBPgwQEesl3QysB3YDl9T9\nMMrMzFLBmS6G4UOCZmYjyzdwNDOz1HPAMjOzVHDAMjOzVHDAMjOzVHDAMjOzVHDAMjOzVHDAMjOz\nVHDAMjOzVHDAMjOzVHDAMjOzVHDAMjOzVHDAMjOzVHDAMjOzVHDAMjOzVHDAMjOzVHDAMjOzVHDA\nMjOzVHDAMjOzVNhvwJJ0raQ+SY9klU2RtErSE5LulDQ5a9llkjZK2iDpndXquJmZNZdCRljXAycN\nKVsCrI6INwB3AZcBSHojsBCYCbwLuEqSKtddMzNrVvsNWBFxL/C7IcWnA8uT58uBM5LnpwE3RUR/\nRPQAG4E5lemqmZk1s1LPYR0aEX0AEbEFODQpPwzYnLXes0mZmZlZWcZUaDtRSqWurq7B552dnXR2\ndlaoO2Zmlgbd3d10d3cXtK4i9h9rJE0Hbo+ItySvNwCdEdEnqQ24OyJmSloCRERckay3ElgaEQ/k\n2GYU0nYtSYKuPAu7oN77b2aWNpKIiJxzHwo9JKjkMWAFsDh5fh5wW1b5+ySNlXQEcBTwYNE9NjMz\nG2K/hwQl3Qh0AgdL2gQsBb4IfE/S+UAvmZmBRMR6STcD64HdwCV1P4wyM7NUKOiQYFUa9iFBMzMb\nohKHBM3MzGrKAcvMzFLBAcvMzFLBAcvMzFLBAcvMzFLBAcvMzFLBAcvMzFLBAcvMzFLBAcvMzFLB\nAcvMzFLBAcvMzFLBAcvMzFLBAcvMzFLBAcvMzFLBAcvMzFLBAcvMzFLBAcvMzFLBAcvMzFJhTDmV\nJfUA24A9wO6ImCNpCvBdYDrQAyyMiG1l9tPMzJpcuSOsPUBnRBwbEXOSsiXA6oh4A3AXcFmZbZiZ\nmZUdsJRjG6cDy5Pny4EzymzDzMys7IAVwI8l/VzShUlZa0T0AUTEFuDQMtswMzMr7xwW8NaI+LWk\n1wGrJD1BJohlG/razMysaGUFrIj4dfLvbyT9BzAH6JPUGhF9ktqA5/LV7+rqGnze2dlJZ2dnOd0x\nM7OU6e7upru7u6B1FVHaAEhSCzAqIrZLGg+sApYBC4DnI+IKSZ8EpkTEkhz1o9S2R4ok6MqzsAvq\nvf9mZmkjiYhQrmXljLBagVslRbKdb0fEKkm/AG6WdD7QCywsow0zMzOgjIAVEf8DzM5R/jzwjnI6\nZWZmNpQzXaRQ29Q2JO3zaJvaVuuumZlVTbmzBK0G+p7ty3lura+rb8T7Ylastqltmf/DObQe1sqW\nZ7aMcI8sLRywzGxE5fvBBf7RZcPzIUEzM0sFByyzIfKdI/R5QkuLRj3P7UOCZkP4kJWlXaOe526q\nEVaj/uowM2sGTTXCatRfHWZmzaCpRlhmzcZHFayRNNUIqx75mhSrJh9VsEZSFyOsZp6VNfiFkuOR\nL5CNhEZ6TxpllNEo+9FI/J4UrhLfKXUxwmqkWVn5Rky1Hi0V269Gek8aZZTRKPvRSBrlPRmJIz2V\n+E6pi4DVSOr1P3C99svqSylfXI3yI61ejcR+pOUHqgOWVUyjfEE0s1K+uOr1x1C99qtYjbIflZDa\ngOUvx/pT7AerkX7Nm1n1pTZg+VdH+jXSr3kH0ury39cgxQHLrJ7UayBtFI3y922ky1hq8SPCAcvM\nbISkZXJDIWrxI6Jq12FJOlnS45KelPTJarVjZlYJjXTtYaOqSsCSNAr4V+AkoAM4R9IxBW/gf4ps\nsNj167WNUuo0Shul1ElxG2V/OaZ438uuU6U29rqI/zyKv4g/xfs+4m2UWKdaI6w5wMaI6I2I3cBN\nwOkF1+4psrVi16/XNkqp0yhtlFInxW3sk+FkLsV9OVapXyPeRil1GqWNUuo0Shsl1qlWwDoM2Jz1\n+pmkrDC/r3R3UsT73py8783J+16UusgluA+/ic3J+96cvO/NqYR9V0RUvB+STgS6IuLk5PUSICLi\niqx1Kt+wmZmlXkQoV3m1AtZo4AlgAfBr4EHgnIjYUPHGzMysKVTlOqyIeEXSR4FVZA47XutgZWZm\n5ajKCMvMzKzS6nPShZmZ2RAOWGZmlgoOWGZmlgoOWGZmlgoOWGYVImmspGsk9UjaJumXkk7OWr5A\n0gZJ2yWtkTQta1mnpLsk/V7S0zm2fZek55LlD0s6baT2y6xeOGCZVc4YYBPw9oiYDHwWuFnSNEkH\nA7cAnwZeCzwEfDer7g7gWuDv8mz7UuCwiDgI+DBwg6TW6uyGWX3ytHazKpL0KzJpbQ8BzouItyXl\nLcBWYHZEPJm1/gLg6xFx5DDbnAN0A38aEb+oXu/N6otHWGZVkoyAjgbWkbnNzq8GlkXES8B/J+WF\nbu92Sf8L3A/c7WBlzcZ3HDarAkljgBuAb0TEk5ImAM8NWe0FYGKh24yI9yRpz94BzKxYZ81SwiMs\nswqTJDLBaifwsaR4OzBpyKqTgReL2XZEvBIRdwInSTq13L6apYkDllnlXUvmnNVZEfFKUrYOmD2w\ngqTxwOuT8lKMSeqbNQ0HLLMKknQ1cAxwWkTsylp0K9Ah6UxJ44ClwNqBCRfKGAeMBUZJGifpgGTZ\nGySdLOmtya9RAAAgAElEQVQ1ksZIWgS8HfjJSO6bWa15lqBZhSTXVfUALwMDI6sAPhwR35E0H/g3\nYBrwALA4IjYldecCdyfrD/hJRMyXdAzwDTLnrV4BNgL/b0SsqPpOmdWR/QYsSdcCpwJ9EfGWpGwW\ncDXwGmA3cMnAjCVJlwHnA/3ApRGxqnrdNzOzZlHIIcHrgZOGlH0JWBoRx5I5tPGPAJLeCCwk80vw\nXcBVyQloMzOzsuw3YEXEvcDvhhTvITPDCeAg4Nnk+WnATRHRHxE9ZA5dzKlMV83MrJmVeh3WXwN3\nSvoyIOBPkvLDgPuy1ns2KTMzMytLqbMEP0Lm/NQ0MsHrusp1yczMbF+ljrDOi4hLASLi+5KuScqf\nBQ7PWm8qrx4u3IskT080M7N9RETOuQ+FjrCUPAY8m0zDHUjWuTEpXwG8L7nNwhHAUcCDw3Qq52Pu\n3Ll5l+V6LF26tKj1S6kzEm14373v9dQv77v3vRb7Ppz9jrAk3Qh0AgdL2kRmVuBFwL8kec1eBv4i\nCUDrJd0MrOfV6e5Fj6Ta29uLrVIV7W1t9Pb1Db5etmzZ4PPpra30bNlS+TbrZN9rwfvenLzvzamU\nfd9vwIqIc/Ms+uM8638B+ELRPclSL29ib1/f4FWcXcljgLICWSXVy77Xgve9OXnfm1Mp+16XqZk6\nOzurun5JbRTdwgj1q0HaKKVOo7RRSp1GaaOUOo3SRil1GqWNUuvULDWTpFKOFo4oSeTroWC/x1vN\nzKw4kog8ky58Pywzswpqb2+nt7e31t2oe9OnT6enp6eoOiXlEkzKPwZcQiZn4B0RsSQpLyiXoEdY\nZtaIkhFCrbtR9/L9ncodYV0PXAl8M2uDncB7gDdHRL+kQ5LymbyaS3AqsFrS0XUfmczMrO6Vmkvw\nI8AXI6I/WWdrUn46ziVoZmZVUOoswRnAn0q6X9Ldkv4oKT8M2Jy1nnMJmplZRZQ66WIMMCUiTpR0\nPPA94MjKdcvMzGxvpY6wNgM/AIiInwOvSDqYzIhqWtZ6eXMJAnR1dQ0+uru7S+yKmVl9a29rQ1LV\nHu1tbQX3ZdeuXVx44YW0t7czefJkjjvuOFauXDm4fM2aNcycOZMJEyawYMECNm3aNLisu7ub+fPn\nc9BBB3HkkfuOUebPn8+hhx7KQQcdxLHHHsuKFfu/KXZ3d/desWBYheR8AtqBR7Ne/wWwLHk+A+hN\nnr8ReBgYCxwB/DfJTMQc24x6B0TkeaSh/2Y28nJ9Nwz3XVKJRzHfRzt27Ihly5bFpk2bIiLihz/8\nYUycODF6e3tj69atMXny5Ljlllti586d8YlPfCJOPPHEwboPPvhg3HDDDfH1r389jjjiiH22/cgj\nj8SuXbsiIuKBBx6IiRMnxpYtWwr+O2WV54xFpeYSvA64XtKjwE7gg0kEqkguQTMzq46WlhYuv/zy\nwdennHIKRxxxBA899BBbt27lTW96E2eddRaQOQp2yCGH8OSTTzJjxgyOP/54jj/+eNasWZNz229+\n85v3et3f38/mzZtpbW2tSN/LySX4gTzrl51L0MzMRkZfXx8bN26ko6ODq666ilmzZg0ua2lp4aij\njmLdunXMmDGjoO295z3vYfXq1ezcuZN3vetd/PEf50w7WxJnujAza1L9/f0sWrSIxYsXM2PGDLZv\n386hhx661zqTJk3ixRdfLHibt99+O6+88gqrV69mw4YNFe1vXSa/NTOz6ooIFi1axLhx47jyyisB\nmDBhAi+88MJe623bto2JEycWte3Ro0dz0kknceedd/LDH/6wYn12wDIza0IXXHABW7du5Qc/+AGj\nR48GoKOjg7Vr1w6us2PHDp566ik6OjpKaqO/v5+nnnqqIv2FAgKWpGsl9Ul6JMeyv5W0R9Jrs8ou\nk7RR0gZJ76xYT83MrCIuvvhiHn/8cVasWMHYsWMHy88880zWrVvHrbfeys6dO1m2bBmzZ88ePH8V\nEezcuZNdu3axZ88edu7cye7duwF44oknWLlyJS+//DL9/f3ccMMN3HPPPcydO7dyHc83fXDgAbwN\nmA08MqR8KrAS+B/gtUnZTDLT2seQmQrvae1m1lRyfTcM910y0tPae3t7Q1IceOCBMWHChJgwYUJM\nnDgxbrzxxoiIWLNmTRxzzDHR0tIS8+bNi97e3sG63d3dISlGjRo1+Jg3b15ERGzYsCFOOOGEmDRp\nUkyZMiXmzJkTt912W1F/p6zynPGooPthSZoO3B57Z2v/HvA5YAXwRxHxvKQlSWNXJOv8J9AVEQ/k\n2GYU0nYtOVu7mRUrVxby9rY2eqt0l3KA6a2t9GzZUrXtV0O1srXn2uBpwOaIeFTaa7uHAfdlvXYu\nQTNremkLJvWq6IAl6UDgU8CfVb47ZmZmuZUywno9mfNTv1JmeDUV+KWkOZSQS3BAZ2cnnZ2dJXTH\nzMzSqru7u+BcsoWew2oncw7rzTmW/Q9wXET8TtIbgW8DJ5A5FPhjIOcNHH0Oy8wake84XJhSzmEV\nMq39RuBnwAxJmyR9aMgqQeb7m4hYDwzkEvwRziVoZmYVUtAIqyoNe4RlZg3II6zCjNgsQTMzy236\n9OkMmT1tOUyfPr3oOh5hDcMjLDOzkVXWOSwzM7N64IBlZmapUFLyW0lfSpLbrpV0i6RJWcuc/NbM\nzCqukBHW9cBJQ8pWAR0RMRvYCFwGkFyHtZBMEtx3AVfJZx/NzKwC9huwIuJe4HdDylZHxJ7k5f1k\nMloAnAbcFBH9EdFDJpjNqVx3zcysWVXiHNb5ZC4Shkx2i81Zy5z81szMKqKs67AkfRrYHRHfKaW+\ncwmamTW3auQSzHU/rMXARcD8iNiZlA29H9ZKYKnvh2VmZoWoxHVYSh4DGzwZ+ARw2kCwSqwA3idp\nrKQjgKOAB0vrtpmZ2av2e0gwSX7bCRwsaROwlMz9sMYCP04mAd4fEZdExHpJA8lvd+Pkt2ZmViFO\nzTQMHxI0MxtZTs1kZmap54BlZmap4IBlZmapUGouwSmSVkl6QtKdkiZnLXMuQTMzq7hScwkuAVZH\nxBuAu3AuQTMzq7KScgkCpwPLk+fLgTOS584laGZmVVHqOaxDI6IPICK2AIcm5c4laGZmVVFWLsEs\nJV2Q5FyCZmbNreq5BCVtADojok9SG3B3RMx0LkEzMytHxXMJkskZuDh5fh5wW1a5cwmamVnFlZpL\n8IvA9ySdD/SSmRmIcwmamVm1OJfgMHxI0MxsZDmXoJmZpZ4DlpmZpYIDlpmZpUJZAUvSX0t6TNIj\nkr6dzA7Mm2fQzMysVCUHLEl/CHwMOC65PmsMcA558gyamZmVo9xDgqOB8ZLGAAeSScWUL8+gmZlZ\nyUoOWBHxf4AvA5vIBKptEbEaaM2TZ9DMzKxk5RwSPIjMaGo68IdkRlrvZ9+8gr5YyczMylZO8tt3\nAE9HxPMAkm4F/gTok9SalWfwuXwbcPJbaG9ro7evL+ey6a2t9GzZMsI9MjMbORVPfpuzojQHuBY4\nHthJ5kaPPwemAc9HxBWSPglMiYglOeo708UItWFmlhbDZbooeYQVEQ9K+j7wMJm8gQ8DXwMmAjcP\nzTNoZmZWDucSHIZHWGZmI8u5BM3MLPUcsMzMLBUcsMzMLBXKzSU4WdL3JG2QtE7SCc4laGZm1VDu\nCOurwI8iYiYwC3gc5xI0M7MqKOc6rEnAwxHx+iHljwNzsy4c7o6IY3LU9yzBEWrDzCwtqjVL8Ahg\nq6TrJf1S0tckteBcgmZmVgXlBKwxwHHAv0XEccAOMocDnUvQzMwqrpxcgs8AmyPiF8nrW8gELOcS\nNDOzgoxILkEAST8BLoqIJyUtBVqSRc4lWEdtmJmlxXDnsMoNWLOAa4ADgKeBD5G5qePNwOEkuQQj\n4vc56jpgjVAbZmZpUbWAVQ4HrJFrw8wsLZxL0MzMUs8Byxpee1sbkvZ5tLe11bprZlYEB6wK85dj\n/ent6yNgn0e+Oz2bWX0q+xyWpFHAL4BnIuI0SVOA7wLTgR4yky625ajXkOew8tUpdv3h6lhxin1P\nzKx2qn0O61JgfdZr5xI0M7OKKzdb+1Tg3WSmtg84HViePF8OnFFOG5Xkw3VmZulV7gjrK8An2Dv9\nUt3mEvS5DDNLG//QflXJAUvSKUBfRKwlczogH58kMDMrkX9ov6qcXIJvBU6T9G7gQGCipG8BW5xL\n0MzMCjFiuQQHNyLNBf42mSX4JeC39ZhLcCRm8HmWYP3xLEFLs2b7/zvSmS6+CPyZpCeABclrMzOz\nsjRVLkGPsJpTs/1CtcbSbP9/nUvQzMxSzwHLrIF5SrQ1Egcss5QoJfh4SrQVIt//rXr7cVPOdVhT\nJd0laZ2kRyV9PCmfImmVpCck3SlpcuW6a9Dcv5qbed8dfKxa8v3fqrf/XyVPukiusWqLiLWSJgAP\nkUnL9CEy09q/5Gnt9dFGIyll34ut097WlvdDOr21lZ4tWwrubyWNxL5b/RmJ97CeJn9VZdJFRGxJ\nslwQEduBDcBU6jiXoFkh0vJr09InLYfe6lVFzmFJagdmA/dTx7kEzczyGYlg4h9D5SknNRMAyeHA\n7wOXRsR2SUPHjj7uYGZ1byCY5CIHk7pQVsCSNIZMsPpWRNyWFPc5l6CZNYN85ztrea4zbUYsl6Ck\nbwJbI+JvssquAJ53LsH6aaORjMTEg1Lek5H44vKki+pq5s97Pf2fr8qkC0lvBd4PzJf0sKRfSjoZ\nuIIicwn6RGT11eN08EZ634udct5I+16P/7ea3Ui8J7W4zKIucgmO1JTKevw1NFK/uOrxl3a97rvf\n9+LU4/+tUjTz+15PI7+qjLBqzb/q6o/fk/RrpJGfNZ7UjrAa5VdHve57KRpl35v5fa+nX9ojze97\ndftV6AX5DTnCMrPmUcro3SP++lKJa9CqFrAknSzpcUlPKjNb0FLEh4asnpRygt+5FxtPVQKWpFHA\nvwInAR3AOZKOKbR+d5HtFbt+vbZRSp1qtZH9Yb+b4j/w1epXI7ZRSp00t1Huj6Fq9Wuk2yilTqO0\nUWqdao2w5gAbI6I3InYDN5HJMViQ7iIbK3b9em2jlDqN0kYpdRqljVLqpLmNoSOfpTTnj6FS6jRK\nG6XWqVbAOgzYnPX6maSsID2V7k2K9NS6AzXUU+sO1FBPrTtQQz217kAN9dS6AzXUU0Kdupx00VPr\nDtRQT607UEM9te5ADfXUugM11FPrDtRQT607UEM9JdSpyrR2SScCXRFxcvJ6CRARcUXWOumZ72pm\nZiMm37T2agWs0cBAaqZfAw8C50TEhoo3ZmZmTaHs24vkEhGvSPoosIrMYcdrHazMzKwcNct0YWZm\nVoy6nHRhZmY2lAOWmZmlggOWmZmlggOWmZmlggOWWYVIGivpGkk9krbp1btwDyxfIGmDpO2S1kia\nlrWsU9Jdkn4v6elh2pgraY+kz1V7f8zqjQOWWeWMATYBb4+IycBngZslTZN0MHAL8GngtcBDwHez\n6u4ArgX+Lt/GJY0B/hm4vzrdN6tvntZuVkWSfgV0AYcA50XE25LyFmArMDsinsxafwHw9Yg4Mse2\nPglMAQ4FnomIy6u/B2b1wyMssyqR1AocDawjc5udXw0si4iXgP9OygvZ1nTgQ8DnyNzU1azpOGCZ\nVUFy+O4G4BvJCGoCsG3Iai8AEwvc5FeBzySBzqwpOWCZVZgkkQlWO4GPJcXbgUlDVp0MvFjA9t4D\nTIyI71eyn2ZpU5VcgmZN7loy56zeHRGvJGXrgPMGVpA0Hnh9Ur4/84E/kvTr5PVkoF/SmyPizMp1\n26y+eYRlVkGSrgaOAU6LiF1Zi24FOiSdKWkcmRvtrh2YcKGMccBYYJSkcZIOSOp+BpgBzEoeK4Cv\nkzmnZdY0HLDMKiS5ruovgNlAn6QXJb0g6ZyI2AqcDXweeB74Y+B9WdX/FPhf4IfA4cBLwJ0AEbEj\nIp4beCTr7YiI34/UvpnVg/1Oa09+9f2UzC+/McD3I2KZpClkriOZTubmkQsjYltS5zLgfKAfuDQi\nVlVtD8zMrCkUdB2WpJaIeCm5MeN/AR8n82vxtxHxpYHrQyJiiaQ3At8GjgemAquBo8MXfJmZWRkK\nOiSYNZV2HJlRVgCnA8uT8uXAGcnz04CbIqI/InqAjcCcSnXYzMyaU0EBS9IoSQ8DW4AfR8TPgdaI\n6AOIiC1krr4HOAzYnFX92aTMzMysZIWOsPZExLFkDvHNkdRBZpS112qV7pyZmdmAoq7DiogXJHUD\nJ5OZBdUaEX2S2oDnktWeJTPLacDUpGwvkhzgzMxsHxGRM/3YfkdYkg6RNDl5fiDwZ8AGMteCLE5W\nOw+4LXm+AnhfcquFI4CjgAfzdCrnY+7cuXmX5XosXbq0qPVLqTMSbXjfve/11C/vu/e9Fvs+nEJG\nWH8ALJc0ikyA+25E/EjS/WRunXA+0AssTILQekk3A+uB3cAlsb9eDNHe3l7M6g3F+96cvO/Nyfte\nnP0GrIh4FDguR/nzwDvy1PkC8IWie5Pwm9icvO/NyfvenErZ99FdXV0V70ghli1b1jVc28XuTCk7\nX49tlFKnUdoopU6jtFFKnUZpo5Q6jdJGKXUapY18dZYtW0ZXV9eyXOvX7AaOkoo9UmhmZg1OEpFn\n0oWztZuZVVB7ezu9vb217kbdmz59Oj09PUXV8QjLzKyCkhFCrbtR9/L9nYYbYTlbu5mZpYIDlpmZ\npYIDlpmZpYIDlpmZpYIDlplZlbVNm4akqj3apk0ruC+7du3iwgsvpL29ncmTJ3PcccexcuXKweVr\n1qxh5syZTJgwgQULFrBp06bBZd3d3cyfP5+DDjqII488Mm8bP/nJTxg1ahSXX355aX+wPPY7rV3S\nVOCbQCuwB/haRFwpaSlwEa8mvf1URKxM6viOw2Zmib7Nm+Huu6u3/XnzCl63v7+fadOmcc8993D4\n4Ydzxx13sHDhQh577DHGjx/P2WefzXXXXcepp57KZz7zGd773vdy3333ATB+/HguuOACzj33XD7/\n+c/n3f5f/dVfceKJJ1Zk37IVch1WP/A3EbFW0gTgIUk/Tpb9U0T8U/bKkmaSySs4k+SOw5J8x2Ez\nszrQ0tKy18jnlFNO4YgjjuChhx5i69atvOlNb+Kss84CoKuri0MOOYQnn3ySGTNmcPzxx3P88cez\nZs2avNv/8pe/zEknncRzzz2Xd51S7feQYERsiYi1yfPtZDK1D9yQMddc+dNpkDsODzeML2YIbmZW\nr/r6+ti4cSMdHR2sW7eOWbNmDS5raWnhqKOOYt26dQVtq7e3l+uvv57LL7+8KteiFZXpQlI7MBt4\nAHgb8FFJHwB+AfxtRGwjE8zuy6qW2jsODzeML2YIbmZWj/r7+1m0aBGLFy9mxowZbN++nUMPPXSv\ndSZNmsSLL75Y0PYuvfRS/uEf/oGWlpZqdLfwSRfJ4cDvkzkntR24CjgyImYDW4AvV6WHZmZWcRHB\nokWLGDduHFdeeSUAEyZM4IUXXthrvW3btjFx4sT9bu/222/nxRdf5M///M+r0l8ocIQlaQyZYPWt\niLgNICJ+k7XK14Hbk+cF3XEYMsdHB3R2dtLZ2Vlgt83MrBwXXHABW7du5Uc/+hGjR48GoKOjg+XL\nlw+us2PHDp566ik6Ojr2u7277rqLhx56iD/4gz8AMoFuzJgxPProo9x6661563V3d9Pd3V1QnwvK\nJSjpm8DWiPibrLK2iNiSPP9r4PiIOFfSG4FvAyeQORT4Y2CfSRdpyCUoKf/MnnnznC/MzPaRK0fe\nsN8llVDk99HFF1/MI488wurVq/c6fLd161aOPvporrvuOt797nfz2c9+lnvvvZef/exnQGZUtmvX\nLu666y4+8pGP8MQTTzBq1CgOOOAAduzYwY4dOwa39fGPf5zDDjuMz372sxx00EH79KGUXIKFTGt/\nK/B+4FFJDwMBfAo4V9JsMlPde4APJztU9h2HzcysOjZt2sTXvvY1XvOa19Da2gpkgsS///u/c845\n53DLLbfwl3/5lyxatIgTTjiBm266abDuT3/6U+bNm5cJwGQmZcydO5e77rqL8ePHM378+MF1Dzzw\nQMaPH58zWJXK2dqH4RGWmRUr18ihbdq0zCSuKmk9/HC2ZF3gmwZVGWGZmVl50hZM6pVTM5mZWSo4\nYJmZWSo4YJmZWSo4YJmZWSo4YJmZWSp4lqCZWQVNnz598Doly2/69OlF13HAMjOroJ6enlp3oWH5\nkKCZmaWCA5aZmaXCfgOWpKmS7pK0TtKjkj6elE+RtErSE5LulDQ5q85lkjZK2iDpndXcATMzaw6F\njLD6gb+JiA7g/wL+UtIxwBJgdUS8AbgLuAwgyda+EJgJvAu4Sj4DaWZmZdpvwIqILRGxNnm+HdhA\n5h5XpwMDN05ZDpyRPD8NuCki+iOiB9gIzKlwv83MrMkUdQ5LUjswG7gfaI2IPsgENWDgvsqHAdlp\niZ9NyszMzEpW8LR2SRPI3HX40ojYLmloXvii77XhOw6bmTW3atxxeAzwQ+A/I+KrSdkGoDMi+iS1\nAXdHxExJS4CIiCuS9VYCSyPigSHb9P2wzMxsL8PdD6vQQ4LXAesHglViBbA4eX4ecFtW+fskjZV0\nBHAU8GDRvTYzM8uy30OCkt4KvB94VNLDZA79fQq4ArhZ0vlAL5mZgUTEekk3A+uB3cAldT+UMjOz\nulfQIcGqNOxDgmZmNkQlDgmamZnVlAOWmZmlggOWmZmlggOWmZmlggOWmZmlggOWmZmlggOWmZml\nggOWmZmlggOWmZmlQiF3HL5WUp+kR7LKlkp6RtIvk8fJWct8t2EzM6u4QkZY1wMn5Sj/p4g4Lnms\nBJA0E99t2MzMqqCQOw7fC/wux6Jcgeh0fLdhMzOrgnLOYX1U0lpJ10ianJT5bsNmZlYVBd9xeIir\ngM9FREj6B+DLwIXFbsR3HDYza27VuOPwdOD2iHjLcMsKvdtwssy3FzEzs71U4vYiIuuclaS2rGVn\nAY8lz323YTMzq4pC7jh8I9AJHCxpE7AUmCdpNrAH6AE+DL7bsJmZVY/vODwMHxI0MxtZvuOwmZml\nngOWmZmlggOWmZmlggOWmZmlggOWmZmlggOWmZmlggOWmZmlggOWmZmlggOWmZmlQql3HJ4iaZWk\nJyTdmXV7Ed9x2MzMqqLUOw4vAVZHxBuAu4DLACS9Ed9x2MzMqqDUOw6fDixPni8Hzkien4bvOGxm\nZlVQ6jmsQyOiDyAitgCHJuW+47CZmVVFpSZdOG25mZlV1X7vh5VHn6TWiOhLbub4XFL+LHB41npT\nk7Kcurq6Bp93dnbS2dlZYnfMzCyNuru76e7uLmjdgu6HJakduD0i3py8vgJ4PiKukPRJYEpELEkm\nXXwbOIHMocAfA0fnuvFVo94Pq23aNPo2b96nvPXww9myaVOlu2hm1lCGux9WqXcc/iLwPUnnA71k\nZgb6jsOQCVY5glzfvHk16I2ZWePYb8CKiHPzLHpHnvW/AHyhnE6ZmZkN5UwXZmaWCg5YZmaWCg5Y\nZmaWCg5YZmaWCg5Ylipt06YhaZ9H27Rpte6amVVZqRcOm9WELxswa14eYZmZWSo4YJmZWSo4YJmZ\nWSqUdQ5LUg+wDdgD7I6IOZKmAN8FpgM9wMKI2FZmP83MrMmVO8LaA3RGxLERMXCjxpx3IzYzMytH\nuQFLObaR727EZmZmJSs3YAXwY0k/l3RhUtaa527EZmZmJSv3Oqy3RsSvJb0OWCXpCfa9+3BT3V7E\nzMyqo6yAFRG/Tv79jaT/AOaQ/27E+/Adh83MmlvF7zics6LUAoyKiO2SxgOrgGXAAnLcjThH/bq/\nt2MpdxzOWyfP+lYc/33NGltZdxweRitwq6RItvPtiFgl6RfAzUPvRmxmZlaOkgNWRPwPMDtH+fPk\nuRuxmZlZqZzpwszMUqGpApZvTWE2vHyfEX9OKsN/3/I01e1FfGsKs+Hl+4yAPyeV4L9veZpqhFWP\n/IvLzKwwTTXCqkf+xWVmVhiPsKxmPLosTinnYH3etrr89y1cJT7vHmFZzYzU6LJt2rRMW0O0Hn44\nWzZtqlg7xcjXJ8jfr1LOwfq8bXX571u4Snze6yJglfLhrccvoUZSyntSr+rxS8WHgq1QpXzXFVsn\nLZ/3ughYpXx46/FLqJE08xdqWj68aVWvP1Dr9X0fiZF1Wj7vVQtYkk4G/pnMebJrI+KKarXVbEbi\nF9dI9asepeXDWy+Kfd9H6gfqSPSrmdXi816VSReSRgH/CpwEdADnSDqm4A2sXVtcg8WuX69tFFhn\n8IN1993wla8MPs/367DUOsX0qew2imin5PWr2EbZJ99TvO/1+r6PxP/5Ea9TR22M+PtO9WYJzgE2\nRkRvROwGbiJzJ+LCpPhNHPE6jdJGKXXqqI29PrznnVc3X9p130YpdRqljVLqNEobJdapVsA6DMj+\npD6TlBVmy5ZK9yc9vO/NyfvenLzvRanP67D8JjYn73tz8r43pxL2veQbOA67UelEoCsiTk5eLwEi\ne+JFch8tMzOzveS7gWO1AtZo4Akydx/+NfAgcE5EbKh4Y2Zm1hSqMq09Il6R9FFgFa9Oa3ewMjOz\nklVlhGVmZlZp9TnpwszMbAgHLDMzS4VUBixJx0haIGnCkPKTh6kzR9LxyfM3SvobSe8uos1vFtnH\ntyVtvDPP8hMkTUqeHyhpmaTbJV0haXKeOh+XdHgRfRgr6YOS3pG8PlfSv0r6S0kHDFPvSEl/J+mr\nkv5J0sUDfTVrBpIOHYE2Dq52G42mrgOWpA/lKPs4cBvwMeAxSdkZND6fZztLgX8B/j9JXyCTNmo8\nsETSp3Osv2LI43bgrIHXedp4MOv5RUkbE4GlybT+oa4DXkqefxWYDFyRlF2fqw3g/wEekHSPpEsk\nvS7PegOuB04BLpX0LeD/Bh4AjgeuybMfHweuBl6TrDcO/v/2zjXWiquK479/oVSveC/PAE2R2hZK\nrXsQBtAAAAibSURBVC0UaWO0CpFGqQ/EBBNtYsUv/SQ02ERMWgOSxqIxbdQWPlRSgQa0lrT1g1Br\nQYlaBEIpF7w0sTyqkVYsWvogtsL2w15HJtPZ59y53DP3nMv6JTtnn7XXmrVnz561Z/a8mAjskDS7\ngb9BiQevYiR1SVop6aCkE5JekdRjshEll7U5Ie+UdI+k9ZJuyZWtStiMl7Ra0gOSRktaLqlb0iOS\nJhToj8ql0cBOSSMljUr4mJvJd0laI2mfpA2SxhXor5Q0xvIzJR0i7stHJc1K+Ngj6S5JlxeVJ2xm\nStom6WFJEyU9JelVSbskXVegP1zSCkkHTO+4pB2SFtbx0fTtniSE0LIJeLFA1g0Mt/ylwG7gdvv/\nbGI53cAQoAM4CXSa/N3AvgL9PcDDwGxglv0es/yshI9nM/ldwFjLvwfoLtDvyfrLle1N+SAeZHwS\nWAMcB7YAXwXeW6C/z36HAi8DQ+y/itY721aW7wB+a/n31WnfLmAlcBA4AbwC9JhsRB+2++YCWSdw\nD7AeuCVXtiqxnPHAauABYDSw3NbvEWBCwmZULo0GjgAjgVEF+nNz7bAG2AdsAMYlfKwExlh+JnAI\n+AtwtKh/WX+8C7i8RBvOBLZZP54IPAW8an3zuoTNcGAFcMB0jwM7gIUJ/SeBpcD4XJsvBX5doD8j\nkT4EHEv42GTtNR/4pf2/qGi/ydhsIR7Qfsu2xVJrg0XAEwX6Z4DDufS2/R5K+NiTyf8EuBuYBCwB\nHi/arzL5bcD1lp8C7E74OAz8AHiR+GjQEuDiBtt9J3Az8GXi24YWmHwO8EyB/hPAQuAS4BvAt4HJ\nwFrguwO13ZPrV0a5Gck6VFHqBv5ToH+gYCfbAtxLnUBflLf/77AhDgpLiDv5dJMVdtyMzXPEoDY6\nvyPlfZrsF8DXLP8QMDPTgXc12kns/4XAPGAjcLxAfz8wzOr1GhZwiWdPPQkf3ZwNCCOzOxOwvz86\ncF86MRUELrMpFbwoGbhqbZzJNwxeVBC4rKxU8AKer+P/HWXAaWCrrXM+nUosZ2/u/53AHyjYz4r2\nN3IHvfnlmewO6yvXZNu8QfvuqVPHIh89wFDL70j1hzo+PgasAl6y9rqtD+teFIeey/3fZb8XAAd7\nu237e7snl19GuRmJeOQ/3XbybLoU+HuB/lZsEMnIhgLrgNMJH38COmobIiPvSnV6K7+EOLDcn9/4\nBbpHiEfKh+13gsmHJzpwF/BT4AWr39tm9ztgWqPOWFDWUSBbYss8CiwGngYeJA5KyxLLuZ0Y3B8k\nnjHVBtWxwPb+6MB96cT5NqQJgcvkpYIXJQOXyUsFLyoIXCYvFbyIz1l+k8yZJDCOeGDwmwL9/cDk\nhO+/1mmrC3KyhcSzwKON1gO4u1H7mry2r99LnMpvdID6N+Kgfgdxn1emrGjWZpG11yeIZ/o/JM7Y\nfAdY36hvZWRDgLnAQwmbZ4gzMF8k7vfzTT6L4oOhPwI3Wn4e8GSmLLXvNn27J9u9jHIzEnEK5cZE\n2YZExxqf0P9oQn5RQj6GTGCqU8fPkDg97oVtB/D+OuWdwDTimUXhFFJGd0of/F+MHY0DI4AFwA0N\nbK42vam99FGqA1t5qU5cVeDK9LFeBa+ygcvkpYJXFYHLykoFL+IZ+PeIBzb/Ik4H95isaPp0AXBl\nwvf8hPz7wE0F8rnEL0IU2azALhvk5FcAjzboy/OI06AvNdBblku1SwDjgXUJm9nAz4lT+93Ar4Db\ngAsT+j+rV4eEzTTijMdmYKr1rX/bfvKRhP5O236/r20f4gHq4oSPpm/35PqVbRBPnvIp14FP5Drw\nyIRNqU5cdeAyvYbBqy+By8pTwWtogW7TA5fZXJsLXlNMXi94TQVuyrczmWt7BfpzeqvfwObmPtg0\nrBfx2vYHz6FeVax7PZurStbrqjLb0Mpu4OxU9tXEA7ZP91L/A8SDvKR+cjllDTx5KpOwKcVm2jTT\nRy54tUy9qvSRsiFOMz8PPE6cEv98pqzorLCUvskXNduminpVuO6LiQeOZerVa32TLyMeyO0m3gj1\nNPF653bgzl7ob62nX7cflu24njyVSTS49tcfNlX4aNV6DeS6U/KO3bL6VdkMFh8V16vMXdel9Oul\nprz81jm/kLQvVUS8lnXONlX4aNV6teq6E68pvg4QQjhiz+k9KmmS2ZyrflU2g8VHVfX6bwjhNPCm\npBdCCCfN/pSkM/2gn8QHLKc/GAd8injtI4uIF/L7w6YKH61ar1Zd95clTQ8h7AUIIbwu6bPEh+Kv\n6Qf9qmwGi4+q6vWWpI4QwpvEm8WA+EAx8bGQc9VPU+Z0zJOnokTJOz37YlOFj1atVwuve6k7dsvq\nV2UzWHxUWK9Sd12X1a+X/PMijuM4TlvQ0u8SdBzHcZwaPmA5juM4bYEPWI7jOE5b4HcJOk6TkXSa\n+HLkYcR3Rq4H7gt+AdlxSuEDluM0nzdCCDMA7JtIG4nvkFw+kJVynHbDpwQdp0JCCP8kvjPw6wCS\nJknaLmm3pQ+bfK2keTU7+yDf5wam1o7TGvht7Y7TZCSdDCF05mQngCuJ3yk7E0J4S9IVwMYQwvWS\nPg4sCSF8QVIn8SW5k0MI5R60dJxBhE8JOs7AUHvtzTDgfknTid8ImwwQQtgu+8Q78c32m3ywcs53\nfMBynIqRdBnx/WrHJS0jfr7kWklDgFMZ1XXAV4AvEb/95TjnNT5gOU7z+f9LRCWNBVYDPzZRF/ET\n9gC3Et9qXWMt8ftUx0IIByuop+O0ND5gOU7zeZekPZy9rX1dCOE+K1sFbJJ0K7AFeKNmFEL4h6Qe\n4LGqK+w4rYjfdOE4LYqkDuLzWzNCCK8NdH0cZ6Dx29odpwWRNAf4M/AjH6wcJ+JnWI7jOE5b4GdY\njuM4TlvgA5bjOI7TFviA5TiO47QFPmA5juM4bYEPWI7jOE5b4AOW4ziO0xb8Dyfj9m4VOlaBAAAA\nAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plot multiple plots on the same plot (plots neeed to be in column format)\n", + "ufo_fourth = ufo[(ufo.Year.isin([2011, 2012, 2013, 2014])) & (ufo.Month == 7)]\n", + "\n", + "\n", + "# unstack will take a groupby of multiple indices and split it by column (mainly great for sub plotting)\n", + "\n", + "# Hmm let's make that prettier by making it 4 seperate charts\n", + "ufo_fourth.groupby(['Year', 'Day']).City.count().unstack(0).plot(\n", + " kind = 'bar',\n", + " subplots=True, \n", + " figsize = (7,9))\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "\n", + "'''\n", + "Further Exploration\n", + "'''\n", + "\n", + "'''\n", + "Joining Data\n", + "\n", + "MovieLens 100k data:\n", + " main page: http://grouplens.org/datasets/movielens/\n", + " data dictionary: http://files.grouplens.org/datasets/movielens/ml-100k-README.txt\n", + " files: u.user, u.data, u.item\n", + "'''\n", + "\n", + "# read 'u.data' into 'ratings'\n", + "r_cols = ['user_id', 'movie_id', 'rating', 'unix_timestamp']\n", + "ratings = pd.read_table('https://raw.githubusercontent.com/sinanuozdemir/sfdat26/master/data/u.data', header=None, names=r_cols, sep='\\t')\n", + "\n", + "# read 'u.item' into 'movies'\n", + "m_cols = ['movie_id', 'title']\n", + "movies = pd.read_table('https://raw.githubusercontent.com/sinanuozdemir/sfdat26/master/data/u.item', header=None, names=m_cols, sep='|', usecols=[0,1])" + ] + }, + { + "cell_type": "code", + "execution_count": 64, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
movie_idtitle
01Toy Story (1995)
12GoldenEye (1995)
23Four Rooms (1995)
34Get Shorty (1995)
45Copycat (1995)
\n", + "
" + ], + "text/plain": [ + " movie_id title\n", + "0 1 Toy Story (1995)\n", + "1 2 GoldenEye (1995)\n", + "2 3 Four Rooms (1995)\n", + "3 4 Get Shorty (1995)\n", + "4 5 Copycat (1995)" + ] + }, + "execution_count": 64, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "movies.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
user_idmovie_idratingunix_timestamp
01962423881250949
11863023891717742
2223771878887116
3244512880606923
41663461886397596
\n", + "
" + ], + "text/plain": [ + " user_id movie_id rating unix_timestamp\n", + "0 196 242 3 881250949\n", + "1 186 302 3 891717742\n", + "2 22 377 1 878887116\n", + "3 244 51 2 880606923\n", + "4 166 346 1 886397596" + ] + }, + "execution_count": 65, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ratings.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
movie_idtitleuser_idratingunix_timestamp
01Toy Story (1995)3084887736532
11Toy Story (1995)2875875334088
21Toy Story (1995)1484877019411
31Toy Story (1995)2804891700426
41Toy Story (1995)663883601324
\n", + "
" + ], + "text/plain": [ + " movie_id title user_id rating unix_timestamp\n", + "0 1 Toy Story (1995) 308 4 887736532\n", + "1 1 Toy Story (1995) 287 5 875334088\n", + "2 1 Toy Story (1995) 148 4 877019411\n", + "3 1 Toy Story (1995) 280 4 891700426\n", + "4 1 Toy Story (1995) 66 3 883601324" + ] + }, + "execution_count": 66, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# merge 'movies' and 'ratings' (inner join on 'movie_id')\n", + "movie_ratings = pd.merge(movies, ratings)\n", + "movie_ratings.