{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "c8887209-fece-ace3-c60d-183a2e4e12e9" }, "outputs": [], "source": [ "# Ignore warnings\n", "import warnings\n", "warnings.filterwarnings('ignore')\n", "\n", "# Handle table-like data and matrices\n", "import numpy as np\n", "import pandas as pd\n", "\n", "# Modelling Algorithms\n", "from sklearn.tree import DecisionTreeClassifier\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.neighbors import KNeighborsClassifier\n", "from sklearn.naive_bayes import GaussianNB\n", "from sklearn.svm import SVC, LinearSVC\n", "from sklearn.ensemble import RandomForestClassifier , GradientBoostingClassifier\n", "\n", "# Modelling Helpers\n", "from sklearn.preprocessing import Imputer , Normalizer , scale\n", "from sklearn.cross_validation import train_test_split , StratifiedKFold\n", "from sklearn.feature_selection import RFECV\n", "\n", "# Visualisation\n", "import matplotlib as mpl\n", "import matplotlib.pyplot as plt\n", "import matplotlib.pylab as pylab\n", "import seaborn as sns\n", "\n", "# Configure visualisations\n", "%matplotlib inline\n", "mpl.style.use( 'ggplot' )\n", "sns.set_style( 'white' )\n", "pylab.rcParams[ 'figure.figsize' ] = 8 , 6" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "185b12dd-f6ea-80db-8d18-0a1b610d5157" }, "outputs": [], "source": [ "def plot_histograms( df , variables , n_rows , n_cols ):\n", " fig = plt.figure( figsize = ( 16 , 12 ) )\n", " for i, var_name in enumerate( variables ):\n", " ax=fig.add_subplot( n_rows , n_cols , i+1 )\n", " df[ var_name ].hist( bins=10 , ax=ax )\n", " ax.set_title( 'Skew: ' + str( round( float( df[ var_name ].skew() ) , ) ) ) # + ' ' + var_name ) #var_name+\" Distribution\")\n", " ax.set_xticklabels( [] , visible=False )\n", " ax.set_yticklabels( [] , visible=False )\n", " fig.tight_layout() # Improves appearance a bit.\n", " plt.show()\n", "\n", "def plot_distribution( df , var , target , **kwargs ):\n", " row = kwargs.get( 'row' , None )\n", " col = kwargs.get( 'col' , None )\n", " facet = sns.FacetGrid( df , hue=target , aspect=4 , row = row , col = col )\n", " facet.map( sns.kdeplot , var , shade= True )\n", " facet.set( xlim=( 0 , df[ var ].max() ) )\n", " facet.add_legend()\n", "\n", "def plot_categories( df , cat , target , **kwargs ):\n", " row = kwargs.get( 'row' , None )\n", " col = kwargs.get( 'col' , None )\n", " facet = sns.FacetGrid( df , row = row , col = col )\n", " facet.map( sns.barplot , cat , target )\n", " facet.add_legend()\n", "\n", "def plot_correlation_map( df ):\n", " corr = titanic.corr()\n", " _ , ax = plt.subplots( figsize =( 12 , 10 ) )\n", " cmap = sns.diverging_palette( 220 , 10 , as_cmap = True )\n", " _ = sns.heatmap(\n", " corr, \n", " cmap = cmap,\n", " square=True, \n", " cbar_kws={ 'shrink' : .9 }, \n", " ax=ax, \n", " annot = True, \n", " annot_kws = { 'fontsize' : 12 }\n", " )\n", "\n", "def describe_more( df ):\n", " var = [] ; l = [] ; t = []\n", " for x in df:\n", " var.append( x )\n", " l.append( len( pd.value_counts( df[ x ] ) ) )\n", " t.append( df[ x ].dtypes )\n", " levels = pd.DataFrame( { 'Variable' : var , 'Levels' : l , 'Datatype' : t } )\n", " levels.sort_values( by = 'Levels' , inplace = True )\n", " return levels\n", "\n", "def plot_variable_importance( X , y ):\n", " tree = DecisionTreeClassifier( random_state = 99 )\n", " tree.fit( X , y )\n", " plot_model_var_imp( tree , X , y )\n", " \n", "def plot_model_var_imp( model , X , y ):\n", " imp = pd.DataFrame( \n", " model.feature_importances_ , \n", " columns = [ 'Importance' ] , \n", " index = X.columns \n", " )\n", " imp = imp.sort_values( [ 'Importance' ] , ascending = True )\n", " imp[ : 10 ].plot( kind = 'barh' )\n", " print (model.score( X , y ))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "f6015875-892e-f8c5-f0b8-1c34dcaf3f11" }, "outputs": [], "source": [ "# get titanic & test csv files as a DataFrame\n", "train = pd.read_csv(\"../input/train.csv\")\n", "test = pd.read_csv(\"../input/test.csv\")\n", "\n", "full = train.append( test , ignore_index = True )\n", "titanic = full[ :891 ]\n", "\n", "del train , test\n", "\n", "print ('Datasets:' , 'full:' , full.shape , 'titanic:' , titanic.shape)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "f026aa69-1b06-d614-f14a-025a1464e5c6" }, "outputs": [], "source": [ "# Run the code to see the variables, then read the variable description below to understand them.