Data Cleaning

dataclean.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pclass       1309\n",
       "survived     1309\n",
       "name         1309\n",
       "sex          1309\n",
       "age          1046\n",
       "sibsp        1309\n",
       "parch        1309\n",
       "ticket       1309\n",
       "fare         1308\n",
       "cabin         295\n",
       "embarked     1307\n",
       "boat          486\n",
       "body          121\n",
       "home.dest     745\n",
       "dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_df.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "titanic_df = titanic_df.drop(['body','cabin','boat'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "titanic_df[\"home.dest\"] = titanic_df[\"home.dest\"].fillna(\"NA\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "titanic_df = titanic_df.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pclass       1043\n",
       "survived     1043\n",
       "name         1043\n",
       "sex          1043\n",
       "age          1043\n",
       "sibsp        1043\n",
       "parch        1043\n",
       "ticket       1043\n",
       "fare         1043\n",
       "embarked     1043\n",
       "home.dest    1043\n",
       "dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_df.count()"
   ]
  }
 ],
 "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": "3.4.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}