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Star Wars (1977) 583\n", + "Contact (1997) 509\n", + "Fargo (1996) 508\n", + "Return of the Jedi (1983) 507\n", + "Liar Liar (1997) 485\n", + "English Patient, The (1996) 481\n", + "Scream (1996) 478\n", + "Toy Story (1995) 452\n", + "Air Force One (1997) 431\n", + "Independence Day (ID4) (1996) 429\n", + "Raiders of the Lost Ark (1981) 420\n", + "Godfather, The (1972) 413\n", + "Pulp Fiction (1994) 394\n", + "Twelve Monkeys (1995) 392\n", + "Silence of the Lambs, The (1991) 390\n", + "Jerry Maguire (1996) 384\n", + "Chasing Amy (1997) 379\n", + "Rock, The (1996) 378\n", + "Empire Strikes Back, The (1980) 367\n", + "Star Trek: First Contact (1996) 365\n", + "Back to the Future (1985) 350\n", + "Titanic (1997) 350\n", + "Mission: Impossible (1996) 344\n", + "Fugitive, The (1993) 336\n", + "Indiana Jones and the Last Crusade (1989) 331\n", + "Willy Wonka and the Chocolate Factory (1971) 326\n", + "Princess Bride, The (1987) 324\n", + "Forrest Gump (1994) 321\n", + "Monty Python and the Holy Grail (1974) 316\n", + "Saint, The (1997) 316\n", + " ... \n", + "Brother's Kiss, A (1997) 1\n", + "Coldblooded (1995) 1\n", + "Silence of the Palace, The (Saimt el Qusur) (1994) 1\n", + "Century (1993) 1\n", + "Homage (1995) 1\n", + "Hana-bi (1997) 1\n", + "Symphonie pastorale, La (1946) 1\n", + "They Made Me a Criminal (1939) 1\n", + "Brothers in Trouble (1995) 1\n", + "Girls Town (1996) 1\n", + "Touki Bouki (Journey of the Hyena) (1973) 1\n", + "Marlene Dietrich: Shadow and Light (1996) 1\n", + "Sleepover (1995) 1\n", + "Sunchaser, The (1996) 1\n", + "Nothing Personal (1995) 1\n", + "Niagara, Niagara (1997) 1\n", + "Further Gesture, A (1996) 1\n", + "Great Day in Harlem, A (1994) 1\n", + "Eye of Vichy, The (Oeil de Vichy, L') (1993) 1\n", + "Daens (1992) 1\n", + "Woman in Question, The (1950) 1\n", + "Someone Else's America (1995) 1\n", + "Man from Down Under, The (1943) 1\n", + "Jupiter's Wife (1994) 1\n", + "Spanish Prisoner, The (1997) 1\n", + "Next Step, The (1995) 1\n", + "I, Worst of All (Yo, la peor de todas) (1990) 1\n", + "Two Friends (1986) 1\n", + "Gate of Heavenly Peace, The (1995) 1\n", + "Crude Oasis, The (1995) 1\n", + "Name: title, dtype: int64" + ] + }, + "execution_count": 67, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# for each movie, count number of ratings\n", + "movie_ratings.title.value_counts()" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/sinanozdemir/anaconda/envs/sfdat26-env/lib/python2.7/site-packages/ipykernel/__main__.py:1: FutureWarning: order is deprecated, use sort_values(...)\n", + " if __name__ == '__main__':\n" + ] + }, + { + "data": { + "text/plain": [ + "title\n", + "Marlene Dietrich: Shadow and Light (1996) 5.000000\n", + "Prefontaine (1997) 5.000000\n", + "Santa with Muscles (1996) 5.000000\n", + "Star Kid (1997) 5.000000\n", + "Someone Else's America (1995) 5.000000\n", + "Entertaining Angels: The Dorothy Day Story (1996) 5.000000\n", + "Saint of Fort Washington, The (1993) 5.000000\n", + "Great Day in Harlem, A (1994) 5.000000\n", + "They Made Me a Criminal (1939) 5.000000\n", + "Aiqing wansui (1994) 5.000000\n", + "Pather Panchali (1955) 4.625000\n", + "Anna (1996) 4.500000\n", + "Everest (1998) 4.500000\n", + "Maya Lin: A Strong Clear Vision (1994) 4.500000\n", + "Some Mother's Son (1996) 4.500000\n", + "Close Shave, A (1995) 4.491071\n", + "Schindler's List (1993) 4.466443\n", + "Wrong Trousers, The (1993) 4.466102\n", + "Casablanca (1942) 4.456790\n", + "Wallace & Gromit: The Best of Aardman Animation (1996) 4.447761\n", + "Shawshank Redemption, The (1994) 4.445230\n", + "Rear Window (1954) 4.387560\n", + "Usual Suspects, The (1995) 4.385768\n", + "Star Wars (1977) 4.358491\n", + "12 Angry Men (1957) 4.344000\n", + "Third Man, The (1949) 4.333333\n", + "Letter From Death Row, A (1998) 4.333333\n", + "Bitter Sugar (Azucar Amargo) (1996) 4.333333\n", + "Citizen Kane (1941) 4.292929\n", + "Some Folks Call It a Sling Blade (1993) 4.292683\n", + " ... \n", + "Symphonie pastorale, La (1946) 1.000000\n", + "Baton Rouge (1988) 1.000000\n", + "Boys in Venice (1996) 1.000000\n", + "Tigrero: A Film That Was Never Made (1994) 1.000000\n", + "Office Killer (1997) 1.000000\n", + "T-Men (1947) 1.000000\n", + "Terror in a Texas Town (1958) 1.000000\n", + "Nobody Loves Me (Keiner liebt mich) (1994) 1.000000\n", + "The Courtyard (1995) 1.000000\n", + "King of New York (1990) 1.000000\n", + "Liebelei (1933) 1.000000\n", + "Stefano Quantestorie (1993) 1.000000\n", + "Hostile Intentions (1994) 1.000000\n", + "Pharaoh's Army (1995) 1.000000\n", + "New Age, The (1994) 1.000000\n", + "Hungarian Fairy Tale, A (1987) 1.000000\n", + "Death in the Garden (Mort en ce jardin, La) (1956) 1.000000\n", + "Promise, The (Versprechen, Das) (1994) 1.000000\n", + "I, Worst of All (Yo, la peor de todas) (1990) 1.000000\n", + "Power 98 (1995) 1.000000\n", + "Police Story 4: Project S (Chao ji ji hua) (1993) 1.000000\n", + "Low Life, The (1994) 1.000000\n", + "Somebody to Love (1994) 1.000000\n", + "Invitation, The (Zaproszenie) (1986) 1.000000\n", + "Lotto Land (1995) 1.000000\n", + "Touki Bouki (Journey of the Hyena) (1973) 1.000000\n", + "JLG/JLG - autoportrait de d�cembre (1994) 1.000000\n", + "Daens (1992) 1.000000\n", + "Butterfly Kiss (1995) 1.000000\n", + "Eye of Vichy, The (Oeil de Vichy, L') (1993) 1.000000\n", + "Name: rating, dtype: float64" + ] + }, + "execution_count": 68, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "movie_ratings.groupby('title').rating.mean().order(ascending=False)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python [bersonenv]", + "language": "python", + "name": "Python [bersonenv]" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.12" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} diff --git a/notebooks/.ipynb_checkpoints/Yelp_Eugene-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/Yelp_Eugene-checkpoint.ipynb new file mode 100644 index 0000000..7ab0ba3 --- /dev/null +++ b/notebooks/.ipynb_checkpoints/Yelp_Eugene-checkpoint.ipynb @@ -0,0 +1,861 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 61, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
business_iddatereview_idstarstexttypeuser_idcoolusefulfunny
09yKzy9PApeiPPOUJEtnvkg2011-01-26fWKvX83p0-ka4JS3dc6E5A5My wife took me here on my birthday for breakf...reviewrLtl8ZkDX5vH5nAx9C3q5Q250
1ZRJwVLyzEJq1VAihDhYiow2011-07-27IjZ33sJrzXqU-0X6U8NwyA5I have no idea why some people give bad review...review0a2KyEL0d3Yb1V6aivbIuQ000
26oRAC4uyJCsJl1X0WZpVSA2012-06-14IESLBzqUCLdSzSqm0eCSxQ4love the gyro plate. Rice is so good and I als...review0hT2KtfLiobPvh6cDC8JQg010
3_1QQZuf4zZOyFCvXc0o6Vg2010-05-27G-WvGaISbqqaMHlNnByodA5Rosie, Dakota, and I LOVE Chaparral Dog Park!!...reviewuZetl9T0NcROGOyFfughhg120
46ozycU1RpktNG2-1BroVtw2012-01-051uJFq2r5QfJG_6ExMRCaGw5General Manager Scott Petello is a good egg!!!...reviewvYmM4KTsC8ZfQBg-j5MWkw000
\n", + "
" + ], + "text/plain": [ + " business_id date review_id stars \\\n", + "0 9yKzy9PApeiPPOUJEtnvkg 2011-01-26 fWKvX83p0-ka4JS3dc6E5A 5 \n", + "1 ZRJwVLyzEJq1VAihDhYiow 2011-07-27 IjZ33sJrzXqU-0X6U8NwyA 5 \n", + "2 6oRAC4uyJCsJl1X0WZpVSA 2012-06-14 IESLBzqUCLdSzSqm0eCSxQ 4 \n", + "3 _1QQZuf4zZOyFCvXc0o6Vg 2010-05-27 G-WvGaISbqqaMHlNnByodA 5 \n", + "4 6ozycU1RpktNG2-1BroVtw 2012-01-05 1uJFq2r5QfJG_6ExMRCaGw 5 \n", + "\n", + " text type \\\n", + "0 My wife took me here on my birthday for breakf... review \n", + "1 I have no idea why some people give bad review... review \n", + "2 love the gyro plate. Rice is so good and I als... review \n", + "3 Rosie, Dakota, and I LOVE Chaparral Dog Park!!... review \n", + "4 General Manager Scott Petello is a good egg!!!... review \n", + "\n", + " user_id cool useful funny \n", + "0 rLtl8ZkDX5vH5nAx9C3q5Q 2 5 0 \n", + "1 0a2KyEL0d3Yb1V6aivbIuQ 0 0 0 \n", + "2 0hT2KtfLiobPvh6cDC8JQg 0 1 0 \n", + "3 uZetl9T0NcROGOyFfughhg 1 2 0 \n", + "4 vYmM4KTsC8ZfQBg-j5MWkw 0 0 0 " + ] + }, + "execution_count": 61, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "from sklearn.linear_model import LinearRegression\n", + "from sklearn.cross_validation import cross_val_score\n", + "from sklearn import metrics\n", + "import statsmodels.formula.api as smf\n", + "from sklearn.neighbors import KNeighborsClassifier\n", + "\n", + "# visualization\n", + "import seaborn as sns\n", + "import matplotlib.pyplot as plt\n", + "%matplotlib inline\n", + "\n", + "data = pd.read_csv('http://localhost:8888/files/data/yelp.csv')\n", + "data.