Skip to content

M
model_mvp
Commit b5a3f366 authored by linfang.wang's avatar linfang.wang
Browse files
Options

引入电话邦

parent dda80e02
Hide whitespace changes
Inline Side-by-side
Showing with 49 additions and 46 deletions
mvp/allocator.py
View file @ b5a3f366
......@@ -3,51 +3,54 @@ import numpy as np
import datetime
from mvp import xgbreport
from data.analyis import datacal
from mvp import dhb
if __name__ == '__main__':
features=[
'third_data_source#xy_pan_newapplyAcredibility',
'third_data_source#xy_pan_newapplyAscore',
'third_data_source#xy_pan_newconsfinAavgAlimit',
'third_data_source#xy_pan_newconsfinAcredibility',
'third_data_source#xy_pan_newconsfinAcreditAlimit',
'third_data_source#xy_pan_newconsfinAmaxAlimit',
'third_data_source#xy_pan_newconsfinAorgAcountq',
'third_data_source#xy_pan_newconsfinAorgAcountx',
'third_data_source#xy_pan_newconsfinAproductAcount',
'third_data_source#xy_pan_newhistoryAfailAfee',
'third_data_source#xy_pan_newhistoryAsucAfee',
'third_data_source#xy_pan_newlatestAoneAmonthAfail',
'third_data_source#xy_pan_newlatestAoneAmonthAsuc',
'third_data_source#xy_pan_newlatestAoneAmonthd',
'third_data_source#xy_pan_newlatestAoneAmonthj',
'third_data_source#xy_pan_newlatestAqueryAtime',
'third_data_source#xy_pan_newlatestAsixAmontha',
'third_data_source#xy_pan_newlatestAsixAmonthv',
'third_data_source#xy_pan_newlatestAthreeAmonthb',
'third_data_source#xy_pan_newlatestAthreeAmonthf',
'third_data_source#xy_pan_newloansAavgAlimit',
'third_data_source#xy_pan_newloansAcashAcount',
'third_data_source#xy_pan_newloansAcount',
'third_data_source#xy_pan_newloansAcredibilityh',
'third_data_source#xy_pan_newloansAcredibilitys',
'third_data_source#xy_pan_newloansAcreditAlimit',
'third_data_source#xy_pan_newloansAlatestAtime',
'third_data_source#xy_pan_newloansAlongAtime',
'third_data_source#xy_pan_newloansAmaxAlimit',
'third_data_source#xy_pan_newloansAorgAcounta',
'third_data_source#xy_pan_newloansAorgAcountg',
'third_data_source#xy_pan_newloansAoverdueAcount',
'third_data_source#xy_pan_newloansAproductAcount',
'third_data_source#xy_pan_newloansAscore',
'third_data_source#xy_pan_newloansAsettleAcount',
'third_data_source#xy_pan_newqueryAcashAcount',
'third_data_source#xy_pan_newqueryAfinanceAcount',
'third_data_source#xy_pan_newqueryAorgAcount',
'third_data_source#xy_pan_newqueryAsumAcount'
]
label='y'
df=pd.read_csv('test.csv')
# features=[
# 'third_data_source#xy_pan_newapplyAcredibility',
# 'third_data_source#xy_pan_newapplyAscore',
# 'third_data_source#xy_pan_newconsfinAavgAlimit',
# 'third_data_source#xy_pan_newconsfinAcredibility',
# 'third_data_source#xy_pan_newconsfinAcreditAlimit',
# 'third_data_source#xy_pan_newconsfinAmaxAlimit',
# 'third_data_source#xy_pan_newconsfinAorgAcountq',
# 'third_data_source#xy_pan_newconsfinAorgAcountx',
# 'third_data_source#xy_pan_newconsfinAproductAcount',
# 'third_data_source#xy_pan_newhistoryAfailAfee',
# 'third_data_source#xy_pan_newhistoryAsucAfee',
# 'third_data_source#xy_pan_newlatestAoneAmonthAfail',
# 'third_data_source#xy_pan_newlatestAoneAmonthAsuc',
# 'third_data_source#xy_pan_newlatestAoneAmonthd',
# 'third_data_source#xy_pan_newlatestAoneAmonthj',
# 'third_data_source#xy_pan_newlatestAqueryAtime',
# 'third_data_source#xy_pan_newlatestAsixAmontha',
# 'third_data_source#xy_pan_newlatestAsixAmonthv',
# 'third_data_source#xy_pan_newlatestAthreeAmonthb',
# 'third_data_source#xy_pan_newlatestAthreeAmonthf',
# 'third_data_source#xy_pan_newloansAavgAlimit',
# 'third_data_source#xy_pan_newloansAcashAcount',
# 'third_data_source#xy_pan_newloansAcount',
# 'third_data_source#xy_pan_newloansAcredibilityh',
# 'third_data_source#xy_pan_newloansAcredibilitys',
# 'third_data_source#xy_pan_newloansAcreditAlimit',
# 'third_data_source#xy_pan_newloansAlatestAtime',
# 'third_data_source#xy_pan_newloansAlongAtime',
# 'third_data_source#xy_pan_newloansAmaxAlimit',
# 'third_data_source#xy_pan_newloansAorgAcounta',
# 'third_data_source#xy_pan_newloansAorgAcountg',
# 'third_data_source#xy_pan_newloansAoverdueAcount',
# 'third_data_source#xy_pan_newloansAproductAcount',
# 'third_data_source#xy_pan_newloansAscore',
# 'third_data_source#xy_pan_newloansAsettleAcount',
# 'third_data_source#xy_pan_newqueryAcashAcount',
# 'third_data_source#xy_pan_newqueryAfinanceAcount',
# 'third_data_source#xy_pan_newqueryAorgAcount',
# 'third_data_source#xy_pan_newqueryAsumAcount'
# ]
dhb = dhb.dhb()
df=dhb.dhb_features_extract()
label='target'
# df=pd.read_csv('test.csv')
dftrain,dftest=datacal.split_train_val(df,trainsplit='timeSeries',trainsplitRatio=0.8,sort_col='applied_at')
xgbreport.report(dftrain,dftest,features,label,'','tmp.doc')
xgbreport.report(dftrain,dftest,dhb.features,label,'','tmp.doc')
mvp/dhb.py
View file @ b5a3f366
......@@ -18,7 +18,7 @@ API :
'''
class dhb():
class dhb:
# features as Series format
features = ['dhb_last_30_and_60_days_dun_call_avg_duration',
'dhb_last_30_and_60_days_dun_call_duration_above60',
......@@ -249,7 +249,7 @@ class dhb():
dhb_loan.loc[dhb_loan.dhb_overview_dun_call_tel_total_nums>= 22,"dhb_overview_dun_call_tel_total_nums"] = 22
dhb_loan.loc[dhb_loan.dhb_last_30_days_dun_call_total_duration>= 1100,"dhb_last_30_days_dun_call_total_duration"] = 1100
dhb_loan.loc[dhb_loan.dhb_last_two_weeks_ntdun_call_in_duration>= 300,"dhb_last_two_weeks_ntdun_call_in_duration"] = 300
dhb_loan.to_csv("./dhb_loan_sample——"+str(datetime.date.today())+".csv")
# dhb_loan.to_csv("./dhb_loan_sample——"+str(datetime.date.today())+".csv")
print( datetime.time.strftime('%Y.%m.%d %H:%M:%S',datetime.time.localtime(datetime.time.time())) +"提取了dhb {}+ ".format(str(self.overdue_days)) + self.start_time_period + "to" + self.end_time_period + "时段样本")
return dhb_loan
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment