{"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%matplotlib inline\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\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output."},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# Get first 10000 rows and print some info about columns\ntrain = pd.read_csv(\"../input/train.csv\", parse_dates=['srch_ci', 'srch_co'], nrows=10000)\ntrain.info()"},{"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(y='hotel_continent', data=train)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# most of people booking are from continent 3 I guess is one of the rich continent?\nsns.countplot(y='posa_continent', data=train)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# putting the two above together\nsns.countplot(y='hotel_continent', hue='posa_continent', data=train)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# how many people by continent are booking from mobile\nsns.countplot(y='posa_continent', hue='is_mobile', data = train)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# Difference between user and destination country\nsns.distplot(train['user_location_country'], label=\"User country\")\nsns.distplot(train['hotel_country'], label=\"Hotel country\")\nplt.legend()"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"import numpy as np\n# get number of booked nights as difference between check in and check out\nhotel_nights = train['srch_co'] - train['srch_ci'] \nhotel_nights = (hotel_nights / np.timedelta64(1, 'D')).astype(float) # convert to float to avoid NA problems\ntrain['hotel_nights'] = hotel_nights\nplt.figure(figsize=(11, 9))\nsns.boxplot(x='hotel_nights', y='hotel_country', data=train)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"plt.figure(figsize=(11, 9))\nsns.countplot(x=\"hotel_nights\", data=train)"},{"cell_type":"code","execution_count":null,"metadata":{"collapsed":false},"outputs":[],"source":"# distribution of the total number of people per cluster\nsrc_total_cnt = train.srch_adults_cnt + train.srch_children_cnt\ntrain['src_total_cnt'] = src_total_cnt\nax = sns.kdeplot(train['hotel_cluster'], train['src_total_cnt'], cmap=\"Purples_d\")\nlim = ax.set(ylim=(0.5, 4.5))"}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}},"nbformat":4,"nbformat_minor":0}