From 4d781584b03583b438d00011ecba959b7e517e41 Mon Sep 17 00:00:00 2001 From: Zack Cooper Date: Mon, 9 Feb 2015 15:57:43 -0500 Subject: [PATCH 1/3] went through both python tutorials on kaggle --- assignments/titanic/requirements.txt | 6 + assignments/titanic/titanic.ipynb | 315 +++++++++++++++++++++++++++ 2 files changed, 321 insertions(+) create mode 100644 assignments/titanic/requirements.txt create mode 100644 assignments/titanic/titanic.ipynb diff --git a/assignments/titanic/requirements.txt b/assignments/titanic/requirements.txt new file mode 100644 index 0000000..b51c073 --- /dev/null +++ b/assignments/titanic/requirements.txt @@ -0,0 +1,6 @@ +pandas +ipython[all] +matplotlib.pyplot +seaborn +numpy +scikit-learn diff --git a/assignments/titanic/titanic.ipynb b/assignments/titanic/titanic.ipynb new file mode 100644 index 0000000..1a4cabf --- /dev/null +++ b/assignments/titanic/titanic.ipynb @@ -0,0 +1,315 @@ +{ + "metadata": { + "name": "", + "signature": "sha256:95dce6a6b20c96ec60404b98fb14efc34bb4288832da7647e85b81c3e917b9d4" + }, + "nbformat": 3, + "nbformat_minor": 0, + "worksheets": [ + { + "cells": [ + { + "cell_type": "code", + "collapsed": false, + "input": [ + "import numpy as np\n", + "import seaborn as sns\n", + "import matplotlib.pyplot as plt\n", + "import pandas as pd\n", + "import csv\n", + "\n", + "%matplotlib inline\n", + "\n", + "train_file = pd.read_csv('train.csv')\n", + "train_file.info()" + ], + "language": "python", + "metadata": {}, + "outputs": [ + { + "output_type": "stream", + "stream": "stdout", + "text": [ + "\n", + "Int64Index: 891 entries, 0 to 890\n", + "Data columns (total 12 columns):\n", + "PassengerId 891 non-null int64\n", + "Survived 891 non-null int64\n", + "Pclass 891 non-null int64\n", + "Name 891 non-null object\n", + "Sex 891 non-null object\n", + "Age 714 non-null float64\n", + "SibSp 891 non-null int64\n", + "Parch 891 non-null int64\n", + "Ticket 891 non-null object\n", + "Fare 891 non-null float64\n", + "Cabin 204 non-null object\n", + "Embarked 889 non-null object\n", + "dtypes: float64(2), int64(5), object(5)\n", + "memory usage: 90.5+ KB\n" + ] + } + ], + "prompt_number": 270 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "train_file[train_file['Age'].isnull()][['Sex', 'Pclass', 'Age']].head()" + ], + "language": "python", + "metadata": {}, + "outputs": [ + { + "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", + "
SexPclassAge
5 male 3NaN
17 male 2NaN
19 female 3NaN
26 male 3NaN
28 female 3NaN
\n", + "
" + ], + "metadata": {}, + "output_type": "pyout", + "prompt_number": 271, + "text": [ + " Sex Pclass Age\n", + "5 male 3 NaN\n", + "17 male 2 NaN\n", + "19 female 3 NaN\n", + "26 male 3 NaN\n", + "28 female 3 NaN" + ] + } + ], + "prompt_number": 271 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "male = train_file['Sex'] == 'male'\n", + "female = train_file['Sex'] == 'female'\n", + "\n", + "for num in range(1,4):\n", + " count = len(train_file[male & (train_file['Pclass'] == num)])\n", + " print(num, count)" + ], + "language": "python", + "metadata": {}, + "outputs": [ + { + "output_type": "stream", + "stream": "stdout", + "text": [ + "1 122\n", + "2 108\n", + "3 347\n" + ] + } + ], + "prompt_number": 272 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "train_file.Age.dropna().hist()" + ], + "language": "python", + "metadata": {}, + "outputs": [ + { + "metadata": {}, + "output_type": "pyout", + "prompt_number": 273, + "text": [ + "" + ] + }, + { + "metadata": {}, + "output_type": "display_data", + "png": "iVBORw0KGgoAAAANSUhEUgAAAXgAAAECCAYAAAD0JMwBAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text": [ + "" + ] + } + ], + "prompt_number": 273 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "train_file['Gender'] = train_file['Sex'].map( {'female': 0, 'male': 1} ).astype(int)" + ], + "language": "python", + "metadata": {}, + "outputs": [], + "prompt_number": 274 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "train_file['Embarked'].fillna(0, inplace=True)\n", + "train_file['Embark_binary'] = train_file['Embarked'].map({'S':1, 'C':2, 'Q':3, 0:0}).astype(int)\n", + "train_file['Age Is Null'] = train_file.Age.isnull().astype(int)" + ], + "language": "python", + "metadata": {}, + "outputs": [], + "prompt_number": 275 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "for _ in range(0,4):\n", + " med_age = train_file[(train_file['Embark_binary'] == _)]['Age'].median()\n", + " embark_two = train_file[train_file['Embark_binary'] == _]\n", + " embark_two['Age'].fillna(med_age, inplace=True)\n", + " train_file[(train_file['Embark_binary'] == _)] = embark_two" + ], + "language": "python", + "metadata": {}, + "outputs": [], + "prompt_number": 276 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "train_file['FamilySize'] = train_file['SibSp'] + train_file['Parch']" + ], + "language": "python", + "metadata": {}, + "outputs": [], + "prompt_number": 280 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "train_file.dtypes[train_file.dtypes.map(lambda x: x=='object')]" + ], + "language": "python", + "metadata": {}, + "outputs": [ + { + "metadata": {}, + "output_type": "pyout", + "prompt_number": 293, + "text": [ + "Name object\n", + "Sex object\n", + "Ticket object\n", + "Cabin object\n", + "Embarked object\n", + "dtype: object" + ] + } + ], + "prompt_number": 293 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "train_file_clean = train_file.drop(['Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1)" + ], + "language": "python", + "metadata": {}, + "outputs": [], + "prompt_number": 295 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "train_clean = train_file_clean.values" + ], + "language": "python", + "metadata": {}, + "outputs": [], + "prompt_number": 297 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "train_clean" + ], + "language": "python", + "metadata": {}, + "outputs": [ + { + "metadata": {}, + "output_type": "pyout", + "prompt_number": 298, + "text": [ + "array([[ 1., 0., 3., ..., 1., 0., 1.],\n", + " [ 2., 1., 1., ..., 2., 0., 1.],\n", + " [ 3., 1., 3., ..., 1., 0., 0.],\n", + " ..., \n", + " [ 889., 0., 3., ..., 1., 1., 3.],\n", + " [ 890., 1., 1., ..., 2., 0., 0.],\n", + " [ 891., 0., 3., ..., 3., 0., 0.]])" + ] + } + ], + "prompt_number": 298 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [], + "language": "python", + "metadata": {}, + "outputs": [] + } + ], + "metadata": {} + } + ] +} \ No newline at end of file From 889b020aa490ee395ebd069fb021918d4129decc Mon Sep 17 00:00:00 2001 From: Zack Cooper Date: Mon, 9 Feb 2015 17:07:33 -0500 Subject: [PATCH 2/3] finished the model as described in the tutorial. It made my score worse. Wahoo. --- assignments/titanic/test_titanic_answer.csv | 419 ++++++++++++++++++++ assignments/titanic/titanic.ipynb | 277 ++++++------- 2 files changed, 536 insertions(+), 160 deletions(-) create mode 100644 assignments/titanic/test_titanic_answer.csv diff --git a/assignments/titanic/test_titanic_answer.csv b/assignments/titanic/test_titanic_answer.csv new file mode 100644 index 0000000..b956c05 --- /dev/null +++ b/assignments/titanic/test_titanic_answer.csv @@ -0,0 +1,419 @@ +Survived,PassengerId +0,892 +0,893 +0,894 +1,895 +0,896 +0,897 +0,898 +0,899 +0,900 +0,901 +0,902 +0,903 +1,904 +0,905 +1,906 +1,907 +0,908 +0,909 +0,910 +0,911 +0,912 +1,913 +1,914 +1,915 +1,916 +0,917 +1,918 +0,919 +0,920 +0,921 +0,922 +0,923 +1,924 +0,925 +0,926 +0,927 +1,928 +1,929 +0,930 +0,931 +0,932 +1,933 +0,934 +1,935 +1,936 +0,937 +0,938 +0,939 +1,940 +0,941 +1,942 +0,943 +1,944 +1,945 +0,946 +0,947 +0,948 +0,949 +0,950 +1,951 +0,952 +0,953 +0,954 +1,955 +1,956 +1,957 +0,958 +0,959 +0,960 +1,961 +1,962 +0,963 +0,964 +1,965 +1,966 +1,967 +0,968 +1,969 +0,970 +1,971 +1,972 +0,973 +1,974 +0,975 +0,976 +0,977 +1,978 +1,979 +1,980 +1,981 +0,982 +0,983 +0,984 +0,985 +0,986 +0,987 +1,988 +0,989 +0,990 +0,991 +1,992 +0,993 +0,994 +0,995 +0,996 +0,997 +0,998 +0,999 +0,1000 +0,1001 +0,1002 +1,1003 +1,1004 +0,1005 +1,1006 +0,1007 +0,1008 +1,1009 +0,1010 +1,1011 +1,1012 +0,1013 +1,1014 +0,1015 +0,1016 +1,1017 +0,1018 +1,1019 +0,1020 +0,1021 +1,1022 +0,1023 +0,1024 +0,1025 +0,1026 +0,1027 +1,1028 +0,1029 +1,1030 +0,1031 +0,1032 +1,1033 +0,1034 +0,1035 +1,1036 +0,1037 +1,1038 +0,1039 +1,1040 +0,1041 +1,1042 +0,1043 +0,1044 +0,1045 +0,1046 +0,1047 +1,1048 +1,1049 +1,1050 +1,1051 +1,1052 +1,1053 +1,1054 +0,1055 +0,1056 +0,1057 +0,1058 +0,1059 +1,1060 +1,1061 +0,1062 +1,1063 +0,1064 +0,1065 +0,1066 +1,1067 +1,1068 +0,1069 +1,1070 +1,1071 +0,1072 +0,1073 +1,1074 +0,1075 +1,1076 +0,1077 +1,1078 +0,1079 +0,1080 +0,1081 +0,1082 +1,1083 +1,1084 +0,1085 +1,1086 +0,1087 +1,1088 +1,1089 +0,1090 +1,1091 +1,1092 +1,1093 +1,1094 +1,1095 +0,1096 +1,1097 +0,1098 +0,1099 +1,1100 +0,1101 +1,1102 +0,1103 +0,1104 +0,1105 +1,1106 +1,1107 +1,1108 +0,1109 +1,1110 +0,1111 +1,1112 +0,1113 +1,1114 +0,1115 +0,1116 +1,1117 +0,1118 +1,1119 +0,1120 +0,1121 +0,1122 +1,1123 +0,1124 +0,1125 +1,1126 +0,1127 +0,1128 +0,1129 +1,1130 +1,1131 +1,1132 +1,1133 +0,1134 +0,1135 +0,1136 +0,1137 +1,1138 +0,1139 +1,1140 +1,1141 +1,1142 +0,1143 +0,1144 +0,1145 +1,1146 +0,1147 +0,1148 +0,1149 +1,1150 +0,1151 +0,1152 +0,1153 +1,1154 +1,1155 +0,1156 +0,1157 +1,1158 +0,1159 +1,1160 +0,1161 +0,1162 +0,1163 +1,1164 +1,1165 +0,1166 +1,1167 +0,1168 +0,1169 +0,1170 +0,1171 +1,1172 +1,1173 +1,1174 +0,1175 +1,1176 +0,1177 +0,1178 +1,1179 +0,1180 +0,1181 +1,1182 +0,1183 +0,1184 +0,1185 +0,1186 +0,1187 +1,1188 +0,1189 +0,1190 +0,1191 +1,1192 +0,1193 +0,1194 +0,1195 +1,1196 +1,1197 +1,1198 +1,1199 +0,1200 +0,1201 +0,1202 +0,1203 +0,1204 +0,1205 +1,1206 +1,1207 +0,1208 +0,1209 +1,1210 +0,1211 +0,1212 +0,1213 +0,1214 +0,1215 +1,1216 +0,1217 +1,1218 +0,1219 +0,1220 +0,1221 +1,1222 +1,1223 +0,1224 +0,1225 +1,1226 +0,1227 +0,1228 +0,1229 +0,1230 +0,1231 +0,1232 +1,1233 +0,1234 +1,1235 +0,1236 +0,1237 +0,1238 +0,1239 +0,1240 +1,1241 +1,1242 +0,1243 +0,1244 +0,1245 +1,1246 +1,1247 +1,1248 +0,1249 +0,1250 +0,1251 +0,1252 +1,1253 +1,1254 +1,1255 +1,1256 +0,1257 +0,1258 +1,1259 +1,1260 +0,1261 +0,1262 +1,1263 +1,1264 +0,1265 +1,1266 +1,1267 +0,1268 +0,1269 +0,1270 +0,1271 +0,1272 +0,1273 +1,1274 +1,1275 +0,1276 +1,1277 +0,1278 +0,1279 +0,1280 +0,1281 +1,1282 +1,1283 +0,1284 +0,1285 +0,1286 +1,1287 +0,1288 +1,1289 +0,1290 +0,1291 +1,1292 +0,1293 +1,1294 +1,1295 +1,1296 +0,1297 +0,1298 +0,1299 +1,1300 +1,1301 +1,1302 +1,1303 +0,1304 +0,1305 +1,1306 +0,1307 +0,1308 +0,1309 diff --git a/assignments/titanic/titanic.ipynb b/assignments/titanic/titanic.ipynb index 1a4cabf..b744c2f 100644 --- a/assignments/titanic/titanic.ipynb +++ b/assignments/titanic/titanic.ipynb @@ -1,7 +1,7 @@ { "metadata": { "name": "", - "signature": "sha256:95dce6a6b20c96ec60404b98fb14efc34bb4288832da7647e85b81c3e917b9d4" + "signature": "sha256:d4564e41dd7ce263e7793aaf047bc32b2f91c0bd0bd4c5a35715d84acd78d070" }, "nbformat": 3, "nbformat_minor": 0, @@ -13,6 +13,7 @@ "collapsed": false, "input": [ "import numpy as np\n", + "from sklearn.ensemble import RandomForestClassifier \n", "import seaborn as sns\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", @@ -21,107 +22,12 @@ "%matplotlib inline\n", "\n", "train_file = pd.read_csv('train.csv')\n", - "train_file.info()" + "test_file = pd.read_csv('test.csv')" ], "language": "python", "metadata": {}, - "outputs": [ - { - "output_type": "stream", - "stream": "stdout", - "text": [ - "\n", - "Int64Index: 891 entries, 0 to 890\n", - "Data columns (total 12 columns):\n", - "PassengerId 891 non-null int64\n", - "Survived 891 non-null int64\n", - "Pclass 891 non-null int64\n", - "Name 891 non-null object\n", - "Sex 891 non-null object\n", - "Age 714 non-null float64\n", - "SibSp 891 non-null int64\n", - "Parch 891 non-null int64\n", - "Ticket 891 non-null object\n", - "Fare 891 non-null float64\n", - "Cabin 204 non-null object\n", - "Embarked 889 non-null object\n", - "dtypes: float64(2), int64(5), object(5)\n", - "memory usage: 90.5+ KB\n" - ] - } - ], - "prompt_number": 270 - }, - { - "cell_type": "code", - "collapsed": false, - "input": [ - "train_file[train_file['Age'].isnull()][['Sex', 'Pclass', 'Age']].head()" - ], - "language": "python", - "metadata": {}, - "outputs": [ - { - "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", - "