\n", "titanic.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "38f773ed-f16b-4faf-b15c-59ff7d7f4c51" }, "outputs": [], "source": [ "" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "a6a1da2f-ca1e-c40a-7eca-cb37a66920e4" }, "outputs": [], "source": [ "titanic.describe()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "bb8be1a1-a92d-b318-ff61-741604821499" }, "outputs": [], "source": [ "plot_correlation_map(titanic)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "28f37db5-d686-c103-c291-532280670b13" }, "outputs": [], "source": [ "plot_distribution(titanic, var='Age', target='Survived', row='Sex')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "72818b12-6a85-f115-6503-a089266723b8" }, "outputs": [], "source": [ "plot_distribution(titanic, var='Fare', target='Survived', row='Sex')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "dc10055e-3293-f38b-8f5f-0685a9764955" }, "outputs": [], "source": [ "plot_categories(titanic, cat='Embarked', target='Survived')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "603feee9-2515-f016-17a3-e532eca17e12" }, "outputs": [], "source": [ "plot_categories(titanic, cat='Sex', target='Survived')\n", "plot_categories(titanic, cat='Pclass', target='Survived')\n", "plot_categories(titanic, cat='SibSp', target='Survived')\n", "plot_categories(titanic, cat='Parch', target='Survived')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "a6379969-67ea-bd00-5e1c-143b5e2553c8" }, "outputs": [], "source": [ "sex = pd.Series(np.where(full.Sex == 'male', 1, 0), name = 'Sex')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "4648e2fb-ab4c-ffd9-10fa-bb654fe86dfc" }, "outputs": [], "source": [ "embarked = pd.get_dummies(full.Embarked, prefix='Embarked')\n", "embarked.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "65e692bf-476e-47df-a004-9347f12684d0" }, "outputs": [], "source": [ "pclass = pd.get_dummies(full.Pclass, prefix='Pclass')\n", "pclass.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "a723e968-a874-dcdd-6c81-8468751d9c16" }, "outputs": [], "source": [ "imputed = pd.DataFrame()\n", "imputed['Age'] = full.Age.fillna(full.Age.mean())\n", "imputed['Fare'] = full.Fare.fillna(full.Fare.mean())\n", "imputed.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "dca09ebe-e5de-8367-6d89-f5470acac8d1" }, "outputs": [], "source": [ "title = pd.DataFrame()\n", "title['Title'] = full['Name'].map(lambda name: name.split(',')[1].split('.')[0].strip())\n", "\n", "Title_Dictionary = {\n", " \"Capt\": \"Officer\",\n", " \"Col\": \"Officer\",\n", " \"Major\": \"Officer\",\n", " \"Jonkheer\": \"Royalty\",\n", " \"Don\": \"Royalty\",\n", " \"Sir\" : \"Royalty\",\n", " \"Dr\": \"Officer\",\n", " \"Rev\": \"Officer\",\n", " \"the Countess\":\"Royalty\",\n", " \"Dona\": \"Royalty\",\n", " \"Mme\": \"Mrs\",\n", " \"Mlle\": \"Miss\",\n", " \"Ms\": \"Mrs\",\n", " \"Mr\" : \"Mr\",\n", " \"Mrs\" : \"Mrs\",\n", " \"Miss\" : \"Miss\",\n", " \"Master\" : \"Master\",\n", " \"Lady\" : \"Royalty\"\n", "}\n", "\n", "title['Title'] = title.Title.map(Title_Dictionary)\n", "title = pd.get_dummies(title.Title)\n", "title.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "52b30713-fd8e-5047-be32-c98625571339" }, "outputs": [], "source": [ "cabin = pd.DataFrame()\n", "\n", "cabin['Cabin'] = full.Cabin.fillna('U')\n", "cabin['Cabin'] = cabin['Cabin'].map(lambda c: c[0])\n", "cabin = pd.get_dummies(cabin['Cabin'], prefix='Cabin')\n", "cabin.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "816d8c3b-221f-7ca9-88c3-190886675aa3" }, "outputs": [], "source": [ "def cleanTicket(ticket):\n", " ticket = ticket.replace('.','')\n", " ticket = ticket.replace('/','')\n", " ticket = ticket.split()\n", " ticket = map(lambda t:t.strip(), ticket)\n", " ticket = list(filter(lambda t : not t.isdigit(), ticket))\n", " if len(ticket) > 0:\n", " return ticket[0]\n", " else:\n", " return 'XXX'\n", " \n", "ticket = pd.DataFrame()\n", "\n", "ticket['Ticket'] = full['Ticket'].map(cleanTicket)\n", "ticket = pd.get_dummies(ticket['Ticket'], prefix = 'Ticket')\n", "\n", "ticket.shape\n", "ticket.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "31d4adc3-8004-b552-2fa9-ab569b5689e6" }, "outputs": [], "source": [ "family = pd.DataFrame()\n", "\n", "family['FamilySize'] = full['Parch'] + full['SibSp'] + 1\n", "\n", "family['Family_Single'] = family['FamilySize'].map(lambda s : 1 if s == 1 else 0)\n", "family['Family_Small'] = family['FamilySize'].map(lambda s : 1 if 2 <= s <= 4 else 0)\n", "family['Fmaily_Large'] = family['FamilySize'].map(lambda s : 1 if 5 <= s else 0)\n", "family.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "21b5c12f-2f68-0e8d-5315-523c5864b9aa" }, "outputs": [], "source": [ "full_X = pd.concat([imputed, embarked, cabin, sex], axis=1)\n", "full_X.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "8e10eefc-853e-ec31-f6c3-5862057655e5" }, "outputs": [], "source": [ "train_valid_x = full_X[0:891]\n", "train_valid_y = titanic.Survived\n", "test_X = full_X[891:]\n", "train_X, valid_X, train_y, valid_y = train_test_split(train_valid_x, train_valid_y, train_size = 0.7)\n", "\n", "print(full_X.shape, train_X.shape, valid_X.shape, train_y.shape, valid_y.shape, test_X.shape)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "1dcaab17-3d55-c19c-25b8-5bbe88299411" }, "outputs": [], "source": [ "plot_variable_importance(train_X, train_y)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "dfbfae16-a2ad-d6f6-ae09-7bbc7ce1df2e" }, "outputs": [], "source": [ "model = RandomForestClassifier(n_estimators=100)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "0670a40b-4159-92c9-16c5-41c97d3c364e" }, "outputs": [], "source": [ "model = SVC()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "c81b3a7c-c285-0000-0e2d-92eb1edf4b14" }, "outputs": [], "source": [ "model = GradientBoostingClassifier()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "2acbfada-e518-435a-78cd-7cfc1cf8dc7d" }, "outputs": [], "source": [ "model = KNeighborsClassifier(n_neighbors = 3)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "0a6fb3db-ed5b-ca22-d57b-a9c59805d6b9" }, "outputs": [], "source": [ "model = GaussianNB()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "35550142-0613-7027-00c4-5b045edb8954" }, "outputs": [], "source": [ "model = LogisticRegression()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "4d2d1579-2e80-da87-35ec-d4bef870f9f9" }, "outputs": [], "source": [ "model.fit(train_X, train_y)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "296b9c6d-969f-49ec-a07c-4a05befed28a" }, "outputs": [], "source": [ "print(model.score(train_X, train_y), model.score(valid_X, valid_y))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "cb7b9a06-785e-7a84-37d2-7763d4e7c773" }, "outputs": [], "source": [ "rfecv = RFECV(estimator = model, step = 1, cv = StratifiedKFold(train_y, 2), scoring = 'accuracy')\n", "rfecv.fit(train_X, train_y)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "ac327f82-9f52-0149-e0e2-c6e1514f0ddf" }, "outputs": [], "source": [ "test_Y = model.predict(test_X)\n", "passenger_id = full[891:].PassengerId\n", "test = pd.DataFrame({'PassengerId': passenger_id, 'Survived': test_Y})\n", "test.shape\n", "test.head()\n", "test.to_csv('titanic_pred.csv', index=False)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "d7f1f06c-a70d-331d-4add-a089a4a45b86" }, "outputs": [], "source": [ "" ] } ], "metadata": { "_change_revision": 0, "_is_fork": false, "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.0" } }, "nbformat": 4, "nbformat_minor": 0 }