欺诈黑名单获取

import numpy as np
# a=np.load('ip_dict.npy',allow_pickle=True)
# data=a.item()   
temp = train[['ip','label']].groupby('ip')['label'].agg({'mean_label':'mean','count_label':'count','sum_label':'sum'}).reset_index()
ip_dict={}
for k,v in tqdm.tqdm_notebook(temp[['ip','mean_label']].values):
    if v==1 or v==0:
        if k in ip_dict:
            continue
        else:
            ip_dict[k]=v

np.save('ip_dict.npy', ip_dict)

temp = train[['adidmd5','label']].groupby('adidmd5')['label'].agg({'mean_label':'mean','count_label':'count','sum_label':'sum'}).reset_index()
ip_dict={}
for k,v in tqdm.tqdm_notebook(temp[['adidmd5','mean_label']].values):
    if v==1 or v==0:
        if k in ip_dict:
            continue
        else:
            ip_dict[k]=v

np.save('adidmd5_dict.npy', ip_dict)

temp = train[['imeimd5','label']].groupby('imeimd5')['label'].agg({'mean_label':'mean','count_label':'count','sum_label':'sum'}).reset_index()
ip_dict={}
for k,v in tqdm.tqdm_notebook(temp[['imeimd5','mean_label']].values):
    if v==1 or v==0:
        if k in ip_dict:
            continue
        else:
            ip_dict[k]=v

np.save('imeimd5_dict.npy', ip_dict)


temp = train[['idfamd5','label']].groupby('idfamd5')['label'].agg({'mean_label':'mean','count_label':'count','sum_label':'sum'}).reset_index()
ip_dict={}
for k,v in tqdm.tqdm_notebook(temp[['idfamd5','mean_label']].values):
    if v==1 or v==0:
        if k in ip_dict:
            continue
        else:
            ip_dict[k]=v

np.save('idfamd5_dict.npy', ip_dict)

temp = train[['openudidmd5','label']].groupby('openudidmd5')['label'].agg({'mean_label':'mean','count_label':'count','sum_label':'sum'}).reset_index()
ip_dict={}
for k,v in tqdm.tqdm_notebook(temp[['openudidmd5','mean_label']].values):
    if v==1 or v==0:
        if k in ip_dict:
            continue
        else:
            ip_dict[k]=v

np.save('openudidmd5_dict.npy', ip_dict)

temp = train[['macmd5','label']].groupby('macmd5')['label'].agg({'mean_label':'mean','count_label':'count','sum_label':'sum'}).reset_index()
ip_dict={}
for k,v in tqdm.tqdm_notebook(temp[['macmd5','mean_label']].values):
    if v==1 or v==0:
        if k in ip_dict:
            continue
        else:
            ip_dict[k]=v

np.save('macmd5_dict.npy', ip_dict)