SexPclassAge
5 male 3NaN
17 male 2NaN
19 female 3NaN
26 male 3NaN
28 female 3NaN
\n", - "
" - ], - "metadata": {}, - "output_type": "pyout", - "prompt_number": 271, - "text": [ - " Sex Pclass Age\n", - "5 male 3 NaN\n", - "17 male 2 NaN\n", - "19 female 3 NaN\n", - "26 male 3 NaN\n", - "28 female 3 NaN" - ] - } - ], - "prompt_number": 271 + "outputs": [], + "prompt_number": 25 }, { "cell_type": "code", @@ -147,7 +53,7 @@ ] } ], - "prompt_number": 272 + "prompt_number": 26 }, { "cell_type": "code", @@ -161,9 +67,9 @@ { "metadata": {}, "output_type": "pyout", - "prompt_number": 273, + "prompt_number": 27, "text": [ - "" + "" ] }, { @@ -171,114 +77,141 @@ "output_type": "display_data", "png": "iVBORw0KGgoAAAANSUhEUgAAAXgAAAECCAYAAAD0JMwBAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text": [ - "" + "" ] } ], - "prompt_number": 273 + "prompt_number": 27 }, { "cell_type": "code", "collapsed": false, "input": [ - "train_file['Gender'] = train_file['Sex'].map( {'female': 0, 'male': 1} ).astype(int)" + "def gender_mapping(a_file):\n", + " a_file['Gender'] = a_file['Sex'].map( {'female': 0, 'male': 1} ).astype(int)\n", + " return a_file\n", + "\n", + "def embark_mapping(a_file):\n", + " a_file['Embarked'].fillna(0, inplace=True)\n", + " a_file['Embark_binary'] = a_file['Embarked'].map({'S':1, 'C':2, 'Q':3, 0:0}).astype(int)\n", + " return a_file\n", + "\n", + "def age_mapping(a_file):\n", + " a_file['Age Is Null'] = a_file.Age.isnull().astype(int)\n", + "\n", + " for _ in range(0,4):\n", + " med_age = a_file[(a_file['Embark_binary'] == _)]['Age'].median()\n", + " embark_two = a_file[a_file['Embark_binary'] == _]\n", + " embark_two['Age'].fillna(med_age, inplace=True)\n", + " a_file[(a_file['Embark_binary'] == _)] = embark_two\n", + " return a_file\n", + "\n", + "def family_size(a_file):\n", + " a_file['FamilySize'] = a_file['SibSp'] + a_file['Parch']\n", + " return a_file\n", + "\n", + "def string_objects(a_file):\n", + " a_file_clean = a_file.drop(['Fare', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked', 'PassengerId'], axis=1)\n", + " return a_file_clean\n", + "\n", + "def clean_file_array(a_file):\n", + " a_file1 = gender_mapping(a_file)\n", + " a_file2 = embark_mapping(a_file1)\n", + " a_file3 = age_mapping(a_file2)\n", + " a_file4 = family_size(a_file3)\n", + " a_file5 = string_objects(a_file4)\n", + " return a_file5" ], "language": "python", "metadata": {}, "outputs": [], - "prompt_number": 274 + "prompt_number": 28 }, { "cell_type": "code", "collapsed": false, "input": [ - "train_file['Embarked'].fillna(0, inplace=True)\n", - "train_file['Embark_binary'] = train_file['Embarked'].map({'S':1, 'C':2, 'Q':3, 0:0}).astype(int)\n", - "train_file['Age Is Null'] = train_file.Age.isnull().astype(int)" + "clean_train_file = clean_file_array(train_file)\n", + "clean_train_file_array = clean_train_file.values\n", + "\n", + "clean_test_file = clean_file_array(test_file)\n", + "clean_test_file_array = clean_file_array(test_file).values" ], "language": "python", "metadata": {}, - "outputs": [], - "prompt_number": 275 + "outputs": [ + { + "output_type": "stream", + "stream": "stderr", + "text": [ + "/Users/zackjcooper/.pyenv/versions/sandbox/lib/python3.4/site-packages/pandas/core/generic.py:2390: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame\n", + "\n", + "See the the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n", + " self._update_inplace(new_data)\n" + ] + } + ], + "prompt_number": 29 }, { "cell_type": "code", "collapsed": false, - "input": [ - "for _ in range(0,4):\n", - " med_age = train_file[(train_file['Embark_binary'] == _)]['Age'].median()\n", - " embark_two = train_file[train_file['Embark_binary'] == _]\n", - " embark_two['Age'].fillna(med_age, inplace=True)\n", - " train_file[(train_file['Embark_binary'] == _)] = embark_two" - ], + "input": [], "language": "python", "metadata": {}, "outputs": [], - "prompt_number": 276 + "prompt_number": 29 }, { "cell_type": "code", "collapsed": false, - "input": [ - "train_file['FamilySize'] = train_file['SibSp'] + train_file['Parch']" - ], + "input": [], "language": "python", "metadata": {}, "outputs": [], - "prompt_number": 280 + "prompt_number": 29 }, { "cell_type": "code", "collapsed": false, - "input": [ - "train_file.dtypes[train_file.dtypes.map(lambda x: x=='object')]" - ], + "input": [], "language": "python", "metadata": {}, - "outputs": [ - { - "metadata": {}, - "output_type": "pyout", - "prompt_number": 293, - "text": [ - "Name object\n", - "Sex object\n", - "Ticket object\n", - "Cabin object\n", - "Embarked object\n", - "dtype: object" - ] - } - ], - "prompt_number": 293 + "outputs": [], + "prompt_number": 29 }, { "cell_type": "code", "collapsed": false, - "input": [ - "train_file_clean = train_file.drop(['Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1)" - ], + "input": [], "language": "python", "metadata": {}, "outputs": [], - "prompt_number": 295 + "prompt_number": 29 }, { "cell_type": "code", "collapsed": false, - "input": [ - "train_clean = train_file_clean.values" - ], + "input": [], "language": "python", "metadata": {}, "outputs": [], - "prompt_number": 297 + "prompt_number": 29 }, { "cell_type": "code", "collapsed": false, "input": [ - "train_clean" + "# Create the random forest object which will include all the