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 62, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAABNQAAAJQCAYAAABGuTl9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "sns.pairplot(data, x_vars=['cool','useful','funny'], y_vars='stars', size=6, aspect=0.7, kind='reg')" + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 63, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA+AAAAPgCAYAAACyJxZ9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\niIhIAv8PHDnCfQbnykwAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "sns.pairplot(data)" + ] + }, + { + "cell_type": "code", + "execution_count": 64, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
starscoolusefulfunny
stars1.0000000.052555-0.023479-0.061306
cool0.0525551.0000000.8871020.764342
useful-0.0234790.8871021.0000000.723406
funny-0.0613060.7643420.7234061.000000
\n", + "
" + ], + "text/plain": [ + " stars cool useful funny\n", + "stars 1.000000 0.052555 -0.023479 -0.061306\n", + "cool 0.052555 1.000000 0.887102 0.764342\n", + "useful -0.023479 0.887102 1.000000 0.723406\n", + "funny -0.061306 0.764342 0.723406 1.000000" + ] + }, + "execution_count": 64, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.corr()" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 65, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAesAAAFhCAYAAABQ2IIfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAAPYQAAD2EBqD+naQAAIABJREFUeJzt3XucJVV16PFf96i80SsYBjW8VBbigxiMkAkYJBqCGBEE\n41WMAmpEURJAUCMgKJE3KlG4qEH5BBUjGBT0YhQc5BGEASbqxQWKCA44EQQlzAwD033/2KfhcOb0\nzOma6u4qzu/7+dRn+ux6nFXd073O2rVr18j4+DiSJKm5Rmc7AEmStGoma0mSGs5kLUlSw5msJUlq\nOJO1JEkNZ7KWJKnhTNaSJDWcyVqSpIZ70mwHMOFdI1s4O8sM+tT91892CEPnoSevN9shDJ3lK/yz\nMhs22mDdkek69prkirPGb5+2uKablbUkSQ3XmMpakqTVmdPa2njNmKwlSa0xZ2Q4s7XJWpLUGsNa\nWXvNWpKkhrOyliS1ht3gkiQ13LB2g5usJUmtYWUtSVLDWVlLktRww1pZOxpckqSGs7KWJLXGsFaY\nJmtJUmsMaze4yVqS1BoOMJMkqeGGtbIe1u5/SZJaw8paktQadoNLktRww9oNbrKWJLWGlbUkSQ1n\nZS1JUsMNa2XtaHBJkhrOylqS1BrDWlmbrCVJreE1a0mSGm4mK+uIWAv4DLA3sAQ4NTNPm2TbvYDj\ngT8EbgQOycwb64rFa9aSpNaYMzJSeangFOCPgV2AdwPHRMTevRtFxLbAeZRk/WJgIXBJRKxd9Tx7\nVaqsI+JpwLLMXBYRLwZ2A27IzO/VFZgkSb1mqrKOiHWBA4HdMnMhsDAiTgIOBi7s2fwvgR9n5nmd\nfT8IvAfYFrihjnimXFlHxJ7AImCniHgu8APgbcBFEXFwHUFJkjTLtqMUtNd0tV0J7NBn23uBF0TE\nvIgYAQ4Afgf8vK5gqnSDHw8cnZnfBd4O3JmZLwDeCBxWV2CSJPWawW7wTYF7MvORrrbFwNoRsVHP\ntucD36Ik8+XAScA+mfm7iqe5kirJ+jnAVztf78lj3QE/Bv6gjqAkSepnzkj1ZYrWBR7qaZt4vVZP\n+0bAXMp17ZcB5wJfiIiNp/yuk6hyzfqXwC4RsQgI4Bud9jcDt9QVmCRJvWbw1q1lrJyUJ14v6Wk/\nEfivzDwLICL+DrgZ2B84uY5gqlTWxwCfA/4DuDgzr4+Ik4EPAkfUEZQkSf2MjoxUXqZoEbBxRHTn\nybnA0sy8v2fb7SkjwAHIzPHO680rnGJfVSrr64FnA8/KzJs6bZ8DTsnMxXUFJklSr5GZu9H6JuBh\nYEfg6k7bzsB1fba9izLyu1sAP6wrmCrJ+ipgj8xcMNGQmVlXQJIkzbbMXBoR5wJnRcQBlCL1MOCt\nABGxCfC7zFwGfBY4JyKup4wefwewGfDFuuKpkqx/DWxSVwCSJA1qdGYnBz+UMoPZZZRbsY7KzIs6\n6+6m3LZ8bmZ+NSLWAz4EPItSlb8iM++pK5AqyfpGyj3V1wG3Uy7CPyozD6ghLkmSVjIyZ+Ym3szM\npZRBYvv3WTfa8/oc4JzpiqXq3OD/2vX1cM6qLkmacTN4zbpRppysM3OlTxiSJM2EGe4Gb4wpJ+vO\nVGp7Ai8A5nSaRyj3n70kM3evLzxJklSlG/wMyuTmN1JmarmaMqvZXODM+kKTJOnxRkaH82GRVc76\nb4A3Z+Y84GfAQZQbv78MPKXG2CRJepzROSOVlzarkqw3pEyMAvAj4GWdic4/Dry6rsAkSeo1Mmek\n8tJmVZL1bcBLOl//hNIVDuW69VPrCEqSpH5G5oxWXtqsyjXrU4EvdWZ0OR9YEBGPAPMos5tJkjQt\n2t6dXdWUP2pk5ueA3YFbM/NmYC/K4LLr6EzDJkmS6lPl1q2jKQ/tWAKQmZcCl0bEhpQnch1Wb4iS\nJBUjo8NZWQ+UrCMieGw+8GOAhRFxX89mLwTehclakjRNRlt+7bmqQSvrZwLf63r99T7bPAh8Yo0j\nkiRpEm0f1V3VQMk6My+nc307In5BGQH+28xcERHPBHYCFvqoTEnSdBrWZF2lP2E/yuO/Xh4Rm1Lu\nuf4/wI8iYt86g5MkqdvonNHKS5tVif50yi1b11IesL2Mcj37HcBx9YUmSZKgWrJ+EfCJzmjwPYEL\nM3M58H3KtKOSJE2LYZ3BrMqkKIuBbSNifcpMZod22l8J3FFXYJIk9Rr11q2BnQb8OzAGXJeZ8yPi\nQ5RbunzWtSRp2rR92tCqppysM/NTEXEFsAVwaaf5MuCSzFxYY2ySJD3OsE43WqWyJjNvoowIn3j9\nn7VFJEnSJNp+7bmq4exPkCSpRSpV1pIkzQavWUuS1HBes5YkqeF86pYkSQ3X9mlDqxrOs5YkqUWs\nrCVJrTGst26ZrCVJreFocEmSGm5k1GQtSVKjDesAM5O1JKk1hrUbfDjPWpKkFrGyliS1xrBW1iZr\nSVJrOMBMkqSGG5kzZ7ZDmBUma0lSa9gNLklSw40OaTf4cJ61JEktYmUtSWoNu8ElSWo4k7UkSQ3n\nrVuz7FP3Xz/bIQyV9z3tpbMdwtB5/gZrzXYIQ2ebuevNdghDabdbbpi2Y1tZS5LUcMOarIfzrCVJ\nahEra0lSa/iITEmSGs4BZpIkNdywXrM2WUuSWmNYk/VwnrUkSS1iZS1Jag2vWUuS1HCjM/g864hY\nC/gMsDewBDg1M09bzT5bAD8C9sjMK+qKxWQtSWqNGb5mfQrwx8AuwBbAuRFxe2ZeuIp9zgTWrTsQ\nk7UkqTVmKllHxLrAgcBumbkQWBgRJwEHA32TdUS8GVh/OuIZzs5/SVIrjYyOVl6maDtKQXtNV9uV\nwA79No6IjYATgHcCIxVObZVM1pIkrWxT4J7MfKSrbTGwdicx9zoN+EJm3jwdwdgNLklqjRm8Zr0u\n8FBP28Trxz1CLyJeCcwD3jFdwZisJUmtMYPJehk9Sbnr9ZKJhohYGzgLOCgzl09XMHaDS5JaYwav\nWS8CNo6I7h3nAksz8/6utpcBWwIXRMQDEfFAp/3bEfGZyifaw8paktQaI6Mzdp/1TcDDwI7A1Z22\nnYHrera7FnheT9vPKCPJv1tXMCZrSVJ7zFCyzsylEXEucFZEHAA8GzgMeCtARGwC/C4zlwG3de8b\nEQB3ZeY9dcVjN7gkSf0dCiwALgPOAI7KzIs66+4G3jDJfuN1B2JlLUlqjxmcGzwzlwL7d5bedZMG\nkpm1l/8ma0lSa4zM4NzgTWKyliS1x8wNMGsUk7UkqT1M1pIkNduwPs96OM9akqQWsbKWJLWH3eCS\nJDWcyVqSpGYb1mvWAyfriDh60G0z87hq4UiStApW1qv1igG3GwdM1pIk1WTgZJ2ZgyZrSZKmh5X1\n1ETES4DDgecDc4AEPp2Z82uKTZKkxxnW6UYrXamPiL0oz/AcBc7pLOPAf0TEnvWFJ0lSl9HR6kuL\nVa2sPwocmZmnd7V9IiL+ATgWuKj/bpIkrQG7wadkK+Cbfdq/CfxT9XAkSZrcyJAm66r9AjcDu/dp\nfzVwe+VoJEnSSqpW1scAF0TEDpRr1wA7AvsAb6kjMEmSVtLya89VVTrrzLyYUlmvAxwE7N851s6Z\n+dX6wpMk6TEjo3MqL21W+datzLwMuCwiNgTmZOZ99YUlSVIfLU+6VVXuT4iIQyJiEXAfcE9E/Hoq\nU5JKkjRl3ro1uIg4CngvcBRwNWVSlHnARyJieWaeUF+IkiQVwzopStVu8HcCB2Zm9+1bN3Uq7U8B\nJmtJkmpSNVlvCNzSpz2BZ1QPR5KkVfCa9ZRcDRweEY/uHxFzgPcDP6wjMEmSVjI6p/rSYlUr60OB\nK4BXRcSCTtv2wFrAX9URmCRJvUZaPlCsqkrJOjNvjoi/BzYCtgGWAa8B9snMhTXGJ0nSY1peIVdV\n9alb7wXOBH6Xme/OzEOBM4DzIuIddQYoSdKwq9qfcBjwpsz84kRDZh4O7Ad8oI7AJElaycho9aXF\nql6z3gj4WZ/2BOZWD0eSpFVoedKtqupZXwkcGxHrTjRExNrAP1JGikuSVLvxkdHKS5tVrawPBr4D\n3B0RE/dbPxf4NbBnHYFJkrSSlifdqqqOBv95RGwL7AZsDTwM3ApcmpkraoxPkqTHjIzMdgSzYk2e\nuvUQ8I0aY5EkSX1UTtaSJM04J0WRJKnZ2j5QrCqTtSSpPUzWkiQ1nMlakqSGG9JkPZxnLUlSi1hZ\nS5JawwFmkiQ1nclakqSGcwYzSZIazspakqRmG9Zr1sN51pIktYiVtSSpPZwbXJKkhhvSbnCTtSSp\nPUzWkiQ13JAm6+E8a0mSWsTKWpLUGjN561ZErAV8BtgbWAKcmpmnTbLtS4AzgRcBPwYOyswb6orF\nylqS1B4jo9WXqTsF+GNgF+DdwDERsXfvRhGxLnAJML+z/TXAJRGxTtXT7GVlLUlqjxmabrSTgA8E\ndsvMhcDCiDgJOBi4sGfzNwJLMvPIzuu/j4hXA/sC59YRj5W1JKk9Zq6y3o5S0F7T1XYlsEOfbXfo\nrOt2FfCnU33TyZisJUmtMT4yWnmZok2BezLzka62xcDaEbFRn23v6mlbDDx7qm86GZO1JEkrWxd4\nqKdt4vVaA27bu11lXrOWJLXHzI0GX8bKyXbi9ZIBt+3drrLGJOuHnrzebIcwVJ6/QW0f+DSgmx/o\n/eCt6bbd1k+f7RBUs/GZe571ImDjiBjNzLFO21xgaWbe32fbuT1tc4G76wrGbnBJUmuMj1dfpugm\n4GFgx662nYHr+mz7n8C8nrY/67TXojGVtSRJqzNWIetWkZlLI+Jc4KyIOIAyWOww4K0AEbEJ8LvM\nXAZ8Dfh4RJwOnA28i3Id+6t1xWNlLUlqjfE1WCo4FFgAXAacARyVmRd11t0NvAEgMx8AXgO8HLge\neBmwe2Yurfa2K7OyliSpj06y3b+z9K4b7Xl9PbD9dMVispYktcbYzPSCN47JWpLUGuMzdM26aUzW\nkqTWsLKWJKnhhjRXm6wlSe0xrJW1t25JktRwVtaSpNZwgJkkSQ03tvpNnpBM1pKk1hjSwtpkLUlq\nDweYSZKkRrKyliS1hgPMJElqOAeYSZLUcENaWJusJUntMTak2dpkLUlqjeFM1Y4GlySp8QaurCPi\n5YNum5lXVAtHkqTJDet91lPpBv/+gNuNA3OmHookSas2pJesB0/WmWmXuSRpVo0N6VXrSgPMImKz\nVa3PzDuqhSNJ0uSsrKfmdkp390jnde+3z25wSVLtvGY9NVv2Oc5zgGOB49YoIkmS9DiVknVm/rJP\n888j4j7gPODbaxSVJEl92A1ej3HgWTUfU5IkwAFmUxIRR/dp3gB4A/CdNYpIkqRJWFlPzSt6Xo8D\ny4FzgdPWKCJJkibh3OCrERHnAIdn5r3AMcA1mfnwtEUmSVKPFUP6jMypTHTyRuDpna8vB55WfziS\nJKnXVLrBfwhcHhG3Uu6v/npELO+3YWbuWkdwkiR1sxt89fYG9gOeCvw5cA3wP9MRlCRJ/awwWa9a\n51r1JwEiYgQ4OTOXTFdgkiT1srKegsw8NiK2ioiDgOcBBwG7l1V5VZ0BSpI0wQFmU9B5tvV/UaYd\n/StgHWAbyjXtvesLT5IkVX3s5UnABzJzH+BhgMw8AjgC5waXJE2TsfHxykubVU3WLwK+1af9G5QH\nekiSVLsV4+OVlzZbk0dk/glwW0/7Hp11kiTVzkdkTs2HgS9ExEs7x/jbiNiSMnHKW+oKTpKkbiuG\nNFtX6gbPzK8DLwc2AX4M7AmsBbw8M79aX3iSJD1mWK9ZV35EZmYuBP524nVEPAO4p46gJEnSY6o+\nIvOZlKdrnQD8FLgU2An4VUS8tpPIJUmq1Yp2F8iVVR0NfibwDOBe4G2U0eHzKKPBz6glMkmSetgN\nPjW7Attn5p0RsRdwUWZeGxH/DfykvvAkSXrMsA4wq5qslwHrRMT/AnYB3tRp3xL4bQ1xSZK0krZX\nyFVVTdb/DpwPLAXuBy6JiDdQHvTxhXpCkyTp8bxmPTUHAWcB3wd2ycxllFu3PpaZH6wpNkmSRPXK\n+jtdX386Ih59ERGvz8xd1ygqSZL6sBt8aub3Oc5WlOlGP7ZGEUmSNIkxB5gNLjOP7dceEW8DXg+c\nsgYxSZLU17Bes648g9kk5gOfqfmYkiQBdoNPSURs1qd5A+D9+NQtSdI0adKjLiPiBOAAymDtz2fm\nkQPssyHw/4APZea5g77Xmjwis/c7NgLcSQlckqQnrIg4jPKkyT2BpwDnRcTizDxtNbueBGw61fer\nmqy37Hk9DiwHFmdmcz72SJKeUBo0wOx9wIcz8xqAiDgS+CjluRl9RcROlBlAfz3VN6s6wOyXVfaT\nJGlNNGGAWURsCvwh8IOu5iuBzSNik8xc3GefpwBnA+8GPjvV96w6KYokSTOuIQ/y2JTSo3xXV9ti\nyuXgZ0+yzz8CCzLzu1XesO7R4JIkTZuZGmAWEWsDz5pk9foAmbm8q+2hzr9r9TnWtsA7KU+orMTK\nWpKkle0A3Arc0md5GTzatT1hIkkv6XOss4GjM/OeqsFYWUuSWmOmHpGZmfOZpKDtXLM+EZgL3NFp\nnkvpGr+7Z9vNgHnAiyNiYvDZusBZEfE3mbnHIPGYrCVJrdGE51ln5t0RcSewE/ClTvPOwB19Bpct\nAp7b0zYf+ETXvqtlspYktUYTknXHmcCJEbGIMrDs48DJEysjYmNgaWY+CNzWvWNEPAL8JjMfV4Wv\nislaktQaDUrWJwPPAC4EHgE+l5mf7Fp/HXAOcFyffad8EiZrSVJrNCVZZ+YYcHhn6be+d/Kw7nVb\nTfX9HA0uSVLDWVlLklqjKZX1TDNZS5Jaw2QtSVLDmawlSWo4k7UkSQ03rMna0eCSJDWclbUkqTUe\nGdLK2mQtSWqNYe0GN1lLklrDZD3Llq8Yzh/AbNlm7nqzHcLQ2W7rp892CEPnKwsGfk6CarTLNB57\nxfhw5orGJGtJklZnWCtrR4NLktRwVtaSpNYY1sraZC1Jag2TtSRJDbdibGy2Q5gVJmtJUmsMa2Xt\nADNJkhrOylqS1BrDWlmbrCVJreHc4JIkNZyVtSRJDWeyliSp4YY1WTsaXJKkhrOyliS1xrBW1iZr\nSVJrmKwlSWq4cZO1JEnNNmayliSp2cbHhzNZOxpckqSGs7KWJLWG16wlSWo4r1lLktRw42OzHcHs\nMFlLklpjWAeYTTlZR8QvgS8D52fmjfWHJElSf3aDD+5QYF/giohYBJwPfCUzb641MkmSBFRI1pl5\nAXBBRKwDvAZ4PXBlRPyKUnF/JTNvrzVKSZIY3tHgle+zzsylwAXA2cCXgOcB/wD8JCK+ExFb1xOi\nJEnF+Nh45aXNqlyzHgV2pXSFv65zjAuBvwYuB9YHzgK+AWxTW6SSpKE35gCzgf03sDZwMfBO4NuZ\nubxr/e8j4kJghxrikyTpUW2vkKuqkqzfB1yUmQ9OtkFmfg34WuWoJEnSo6oMMPtSRGwQETsCTwZG\netZfUVdwkiR1s7IeUETsR7kmvW6f1ePAnDUNSpKkfrzPenD/BHwWODozH6g5HkmSJuUMZoPbCPik\niVqSNNOGdW7wKvdZf5MyEYokSTNqbGy88tJmVSrrRcDxEfEG4Fag+7YtMvOAOgKTJElFlWT9dMq0\nohNGJttQkqQ6ORp8QJm5/3QEIknS6pispyAi/gL4E/rfZ31cDXFJkrQSpxsdUEScChwCLAR+37N6\nHDBZS5KmRZMq64g4ATiAMlj785l55Cq23Rk4nfLMjFuA92fm9wZ9ryqV9QHAWzPzvAr7SpJUWVOS\ndUQcBrwR2BN4CnBeRCzOzNP6bPsMysOtPkp58NX/Bi6KiK0z865B3q/KrVuPAD+ssJ8kSU8U7wOO\nysxrMnM+cCRw8CTb/hnwcGaelpm3Z+bHgWXAjoO+WZVk/Wng2IhYr8K+kiRV1oT7rCNiU+APgR90\nNV8JbB4Rm/TZ5V5go4jYq7P/6yiPk/7RoO9ZpRv8z4F5wL4RsZiV77PeqsIxJUlarYZMN7opZYxW\ndxf2YsqA62d3vn5UZv4gIj4DfC0ixiiF8v6Zeeugb1glWX+hs0iSNKNm6pp1RKwNPGuS1esDZGZ3\nsfpQ59+1+hxrfWAr4GjgEmBv4IyI+M/MvGWQeKrcZ/3Fqe4jSVIdZnDa0B2AyykVdK8jASLiKV0J\neyJJL+mz/REAmXl85/VNncdMHwK8Z5Bgqty6NVnwdILZdarHlCSpSTqDxvqO6+pcsz4RmAvc0Wme\nS8mNd/fZZXvK7c7dbgReMGg8VbrBv9/nGFsBewAfq3A8SZIGMj62YrZDIDPvjog7gZ2AL3Wadwbu\nyMzFfXa5C9i2p20b4BeDvmeVbvBj+7VHxNsoT+M6ZarHlCRpEE1I1h1nAidGxCLKwLKPAydPrIyI\njYGlmfkg8DngBxFxCOV+6z2B3YA/GvTNqty6NZn5wF/UeDxJkh5nfGxF5aVmJwPnUyY5OR/4YmZ+\nsmv9dcBhAJl5LWVQ2dso3eFvBnbPzJ8O+mZVrllv1qd5A+D9wO1TPZ4kSYMaX9GMyjozx4DDO0u/\n9Vv2vL4YuLjq+w2UrCPiVcAVmfkQJSGPs/KjMe8EDqwaiCRJq9OgbvAZNWhl/XXKxfBfAb8E9gV+\n01k3TpkYZXFmNuJudUmSnkgGTdb3AUdHxFXAZpT5THufuEVEkJnn1hifJEmPsrJetfcAxwKv7Lw+\nAuj3HRsHTNaSpGlhsl6FzPwGZbg5EfEL4KWZee90BiZJUi+T9YB6R7hJkjRTTNaSJDXc2JAm6zon\nRZEkSdPAylqS1Bp2g0uS1HAma0mSGq4p043ONJO1JKk1rKwlSWq4YU3WjgaXJKnhrKwlSa0xrJW1\nyVqS1BrjY2OzHcKsMFlLklrDylqSpIYb1mTtADNJkhrOylqS1BrD+iAPk7UkqTWcwUySpIYb1mvW\nJmtJUmuYrCVJarhhTdaOBpckqeFGxsfHZzsGSZK0ClbWkiQ1nMlakqSGM1lLktRwJmtJkhrOZC1J\nUsOZrCVJajiTtSRJDWeyliSp4UzWkiQ1nMlakqSGM1kPICJeEREx23FoaiLi8og4erbjeCKKiI0i\nYn5ELI2IcwbYfiwiXj4TsTVFRLw2Iu6MiP+JiFfNdjxqN5P1YL4HbDLbQUgNsh/wHODFwOGzHEtT\nHQt8G9gGuGKWY1HL+YhMSVU8Fbg1M2+d7UAa7KnAVZn5q9kORO1nsu4SEe8DDqVU0T8C/gH4187q\nyyPi2Mw8LiLeDhwGbAX8HjgfeG9mjnd1Cb4EmAv8GfBSyqfszYGfA/+YmRfN0Gm1QkQ8B/hnYCfg\nXuDUzDwjIp4PnAbMo3yvz87Mj3bt9xrK9/b5wG3AUZn59ZmOv6kiYnPgF8AWmXlHp+0Y4M+BvwTO\nBF4HrA1cBhyUmXd1ttsL+BiwBeX34YjMvKKz/zGdbVYAr6D8DC7PzOMme99hEhG/ADYD/iUiPkL5\n3e/9GeySma+IiLcCbwPmA++h/F3+l8w8rLPtOcBvgWcBf035/fhQZv5rRLwJ+BTwB5k51tn+9cBp\nmbn5TJ2vpp/d4B0R8UfAScC7gACuBL4KvKyzyd7AKZ3rbp8EPgA8D/g74EBgz67D7Qd8CNiDkmDO\nBY4HtgbOAb4UEU+b5lNqjYhYC/gO5Xv1J8DBwPER8WZK9+GvKD+HdwPvjYhDOvvtClwAfIHSHft5\n4PyIeMlMn0PDTfYc3IOBnYFXAtsD61M+GBER21G+r8cBL6J8aP1WRGwFnAycClxN+UB6zRTfdxi8\nFFgEHALsS//vRXfbPMrfh3mUn8shEfEXXevfA1wHvIDyf/6siNgAuIjyQWvXrm33Bb5cz2moKUzW\nj9kCGAPu6Hz6/TAl6f62s/6+zFwC/A9wQGZelJl3ZOaFwI2UX6IJ12XmtzJzAeXT8JOARZl5Z2ae\nSknsy2bkrNphN2BjYP/M/GlmXgy8F9gIeBD4uyy+CRwFHNHZ7z3Av2XmGZn5s8w8nfKHzGuog9kc\nWEr5P38Lpbo7obPuMEovxvmZeVtm/jPwfymV98TvwfLM/E1mPjzJ8UemN/zmysx7gRWUD6C/YfXf\ni1HgHZl5a2aeByykfHCdsDAzT83M24GjgXWBF2Tmg8DFlARNRKxDKRLOr/F01AAm68dcSunq+3FE\nLKD8wf9pZq7o3igzbwD+KyI+EhH/FhE/pVR9c7o2u71r+5uAS4DvRsTNEXECcHtmmqwfszVwSycJ\nAJCZX6QMzFkw0b3XcTUwNyI2pHR9X9tzrKs77Vq9s4FnAr+OiEspf+R/2ln3fODgiHhgYgFeQ+lN\nUv0WdxLvhN8DT+56/ejYgMx8oPPlxPovA6+LiFHKz2hRZt44ncFq5pmsOzJzaWbuQLn+djmlylgQ\nEc/s3i4idgMWUK5rfwt4PSVBdHtcIs7M11IS+r9RfpkWRMSLp+E02mqyyqzfB5o5Xf9Otn5On/Zh\n1a/79UkAmXkzpbp+E3AX8E+UD60T25wIbNe1bAscNOD7PGmS9x5Gk/4Muizvs83IgOu/3TneLpS/\nR1bVT0Am646I2DEiPpSZ8zPzcEpVtw5lwFO3twOfz8yDMvMcICm3sPTt5ori5My8PjOPzswXUq7B\n7jZ9Z9M6twLPjYi1Jxoi4hRKN/f2EdGdfOcBv8nM+yjf+x17jvWnnXYVyyn/NzfoatsKICLeArw2\nMy/IzP2B3YGdIuIZlO/hlp0u8Nsy8zbKeI7dV/E+3e/xnJrPo80mEu1KP4M6ZOZy4EJgL+BVwFfq\nOraaw9Hgj1kKHBMRi4HvUj6lrke5dvQg8MKIuIkyEnNeRLyQ8on5g5RBNmtNctz7gYMi4n7gPOCF\nlGrmhuk7lda5FPg1cHZEHE8Z4PdOYB9KV+3ZEXFyp/0jlFHjAKcDP4iIaym9HH/NY3+wVCwG7gTe\nHxHHUkaB70H5/7ch8OGIuIcycns/ygfJeyjf2ysi4nrKZZzXAn9P6Xnq5zrgbyPifMqHg2On7Yza\nZ1U/g7p8Bfgm5Xa6m2s8rhrCyrojMxcC+wPvB26mjPZ+c2Ym5daIkym3qxxDGTByDSXJLKHc/tJ3\nBHJmLqbQvTohAAABBklEQVQkkH2AnwBnAB/IzO9N5/m0SWdcwJ7AppQ/YKcDh3UGlP0VpUq7gfJz\nOG3i9qDM/CHwFkrX7I+AtwL7Zub8zqGHvhs2M8eBAyiXYX5C6Sb9WGfdpykjvs/trNuOUmmPZ+a1\nlO/tuzvr3g68MTOvmuStTqP8jOZTPpQe17N+GH8W4/Doz+BA+vwMVrfvFNZfDjyAo8CfsEbGx4fx\nd0iSnjg6Ay7vpowQv32Ww9E0sBtcklosIvahzANxlYn6ictkLUntdiLljorXznYgmj52g0uS1HAO\nMJMkqeFM1pIkNZzJWpKkhjNZS5LUcCZrSZIazmQtSVLDmawlSWo4k7UkSQ33/wEo3MQd6O4i1gAA\nAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "sns.heatmap(data.corr())" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Intercept 3.750433\n", + "cool 0.030870\n", + "dtype: float64" + ] + }, + "execution_count": 66, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "### STATSMODELS ###\n", + "\n", + "# create a fitted model\n", + "lm = smf.ols(formula='stars ~ cool', data=data).fit()\n", + "\n", + "# print the coefficients\n", + "lm.params" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
starscoolusefulfunny
count10000.00000010000.00000010000.00000010000.000000
