{"cells":[
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "import pandas as pd\nimport numpy as np\n\nfields = ['site_name', 'posa_continent' ]\ntrain = pd.read_csv(\"../input/train.csv\", \n                   #usecols = fields,\n                  nrows= 5)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train.columns"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train = pd.read_csv(\"../input/train.csv\", \n                   usecols = fields,\n                  #nrows= 5,\n                   )"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "import seaborn as sns\nimport matplotlib.pyplot as plt\n# preferred continent destinations\nsns.countplot(x='site_name', data=train)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train.site_name.value_counts()"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "sns.countplot(x='posa_continent', data=train)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train.posa_continent.value_counts()"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "fields = [ 'posa_continent', 'hotel_continent', 'is_mobile']\ntrain = pd.read_csv('../input/train.csv', usecols = fields)\n"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "sns.countplot(x= 'hotel_continent', data = train)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "sns.countplot(x='posa_continent', hue ='is_mobile', data=train)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "sns.countplot(x='hotel_continent', hue ='is_mobile', data=train)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "# Observign plots 14-17, makes sense, since most of the users are from continent 3\n# They are also the one who most search for hotels in continent in 2\n# 2 must be a very loved continent \n\nsns.countplot(x='posa_continent', hue ='hotel_continent', data=train)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "fields = ['hotel_country' , 'user_location_country']\ntrain = pd.read_csv('../input/train.csv', usecols= fields)\nsns.distplot(train.hotel_country, label = \"Hotel Coutry\")\nsns.distplot(train.user_location_country, label = \"User Country\")\nplt.legend()"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "import pandas as pd\nfrom datetime import datetime\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns \n\nfields = ['hotel_continent' , 'posa_continent', 'srch_co', 'srch_ci']\ntrain = pd.read_csv('../input/train.csv', usecols= fields, parse_dates=['srch_ci', 'srch_co'], nrows =100000)\n\ntrain['hotel_nights'] = ((train.srch_co - train.srch_ci) / np.timedelta64( 1, 'D')).astype(float)\nplt.figure(figsize=(11, 9))\nax = sns.boxplot(x='hotel_continent', y='hotel_nights', data=train)\nlim = ax.set(ylim=(0, 15))"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": ""
 }
],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}}, "nbformat": 4, "nbformat_minor": 0}