parameters for the fit\n", + "forest = RandomForestClassifier(n_estimators = 100)\n", + "\n", + "# Fit the training data to the Survived labels and create the decision trees\n", + "forest = forest.fit(clean_train_file_array[0::,1::],clean_train_file_array[0::,0])\n", + "\n", + "# Take the same decision trees and run it on the test data\n", + "output = forest.predict(clean_test_file_array)\n", + "output" ], "language": "python", "metadata": {}, @@ -286,19 +219,43 @@ { "metadata": {}, "output_type": "pyout", - "prompt_number": 298, + "prompt_number": 32, "text": [ - "array([[ 1., 0., 3., ..., 1., 0., 1.],\n", - " [ 2., 1., 1., ..., 2., 0., 1.],\n", - " [ 3., 1., 3., ..., 1., 0., 0.],\n", - " ..., \n", - " [ 889., 0., 3., ..., 1., 1., 3.],\n", - " [ 890., 1., 1., ..., 2., 0., 0.],\n", - " [ 891., 0., 3., ..., 3., 0., 0.]])" + "array([0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1,\n", + " 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0,\n", + " 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0,\n", + " 1, 1, 0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0,\n", + " 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1,\n", + " 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0,\n", + " 1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1,\n", + " 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0,\n", + " 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0,\n", + " 0, 1, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0,\n", + " 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0,\n", + " 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1,\n", + " 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0,\n", + " 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0,\n", + " 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0,\n", + " 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1,\n", + " 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1,\n", + " 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0,\n", + " 1, 0, 0, 0])" ] } ], - "prompt_number": 298 + "prompt_number": 32 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "test_file['Survived'] = output.astype(int)\n", + "test_file[['Survived', 'PassengerId']].to_csv('test_titanic_answer.csv', index=False)" + ], + "language": "python", + "metadata": {}, + "outputs": [], + "prompt_number": 34 }, { "cell_type": "code", From b430817dbe0b088af475bbc86fae6cf1df5db615 Mon Sep 17 00:00:00 2001 From: Zack Cooper Date: Mon, 9 Feb 2015 21:28:24 -0500 Subject: [PATCH 3/3] finished --- assignments/titanic/test_titanic_answer.csv | 60 ++--- assignments/titanic/titanic.ipynb | 247 +++++++++++++++----- 2 files changed, 217 insertions(+), 90 deletions(-) diff --git a/assignments/titanic/test_titanic_answer.csv b/assignments/titanic/test_titanic_answer.csv index b956c05..b5d2026 100644 --- a/assignments/titanic/test_titanic_answer.csv +++ b/assignments/titanic/test_titanic_answer.csv @@ -22,7 +22,7 @@ Survived,PassengerId 0,912 1,913 1,914 -1,915 +0,915 1,916 0,917 1,918 @@ -62,14 +62,14 @@ Survived,PassengerId 0,952 0,953 0,954 -1,955 +0,955 1,956 1,957 0,958 0,959 0,960 1,961 -1,962 +0,962 0,963 0,964 1,965 @@ -78,22 +78,22 @@ Survived,PassengerId 0,968 1,969 0,970 -1,971 +0,971 1,972 0,973 -1,974 +0,974 0,975 0,976 0,977 -1,978 +0,978 1,979 -1,980 +0,980 1,981 0,982 0,983 0,984 0,985 -0,986 +1,986 0,987 1,988 0,989 @@ -110,7 +110,7 @@ Survived,PassengerId 0,1000 0,1001 0,1002 -1,1003 +0,1003 1,1004 0,1005 1,1006 @@ -126,7 +126,7 @@ Survived,PassengerId 0,1016 1,1017 0,1018 -1,1019 +0,1019 0,1020 0,1021 1,1022 @@ -137,7 +137,7 @@ Survived,PassengerId 0,1027 1,1028 0,1029 -1,1030 +0,1030 0,1031 0,1032 1,1033 @@ -156,10 +156,10 @@ Survived,PassengerId 0,1046 0,1047 1,1048 -1,1049 +0,1049 1,1050 1,1051 -1,1052 +0,1052 1,1053 1,1054 0,1055 @@ -180,7 +180,7 @@ Survived,PassengerId 1,1070 1,1071 0,1072 -0,1073 +1,1073 1,1074 0,1075 1,1076 @@ -199,7 +199,7 @@ Survived,PassengerId 1,1089 0,1090 1,1091 -1,1092 +0,1092 1,1093 1,1094 1,1095 @@ -213,9 +213,9 @@ Survived,PassengerId 0,1103 0,1104 0,1105 -1,1106 +0,1106 1,1107 -1,1108 +0,1108 0,1109 1,1110 0,1111 @@ -226,7 +226,7 @@ Survived,PassengerId 0,1116 1,1117 0,1118 -1,1119 +0,1119 0,1120 0,1121 0,1122 @@ -244,7 +244,7 @@ Survived,PassengerId 0,1134 0,1135 0,1136 -0,1137 +1,1137 1,1138 0,1139 1,1140 @@ -279,9 +279,9 @@ Survived,PassengerId 0,1169 0,1170 0,1171 -1,1172 +0,1172 1,1173 -1,1174 +0,1174 0,1175 1,1176 0,1177 @@ -303,9 +303,9 @@ Survived,PassengerId 0,1193 0,1194 0,1195 -1,1196 +0,1196 1,1197 -1,1198 +0,1198 1,1199 0,1200 0,1201 @@ -330,7 +330,7 @@ Survived,PassengerId 0,1220 0,1221 1,1222 -1,1223 +0,1223 0,1224 0,1225 1,1226 @@ -371,7 +371,7 @@ Survived,PassengerId 0,1261 0,1262 1,1263 -1,1264 +0,1264 0,1265 1,1266 1,1267 @@ -389,9 +389,9 @@ Survived,PassengerId 0,1279 0,1280 0,1281 -1,1282 +0,1282 1,1283 -0,1284 +1,1284 0,1285 0,1286 1,1287 @@ -402,14 +402,14 @@ Survived,PassengerId 1,1292 0,1293 1,1294 -1,1295 +0,1295 1,1296 0,1297 0,1298 0,1299 -1,1300 +0,1300 1,1301 -1,1302 +0,1302 1,1303 0,1304 0,1305 diff --git a/assignments/titanic/titanic.ipynb b/assignments/titanic/titanic.ipynb index b744c2f..8ab3159 100644 --- a/assignments/titanic/titanic.ipynb +++ b/assignments/titanic/titanic.ipynb @@ -1,7 +1,7 @@ { "metadata": { "name": "", - "signature": "sha256:d4564e41dd7ce263e7793aaf047bc32b2f91c0bd0bd4c5a35715d84acd78d070" + "signature": "sha256:828b3a34ebc03b23c95cc6d626dc3ecca3d1125069c1ef467f7afcb9ba1c99ea" }, "nbformat": 3, "nbformat_minor": 0, @@ -27,7 +27,7 @@ "language": "python", "metadata": {}, "outputs": [], - "prompt_number": 25 + "prompt_number": 1 }, { "cell_type": "code", @@ -53,7 +53,7 @@ ] } ], - "prompt_number": 26 + "prompt_number": 2 }, { "cell_type": "code", @@ -67,9 +67,9 @@ { "metadata": {}, "output_type": "pyout", - "prompt_number": 27, + "prompt_number": 