mean3.7775000.8768001.4093000.701300
std1.2146362.0678612.3366471.907942
min1.0000000.0000000.0000000.000000
25%3.0000000.0000000.0000000.000000
50%4.0000000.0000001.0000000.000000
75%5.0000001.0000002.0000001.000000
max5.00000077.00000076.00000057.000000
\n", + "
" + ], + "text/plain": [ + " stars cool useful funny\n", + "count 10000.000000 10000.000000 10000.000000 10000.000000\n", + "mean 3.777500 0.876800 1.409300 0.701300\n", + "std 1.214636 2.067861 2.336647 1.907942\n", + "min 1.000000 0.000000 0.000000 0.000000\n", + "25% 3.000000 0.000000 0.000000 0.000000\n", + "50% 4.000000 0.000000 1.000000 0.000000\n", + "75% 5.000000 1.000000 2.000000 1.000000\n", + "max 5.000000 77.000000 76.000000 57.000000" + ] + }, + "execution_count": 67, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(10000, 10)" + ] + }, + "execution_count": 68, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": { + "collapsed": false, + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Intercept 3.794700\n", + "useful -0.012205\n", + "dtype: float64" + ] + }, + "execution_count": 69, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "### STATSMODELS ###\n", + "\n", + "# create a fitted model\n", + "lm = smf.ols(formula='stars ~ useful', data=data).fit()\n", + "\n", + "# print the coefficients\n", + "lm.params" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Intercept 3.804871\n", + "funny -0.039029\n", + "dtype: float64" + ] + }, + "execution_count": 70, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "### STATSMODELS ###\n", + "\n", + "# create a fitted model\n", + "lm = smf.ols(formula='stars ~ funny', data=data).fit()\n", + "\n", + "# print the coefficients\n", + "lm.params" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "pandas.core.frame.DataFrame" + ] + }, + "execution_count": 71, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "type(data)" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[2, 5, 0],\n", + " [0, 0, 0],\n", + " [0, 1, 0],\n", + " ..., \n", + " [0, 0, 0],\n", + " [0, 0, 0],\n", + " [0, 0, 0]], dtype=int64)" + ] + }, + "execution_count": 72, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn.cross_validation import train_test_split\n", + "features = np.array([data.cool, data.useful, data.funny]).T\n", + "features # 2D array" + ] + }, + { + "cell_type": "code", + "execution_count": 88, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[5],\n", + " [5],\n", + " [4],\n", + " ..., \n", + " [4],\n", + " [2],\n", + " [5]], dtype=int64)" + ] + }, + "execution_count": 88, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "response = np.array([data.stars]).T \n", + "response # 1D array\n" + ] + }, + { + "cell_type": "code", + "execution_count": 74, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "# step 1: split data into training set and test set\n", + "features_train, features_test, response_train, response_test = train_test_split(features, response, random_state=4)\n", + "# the random_state allows us all to get the same random numbers" + ] + }, + { + "cell_type": "code", + "execution_count": 82, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[1, 6, 4],\n", + " [1, 2, 1],\n", + " [0, 1, 0],\n", + " ..., \n", + " [0, 0, 0],\n", + " [2, 3, 2],\n", + " [0, 2, 0]], dtype=int64)" + ] + }, + "execution_count": 82, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "features_train" + ] + }, + { + "cell_type": "code", + "execution_count": 83, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[1, 3, 1],\n", + " [0, 1, 0],\n", + " [0, 0, 0],\n", + " ..., \n", + " [0, 0, 0],\n", + " [0, 0, 0],\n", + " [0, 0, 0]], dtype=int64)" + ] + }, + "execution_count": 83, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "features_test" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[3],\n", + " [5],\n", + " [5],\n", + " ..., \n", + " [4],\n", + " [2],\n", + " [1]], dtype=int64)" + ] + }, + "execution_count": 84, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "response_train" + ] + }, + { + "cell_type": "code", + "execution_count": 85, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[5],\n", + " [5],\n", + " [5],\n", + " ..., \n", + " [3],\n", + " [4],\n", + " [3]], dtype=int64)" + ] + }, + "execution_count": 85, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 89, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\Eugene\\Anaconda2\\envs\\bersonenv\\lib\\site-packages\\ipykernel\\__main__.py:2: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n", + " from ipykernel import kernelapp as app\n" + ] + }, + { + "data": { + "text/plain": [ + "0.35320000000000001" + ] + }, + "execution_count": 89, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "knn = KNeighborsClassifier(n_neighbors=5)\n", + "knn.fit(features_train, response_train) # Note that I fit to the training\n", + "knn.score(features_test, response_test) # and scored on the test set" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 102, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "X = data[['cool', 'useful', 'funny']]\n", + "y = data['stars']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 103, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "from sklearn.cross_validation import cross_val_score\n", + "knn = KNeighborsClassifier(n_neighbors=5)\n", + "scores = cross_val_score(knn, X, y, cv=5, scoring='accuracy')" + ] + }, + { + "cell_type": "code", + "execution_count": 104, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([ 0.28657014, 0.24787606, 0.22011006, 0.17558779, 0.24274274])" + ] + }, + "execution_count": 104, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "scores" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python [bersonenv]", + "language": "python", + "name": "Python [bersonenv]" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.12" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} diff --git a/notebooks/02_pandas.ipynb b/notebooks/02_pandas.ipynb index 722e3b2..b826e3f 100644 --- a/notebooks/02_pandas.ipynb +++ b/notebooks/02_pandas.ipynb @@ -7191,9 +7191,9 @@ ], "metadata": { "kernelspec": { - "display_name": "Python [sfdat26-env]", + "display_name": "Python [bersonenv]", "language": "python", - "name": "Python [sfdat26-env]" + "name": "Python [bersonenv]" }, "language_info": { "codemirror_mode": { diff --git a/notebooks/05_bias_variance_tradeoff.ipynb b/notebooks/05_bias_variance_tradeoff.ipynb index 82fc5ab..f41c77b 100644 --- a/notebooks/05_bias_variance_tradeoff.ipynb +++ b/notebooks/05_bias_variance_tradeoff.ipynb @@ -589,9 +589,9 @@ "metadata": { "anaconda-cloud": {}, "kernelspec": { - "display_name": "Python [sfdat26-env]", + "display_name": "Python [bersonenv]", "language": "python", - "name": "Python [sfdat26-env]" + "name": "Python [bersonenv]" }, "language_info": { "codemirror_mode": { diff --git a/notebooks/05_linear_regression.ipynb b/notebooks/05_linear_regression.ipynb index 2a46cce..6902367 100644 --- a/notebooks/05_linear_regression.ipynb +++ b/notebooks/05_linear_regression.ipynb @@ -1627,9 +1627,9 @@ "metadata": { "anaconda-cloud": {}, "kernelspec": { - "display_name": "Python [sfdat26-env]", + "display_name": "Python [bersonenv]", "language": "python", - "name": "Python [sfdat26-env]" + "name": "Python [bersonenv]" }, "language_info": { "codemirror_mode": { diff --git a/notebooks/05_model_evaluation.ipynb b/notebooks/05_model_evaluation.ipynb index e2cb051..2f2ac4d 100644 --- a/notebooks/05_model_evaluation.ipynb +++ b/notebooks/05_model_evaluation.ipynb @@ -96,7 +96,8 @@ "cell_type": "code", "execution_count": 8, "metadata": { - "collapsed": false + "collapsed": false, + "scrolled": true }, "outputs": [ { @@ -126,7 +127,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 2, "metadata": { "collapsed": false }, @@ -137,7 +138,7 @@ "['even', 'odd', 'even', 'odd', 'even', 'odd', 'even', 'odd', 'even', 'odd']" ] }, - "execution_count": 9, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" } @@ -698,9 +699,9 @@ "metadata": { "anaconda-cloud": {}, "kernelspec": { - "display_name": "Python [sfdat26-env]", + "display_name": "Python [bersonenv]", "language": "python", - "name": "Python [sfdat26-env]" + "name": "Python [bersonenv]" }, "language_info": { "codemirror_mode": { From 0f209e2c9b4e1ac884837c63b7f8501a98c318a3 Mon Sep 17 00:00:00 2001 From: Eugene Berson Date: Sat, 22 Oct 2016 20:58:49 -0700 Subject: [PATCH 3/3] removed project.md --- project.md | 85 ------------------------------------------------------ 1 file changed, 85 deletions(-) delete mode 100644 project.md diff --git a/project.md b/project.md deleted file mode 100644 index 2531c6a..0000000 --- a/project.md +++ /dev/null @@ -1,85 +0,0 @@ -# Course Project - - -## Overview - -The final project should represent significant original work applying data science techniques to an interesting problem. Final projects are individual attainments, but you should be talking frequently with your instructors and classmates about them. - -Address a data-related problem in your professional field or a field you're interested in. Pick a subject that you're passionate about; if you're strongly interested in the subject matter it'll be more fun for you and you'll produce a better project! - -To stimulate your thinking, here is an excellent list of [public data sources](public_data.md). Using public data is the most common choice. If you have access to private data, that's also an option, though you'll have to be careful about what results you can release. You are also welcome to compete in a [Kaggle competition](http://www.kaggle.com/) as your project, in which case the data will be provided to you. - -You should also take a look at [past projects](project-examples.md) from other GA Data Science students, to get a sense of the variety and scope of projects. - - -## Project Deliverables - -You are responsible for creating a **project paper** and a **project presentation**. The paper should be written with a technical audience in mind, while the presentation should target a more general audience. You will deliver your presentation (including slides) during the final week of class, though you are also encouraged to present it to other audiences. - -Here are the components you should aim to cover in your **paper**: - -* Problem statement and hypothesis -* Description of your data set and how it was obtained -* Description of any pre-processing steps you took -* What you learned from exploring the data, including visualizations -* How you chose which features to use in your analysis -* Details of your modeling process, including how you selected your models and validated them -* Your challenges and successes -* Possible extensions or business applications of your project -* Conclusions and key learnings - -Your **presentation** should cover these components with less breadth and less depth. Focus on creating an engaging, clear, and informative presentation that tells the story of your project. - -You should create a GitHub repository for your project that contains the following: - -* **Project paper:** any format (PDF, Markdown, etc.) -* **Presentation slides:** any format (PDF, PowerPoint, Google Slides, etc.) -* **Code:** commented Python scripts, and any other code you used in the project -* **Data:** data files in "raw" or "processed" format -* **Data dictionary (aka "code book"):** description of each variable, including units - -If it's not possible or practical to include your entire dataset, you should link to your data source and provide a sample of the data. (GitHub has a [size limit](https://help.github.com/articles/what-is-my-disk-quota/) of 100 MB per file and 1 GB per repository.) If your data is private, you can either include an "anonymized" version of your data or create a private GitHub repository. - - -## Milestones - - -### October 20 (Mandatory): Three potential Questions - -What are three potential questions you would like to try and answer? What data are you planning to use to answer that question? What do you know about the data so far? Why did you choose these topics? Upload this as a **MARKDOWN** file in your sfdat26_work repo. Keep in mind these might not be your final questions, but I want you to start thinking as soon as possible. If you know exactly what you want to do and don't want to icnlude two other ideas, **please still try to think of two more ideas (just in case).** - -Example: - -* I'm planning to predict passenger survival on the Titanic. -* I have Kaggle's Titanic dataset with 10 passenger characteristics. -* I know that many of the fields have missing values, that some of the text fields are messy and will require cleaning, and that about 38% of the passengers in the training set survive. -* I chose this topic because I'm fascinated by the history of the Titanic. - - -### November 11 (Mandatory): First Draft - -Zip up all files relevant to your project, and upload to sfdat26_work repo. Your peers and instructors will provide feedback. - -At a minimum, you should include: - -* Narrative of what you have done so far and what you are still planning to do -* Code, with lots of comments -* At least 3 slides (not including a title or ending slide) - -Ideally, you would also include: - -* Visualizations you have done -* Slides (if you have started making them) -* Data and data dictionary - -Tips for success: - -* The work should stand "on its own", and should not depend upon the reader remembering anything you might have previously said in class about your project. -* Organize your narrative and files so that the reader can easily follow along. -* The better you explain your project, and the easier it is to follow, the more useful feedback you will receive! -* If your reviewers can actually run your code on the provided data, they will be able to give you more useful feedback on your code. (It can be very hard to make useful code suggestions on code that can't be run!) - - -### Dec 8th and 13th: Presentations - -Deliver your project presentation in class, and submit all required deliverables (paper, slides, code, data, and data dictionary). \ No newline at end of file