{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"%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"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"import warnings # current version of seaborn generates a bunch of warnings that we'll ignore\nwarnings.filterwarnings(\"ignore\")"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"import seaborn as sns\nimport matplotlib.pyplot as plt"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"sns.set(style=\"white\", color_codes=True)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"ex_train = pd.read_csv(\"../input/train.csv\", parse_dates=['date_time'], nrows=10000)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"trainci = train\n#trainci.info()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train = pd.read_csv(\"../input/train.csv\", parse_dates=['date_time'], nrows=1000000)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"mask = train.is_booking == True\nmask1 = ex_train.is_booking == True"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"trainm = train[mask]\ntrainm1 = ex_train[mask1]\n#understanding the numerical content \n\nb1 = trainm[['srch_adults_cnt','srch_children_cnt','srch_rm_cnt']]\nb2 = trainm1[['srch_adults_cnt','srch_children_cnt','srch_rm_cnt']]"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"trainm.info()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"def date_Time_Function(ds, fmt='%Y-%m-%d'):\n    if ds != ds:\n        return np.nan\n    year, month, day = ds.split('-')\n    try:\n        d = pd.datetime(int(year), int(month), int(day))\n    except ValueError:\n        d = pd.datetime(2017, 1, 1)\n    d = min([max([d, pd.datetime(2013,1,1)]), pd.datetime(2017,1,1)])\n    return d"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"trainci['srch_ci'] = train['srch_ci'].apply(date_Time_Function)\ntrainci['srch_co'] = train['srch_co'].apply(date_Time_Function)\ntrain_bookings = trainci[trainci['is_booking'] == 1].drop('is_booking', axis=1)\ntrain_clicks = trainci[trainci['is_booking'] == 0].drop('is_booking', axis=1)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"trainci['srch_ci'].tail()\ntrainci['srch_ci'].head()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"f = plt.figure()\nplt.hist(train_bookings['date_time'].values, bins=100, alpha=0.5, normed=True, label='training bookings')\nplt.hist(train_clicks['date_time'].values, bins=100, alpha=0.5, normed=True, label='train clicks')\nplt.title('Booking time distribution')\nplt.legend(loc='best')\nf.savefig('SearchTime.png', dpi=300)\nplt.show()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"f = plt.figure()\nplt.hist(train_bookings['srch_ci'].values, bins=100, alpha=0.5, normed=True, label='train bookings')\nplt.hist(train_clicks['srch_ci'].dropna().values, bins=100, alpha=0.5, normed=True, label='train clicks')\nplt.title('Checkin time')\nplt.legend(loc='best')\nf.savefig('CheckinTime.png', dpi=300)\nplt.show()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"import numpy as np"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"z1 = train_bookings.sort_values(by = ['user_id'])"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"sns.set_style('whitegrid')\n%matplotlib inline"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"train_bookingsz = ex_train[ex_train['is_booking'] == 1].drop('is_booking', axis=1)\nz2 = train_bookingsz.sort_values(by = ['user_id'])\nfig, (axis1) = plt.subplots(1,1,figsize=(15,10))\nsns.countplot('user_id',data=z2,ax=axis1,palette=\"Set3\")"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"%matplotlib inline"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# customers from the most traveling country\nuser_country_id = 66\n\nfig, (axis1) = plt.subplots(1,1,figsize=(15,10))\n\ncountry_customers = train_bookings[train_bookings[\"user_location_country\"] == user_country_id]\ncountry_customers[\"user_id\"].value_counts().plot(kind='bar',colormap=\"Set3\",figsize=(15,5))"},{"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}