3, "text": [ - "" + "" ] }, { @@ -77,11 +77,11 @@ "output_type": "display_data", "png": "iVBORw0KGgoAAAANSUhEUgAAAXgAAAECCAYAAAD0JMwBAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text": [ - "" + "" ] } ], - "prompt_number": 27 + "prompt_number": 3 }, { "cell_type": "code", @@ -125,7 +125,7 @@ "language": "python", "metadata": {}, "outputs": [], - "prompt_number": 28 + "prompt_number": 4 }, { "cell_type": "code", @@ -139,56 +139,177 @@ ], "language": "python", "metadata": {}, + "outputs": [], + "prompt_number": 10 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "pd.pivot_table(clean_train_file, index=[\"Gender\"], values=[\"Survived\"]).plot(kind=\"barh\")\n", + "plt.axvline(x=0.5, linewidth=2, color='r')" + ], + "language": "python", + "metadata": {}, "outputs": [ { - "output_type": "stream", - "stream": "stderr", + "metadata": {}, + "output_type": "pyout", + "prompt_number": 18, + "text": [ + "" + ] + }, + { + "metadata": {}, + "output_type": "display_data", + "png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAD9CAYAAAC7iRw+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text": [ - "/Users/zackjcooper/.pyenv/versions/sandbox/lib/python3.4/site-packages/pandas/core/generic.py:2390: SettingWithCopyWarning: \n", - "A value is trying to be set on a copy of a slice from a DataFrame\n", - "\n", - "See the the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n", - " self._update_inplace(new_data)\n" + "" ] } ], - "prompt_number": 29 + "prompt_number": 18 }, { "cell_type": "code", "collapsed": false, - "input": [], + "input": [ + "pd.pivot_table(clean_train_file, index=[\"SibSp\"], values=[\"Survived\"]).plot(kind=\"barh\")" + ], "language": "python", "metadata": {}, - "outputs": [], - "prompt_number": 29 + "outputs": [ + { + "metadata": {}, + "output_type": "pyout", + "prompt_number": 19, + "text": [ + "" + ] + }, + { + "metadata": {}, + "output_type": "display_data", + "png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAD9CAYAAAC7iRw+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAFU5JREFUeJzt3X+U3XV95/HnJGHUZEJI6MRimGZoZD72rD9KmxX5YWn4\n0dMKScVKPQWBAhEQ+VFd6BIUut3UE1wh3cBWSlQqdZfuKR5/rSyoSJQWURfMUtrKe0LCCGTRTJnZ\nIT+QMMnsH/cGp2zmzq/7/TH3+3yck8O9mTufz/vNvXnNdz73c7/ftpGRESRJ1TGr6AIkSfky+CWp\nYgx+SaoYg1+SKsbgl6SKMfglqWLmFF3AAcPD+0YGB/cUXUZmFi6ci/3NXK3cXyv3Bq3fX2fn/LbJ\nfk9pjvjf+MZlRZeQqTlzZhddQqbsb+Zq5d6g9fubitIEvyQpHwa/JFWMwS9JFWPwS1LFGPySVDGl\nCf6+vr6iS5CkSijNPv7e3l4WLjyi6DIkFWzv3r0888yPmzbe4GAH8+YdTnt7e9PGnOlKE/ySBPDM\nMz/mqk9+lbkLFjdlvD1DO9hwzSqWLTu64eM+//nP8eijP2B4eJhZs2bxoQ/9ESm9aUpz3nLLzbzv\nfefw+tf/4pS+f/36T7Bixakcc8yvT+n7x2PwSyqduQsW07FwSW7zPfXUNr773Qe57bY7ANiypZeP\nf/w/8LnP3TWl8a688t9Nq562tkl/GHdSSrPGL0lF6ejo4Kc//Slf+9pX6O/fwdFH9/DpT9/J5Zdf\nzNNP15advvzlL3DHHRv5yU+e47zz3scVV1zCXXf9Ne9//1mvjLN+/Sd48MFvc8UVl/D0032sXn0e\nP/nJcwBs2nQ/GzbczO7du/jYx/6YK6+8lCuvvJRt2558ZfwLLzyHj3zkCrZs6c2038yCP6U0K6V0\nR0rp71NKD6aUUlZzSdJ0dHYu5sYbb+bxxx/j0ksv5Jxz3stDDz34qiPvn98eGBjgz//8Lzj77PNY\ntuyNPPbYZvbu3cvmzY9ywgnvfOVxZ5yxivvuuweAe+/9GqtWncmdd97B8uVv55Zb/pJrrrmOm266\nkcHBQf72b/+GjRvv5KabNtDW1pbpUX+WSz2/BcyLiBNTSqcCHwfeO9aDTz75ZDZv/lGG5UjSwW3f\n/izz5nWwZs0NADzxxI+4+uorOPzwzlceM/r65Ecc8QbmzKnF58qVZ3LvvV/j+eef58QTT2L27APn\nBmrjtNN+m8su+wBnnPFudu/ezVFH/TLbtj3J5s2P8K1vfROAnTtfYPv2Z1i69KhXxnzLW95GltdD\nz3Kp50VgQUqpDVgA7M1wLkmasief3ML69f+J4eFhALq6uujoOJTDDjuMf/mXfgB6e5945fGzZv08\nOpcvfzu9vcE993yVlSvf/a/GnTevg5TexC233Mzpp68CYOnSo/j93z+bW2+9nRtuWMvv/M4ZHHnk\nL/HUU9t46aWfMTIywo9+9E8z9oj/IeC1wBPA4cDKDOeS1EL2DO3IdayTTlrBj3/8FKtXn8frXvc6\nRkZGuPzyq5g9ew7r13+CxYt/kc7OzlfC+NWhvGLFKTzyyP/iDW/4/9+QXrXqTK6++ko++tE/AeD8\n8y9k3bq1fPWrX2L37t1cdNElHHbYYZx//oV88IOrOfTQQ5k9O9t9N21Z/TqRUrqO2lLPR1NKRwIP\nAG+OiIMe+R955JEjzz77bCa1SJo59u7d2/QPdHZ3d7fyPv5J/2qQ5Y+VecAL9duDwCFAwxNj9/fv\nzLCcYnV2zre/GayV+ytjb838MOfP+3upaWOWSWfn/El/T5bB/0ngr1JKf0ct9NdExIsZzidJmoDM\ngj8i/i9w5kQf/8ADD2RViiRpFD/AJUkVY/BLUsUY/JJUMQa/JFVMaYK/p6en6BIkqRJKE/zd3d1F\nlyBJlVCa4Jck5cPgl6SKMfglqWIMfkmqGINfkiqmNMHf7NOwSpIOrjTBL0nKh8EvSRVj8EtSxRj8\nklQxBr8kVUxpgt9z9UhSPkoT/JKkfJQm+IeHh4suQZIqoTTBL0nKh8EvSRVj8EtSxZQm+B944IGi\nS5CkSpiT5eAppR8CQ/W72yLioiznkySNL7PgTym9FiAiVmQ1hyRp8rI84n8bMDel9PX6PNdFxPcz\nnE+SNAFtIyMjmQycUnozcGxEfDaldDRwL9ATEfsP9vje3t6Rnp6eTGqRpBbWNtlvyPKIvxd4EiAi\ntqSUngeOALaP9Q39/TszLKdYnZ3z7W8Ga+X+Wrk3qEZ/k5Xlrp4LgJsBUkpvAA4FnhvrwSeffHKG\npUiSDsjyiP+zwF+llB6s379grGUeSVJ+Mgv+iBgGzs1qfEnS1JTmA1ySpHwY/JJUMQa/JFVMaYL/\n2WefLboESaqE0gS/JCkfBr8kVYzBL0kVY/BLUsUY/JJUMaUJ/u7u7qJLkKRKKE3wS5LyYfBLUsUY\n/JJUMQa/JFWMwS9JFVOa4O/r6yu6BEmqhNIEvyQpHwa/JFVMltfcnZTe3l4GBnYVXUZmBgc7Stdf\nV9dS2tvbiy5DUs5KE/znrrmLuQsWF11GZewZ2sGGa1axbNnRRZciKWelCf65CxbTsXBJ0WVIUssr\nzRr/w3dfX3QJklQJpQl+SVI+Ml/qSSktBh4FTomI3qznkyQ1lukRf0rpEOB2YHeW80iSJi7rpZ5P\nArcBz2U8jyRpgjIL/pTSHwL9EfGN+l+1ZTWXJGni2kZGRjIZOKX0HWCk/udXgQB+NyJ+erDHr7jw\nUyNu58zPrsHt3H7tqfT09BRdiqTpmfRBdWZv7kbESQdup5Q2AZeMFfoqxsDALvr7dzZlrM7O+U0b\nq4xaub9W7g2q0d9kuZ1Tkioml0/uRsSKPOaRJI3PI35JqhiDX5IqpjTB77l6JCkfpTk758j+fewa\n3F50GZWxZ2hH0SVIKkhpgr9zYQfrLn5H0WVkZtGicl6IRVL1lCb458yZ09IXBWn1vcSSZo7SrPFL\nkvJh8EtSxZQm+Pv6+oouQZIqoTTBL0nKh8EvSRVj8EtSxRj8klQxBr8kVUxpgr+7u7voEiSpEib0\nyd2U0hzgbcDLwOMRkc31GiVJmRv3iD+ldBrwNLARuBPYllJ6e9aFSZKyMZEj/v8MvCsi/jdASmk5\n8JfA8iwLkyRlYyJr/D87EPoAEfEIU7iquySpHCZyxP/dlNJt1I7y9wHnMGq5JyJ+0IxChoeH2bp1\nSzOGKqXBwfKdlrmZ8u6vq2sp7e3tuc0ntZKJBP9bgBFqSz6jfaL+36ZcSH3JsatZs/F7zRhKLW7P\n0A42XLOqpU/jLWVp3OCPiN/MoQ7mLlhMx8IleUwlSZU2ZvCnlGYBHwI2RcQ/ppSuAj4A/BC4PCJe\nyKlGSVITNXpzdx1wGrA7pXQCsBb4I2rBf0sOtUmSMtBoqed04JiIeLl+tH93RNwP3J9SemIig6eU\nZgOfBnqovU9waUT803SLliRNXaMj/uGIeLl+ewXwzQl+32hnAPsj4kTgY8DHJ1+iJKmZGgX4npTS\n0pTSvwHeBHwDIKX0FmBoIoNHxFeAS+p3u4HBsR778N3XT2RISdI0NVrquQ54GDgU+NOIGEgpXQbc\nAFww0QkiYl9K6XPAmcB7p1GrJKkJ2kZGxj7fWkrpNcDciBis3z8WGIiISX/SKqX0euD7wK9ExIuv\n/vpr5x8+ctrFd0x2WFXQrsHt3H7tqfT09BRdilQGkz6TQsN9/BHxEvBSSuldwCnAMLW1/gkFf0rp\nXODIiFgHvAjsr/+RpmVgYBf9/Ttzm6+zc36u8+WplXuDavQ3WRM5O+efAWuAPuD/AGtTSmsmOP4X\ngF9NKX0HuA+4qv7DRJJUkImcsuF3gV87sMMnpXQ78Ci1ff4N1Zd03jetCiVJTTWRbZlDQMeo+4cw\nwV09k3HcWWubPaQk6SAanbLh1vrNl4AfppS+SO3snCuByKE2SVIGGi31PErt07YHzr9/YPvPP4+6\nLUmaYRoF/9cj4rmU0lJqQT96y1DTg3/P0I5mD6kW5WtFmp5Gwf8Zaufr+Q4HD/qjmlnI59ed3dIX\nKlm0qLUvxJJ3f11dS3ObS2o1YwZ/RJyeUloJnBIRW1NK7wEuonZ2zv/Y7EJ6enpafq+t/UkqgzF3\n9aSUrgb+BHhNSumtwH8FvkRth88nm11Id3d3s4eUJB1Eo+2c5wEnRcQ/A2cDX4mIzwAfAX47j+Ik\nSc3XKPj3R8Tu+u0VwNcBImIEd/VI0ozV6M3d4ZTSQmAecAz14E8p/RLwcoPvkySVWKMj/huBzdTO\nqPmZ+tbOs4AHgJvyKE6S1HyNdvV8IaX0MPALEfFY/a/3AKsj4tt5FCdJar7xTsu8Hdg+6v49WRXS\n19fndkBJysFEr50rSWoRBr8kVYzBL0kVY/BLUsUY/JJUMaUJfs/VI0n5mMg1d3MxPDzM1q1bii4j\nM4ODrX1aZvubucrWW1fXUtrb24suo6WVJvj7B3exZuP3ii5DUoH2DO1gwzWrWLbs6KJLaWmlCf62\nWbPpWLik6DIkqeWVZo1fkpQPg1+SKiazpZ6U0iHAHcBS4DXAn0XE/xjr8cedtTarUiRJo2R5xH8O\n0B8Rv0Htil3/JcO5JEkTlOWbu3cDX6jfngUMZziXJGmCMgv+A5dtTCnNp/ZD4KNZzSVJmrhMt3Om\nlLqALwJ/ERH/Pcu5JLWGRYs66Oyc39Qxmz3eTJflm7uvB74BXBYRm7KaR1JrGRjY1dSLMnV2zm/p\nizxN5Ydalm/uXgcsAG5IKW2q/3ntWA9++O7rMyxFknRAlmv8VwFXZTW+JGlq/ACXJFWMwS9JFWPw\nS1LFlObsnCP797FrcHvRZUgq0J6hHUWXUAmlCf7HN/+gVBeDaLZFi8p1sYtms7+Zq2y9dXUtLbqE\nllea4O/p6Wn5vbb2N3O1cn+t3JsOzjV+SaoYg1+SKsbgl6SKMfglqWJKE/zd3d1FlyBJlVCa4Jck\n5cPgl6SKMfglqWIMfkmqGINfkiqmNMHf19dXdAmSVAmlCX5JUj4MfkmqmNKcnbO3t7dUp4ZttsHB\ncp36ttnsb+Zq5d6g+f11dS2lvb29aeMVoTTBf+6au5i7YHHRZUjSmPYM7WDDNatYtuzookuZltIE\n/9wFi+lYuKToMiSp5ZVmjf/hu68vugRJqoTSBL8kKR+5BX9K6diU0qa85pMkHVwua/wppT8G3g+0\n7tYBSZoh8jrifxJ4D9CW03ySpDHkEvwR8UVgOI+5JEmNlWY753FnrS26BEka16JFHXR2zi+6jGkp\nTfBL0kwwMLCL/v6dRZfxiqn8EMp7O+dIzvNJkl4ltyP+iOgDjs9rPknSwfkBLkmqGINfkiqmNMHv\nuXokKR+l2dUzsn8fuwa3F12GJI1pz9COoktoitIEf+fCDtZd/I6iy8jMokWtfbEL+5u5Wrk3aH5/\nXV1LmzZWUUoT/HPmzJnxFzdopLNzfqn2/jab/c1crdwbtH5/U1GaNX5JUj4MfkmqmNIEf19fX9El\nSFIllCb4JUn5MPglqWIMfkmqGINfkirG4JekiilN8Hd3dxddgiRVQmmCX5KUD4NfkirG4JekijH4\nJaliSnN2zuHhYbZu3VJ0GZkZHGztU9/a3/R1dS2lvb090zkkKFHwLzl2NWs2fq/oMqRC7BnawYZr\nVrX0qclVHqUJ/rkLFtOxcEnRZUhSy3ONX5IqxuCXpIrJdKknpTQL+BTwVuAlYHVEbM1yTklSY1kf\n8b8baI+I44FrgZsznk+SNI6sg/8E4D6AiPg+sHysBz589/UZlyJJguyD/1DghVH399WXfyRJBcl6\nO+cLwPxR92dFxP6M55RmpEWLOujsnD/+AzNQ1Lx5afX+Jivr4H8IWAncnVJ6B/APGc8nzVgDA7vo\n79+Z+7ydnfMLmTcvVehvsrIO/i8Bp6WUHqrfvyDj+SRJ48g0+CNiBPhglnNIkianNG+0HnfW2qJL\nkKRKKE3wS5LyYfBLUsWU5uyce4Z2FF2CVBhf/8pTaYL/8+vObukLeSxa1NoXKrG/6evqWprp+NIB\npQn+np6elt9ra38zV6v3p2opzRp/d3d30SVIUiWUJvglSfkw+CWpYgx+SaoYg1+SKsbgl6SKaRsZ\nGSm6BklSjjzil6SKMfglqWIMfkmqGINfkirG4JekijH4Jalicj87Z0ppFvAp4K3AS8DqiNg66usr\ngeuBYeCOiPhM3jVOx3j91R8zF/gmcGFERP5VTs0Enrs/AK6i9tw9DlxWv+7yjDCB/n4P+PfACPDf\nIuKWQgqdoom8NuuP2wg8HxFrci5xWibw/H0YuAjor//VJRHRm3uhUzCB3v4tcDPQBmwHzouIvWON\nV8QR/7uB9og4HriWWrEApJQOAdYDpwEnARenlBYXUON0jNkfQEppOfAgcBS1AJlJGj13rwPWAr8Z\nEScCC4AzCqly6hr1NxtYB5wCHAdcllJaVEiVU9fwtQmQUroEeDMz77UJ4/f3a8C5EbGi/mdGhH5d\no9dmG7AR+MOIeCfwLWr5MqYigv8E4D6AiPg+sHzU134FeDIihiLiZeDvgd/Iv8RpadQfQDu1J3HG\nHOmP0qi3nwHHRcTP6vfnAC/mW960jdlfROwD3hQRO4FOYDYw5hFVSTV8baaUjgfeDtxO7chxphnv\n396vA9ellP4upXRt3sVNU6PeeoDngY+klL4NHDbeSkIRwX8o8MKo+/vqv8Yc+NrQqK/tpHbkOJM0\n6o+I+G5EPJt/WU0xZm8RMRIR/QAppSuAeRFxfwE1Tsd4z93+lNJ7gM3AJmBPzvVN15j9pZSOAG4A\nLmdmhj6M8/wBfwNcApwMnJhSOj3P4qapUW+/ABwP3AqcCpySUlrRaLAigv8FYP7oGiJif/320Ku+\nNh8YzKuwJmnU30zXsLeU0qyU0k3UlkN+L+/immDc5y4ivggsAV4DnJdjbc3QqL/3UguQ/0ntfYyz\nU0qt1B/AhogYqK8m3AMck2t109Oot+eprZRERAxT+83g1b/t/CtFBP9DwLsAUkrvAP5h1NeeAI5O\nKS1MKbVTW+Z5OP8Sp6VRfzPdeL3dTi0Qzxy15DOTjNlfSunQlNJ3Ukrt9TesdwP7iilzysbsLyJu\njYjlEbECuBG4KyL+upgyp6zR87cAeDylNK++Jn4y8EghVU5No39724COlNKy+v13Av/YaLDcT9JW\n/59+4N1pgAuorb11RMSnU0pnUPuVcxbw2Yi4LdcCp2m8/kY9bhMzaFcBNO6N2j+iR6i9cX3Ahoj4\ncq5FTsMEXpsfoLYr5GXgMeCKGbZraaKvzfOBFBHX5V/l1E3g+fsD4MPUdsXcHxF/WkylkzeB3g78\nwG4DHoqIDzcaz7NzSlLF+AEuSaoYg1+SKsbgl6SKMfglqWIMfkmqGINfkirG4JekijH4Jali/h+C\nT4Geq5rFQAAAAABJRU5ErkJggg==\n", + "text": [ + "" + ] + } + ], + "prompt_number": 19 }, { "cell_type": "code", "collapsed": false, - "input": [], + "input": [ + "pd.pivot_table(clean_train_file, index=[\"Parch\"], values=[\"Survived\"]).plot(kind=\"barh\")" + ], "language": "python", "metadata": {}, - "outputs": [], - "prompt_number": 29 + "outputs": [ + { + "metadata": {}, + "output_type": "pyout", + "prompt_number": 20, + "text": [ + "" + ] + }, + { + "metadata": {}, + "output_type": "display_data", + "png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAD9CAYAAAC7iRw+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSUVORK5CYII=\n", + "text": [ + "" + ] + } + ], + "prompt_number": 20 }, { "cell_type": "code", "collapsed": false, - "input": [], + "input": [ + "pd.pivot_table(clean_train_file, index=[\"Pclass\"], values=[\"Survived\"]).plot(kind=\"barh\")" + ], "language": "python", "metadata": {}, - "outputs": [], - "prompt_number": 29 + "outputs": [ + { + "metadata": {}, + "output_type": "pyout", + "prompt_number": 22, + "text": [ + "" + ] + }, + { + "metadata": {}, + "output_type": "display_data", + "png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAD9CAYAAAC7iRw+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nmf8DFiCOaUppPFUAAAAASUVORK5CYII=\n", + "text": [ + "" + ] + } + ], + "prompt_number": 22 }, { "cell_type": "code", "collapsed": false, - "input": [], + "input": [ + "pd.pivot_table(clean_train_file, index=[\"Embark_binary\"], values=[\"Survived\"]).plot(kind=\"barh\")" + ], "language": "python", "metadata": {}, - "outputs": [], - "prompt_number": 29 + "outputs": [ + { + "metadata": {}, + "output_type": "pyout", + "prompt_number": 26, + "text": [ + "" + ] + }, + { + "metadata": {}, + "output_type": "display_data", + "png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAD9CAYAAAC7iRw+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAFCdJREFUeJzt3XuUnHV9x/H3JssqZANJcKNcQpbG8IPjrWpUCIJETY9V\nyBELh1PQYBHCRS5eQEXE2nIQaCE2UdGCTbm06BG8FGnlVK1KSykV5Ch64BtuCxjFrOw2sImCCds/\nZpddIpl9dneey+7zfp2Tk5nZmef58GPymWd/88xv2gYHB5Ek1ceMsgNIkopl8UtSzVj8klQzFr8k\n1YzFL0k1Y/FLUs20lx1g2Nat2wb7+7eUHaMS5s7dBceiwbEY4ViMcCxGdHXNbhvvYypzxP/Sly4q\nO0JltLfPLDtCZTgWIxyLEY7F5FSm+CVJxbD4JalmLH5JqhmLX5JqxuKXpJqpTPH39PSUHUGSaqEy\n5/FLEsDTTz/No48+3PQ+/f2d9PUNZN7mggUL6ejomGy0acPil1Qpjz76MGf97Y3sstv8lmxvy6aN\nrDlnBYsWLW56v2uvvYo77/xftm7dyowZM3j/+z9ASvtPaJ9r117GMcccx4tf/JIJPX716ktYtuyt\nvPrVr53Q48di8UuqnF12m0/n3L0K299DDz3If//3LXzhC+sAuO++9Vx44ae46qrrJrS9M8/88KTy\ntLWN+8O441KZOX5JKktnZye//vWvuemmf6G3dyOLF+/HlVdezemnr+KRRxrTTt/85g2sW3cFjz32\nK1auPIYzzjiZ6667hne/++hnt7N69SXccssPOOOMk3nkkR5OPHEljz32KwC+//3vsmbNZWzePMAn\nPvERzjzzFM488xQefPD+Z7d/wgnH8aEPncF9963P9b/X4pdUe11d87n44su4++6fcMopJ3DccUdx\n6623bHfkPXK5r6+Pz3zm8xx77EoWLXopP/nJXTz99NPcddedHHzwIc/e7/DDV3Dzzf8KwLe/fRMr\nVhzJ1VevY8mS17N27Rc555yPc+mlF9Pf389Xv/plrrjiai69dA1tbW25HvVXZqpn77335oYbbiw7\nRiWM942r6cQ34VSGDRt+waxZnZx77icBuPfeezj77DPYffeuZ+8z+vvJ99hjT9rbG/V5xBFH8u1v\n38Tjjz/OG9/4JmbOHF5HqI3ly9/GaaedxOGHv5PNmzez775/xIMP3s9dd93B9773HQCefPIJNmx4\nlIUL9312m694xavI8/vQK1P8vf0DnHvF/5QdQyXK+iac1Gr3338fN974DS65ZDXt7e0sWLCAzs5d\nmTNnDr/5TS/77LOQ9evvpaur8YbzjBkjkyVLlryeyy9fS29vLx/+8Eefs91ZszpJaX/Wrr2Md7xj\nBQALF+7L/vsfwPLlb6O3dyPf+c7N7L33Pjz00IM89dTv6Oh4Affc83MOPHBpbv+9lSn+thkzC30z\nR1J1bdm0sdBtvelNy3j44Yc48cSV7LzzzgwODnL66Wcxc2Y7q1dfwvz5L6Grq+vZ6Zftp2GWLXsL\nd9zxI/bc8w87bMWKIzn77DM577y/BOD440/goosu4MYbv8HmzZt53/tOZs6cORx//AmceuqJ7Lrr\nrsycmW81t+X568R4vHD27oPLV60rO4ZKNNC/gYtWHficI/6urtn09j5ZYqrqqMtYZDmPf948z+Mf\nNpH1+CtzxC9JAB0dHWNO99XlRTAvntUjSTVTmeI/6OgLyo4gSbVQmeKXJBXD4pekmrH4JalmLH5J\nqpncTudMKc0ErgT2AwaBUyLi53ntT5KUTZ5H/IcDz0TEG4FPABc2u/Nt15+fYxRJ0rDcij8i/gU4\neehqN9Cf174kSdnl+sndiNiWUroKOBI4Ks99SZKyyX3Jhoh4b0rpo8DtKaUDIuK3ee9TU9e8eZ10\ndc1+zm3bX68zx2KEYzFxeb65+x5g74i4CPgt8MzQH2mH+voGnrMGi2uyjHAsRjgWIybyApjnEf8N\nwFUppR8COwFnRcRTOe5PkpRBbsU/NKVzTNb7u1aPJBXDD3BJUs1Y/JJUMxa/JNWMxS9JNWPxS1LN\nVKb4XatHkopRmeKXJBXD4pekmsl9rZ6sBp/ZxkD/hrJjqERbNm0sO4JUC5Up/q65nVy06sCyY1TC\nvHmd9PUNlB2jFAsWLCw7gjTtVab429vbWbRocdkxKsEFqCTlqTJz/D09PWVHkKRaqEzxS5KKYfFL\nUs1Y/JJUMxa/JNWMxS9JNVOZ4u/u7i47giTVQmWKX5JUDItfkmrG4pekmrH4JalmLH5JqpnKFL9r\n9UhSMSpT/JKkYlj8klQzFr8k1YzFL0k1Y/FLUs1Upvhdq0eSilGZ4pckFcPil6SasfglqWYsfkmq\nGYtfkmqmMsXvWj2SVIz2sgMMW79+PX19A2XHqIT+/k7HYsh0GosFCxbS0dFRdgypOsX/nnOvY5fd\n5pcdQ8rFlk0bWXPOChYtWlx2FKk6xb/LbvPpnLtX2TEkadqrzBy/JKkYFr8k1Uxliv+2688vO4Ik\n1UJlil+SVAyLX5JqZsziTym9roggkqRiZDmd829SSl3A1cC1EfFYzpkkSTka84g/IpYB7wBeCPx7\nSummlNJRKaWdck8nSWq5THP8EfEwcA3wZeAVwJnAz1NK79rRY1JKO6WUrk0p3ZJSuj2ldESzfRx0\n9AXjiC1Jmqgsc/wnpZR+CHwXmAkcHBGHAocBX2zy0OOA3qH7vg343OTjSpImK8sc/zLgL4EfRsTg\n8I0R8cuU0mlNHnc9cMPQ5RnA1gmnlCS1TJbiPyAifvB8P4iIG57v9qGfbQZIKc2m8SJw3kQCSpJa\nK0vxP5ZSOhS4PSKeGs/GU0oLgK8Dn4+Ir0wkoDRdzJvXSVfX7EltY7KPn04ci4nLUvxLgB8ApJSG\nbxuMiJnNHpRSejHw78BpEfH9SWSUpoW+vgF6e5+c8OO7umZP6vHTiWMxYiIvgGMWf0R0TSgNfBzY\nDfhkSumTQ7f9aUT87vnufNv157N81boJ7kqSlNWYxT905H4cMAtoo3Fmz74RsbLZ4yLiLOCsVoSU\nJLVOlvP4vw68CngPjfJfAfwiz1CSpPxkKf4XRcTxwLeAb9A4f9/1eyRpispS/H1DfwfwyojYBLwo\nv0iSpDxlOavnP1JK1wNn01ir57XAuE7rlCRVR5ZF2s4DPja0Xs+xwL3ADtfomSjX6pGkYmRZq2cn\n4ICU0krg5TSmft6adzBJUj6yTPVcB+wD3AMMjrr9mlwSSZJylaX4X0FjvZ7BMe8pSaq8LGf13APs\nkXcQSVIxshzxzwIipfQzYHi5hcGIeHMrg2zZtLGVm5Mqxee3qiRL8X/6eW5r+bTPhtu/xA033Njq\nzU5J8+Z10tc3UHaMSphOY7FgwcKyI0hAk+JPKb0mIn5Mo+RHF30bORR/e3s7ixYtbvVmpyRXHhzh\nWEit1+yI/1TgJOCveP6iX5ZLIklSrnZY/BFx0tDfhxWWRpKUuyzLMu8FfAZ4C43vzf0O8MGI6M05\nmyQpB1lO51xH4xu49gX2A+4E/jHHTJKkHGU5q2d+RFw+6vpnUkrHtzpIT0+Pb+JJUgGyHPHflVI6\ncvhKSmk58NP8IkmS8tTsdM4BGmfzzADem1L6Pxpz/C8C/DSKJE1Rzc7q6RzrwSmlwyPiptZGkiTl\nKctUTzMuoi9JU8xki1+SNMVUpvi7u7vLjiBJtVCZ4pckFcPil6SamVDxp5TaWh1EklSMLF+2fup2\n118F3D50dWkeoSRJ+cmyZMNxKaWdgCuAvwbeDXwMICJ+m2M2SVIOskz1/AnwduABYC7wsoi4ptVB\nenp6Wr1JSdLzaLZkw/GMfAHL14A/BgaAI1JK5FH+kqT8NZvqWcZzv3nrZmAOI9+8ZfFL0hTUbK2e\n9wKklC6MiPMKSyRJylWWOf4jUkqe7y9J00SWs3oeB+5NKf0YGD6LZzAiTsgvliQpL1mK/+rnuW3w\neW6blO7ubn70o7tbvVlJ0nbGLP6IuCqltDswC2gDZtL4/l1J0hQ0ZvGnlC4CTgN2ojHtsxfwH8D3\n8o0mScpDlqmePwf2AdbQ+OKVfYBjWx1k69atPPDAfa3e7JTU399JX99A2THGbcGChXR0dJQdQ9IY\nshT/ryJiU0rpbuCPI+JrKaULWx2kt3+Ac6/4n1ZvVgXZsmkja85ZwaJFi8uOImkMWYp/U0rpPcCP\ngTNSSr8E5rc6SNuMmXTO3avVm5UkbSfL+fnvA+ZHxPeBh4AvAp9odZCDjvbreyWpCGMWf0RsANam\nlF4OfAl4bUR8JfdkkqRcZFmP/xDgPhrn8/8zcE9K6XV5B5Mk5SPLHP/fASsi4qcAKaUlwOXA6/MM\nJknKR6Y1eIZLf+jyHTTO6ZckTUHN1uN/DY1P6v48pbSGxvz+NuA4wPMuJWmKajbVs5qRNXn2AdYO\nXW4jh7V6brv+fJavWtfqzUqSttNsPf7DCswhSSpIlrV6DgU+QOP7docNRsSbs+4kpfQG4OKIWDbm\nnSVJucpyVs9VwKeARyayg5TSR4B30/i+XklSybIU/y8m+cXq9wPvAq6dxDYkSS2SpfjXppT+icZS\nzNuGbhvM+mIQEV9PKXVPMJ8kqcWyFP9pQ38fst3tk/kt4A+4Vs/UN29eJ11ds1u+3Ty2OVU5FiMc\ni4nLUvx7RMQBuSfRlNfXN0Bv75Mt3WZX1+yWb3OqcixGOBYjJvICmOWTu/+ZUjoipZTlRaKZlp/7\nL0kavyxlvgI4ESClNHzbYETMzLqTiOgBlo43nCSp9XZ4xJ9SOhUgIl4CvDIiZgz/AT5XVEBJUms1\nm+pZNery9m/kHppDFklSATKtzkljfZ5c3Xb9+XnvQpJE9uKXJE0TFr8k1Uyzs3pellJ6aOjynqMu\nA+yZYyZJUo6aFf9+haWQJBWm2Xr8PQXmkCQVpDJz/K7VI0nFmOwyDC2zZdPGsiNoEvz/J00dlSn+\nay86lr4+v6sFGqtcTsWxWLBgYdkRJGVQmeLfb7/9XG1viCsPSspTZeb4JUnFsPglqWYqU/zd3d1l\nR5CkWqhM8UuSimHxS1LNWPySVDMWvyTVjMUvSTVTmeLv6ekpO4Ik1UJlil+SVAyLX5JqxuKXpJqx\n+CWpZix+SaqZyhS/a/VIUjEqU/ySpGJY/JJUMxa/JNWMxS9JNWPxS1LNVKb4XatHkopRmeKXJBXD\n4pekmrH4JalmLH5Jqpn2sgMMW79+PX19A2XHqIT+/k7HYohjMcKxGOFYjOjqes24H9M2ODiYQ5Tx\ne8GsOYNLj/l02TEkacrYsmkjt3/tU23jfVxljvjbZsykc+5eZceQpGnPOX5JqhmLX5JqxuKXpJqx\n+CWpZipT/AcdfUHZESSpFipT/JKkYlj8klQzFr8k1UxuH+BKKc0ALgdeCTwFnBgRD+S1P0lSNnke\n8b8T6IiIpcDHgMty3JckKaM8i/9g4GaAiLgdWNLszrddf36OUSRJw/Is/l2BJ0Zd3zY0/SNJKlGe\nRfwEMHv0viLimRz3J0nKIM/ivxV4O0BK6UDgpznuS5KUUZ7LMn8DWJ5SunXo+l/kuC9JUka5FX9E\nDAKn5rV9SdLEVObNVtfqkaRiVKb4JUnFsPglqWYsfkmqGYtfkmrG4pekmqlM8btWjyQVozLFL0kq\nhsUvSTWT55IN4zL4zDYG+jeUHUOSpowtmzZO6HGVKf6uuZ1ctOrAsmNUwrx5nfT1DZQdoxIcixGO\nxQjHYnIqU/zt7e0sWrS47BiV0NU1m97eJ8uOUQmOxQjHYoRjMTmVmePv6ekpO4Ik1UJlil+SVAyL\nX5JqxuKXpJqx+CWpZix+SaqZyhR/d3d32REkqRYqU/ySpGJY/JJUMxa/JNWMxS9JNWPxS1LNtA0O\nDpadQZJUII/4JalmLH5JqhmLX5JqxuKXpJqx+CWpZix+SaqZQr9zN6U0A7gceCXwFHBiRDww6udH\nAOcDW4F1EfGlIvMVKcNY/DlwFo2xuBs4LSKm5bm3Y43FqPtdATweEecWHLEwGZ4XrwMuA9qADcDK\niHi6jKx5yzAWRwIfBwZp9MUXSwlaoJTSG4CLI2LZdrePqzuLPuJ/J9AREUuBj9F4AgOQUtoJWA0s\nB94ErEopzS84X5GajcXOwAXAYRHxRmA34PBSUhZjh2MxLKV0MvByGv/Ip7Nmz4s24ArgvRFxCPA9\nYN9SUhZjrOfFcF8cDHw4pbRbwfkKlVL6CHAl8ILtbh93dxZd/AcDNwNExO3AklE/OwC4PyI2RcTv\ngf8CDi04X5GajcXvgIMi4ndD19uB3xYbr1DNxoKU0lLg9cDf0zjSnc6ajcV+wOPAh1JKPwDmREQU\nnrA4TZ8XwO+BOcDONJ4X0/2g4H7gXfzhv4Fxd2fRxb8r8MSo69uGfp0b/tmmUT97ksaR7nS1w7GI\niMGI6AVIKZ0BzIqI75aQsSg7HIuU0h7AJ4HTmf6lD83/jbwIWAp8Fngr8JaU0jKmr2ZjAY3fAO4E\nfgZ8KyJG33faiYiv05jK2d64u7Po4n8CmD16/xHxzNDlTdv9bDbQX1SwEjQbC1JKM1JKlwJvAf6s\n6HAFazYWR9EovH8DPgocm1JaWXC+IjUbi8dpHNlFRGylcTS8/VHwdLLDsUgp7UPjYGAh0A28OKV0\nVOEJq2Hc3Vl08d8KvB0gpXQg8NNRP7sXWJxSmptS6qDxq8ptBecrUrOxgMa0xguAI0dN+UxXOxyL\niPhsRCwZejPrYuC6iLimnJiFaPa8eBDoTCktGrp+CI2j3emq2Vi8ENgGPDX0YrCRxrRPHY27Owtd\npG3ozanhd+kB/gJ4LdAZEVemlA6n8Wv9DOAfIuILhYUrWLOxAO4Y+nPLqIesiYhvFhqyIGM9L0bd\n73ggRcTHi09ZjAz/RoZfANuAWyPig+UkzV+GsfggcCyN98TuB04a+k1o2kopddM4+Fk6dObfhLrT\n1TklqWb8AJck1YzFL0k1Y/FLUs1Y/JJUMxa/JNWMxS9JNWPxS1LNWPySVDP/D99mjDJcoiUXAAAA\nAElFTkSuQmCC\n", + "text": [ + "" + ] + } + ], + "prompt_number": 26 + }, + { + "cell_type": "code", + "collapsed": false, + "input": [ + "pd.pivot_table(clean_train_file, index=[\"FamilySize\"], values=[\"Survived\"]).plot(kind=\"barh\")" + ], + "language": "python", + "metadata": {}, + "outputs": [ + { + "metadata": {}, + "output_type": "pyout", + "prompt_number": 27, + "text": [ + "" + ] + }, + { + "metadata": {}, + "output_type": "display_data", + "png": "iVBORw0KGgoAAAANSUhEUgAAAYMAAAD9CAYAAABeOxsXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRK5CYII=\n", + "text": [ + "" + ] + } + ], + "prompt_number": 27 }, { "cell_type": "code", @@ -197,14 +318,14 @@ "language": "python", "metadata": {}, "outputs": [], - "prompt_number": 29 + "prompt_number": 32 }, { "cell_type": "code", "collapsed": false, "input": [ "# Create the random forest object which will include all the parameters for the fit\n", - "forest = RandomForestClassifier(n_estimators = 100)\n", + "forest = RandomForestClassifier(n_estimators = 10)\n", "\n", "# Fit the training data to the Survived labels and create the decision trees\n", "forest = forest.fit(clean_train_file_array[0::,1::],clean_train_file_array[0::,0])\n", @@ -219,31 +340,45 @@ { "metadata": {}, "output_type": "pyout", - "prompt_number": 32, + "prompt_number": 7, "text": [ - "array([0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1,\n", - " 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0,\n", - " 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0,\n", - " 1, 1, 0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0,\n", - " 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1,\n", - " 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0,\n", - " 1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1,\n", - " 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0,\n", - " 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0,\n", - " 0, 1, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0,\n", - " 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0,\n", - " 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1,\n", - " 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0,\n", - " 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0,\n", - " 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0,\n", - " 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1,\n", - " 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1,\n", - " 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0,\n", - " 1, 0, 0, 0])" + "array([ 0., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 1.,\n", + " 0., 1., 1., 0., 0., 0., 0., 0., 1., 1., 0., 1., 0.,\n", + " 1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 1., 1., 0.,\n", + " 0., 0., 1., 0., 1., 1., 0., 0., 0., 1., 0., 1., 0.,\n", + " 1., 1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0., 1.,\n", + " 1., 0., 0., 0., 1., 0., 0., 0., 1., 1., 1., 0., 1.,\n", + " 0., 0., 1., 0., 0., 0., 0., 0., 0., 1., 0., 1., 0.,\n", + " 0., 0., 0., 1., 0., 1., 0., 0., 0., 1., 0., 0., 0.,\n", + " 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 1., 0., 0.,\n", + " 1., 0., 1., 1., 0., 1., 0., 0., 1., 0., 0., 0., 0.,\n", + " 1., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0., 1., 0.,\n", + " 0., 1., 0., 1., 0., 1., 0., 1., 0., 0., 0., 0., 0.,\n", + " 1., 0., 1., 1., 0., 1., 1., 0., 0., 0., 0., 0., 1.,\n", + " 1., 0., 1., 0., 0., 0., 1., 1., 0., 1., 1., 0., 1.,\n", + " 1., 0., 1., 0., 1., 0., 0., 0., 0., 1., 1., 0., 1.,\n", + " 0., 1., 1., 0., 1., 0., 1., 1., 1., 0., 1., 0., 0.,\n", + " 1., 0., 1., 0., 0., 0., 0., 1., 0., 0., 1., 0., 1.,\n", + " 0., 1., 0., 0., 1., 0., 0., 0., 0., 0., 1., 0., 0.,\n", + " 1., 0., 0., 0., 1., 1., 1., 1., 0., 0., 0., 1., 1.,\n", + " 0., 1., 1., 1., 0., 0., 0., 1., 0., 0., 0., 1., 0.,\n", + " 0., 0., 1., 1., 0., 0., 1., 0., 1., 0., 0., 0., 1.,\n", + " 1., 0., 1., 0., 0., 0., 0., 0., 1., 0., 0., 1., 0.,\n", + " 0., 1., 0., 0., 1., 0., 0., 0., 0., 0., 1., 0., 0.,\n", + " 0., 1., 0., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.,\n", + " 0., 0., 1., 1., 0., 0., 1., 0., 0., 0., 0., 0., 1.,\n", + " 0., 1., 0., 0., 0., 1., 0., 0., 0., 1., 0., 0., 0.,\n", + " 0., 0., 0., 1., 0., 1., 0., 0., 0., 0., 0., 1., 1.,\n", + " 0., 0., 0., 1., 1., 1., 0., 0., 0., 0., 1., 1., 1.,\n", + " 1., 0., 0., 1., 1., 0., 0., 1., 0., 0., 1., 1., 0.,\n", + " 0., 0., 0., 0., 0., 1., 1., 0., 1., 0., 0., 0., 0.,\n", + " 0., 1., 1., 0., 0., 1., 0., 1., 0., 0., 1., 0., 1.,\n", + " 0., 1., 0., 0., 0., 0., 1., 0., 1., 0., 0., 1., 0.,\n", + " 0., 0.])" ] } ], - "prompt_number": 32 + "prompt_number": 7 }, { "cell_type": "code", @@ -255,15 +390,7 @@ "language": "python", "metadata": {}, "outputs": [], - "prompt_number": 34 - }, - { - "cell_type": "code", - "collapsed": false, - "input": [], - "language": "python", - "metadata": {}, - "outputs": [] + "prompt_number": 8 } ], "metadata": {}