kaggle titanic rpart gridsearch w/ mlr

rpart.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "# rpart"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "* [RPubs \\- Kaggle Titanic R Tutorial](https://rpubs.com/anyuanay/283773)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "library(rpart)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "training <- read.csv(\"~/repo/kaggle/input/titanic/train.csv\")\n",
    "testing <- read.csv(\"~/repo/kaggle/input/titanic/test.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "trainingSel = subset(training, select = c('Survived', 'Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Embarked'))\n",
    "testingSel = subset(testing, select = c('Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Embarked'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "trainingSel = subset(trainingSel, Embarked != '')\n",
    "trainingSel$Embarked = droplevels(trainingSel$Embarked, \"\")\n",
    "testingSel = subset(testingSel, Embarked != '')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "agemedian = median(trainingSel$Age, na.rm = TRUE)\n",
    "trainingSel$Age = replace(trainingSel$Age, is.na(trainingSel$Age), agemedian)\n",
    "testingSel$Age = replace(testing$Age, is.na(testing$Age), agemedian)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "tree<-rpart(Survived~., #目的変数~説明変数, 「.」はy以外の全変数を説明変数とするという意味\n",
    "            data=trainingSel, #学習データ\n",
    "            maxdepth=9, #階層数\n",
    "            minbucket=60, #最小ノードサイズ\n",
    "            cp=1e-04, #枝刈りの強さ\n",
    "            method=\"class\", #分類\n",
    "            parms=list(split=\"infomation\") #分割基準, list(split=\"information\")とするとEntropy基準となる\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "pred_test<-predict(tree, testingSel, type=\"class\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "out<-data.frame(testing$PassengerId, pred_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "write.table(out, #出力データ\n",
    "            \"~/repo/kaggle/titanic/submit/submit_1008_7_rpart.csv\", #出力先\n",
    "            quote=FALSE, #文字列を「\"」で囲む有無\n",
    "            col.names=c(\"PassengerId\", \"Survived\"), #変数名(列名)の有無\n",
    "            row.names=FALSE, #行番号の有無\n",
    "            sep=\",\" #区切り文字の指定\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "R",
   "language": "R",
   "name": "ir"
  },
  "language_info": {
   "codemirror_mode": "r",
   "file_extension": ".r",
   "mimetype": "text/x-r-source",
   "name": "R",
   "pygments_lexer": "r",
   "version": "3.4.1"
  },
  "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": "21px",
    "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
}

rpart_mlr.ipynb