{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "## Titanic with Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "code_folding": [],
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from pandas import DataFrame"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "## setup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "DATA_HOME_DIR = \"/home/tsu-nera/repo/kaggle/input/titanic/\"\n",
    "row_data = pd.read_csv(DATA_HOME_DIR + 'train.csv', index_col=0)\n",
    "test_data = pd.read_csv(DATA_HOME_DIR + 'test.csv', index_col=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "## Preprocess"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((1309, 6), (891, 1))"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_ind = test_data.index\n",
    "\n",
    "train_X = row_data[['Pclass','Sex','Age','SibSp','Parch','Cabin']]\n",
    "train_y = row_data[['Survived']]\n",
    "test_X= test_data[['Pclass','Sex','Age','SibSp','Parch', 'Cabin']]\n",
    "\n",
    "all_data = pd.concat([train_X, test_X])\n",
    "\n",
    "all_data.shape, train_y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "## クラスごとに分割\n",
    "Pclass = pd.get_dummies(all_data['Pclass'])\n",
    "Pclass.columns=['1st','2nd','3rd']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "## 女性、男性、子供ごとに分割\n",
    "Sex = pd.get_dummies(all_data['Sex'])\n",
    "\n",
    "def male_female_child(passenger):\n",
    "    age,sex = passenger\n",
    "    if np.isnan(age):\n",
    "        age = 30\n",
    "    if age < 16:\n",
    "        return 'child'\n",
    "    else:\n",
    "        return sex\n",
    "\n",
    "Person = all_data[['Age','Sex']].apply(male_female_child,axis=1)\n",
    "Person = pd.get_dummies(Person)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "# 独身かそうでないかで分類\n",
    "Alone = all_data.Parch + all_data.SibSp\n",
    "\n",
    "def is_alone(alone):\n",
    "    if alone > 0:\n",
    "        return 0\n",
    "    else:\n",
    "        return 1\n",
    "\n",
    "Alone = Alone.apply(is_alone)\n",
    "Alone = pd.DataFrame(Alone)\n",
    "Alone.columns = ['Alone']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {
    "code_folding": [],
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "def get_level(deck):\n",
    "    if pd.isnull(deck):\n",
    "        deck = 'CXX'\n",
    "    return deck[0]\n",
    "\n",
    "Level = all_data.Cabin.apply(get_level)\n",
    "Level = pd.get_dummies(Level)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {
    "code_folding": [],
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((891, 15), (891,), (418, 15))"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merge_data = pd.merge(Alone,Pclass,right_index=True,left_index=True)\n",
    "merge_data = pd.merge(merge_data,Person,right_index=True,left_index=True)\n",
    "merge_data = pd.merge(merge_data,Level,right_index=True,left_index=True)\n",
    "\n",
    "X = merge_data[:train_X.shape[0]]\n",
    "y = train_y.values.ravel()\n",
    "\n",
    "test_X = merge_data[train_X.shape[0]:]\n",
    "\n",
    "X.shape, y.shape, test_X.shape\n",
    "# tx"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "## Build Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {
    "code_folding": [],
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "# create model\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "model = LogisticRegression(C=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "## Training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=10, class_weight=None, dual=False, fit_intercept=True,\n",
       "          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,\n",
       "          penalty='l2', random_state=None, solver='liblinear', tol=0.0001,\n",
       "          verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(X, y)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "## Testing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "p_survived = model.predict(test_X.values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "submission = pd.DataFrame()\n",
    "submission['PassengerId'] = test_ind\n",
    "submission['Survived'] = p_survived"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "submission.to_csv('submission.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "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"
  },
  "notify_time": "10",
  "toc": {
   "colors": {
    "hover_highlight": "#DAA520",
    "navigate_num": "#000000",
    "navigate_text": "#333333",
    "running_highlight": "#FF0000",
    "selected_highlight": "#FFD700",
    "sidebar_border": "#EEEEEE",
    "wrapper_background": "#FFFFFF"
   },
   "moveMenuLeft": true,
   "nav_menu": {
    "height": "90px",
    "width": "253px"
   },
   "navigate_menu": true,
   "number_sections": false,
   "sideBar": true,
   "threshold": 4,
   "toc_cell": false,
   "toc_section_display": "block",
   "toc_window_display": false,
   "widenNotebook": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}