{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "cfdaacbc-23a3-423d-8d4d-120939ac7383" }, "outputs": [], "source": [ "# Imports\n", "\n", "# pandas\n", "import pandas as pd\n", "from pandas import Series,DataFrame\n", "\n", "# numpy, matplotlib, seaborn\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "sns.set_style('whitegrid')\n", "%matplotlib inline\n", "\n", "# machine learning\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.svm import SVC, LinearSVC\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.neighbors import KNeighborsClassifier\n", "from sklearn.naive_bayes import GaussianNB" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "3ab4c525-a5cb-4183-9468-c1dd005c4c78" }, "outputs": [], "source": [ "# get titanic & test csv files as a DataFrame\n", "titanic_df = pd.read_csv(\"../input/train.csv\")\n", "test_df = pd.read_csv(\"../input/test.csv\")\n", "\n", "# preview the data\n", "titanic_df.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "86179af8-3cb4-4661-84ea-addd2c7679d4" }, "outputs": [], "source": [ "titanic_df.info()\n", "print(\"----------------------------\")\n", "test_df.info()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "7faffa7c-9776-43fb-9c01-786630f237ab" }, "outputs": [], "source": [ "# drop unnecessary columns, these columns won't be useful in analysis and prediction\n", "titanic_df = titanic_df.drop(['PassengerId','Name','Ticket'], axis=1)\n", "test_df = test_df.drop(['Name','Ticket'], axis=1)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b1441ec8-7d77-4a69-990b-26e0b1e89b68" }, "outputs": [], "source": [ "# Embarked\n", "\n", "# only in titanic_df, fill the two missing values with the most occurred value, which is \"S\".\n", "titanic_df[\"Embarked\"] = titanic_df[\"Embarked\"].fillna(\"S\")\n", "\n", "# plot\n", "sns.factorplot('Embarked','Survived', data=titanic_df,size=4,aspect=3)\n", "\n", "fig, (axis1,axis2,axis3) = plt.subplots(1,3,figsize=(15,5))\n", "\n", "# sns.factorplot('Embarked',data=titanic_df,kind='count',order=['S','C','Q'],ax=axis1)\n", "# sns.factorplot('Survived',hue=\"Embarked\",data=titanic_df,kind='count',order=[1,0],ax=axis2)\n", "sns.countplot(x='Embarked', data=titanic_df, ax=axis1)\n", "sns.countplot(x='Survived', hue=\"Embarked\", data=titanic_df, order=[1,0], ax=axis2)\n", "\n", "# group by embarked, and get the mean for survived passengers for each value in Embarked\n", "embark_perc = titanic_df[[\"Embarked\", \"Survived\"]].groupby(['Embarked'],as_index=False).mean()\n", "sns.barplot(x='Embarked', y='Survived', data=embark_perc,order=['S','C','Q'],ax=axis3)\n", "\n", "# Either to consider Embarked column in predictions,\n", "# and remove \"S\" dummy variable, \n", "# and leave \"C\" & \"Q\", since they seem to have a good rate for Survival.\n", "\n", "# OR, don't create dummy variables for Embarked column, just drop it, \n", "# because logically, Embarked doesn't seem to be useful in prediction.\n", "\n", "embark_dummies_titanic = pd.get_dummies(titanic_df['Embarked'])\n", "embark_dummies_titanic.drop(['S'], axis=1, inplace=True)\n", "\n", "embark_dummies_test = pd.get_dummies(test_df['Embarked'])\n", "embark_dummies_test.drop(['S'], axis=1, inplace=True)\n", "\n", "titanic_df = titanic_df.join(embark_dummies_titanic)\n", "test_df = test_df.join(embark_dummies_test)\n", "\n", "titanic_df.drop(['Embarked'], axis=1,inplace=True)\n", "test_df.drop(['Embarked'], axis=1,inplace=True)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b1a9e2e1-1718-4e6a-b037-a2c1eca1c003" }, "outputs": [], "source": [ "# Fare\n", "\n", "# only for test_df, since there is a missing \"Fare\" values\n", "#test_df[\"Fare\"].fillna(test_df[\"Fare\"].median(), inplace=True)\n", "\n", "# convert from float to int\n", "#titanic_df['Fare'] = titanic_df['Fare'].astype(int)\n", "#test_df['Fare'] = test_df['Fare'].astype(int)\n", "\n", "# get fare for survived & didn't survive passengers \n", "#fare_not_survived = titanic_df[\"Fare\"][titanic_df[\"Survived\"] == 0]\n", "#fare_survived = titanic_df[\"Fare\"][titanic_df[\"Survived\"] == 1]\n", "\n", "# get average and std for fare of survived/not survived passengers\n", "#avgerage_fare = DataFrame([fare_not_survived.mean(), fare_survived.mean()])\n", "#std_fare = DataFrame([fare_not_survived.std(), fare_survived.std()])\n", "\n", "# plot\n", "#titanic_df['Fare'].plot(kind='hist', figsize=(15,3),bins=100, xlim=(0,50))\n", "\n", "#avgerage_fare.index.names = std_fare.index.names = [\"Survived\"]\n", "#avgerage_fare.plot(yerr=std_fare,kind='bar',legend=False)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "22ab0b38-6285-4d65-bb3e-dc923caed94b" }, "outputs": [], "source": [ "# Age \n", "\n", "fig, (axis1,axis2) = plt.subplots(1,2,figsize=(15,4))\n", "axis1.set_title('Original Age values - Titanic')\n", "axis2.set_title('New Age values - Titanic')\n", "\n", "# axis3.set_title('Original Age values - Test')\n", "# axis4.set_title('New Age values - Test')\n", "\n", "# get average, std, and number of NaN values in titanic_df\n", "average_age_titanic = titanic_df[\"Age\"].mean()\n", "std_age_titanic = titanic_df[\"Age\"].std()\n", "count_nan_age_titanic = titanic_df[\"Age\"].isnull().sum()\n", "\n", "# get average, std, and number of NaN values in test_df\n", "average_age_test = test_df[\"Age\"].mean()\n", "std_age_test = test_df[\"Age\"].std()\n", "count_nan_age_test = test_df[\"Age\"].isnull().sum()\n", "\n", "# generate random numbers between (mean - std) & (mean + std)\n", "rand_1 = np.random.randint(average_age_titanic - std_age_titanic, average_age_titanic + std_age_titanic, size = count_nan_age_titanic)\n", "rand_2 = np.random.randint(average_age_test - std_age_test, average_age_test + std_age_test, size = count_nan_age_test)\n", "\n", "# plot original Age values\n", "# NOTE: drop all null values, and convert to int\n", "titanic_df['Age'].dropna().astype(int).hist(bins=70, ax=axis1)\n", "# test_df['Age'].dropna().astype(int).hist(bins=70, ax=axis1)\n", "\n", "# fill NaN values in Age column with random values generated\n", "titanic_df[\"Age\"][np.isnan(titanic_df[\"Age\"])] = rand_1\n", "test_df[\"Age\"][np.isnan(test_df[\"Age\"])] = rand_2\n", "\n", "# convert from float to int\n", "titanic_df['Age'] = titanic_df['Age'].astype(int)\n", "test_df['Age'] = test_df['Age'].astype(int)\n", " \n", "# plot new Age Values\n", "titanic_df['Age'].hist(bins=70, ax=axis2)\n", "# test_df['Age'].hist(bins=70, ax=axis4)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "952009ab-555c-46f8-b419-182f2de39ca0" }, "outputs": [], "source": [ "# .... continue with plot Age column\n", "\n", "# peaks for survived/not survived passengers by their age\n", "facet = sns.FacetGrid(titanic_df, hue=\"Survived\",aspect=4)\n", "facet.map(sns.kdeplot,'Age',shade= True)\n", "facet.set(xlim=(0, titanic_df['Age'].max()))\n", "facet.add_legend()\n", "\n", "# average survived passengers by age\n", "fig, axis1 = plt.subplots(1,1,figsize=(18,4))\n", "average_age = titanic_df[[\"Age\", \"Survived\"]].groupby(['Age'],as_index=False).mean()\n", "sns.barplot(x='Age', y='Survived', data=average_age)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "ef0f0c9d-6b45-4cb0-9026-86b764084398" }, "outputs": [], "source": [ "# Cabin\n", "# It has