{ "cells": [ { "cell_type": "markdown", "metadata": { "_cell_guid": "3e07f3a3-b0dd-8e7c-da33-9e43a68e7a90" }, "source": [ "*This is my first solution, please send me if there is an error*" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "d5960f3e-f779-3bee-8c55-00f230dab592" }, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "%matplotlib inline" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "4ad663cb-0d63-5ce7-be40-224c7d47223e" }, "outputs": [], "source": [ "train_data = pd.read_csv('../input/train.csv')\n", "test_data = pd.read_csv('../input/test.csv')\n", "# gender_submission = pd.read_csv('../input/gender_submission.csv')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "510a4cd8-e77b-6d51-3622-8d9d94cf9091" }, "outputs": [], "source": [ "#drop unnecessary columns\n", "train_data.drop(['PassengerId', 'Ticket', 'Cabin', 'Name'], inplace=True, axis=1)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "53d2fe93-6d0c-ee0d-455a-38919c1c013b" }, "outputs": [], "source": [ "train_data.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "836237f1-9b14-628a-9a92-ca0120a10001" }, "outputs": [], "source": [ "train_data.describe()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "9aa69de5-421d-c0d0-11fa-e4c1dafe4f48" }, "outputs": [], "source": [ "plt.hist(train_data['Pclass'], color='lightblue')\n", "plt.tick_params(top='off', bottom='on', left='off', right='off', labelleft='on', labelbottom='on')\n", "plt.xlim([0, 4])\n", "ax = plt.gca()\n", "ax.spines['right'].set_visible(False)\n", "ax.spines['top'].set_visible(False)\n", "ax.spines['left'].set_visible(True)\n", "ax.spines['bottom'].set_visible(True)\n", "ax.set_xticks([1, 2, 3])\n", "plt.xlabel('Pclass')\n", "plt.ylabel('Count')\n", "plt.grid(True)\n", "plt.tight_layout()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "c4bf44ef-eaed-dd08-b548-652b86ab1988" }, "outputs": [], "source": [ "plt.hist(train_data['Survived'], color='lightblue')\n", "plt.tick_params(top='off', bottom='off', left='off', right='off', labelleft='on', labelbottom='on')\n", "ax = plt.gca()\n", "ax.spines['right'].set_visible(False)\n", "ax.spines['top'].set_visible(False)\n", "ax.spines['left'].set_visible(True)\n", "ax.spines['bottom'].set_visible(True)\n", "plt.grid(True)\n", "plt.xlim([-1, 2])\n", "ax.set_xticks([0, 1])\n", "ax.set_xticklabels(['Not survived', 'Survived'], rotation='vertical')\n", "plt.ylabel('Count')\n", "plt.tight_layout()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "8780012a-6902-d1bd-416d-fadbb4c64046" }, "outputs": [], "source": [ "train_data['Pclass'].unique()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "e749c77b-20fa-e711-72ae-ab1993638bf7" }, "outputs": [], "source": [ "y_surv = [len(train_data[((train_data['Survived'] == 1) & (train_data['Pclass'] == 1))]['Pclass'].tolist()), len(train_data[((train_data['Survived'] == 1) & (train_data['Pclass'] == 2))]['Pclass'].tolist()), len(train_data[((train_data['Survived'] == 1) & (train_data['Pclass'] == 3))]['Pclass'].tolist())]\n", "y_not_surv = [len(train_data[((train_data['Survived'] == 0) & (train_data['Pclass'] == 1))]['Pclass'].tolist()), len(train_data[((train_data['Survived'] == 0) & (train_data['Pclass'] == 2))]['Pclass'].tolist()), len(train_data[((train_data['Survived'] == 0) & (train_data['Pclass'] == 3))]['Pclass'].tolist())]\n", "y_surv , y_not_surv" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b31d0ceb-2455-6def-6c4a-5b490c0d3f6f" }, "outputs": [], "source": [ "x = np.array([1, 2, 3])\n", "width=0.3\n", "fig, ax = plt.subplots()\n", "bar1 = ax.bar(x - width, y_surv, width, color='lightblue', label='Survived')\n", "bar2 = ax.bar(x, y_not_surv, width, color='pink', label='Not survived')\n", "plt.tick_params(top='off', bottom='off', left='off', right='off', labelleft='on', labelbottom='on')\n", "ax.spines['right'].set_visible(False)\n", "ax.spines['top'].set_visible(False)\n", "ax.spines['left'].set_visible(True)\n", "ax.spines['bottom'].set_visible(True)\n", "ax.set_xticks([1, 2, 3])\n", "plt.xlim([0, 4])\n", "plt.ylabel('Count')\n", "plt.grid(True)\n", "plt.legend(loc='upper left')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "6692bd54-0441-5b5e-51e7-9df5b7b831ce" }, "outputs": [], "source": [ "sum(train_data['Age'].isnull()) / len(train_data)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "e00bfbd9-d832-8f60-51de-f4d7ab826212" }, "outputs": [], "source": [ "sum(train_data[train_data['Survived']==1]['Age'].isnull()) / len(train_data)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "d0782494-61d3-70a9-e95d-63484ab83d14" }, "outputs": [], "source": [ "sum(train_data[train_data['Survived']==0]['Age'].isnull()) / len(train_data)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "397bc6ba-b1cf-d788-9cae-fd004a6a1585" }, "outputs": [], "source": [ "mean_age = np.mean(train_data['Age'])\n", "train_data['Age'] = train_data['Age'].fillna(mean_age)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "39629c55-2f51-c1d0-5030-a84b93c4e31d" }, "outputs": [], "source": [ "train_data['Age_group'] = pd.cut(train_data['Age'], 10)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "5bb49691-c360-3478-d33d-b2a2efdef83b" }, "outputs": [], "source": [ "counts = train_data.groupby(['Age_group', 'Survived']).Age_group.count().unstack()\n", "# plt.bar(counts['', stacked=True, color=['lightblue', 'pink'])\n", "counts.plot(kind='bar', stacked=True, color=['lightblue', 'pink'])\n", "plt.tick_params(top='off', bottom='off', left='off', right='off', labelleft='on', labelbottom='on')\n", "ax = plt.gca()\n", "ax.spines['right'].set_visible(False)\n", "ax.spines['top'].set_visible(False)\n", "ax.spines['left'].set_visible(True)\n", "ax.spines['bottom'].set_visible(True)\n", "plt.grid(True)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "aa6caaf0-10cd-4054-0403-6cc42c3c2bc9" }, "outputs": [], "source": [ "sum(train_data['Embarked'].isnull())" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "de20f366-1ce3-fff6-a0b5-93c84366d8d9" }, "outputs": [], "source": [ "train_data['Embarked'].value_counts()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "bdf5ad21-9017-fac1-2e0d-806861e0aaa4" }, "outputs": [], "source": [ "train_data['Embarked'] = train_data['Embarked'].fillna('S')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "97e81813-8b58-93c7-704f-0f5211e88b05" }, "outputs": [], "source": [ "y_surv_2 = [len(train_data[((train_data['Survived'] == 1) & (train_data['Embarked'] == 'S'))]['Embarked'].tolist()), len(train_data[((train_data['Survived'] == 1) & (train_data['Embarked'] == 'C'))]['Embarked'].tolist()), len(train_data[((train_data['Survived'] == 1) & (train_data['Embarked'] == 'Q'))]['Embarked'].tolist())]\n", "y_not_surv_2 = [len(train_data[((train_data['Survived'] == 0) & (train_data['Embarked'] == 'S'))]['Embarked'].tolist()), len(train_data[((train_data['Survived'] == 0) & (train_data['Embarked'] == 'C'))]['Embarked'].tolist()), len(train_data[((train_data['Survived'] == 0) & (train_data['Embarked'] == 'Q'))]['Embarked'].tolist())]\n", "y_surv_2 , y_not_surv_2" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "15b13644-7ed0-3a56-153e-1fb14dac4bbd" }, "outputs": [], "source": [ "x = np.array([1, 2, 3])\n", "width=0.3\n", "fig, ax = plt.subplots()\n", "bar1 = ax.bar(x - width, y_surv_2, width, color='lightblue', label='Survived')\n", "bar2 = ax.bar(x, y_not_surv_2, width, color='pink', label='Not survived')\n", "plt.tick_params(top='off', bottom='off', left='off', right='off', labelleft='on', labelbottom='on')\n", "ax.spines['right'].set_visible(False)\n", "ax.spines['top'].set_visible(False)\n", "ax.spines['left'].set_visible(True)\n", "ax.spines['bottom'].set_visible(True)\n", "ax.set_xticks([1, 2, 3])\n", "ax.set_xticklabels(['S', 'C', 'Q'])\n", "plt.xlim([0, 4])\n", "plt.ylabel('Count')\n", "plt.grid(True)\n", "plt.legend(loc='upper right')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "d6aa4672-7312-6f72-80e5-38a755085aa5" }, "outputs": [], "source": [ "# This makes the model worse\n", "# from sklearn.preprocessing import StandardScaler\n", "# sc = StandardScaler()\n", "# train_data[['Fare', 'Age']] = sc.fit_transform(train_data[['Fare', 'Age']])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "babdd76d-e7ea-c5a7-05a2-f2e3062f23dc" }, "outputs": [], "source": [ "from sklearn.preprocessing import OneHotEncoder, LabelEncoder" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "6f169dcd-4cd0-0c87-6513-6d8f04b9a42f" }, "outputs": [], "source": [ "labelEncoder_sex = LabelEncoder()\n", "train_data['Sex'] = labelEncoder_sex.fit_transform(train_data['Sex'])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "7a49b4d0-2a0c-e288-91a2-cc7617d0fead" }, "outputs": [], "source": [ "labelEncoder_embarked = LabelEncoder()\n", "train_data['Embarked'] = labelEncoder_embarked.fit_transform(train_data['Embarked'])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "5cbbe72e-e347-3241-40ef-c9f43cd7a2ba" }, "outputs": [], "source": [ "train_data.drop(['Age_group'], inplace=True, axis=1)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "3b31b172-92cb-9d3e-6d86-846dc1b93a1e" }, "outputs": [], "source": [ "train_data.head(10)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "f561894b-13b5-e72f-c6c9-d9af3377ba0c" }, "outputs": [], "source": [ "X = train_data.iloc[:, 1:8].values\n", "y = train_data['Survived'].values" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "d380439f-4ebb-3263-b56d-7d69f159a8cb" }, "outputs": [], "source": [ "oneHotEncoder = OneHotEncoder(categorical_features=[0, 6])\n", "X = oneHotEncoder.fit_transform(X).toarray()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "6b0090e8-a0ea-9d2e-52a0-07eda176863b" }, "outputs": [], "source": [ "# avoiding the dummy variable trap\n", "X = X[:, [1, 2, 3, 4, 6, 7, 8, 9, 10]]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "004832a2-e46f-0913-a033-f5074e6ab658" }, "outputs": [], "source": [ "# Splitting the dataset into the Training set and Test set\n", "from sklearn.model_selection import train_test_split\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "5275b4bf-2b50-d1dc-d98b-66f26bd2e28f" }, "outputs": [], "source": [ "from sklearn.linear_model import LogisticRegression\n", "classifier = LogisticRegression(random_state=0)\n", "classifier.fit(X_train, y_train)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "6581799a-406d-6a6f-453a-93a9fdfabf0d" }, "outputs": [], "source": [ "#prepare the test data\n", "# test_data_cp = test_data.copy()\n", "# test_data_cp.drop(['PassengerId', 'Ticket', 'Cabin', 'Name'], inplace=True, axis=1)\n", "# test_data_cp['Age'] = test_data_cp['Age'].fillna(mean_age)\n", "# test_data_cp['Embarked'] = test_data_cp['Embarked'].fillna('S')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "ef2a38f5-4db1-103f-7eeb-d415ba79d41d" }, "outputs": [], "source": [ "# test_data_cp.describe()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "4742a1c4-ba63-e929-e126-dc6aee8cd555" }, "outputs": [], "source": [ "# mean_fare = np.mean(train_data['Fare'])\n", "# test_data_cp['Fare'] = test_data_cp['Fare'].fillna(mean_fare)\n", "# train_data[['Fare', 'Age']] = sc.fit_transform(train_data[['Fare', 'Age']])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "5f5e8a74-fba0-57f4-0521-911720219ca0" }, "outputs": [], "source": [ "# test_data_cp['Sex'] = labelEncoder_sex.transform(test_data_cp['Sex'])\n", "# test_data_cp['Embarked'] = labelEncoder_embarked.transform(test_data_cp['Embarked'])\n", "\n", "# X_test = test_data_cp.iloc[:, :].values\n", "# y_test = gender_submission['Survived'].values\n", "\n", "# X_test = oneHotEncoder.transform(X_test).toarray()\n", "\n", "# X_test = X_test[:, [1, 2, 3, 4, 6, 7, 8, 9, 10]]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "275642db-ad47-7e44-ff26-d60a2141bec5" }, "outputs": [], "source": [ "y_pred = classifier.predict(X_test)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "e4820dc9-008c-13ca-9d3a-33915ee41700" }, "outputs": [], "source": [ "from sklearn.metrics import confusion_matrix\n", "cm = confusion_matrix(y_test, y_pred)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "f21b5a53-e6e4-1eba-d893-8755fb71ba6c" }, "outputs": [], "source": [ "cm" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "9f338d6f-1dbe-1892-8928-7cc9db2f0dd3" }, "outputs": [], "source": [ "from sklearn.tree import DecisionTreeClassifier\n", "classifier = DecisionTreeClassifier(criterion='entropy', random_state=0)\n", "classifier.fit(X_train, y_train)\n", "\n", "y_pred = classifier.predict(X_test)\n", "\n", "from sklearn.metrics import confusion_matrix\n", "cm = confusion_matrix(y_test, y_pred)\n", "\n", "cm" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "a64d8689-8aa9-b08f-c9e1-5777d83c102b" }, "outputs": [], "source": [ "from sklearn.naive_bayes import GaussianNB\n", "classifier = GaussianNB()\n", "classifier.fit(X_train, y_train)\n", "\n", "y_pred = classifier.predict(X_test)\n", "\n", "from sklearn.metrics import confusion_matrix\n", "cm = confusion_matrix(y_test, y_pred)\n", "\n", "cm" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "42bc4d7c-7566-cf91-a662-a2008b838705" }, "outputs": [], "source": [ "#logistic regression seems the best" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b781c1ab-9ebc-db62-7662-1a1cc9c0d873" }, "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 }