{"cells":[
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nfrom subprocess import check_output\n#print(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output.\n%matplotlib inline\nimport numpy as np\nimport pandas as pd \nfrom subprocess import check_output\n#print(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\nimport datetime\nimport seaborn as sns\nimport matplotlib.pyplot as plt"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train1 = pd.read_csv(\"../input/train.csv\", parse_dates=['date_time'], nrows=10000000)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train1[\"date_time\"] = pd.to_datetime(train1[\"date_time\"], format='%Y-%m-%d', errors=\"coerce\")\ntrain1[\"srch_ci\"] = pd.to_datetime(train1[\"srch_ci\"], format='%Y-%m-%d', errors=\"coerce\")\ntrain1[\"search_span\"] = (train1[\"srch_ci\"] - train1[\"date_time\"]).astype('timedelta64[D]')"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_bookings = train1[train1['is_booking'] == 1].drop('is_booking', axis=1)\ntrain_clicks = train1[train1['is_booking'] == 0].drop('is_booking', axis=1)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_clicks.shape"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train1.shape"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_bookings.shape"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_bookingszna = train_bookings.fillna(0)\ntrain_clickszna = train_clicks.fillna(0)\ntrain_bookings_package = train_bookingszna[train_bookingszna['is_package'] == 1]"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_bookingszna.shape"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_bookings_package.shape"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_bookingszna_ss = train_bookings_package['search_span']"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_bookingszna_all = train_bookingszna['search_span']"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "booked_bookings_all, countall = np.unique(train_bookingszna_all, return_counts=True)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "booked_bookings, count = np.unique(train_bookingszna_ss, return_counts=True)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "np.mean(count)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "np.mean(countall)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "np.sort(count)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "np.sort(countall)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "most_visited2 = booked_bookings[count >= 95]"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "most_visited3= booked_bookings_all[countall >= 1150]"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_bookings_package1 = train_bookings_package[train_bookings_package['search_span'].isin(most_visited2)]"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_bookings_package1all = train_bookingszna[train_bookingszna['search_span'].isin(most_visited3)]"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_bookings_package1.ix[(train_bookings_package1['search_span'] <= -1), 'search_span'] = 0"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_bookings_package1all.ix[(train_bookings_package1all['search_span'] <= -1), 'search_span'] = 0"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "f, ax = plt.subplots(figsize=(15, 25))\nsns.countplot(y='search_span', data=train_bookings_package1)\nsns.plt.title('number of days before check in vs count of instances with packages for 10m bookings')\nplt.show()"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "f, ax = plt.subplots(figsize=(10, 15))\nsns.countplot(y='search_span', hue=\"is_package\", data=train_bookings_package1all)\nsns.plt.title('with packages or not: number of days before check in vs count of instances for 10m bookings')\nplt.show()"
 }
],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}}, "nbformat": 4, "nbformat_minor": 0}