1. 函数库导入

# import libraries necessary for this project
import os, sys, pickle

import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
import matplotlib.dates as mdates

import seaborn as sns
import datetime as dt

from datetime import date

from sklearn.linear_model import SGDClassifier, LogisticRegression
from sklearn.metrics import log_loss, roc_auc_score, auc, roc_curve

# display for this notebook
%matplotlib inline
%config InlineBackend.figure_format = 'retina'

2. 读取文件数据

dfoff = pd.read_csv('./data/ccf_offline_stage1_train.csv')
dftest = pd.read_csv('./data/ccf_offline_stage1_test_revised.csv')
dfon = pd.read_csv('./data/ccf_online_stage1_train.csv')

dfoff.head()

	User_id	Merchant_id	Coupon_id	Discount_rate	Distance	Date_received	Date
0	1439408	2632	NaN	NaN	0.0	NaN	20160217.0
1	1439408	4663	11002.0	150:20	1.0	20160528.0	NaN
2	1439408	2632	8591.0	20:1	0.0	20160217.0	NaN
3	1439408	2632	1078.0	20:1	0.0	20160319.0	NaN
4	1439408	2632	8591.0	20:1	0.0	20160613.0	NaN

3. 数据处理

# 1. 将满xx减yy类型(`xx:yy`)的券变成折扣率 : `1 - yy/xx`，同时建立折扣券相关的特征 `discount_rate, discount_man, discount_jian, discount_type`
# 2. 将距离 `str` 转为 `int`
# convert Discount_rate and Distance
def getDiscountType(row):
    if pd.isnull(row):
        return np.nan
    elif ':' in row:
        return 1
    else:
        return 0

    
def convertRate(row):
    """Convert discount to rate"""
    if pd.isnull(row):
        return 1.0
    elif ':' in str(row):
        rows = row.split(':')
        return 1.0 - float(rows[1])/float(rows[0])
    else:
        return float(row)

def getDiscountMan(row):
    if ':' in str(row):
        rows = row.split(':')
        return int(rows[0])
    else:
        return 0

def getDiscountJian(row):
    if ':' in str(row):
        rows = row.split(':')
        return int(rows[1])
    else:
        return 0
    
def processData(df):
    # convert discunt_rate
    df['discount_rate'] = df['Discount_rate'].apply(convertRate)
    df['discount_man'] = df['Discount_rate'].apply(getDiscountMan)
    df['discount_jian'] = df['Discount_rate'].apply(getDiscountJian)
    df['discount_type'] = df['Discount_rate'].apply(getDiscountType)
    #print(df['discount_rate'].unique())
    # convert distance
    df['distance'] = df['Distance'].fillna(-1).astype(int)
    return df

dfoff = processData(dfoff)
dftest = processData(dftest)

dfoff.head()
dftest.head()

	User_id	Merchant_id	Coupon_id	Discount_rate	Distance	Date_received	discount_rate	discount_man	discount_jian	discount_type	distance
0	4129537	450	9983	30:5	1.0	20160712	0.833333	30	5	1	1
1	6949378	1300	3429	30:5	NaN	20160706	0.833333	30	5	1	-1
2	2166529	7113	6928	200:20	5.0	20160727	0.900000	200	20	1	5
3	2166529	7113	1808	100:10	5.0	20160727	0.900000	100	10	1	5
4	6172162	7605	6500	30:1	2.0	20160708	0.966667	30	1	1	2

date_received = dfoff['Date_received'].unique()
date_received = sorted(date_received[pd.notnull(date_received)])

date_buy = dfoff['Date'].unique()
date_buy = sorted(date_buy[pd.notnull(date_buy)])
date_buy