a lot of NaN values, so it won't cause a remarkable impact on prediction\n", "titanic_df.drop(\"Cabin\",axis=1,inplace=True)\n", "test_df.drop(\"Cabin\",axis=1,inplace=True)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "a89c93bb-e45b-44ce-8dee-430f584f4ed4" }, "outputs": [], "source": [ "# Family\n", "\n", "# Instead of having two columns Parch & SibSp, \n", "# we can have only one column represent if the passenger had any family member aboard or not,\n", "# Meaning, if having any family member(whether parent, brother, ...etc) will increase chances of Survival or not.\n", "titanic_df['Family'] = titanic_df[\"Parch\"] + titanic_df[\"SibSp\"]\n", "titanic_df['Family'].loc[titanic_df['Family'] > 0] = 1\n", "titanic_df['Family'].loc[titanic_df['Family'] == 0] = 0\n", "\n", "test_df['Family'] = test_df[\"Parch\"] + test_df[\"SibSp\"]\n", "test_df['Family'].loc[test_df['Family'] > 0] = 1\n", "test_df['Family'].loc[test_df['Family'] == 0] = 0\n", "\n", "# drop Parch & SibSp\n", "titanic_df = titanic_df.drop(['Family'], axis=1)\n", "test_df = test_df.drop(['Family'], axis=1)\n", "\n", "# plot\n", "fig, (axis1,axis2) = plt.subplots(1,2,sharex=True,figsize=(10,5))\n", "\n", "# sns.factorplot('Family',data=titanic_df,kind='count',ax=axis1)\n", "sns.countplot(x='Family', data=titanic_df, order=[1,0], ax=axis1)\n", "\n", "# average of survived for those who had/didn't have any family member\n", "family_perc = titanic_df[[\"Family\", \"Survived\"]].groupby(['Family'],as_index=False).mean()\n", "sns.barplot(x='Family', y='Survived', data=family_perc, order=[1,0], ax=axis2)\n", "\n", "axis1.set_xticklabels([\"With Family\",\"Alone\"], rotation=0)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "23c2f140-1dc0-48cd-a6e1-9786510b2606" }, "outputs": [], "source": [ "# Sex\n", "\n", "# As we see, children(age < ~16) on aboard seem to have a high chances for Survival.\n", "# So, we can classify passengers as males, females, and child\n", "def get_person(passenger):\n", " age,sex = passenger\n", " return 'child' if age < 16 else sex\n", " \n", "titanic_df['Person'] = titanic_df[['Age','Sex']].apply(get_person,axis=1)\n", "test_df['Person'] = test_df[['Age','Sex']].apply(get_person,axis=1)\n", "\n", "# No need to use Sex column since we created Person column\n", "titanic_df.drop(['Sex'],axis=1,inplace=True)\n", "test_df.drop(['Sex'],axis=1,inplace=True)\n", "\n", "# create dummy variables for Person column, & drop Male as it has the lowest average of survived passengers\n", "person_dummies_titanic = pd.get_dummies(titanic_df['Person'])\n", "person_dummies_titanic.columns = ['Child','Female','Male']\n", "person_dummies_titanic.drop(['Male'], axis=1, inplace=True)\n", "\n", "person_dummies_test = pd.get_dummies(test_df['Person'])\n", "person_dummies_test.columns = ['Child','Female','Male']\n", "person_dummies_test.drop(['Male'], axis=1, inplace=True)\n", "\n", "titanic_df = titanic_df.join(person_dummies_titanic)\n", "test_df = test_df.join(person_dummies_test)\n", "\n", "fig, (axis1,axis2) = plt.subplots(1,2,figsize=(10,5))\n", "\n", "# sns.factorplot('Person',data=titanic_df,kind='count',ax=axis1)\n", "sns.countplot(x='Person', data=titanic_df, ax=axis1)\n", "\n", "# average of survived for each Person(male, female, or child)\n", "person_perc = titanic_df[[\"Person\", \"Survived\"]].groupby(['Person'],as_index=False).mean()\n", "sns.barplot(x='Person', y='Survived', data=person_perc, ax=axis2, order=['male','female','child'])\n", "\n", "titanic_df.drop(['Person'],axis=1,inplace=True)\n", "test_df.drop(['Person'],axis=1,inplace=True)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "0f126c1f-74b8-4063-8ac0-f44e6b8fc0bd" }, "outputs": [], "source": [ "# Pclass\n", "\n", "# sns.factorplot('Pclass',data=titanic_df,kind='count',order=[1,2,3])\n", "sns.factorplot('Pclass','Survived',order=[1,2,3], data=titanic_df,size=5)\n", "\n", "# create dummy variables for Pclass column, & drop 3rd class as it has the lowest average of survived passengers\n", "pclass_dummies_titanic = pd.get_dummies(titanic_df['Pclass'])\n", "pclass_dummies_titanic.columns = ['Class_1','Class_2','Class_3']\n", "pclass_dummies_titanic.drop(['Class_3'], axis=1, inplace=True)\n", "\n", "pclass_dummies_test = pd.get_dummies(test_df['Pclass'])\n", "pclass_dummies_test.columns = ['Class_1','Class_2','Class_3']\n", "pclass_dummies_test.drop(['Class_3'], axis=1, inplace=True)\n", "\n", "titanic_df.drop(['Pclass'],axis=1,inplace=True)\n", "test_df.drop(['Pclass'],axis=1,inplace=True)\n", "\n", "titanic_df = titanic_df.join(pclass_dummies_titanic)\n", "test_df = test_df.join(pclass_dummies_test)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "5214295a-19cf-44b5-abe2-8989a0ed9670" }, "outputs": [], "source": [ "# define training and testing sets\n", "\n", "X_train = titanic_df.drop(\"Survived\",axis=1)\n", "Y_train = titanic_df[\"Survived\"]\n", "X_test = test_df.drop(\"PassengerId\",axis=1).copy()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "2b5424c0-196f-4d23-b1b8-1b10ac27be10" }, "outputs": [], "source": [ "# Logistic Regression\n", "\n", "logreg = LogisticRegression()\n", "\n", "logreg.fit(X_train, Y_train)\n", "\n", "Y_pred = logreg.predict(X_test)\n", "\n", "logreg.score(X_train, Y_train)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "74988880-7f9e-45f4-b6b7-f7fd43a63f95" }, "outputs": [], "source": [ "# Support Vector Machines\n", "\n", "svc = SVC()\n", "\n", "svc.fit(X_train, Y_train)\n", "\n", "Y_pred = svc.predict(X_test)\n", "\n", "svc.score(X_train, Y_train)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "0f8b05ff-c21e-4e0e-975d-21af19c6b6b3" }, "outputs": [], "source": [ "# Random Forests\n", "\n", "#random_forest = RandomForestClassifier(n_estimators=100)\n", "\n", "#random_forest.fit(X_train, Y_train)\n", "\n", "#Y_pred = random_forest.predict(X_test)\n", "\n", "#random_forest.score(X_train, Y_train)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "499918bf-8ba4-4a79-b8d8-4c26ece9a3b8" }, "outputs": [], "source": [ "# knn = KNeighborsClassifier(n_neighbors = 3)\n", "\n", "# knn.fit(X_train, Y_train)\n", "\n", "# Y_pred = knn.predict(X_test)\n", "\n", "# knn.score(X_train, Y_train)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "15801b79-73c3-4fa4-b8be-21d32645a403" }, "outputs": [], "source": [ "# Gaussian Naive Bayes\n", "\n", "# gaussian = GaussianNB()\n", "\n", "# gaussian.fit(X_train, Y_train)\n", "\n", "# Y_pred = gaussian.predict(X_test)\n", "\n", "# gaussian.score(X_train, Y_train)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "26dd2732-b34f-4177-8786-8794537494e1" }, "outputs": [], "source": [ "# get Correlation Coefficient for each feature using Logistic Regression\n", "coeff_df = DataFrame(titanic_df.columns.delete(0))\n", "coeff_df.columns = ['Features']\n", "coeff_df[\"Coefficient Estimate\"] = pd.Series(logreg.coef_[0])\n", "\n", "# preview\n", "coeff_df" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "bf28672b-9264-4d5a-95f8-47effc0e2e4c" }, "outputs": [], "source": [ "submission = pd.DataFrame({\n", " \"PassengerId\": test_df[\"PassengerId\"],\n", " \"Survived\": Y_pred\n", " })\n", "submission.to_csv('titanic.csv', index=False)" ] } ], "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 }