{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "# カーネルの場合\n",
    "#df_train = pd.read_csv('../input/train.csv')\n",
    "#df_test = pd.read_csv('../input/test.csv')\n",
    "\n",
    "# 本レポジトリの場合\n",
    "df_train = pd.read_csv(\"./titanic_csv/train.csv\")\n",
    "df_test = pd.read_csv(\"./titanic_csv/test.csv\")\n",
    "\n",
    "# Embarkedの補完\n",
    "df_train.loc[df_train['PassengerId'].isin([62, 830]), 'Embarked'] = 'C'\n",
    "\n",
    "# Fareの補完\n",
    "df_test.loc[df_test['PassengerId'] == 1044, 'Fare'] = 13.675550\n",
    "\n",
    "#Age変換のための関数\n",
    "def impute_age(cols):\n",
    "    Age = cols[0]\n",
    "    Pclass = cols[1]    \n",
    "    if pd.isnull(Age):        \n",
    "        if Pclass == 1:\n",
    "            return 39\n",
    "        elif Pclass == 2:\n",
    "            return 30\n",
    "        else:\n",
    "            return 25    \n",
    "    else:\n",
    "        return Age\n",
    "\n",
    "\n",
    "data = [df_train, df_test]\n",
    "for df in data:\n",
    "    # Ageの補完\n",
    "    df['Age'] = df[['Age','Pclass']].apply(impute_age, axis = 1) \n",
    "\n",
    "    # 性別の変換\n",
    "    df['Sex'] = df['Sex'].map({\"male\": 0, \"female\": 1})\n",
    "        \n",
    "    # Embarked\n",
    "    df['Embarked'] = df['Embarked'].map( {'S': 0, 'C': 1, 'Q': 2} ).astype(int)\n",
    "    \n",
    "    # Fareのカテゴリ変数化\n",
    "    df.loc[ df['Fare'] <= 7.91, 'Fare'] = 0\n",
    "    df.loc[(df['Fare'] > 7.91) & (df['Fare'] <= 14.454), 'Fare'] = 1\n",
    "    df.loc[(df['Fare'] > 14.454) & (df['Fare'] <= 31), 'Fare']   = 2\n",
    "    df.loc[ df['Fare'] > 31, 'Fare'] = 3\n",
    "    df['Fare'] = df['Fare'].astype(int)\n",
    "\n",
    "    # Ageのカテゴリ変数化\n",
    "    df.loc[ df['Age'] <= 16, 'Age'] = 0\n",
    "    df.loc[(df['Age'] > 16) & (df['Age'] <= 32), 'Age'] = 1\n",
    "    df.loc[(df['Age'] > 32) & (df['Age'] <= 48), 'Age'] = 2\n",
    "    df.loc[ df['Age'] > 48, 'Age']  = 3\n",
    "    df['Age'] = df['Age'].astype(int)\n",
    "    \n",
    "     # FamilySizeとIsAloneの作成\n",
    "    df['FamilySize'] = df['SibSp'] + df['Parch'] + 1\n",
    "    df['IsAlone'] = 0\n",
    "    df.loc[df['FamilySize'] == 1, 'IsAlone'] = 1 \n",
    "    \n",
    "# 不要な列の削除    \n",
    "df_train.drop(['Name', 'Cabin', 'Ticket','SibSp','Parch'], axis=1, inplace=True)\n",
    "df_test.drop(['Name', 'Cabin', 'Ticket','SibSp','Parch'], axis=1, inplace=True) \n",
    "\n",
    "# X_train、Y_train、X_testを作成\n",
    "X_train = df_train.drop([\"PassengerId\",\"Survived\"], axis=1)\n",
    "Y_train = df_train[\"Survived\"]\n",
    "X_test  = df_test.drop(\"PassengerId\", axis=1).copy()\n",
    "\n",
    "# 学習\n",
    "forest = RandomForestClassifier(random_state=1)\n",
    "forest.fit(X_train, Y_train)\n",
    "Y_pred = forest.predict(X_test)\n",
    "\n",
    "# 提出データの作成\n",
    "submission = pd.DataFrame({\n",
    "        \"PassengerId\": df_test[\"PassengerId\"],\n",
    "        \"Survived\": Y_pred})\n",
    "submission.to_csv('submit.csv', index=False)"
   ]
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [conda root]",
   "language": "python",
   "name": "conda-root-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  },
  "toc": {
   "colors": {
    "hover_highlight": "#DAA520",
    "running_highlight": "#FF0000",
    "selected_highlight": "#FFD700"
   },
   "moveMenuLeft": true,
   "nav_menu": {
    "height": "318px",
    "width": "252px"
   },
   "navigate_menu": true,
   "number_sections": false,
   "sideBar": true,
   "threshold": 4,
   "toc_cell": false,
   "toc_section_display": "block",
   "toc_window_display": true,
   "widenNotebook": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}