{"nbformat_minor": 1, "cells": [{"cell_type": "code", "metadata": {"_uuid": "d22deac4e91389d6bef9786b431536e44b6be21c", "_cell_guid": "a4d84a98-109d-46b9-b74c-82d9de9d0f9e"}, "source": ["from multiprocessing import Pool, cpu_count\n", "import gc; gc.enable()\n", "import xgboost as xgb\n", "import pandas as pd\n", "import numpy as np\n", "from sklearn import *\n", "import sklearn\n", "\n", "train = pd.read_csv('../input/train.csv')\n", "train = pd.concat((train, pd.read_csv('../input/train_v2.csv')), axis=0, ignore_index=True).reset_index(drop=True)\n", "test = pd.read_csv('../input/sample_submission_v2.csv')\n", "\n", "transactions = pd.read_csv('../input/transactions.csv', usecols=['msno'])\n", "transactions = pd.concat((transactions, pd.read_csv('../input/transactions_v2.csv', usecols=['msno'])), axis=0, ignore_index=True).reset_index(drop=True)\n", "transactions = pd.DataFrame(transactions['msno'].value_counts().reset_index())\n", "transactions.columns = ['msno','trans_count']\n", "train = pd.merge(train, transactions, how='left', on='msno')\n", "test = pd.merge(test, transactions, how='left', on='msno')\n", "transactions = []; print('transaction merge...')\n", "\n", "user_logs = pd.read_csv('../input/user_logs_v2.csv', usecols=['msno'])\n", "#user_logs = pd.read_csv('../input/user_logs.csv', usecols=['msno'])\n", "#user_logs = pd.concat((user_logs, pd.read_csv('../input/user_logs_v2.csv', usecols=['msno'])), axis=0, ignore_index=True).reset_index(drop=True)\n", "user_logs = pd.DataFrame(user_logs['msno'].value_counts().reset_index())\n", "user_logs.columns = ['msno','logs_count']\n", "train = pd.merge(train, user_logs, how='left', on='msno')\n", "test = pd.merge(test, user_logs, how='left', on='msno')\n", "user_logs = []; print('user logs merge...')\n", "\n", "members = pd.read_csv('../input/members_v3.csv')\n", "train = pd.merge(train, members, how='left', on='msno')\n", "test = pd.merge(test, members, how='left', on='msno')\n", "members = []; print('members merge...') "], "execution_count": null, "outputs": []}, {"cell_type": "code", "metadata": {"_uuid": "b24e7f1fb0c01887208a020356d783e46c7b4172", "_cell_guid": "48c17f47-87b0-4bc5-99f2-f4ba90faa921"}, "source": ["\n", "train['is_churn'].describe()"], "execution_count": null, "outputs": []}, {"cell_type": "code", "metadata": {"collapsed": true, "_uuid": "2d1849e5b6c07933039b3d025b3390a7db320c01", "_cell_guid": "4a52098a-2eee-401f-8b5d-eddaa5e28fbd"}, "source": ["transactions = pd.read_csv('../input/transactions_v2.csv') #pd.read_csv('../input/transactions.csv')\n", "#transactions = pd.concat((transactions, pd.read_csv('../input/transactions_v2.csv')), axis=0, ignore_index=True).reset_index(drop=True)\n", "transactions = transactions.sort_values(by=['transaction_date'], ascending=[False]).reset_index(drop=True)\n", "transactions = transactions.drop_duplicates(subset=['msno'], keep='first')\n", "\n", "train = pd.merge(train, transactions, how='left', on='msno')\n", "test = pd.merge(test, transactions, how='left', on='msno')\n", "transactions=[]"], "execution_count": null, "outputs": []}, {"cell_type": "code", "metadata": {"_uuid": "7ad9df92001671b700a49444b797698a13562ed9", "_cell_guid": "ca305fc9-3fe3-4867-a178-9e0c7fe87b19"}, "source": ["test.head()"], "execution_count": null, "outputs": []}, {"cell_type": "code", "metadata": {"collapsed": true, "_uuid": "2555f89e43d3ad95c23e8f99b6d1f39bf3659936", "_cell_guid": "b2804075-d12d-4e4c-a673-99df8e17e1bd"}, "source": ["train.shape"], "execution_count": null, "outputs": []}, {"cell_type": "code", "metadata": {"collapsed": true, "_uuid": "bfb709dbf80d54da36b32b97673e3f2f41374653", "_cell_guid": "f8d247ca-6ae4-4096-a473-37b606972ff3"}, "source": ["train.shape"], "execution_count": null, "outputs": []}, {"cell_type": "code", "metadata": {"_uuid": "ee90ce913f6d2207a2f4dde716e669fc12f1df7f", "_cell_guid": "50f51680-0584-4411-abaa-43c28feb745d"}, "source": ["train['is_churn'].describe()"], "execution_count": null, "outputs": []}, {"cell_type": "code", "metadata": {"_uuid": "04e636d18bcd259d5aaf3d373549e29e7e16cf50", "_cell_guid": "cd507f78-9410-4c5e-b3a5-e098dbf00595"}, "source": ["train\n"], "execution_count": null, "outputs": []}, {"cell_type": "code", "metadata": {"collapsed": true, "_uuid": "0de7839769997cade8bb31b96ec40df398edee90", "_cell_guid": "ef0ff7bd-cc4a-4603-b8a4-72591b6ba6c7"}, "source": ["\n", "\n", "train.to_csv('train.csv', index=False)\n", "test.to_csv('test.csv', index = False)\n"], "execution_count": null, "outputs": []}, {"cell_type": "code", "metadata": {"collapsed": true, "_uuid": "6e0b294f73e8c316cdd5714700e4bf5779e85c9f", "_cell_guid": "6d8a9718-6fa5-4ae0-9e22-a3702b1b0ec2"}, "source": [], "execution_count": null, "outputs": []}], "metadata": {"kernelspec": {"display_name": "Python 3", "name": "python3", "language": "python"}, "language_info": {"codemirror_mode": {"version": 3, "name": "ipython"}, "name": "python", "file_extension": ".py", "nbconvert_exporter": "python", "version": "3.6.3", "pygments_lexer": "ipython3", "mimetype": "text/x-python"}}, "nbformat": 4}