pandas 实现rfm模型

佚名 6年前 (2019-04-23) 随笔 2032人围观抢沙发百度已收录

import pandas as pd
import numpy as np


df = pd.read_csv('./zue_164466.csv')

df['ptdate'] = pd.to_datetime(df['ptdate'],format='%Y-%m-%d')
df['dateDiff'] = pd.to_datetime('today')-df['ptdate']
df['dateDiff'] = df['dateDiff'].dt.days

R_Agg = df.groupby(by=['user_email','product_name'])['dateDiff'].agg({'RecencyAgg': np.min})

F_Agg = df.groupby(by=['user_email','product_name'])['ptdate'].agg({'FrequencyAgg': np.size})

M_Agg = df.groupby(by=['user_email','product_name'])['totalcost'].agg({'MonetaryAgg': np.sum})

aggData = R_Agg.join(F_Agg).join(M_Agg)

bins = aggData.RecencyAgg.quantile(q=[0, 0.2, 0.4, 0.6, 0.8, 1],interpolation='nearest')
bins[0] = 0
labels = [5, 4, 3, 2, 1]
R_S = pd.cut(aggData.RecencyAgg, bins, labels=labels)

#
bins = aggData.FrequencyAgg.quantile(q=[0, 0.2, 0.4, 0.6, 0.8, 1],interpolation='nearest')
bins[0] = 0
labels = [1, 2, 3, 4, 5]
F_S = pd.cut(aggData.FrequencyAgg, bins, labels=labels)


bins = aggData.MonetaryAgg.quantile(q=[0, 0.2, 0.4, 0.6, 0.8, 1],interpolation='nearest')
bins[0] = 0
labels = [1, 2, 3, 4, 5]
M_S = pd.cut(aggData.MonetaryAgg,bins, labels=labels)


aggData['R_S']=R_S
aggData['F_S']=F_S
aggData['M_S']=M_S


aggData['RFM'] = 100*R_S.astype(int) + 10*F_S.astype(int) + 1*M_S.astype(int)


bins = aggData.RFM.quantile(q=[0, 0.125, 0.25, 0.375, 0.5, 0.625, 0.75, 0.875, 1],interpolation='nearest')
bins[0] = 0
labels = [1, 2, 3, 4, 5, 6, 7, 8]
aggData['level'] = pd.cut(aggData.RFM, bins, labels=labels)

aggData = aggData.reset_index()

fe = aggData.sort_values(['level', 'RFM'], ascending=[0, 0])

dd=aggData.groupby(by=['level'])['user_email','product_name'].agg({'size':np.size})

print(fe.head())
fe.to_csv('./rfm_data.csv',index=False)
print("---------------")
print(dd)