def Process1(df):
pri_id = "企业名称"
res = pd.DataFrame()
res[pri_id] = df[pri_id].unique()
# 转换币种
df = prep.Convert_money(df)
# 提取注册资金特征（最大值，最小值，均值，方差）
res = pd.merge(res,fea.GetValAvg(df,pri_id,"注册资金(元)"),on=pri_id)
res = pd.merge(res,fea.GetValMaxMin(df,pri_id,"注册资金(元)"),on=pri_id)
res = pd.merge(res,fea.GetValVar(df,pri_id,"注册资金(元)"),on=pri_id)
# 提取类别特征
num_fea = ['注册资金(元)',"出资比例"]
cat_fea = [col for col in df.columns if col != pri_id and col not in num_fea]
for col in cat_fea:
res = pd.merge(res,fea.GetCategroicalCount(df,pri_id,col),on=pri_id)
# 法定代表人和首席代表标志为空统计
res = pd.merge(res,fea.GetValNaCount(df,pri_id,"法定代表人标志","姓名"),on=pri_id)
res = pd.merge(res,fea.GetValNaCount(df,pri_id,"首席代表标志","姓名"),on=pri_id)
# 统计 相应职务个树
res = pd.merge(res,fea.CatRowsToCols(df,pri_id,"职务","姓名"))
# 提取出资比例（最大值，最小值，均值，方差）
res = pd.merge(res,fea.GetValAvg(df,pri_id,"出资比例"),on=pri_id)
res = pd.merge(res,fea.GetValMaxMin(df,pri_id,"出资比例"),on=pri_id)
res = pd.merge(res,fea.GetValVar(df,pri_id,"出资比例"),on=pri_id)
return res
def ProcessOperation(df):
data = pd.DataFrame()
data[pri_id] = pd.concat((_train[pri_id], _test[pri_id]))
# day处理 (分为上 中 下旬)
temp = _F.MonthCount(df, pri_id)
data = pd.merge(data, temp, on=pri_id, how='left')
# mode
temp = _F.CatRowsToCols(df, pri_id, 'mode', 'os')
data = pd.merge(data, temp, on=pri_id, how='left')
# success
temp = _F.CatRowsToCols(df, pri_id, 'success', 'os')
data = pd.merge(data, temp, on=pri_id, how='left')
# version
temp = _F.CatRowsToCols(df, pri_id, 'version', 'os')
data = pd.merge(data, temp, on=pri_id, how='left')
# time
df['day_period'] = df['time'].apply(_F.TimeInterval)
temp = _F.CatRowsToCols(df, pri_id, 'day_period', 'os')
data = pd.merge(data, temp, on=pri_id, how='left')
cols = [
'device2', 'ip1', 'ip2', 'mac1', 'mac2', 'device_code1',
'device_code2', 'device_code3'
]
for col in cols:
# device2 (用户有多少不同型号的设备)
temp = _F.GetCount(df, pri_id, col, 'os')
data = pd.merge(data, temp, on=pri_id, how='left')
# 统计地理位置次数
temp = _F.CountWS(df)
data = pd.merge(data, temp, on=pri_id, how='left')
#
# # 危险设备（安卓）
# temp = _F.CountDangerous(df,label,pri_id,'Tag','device_code1','time',500)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 危险设备（安卓）
# temp = _F.CountDangerous(df,label,pri_id,'Tag','device_code2','time',500)
# data = pd.merge(data,temp,on=pri_id,how='left')
#
# # 危险设备（苹果）
# temp = _F.CountDangerous(df,label,pri_id,'Tag','device_code3','time',200)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计危险地理位置
# temp = _F.CountDangerous(df,label,pri_id,'Tag','geo_code','time',500)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计危险操作类型
# temp = _F.CountDangerous(df,label,pri_id,'Tag','mode','time',10000)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计危险mac1地址
# temp = _F.CountDangerous(df,label,pri_id,'Tag','mac1','time',600)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计危险mac2地址
# temp = _F.CountDangerous(df,label,pri_id,'Tag','mac2','time',1000)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计危险ip1地址
# temp = _F.CountDangerous(df,label,pri_id,'Tag','ip1','time',1000)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计危险ip1_sub地址
# temp = _F.CountDangerous(df,label,pri_id,'Tag','ip1_sub','time',1000)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计危险ip2_sub地址
# temp = _F.CountDangerous(df,label,pri_id,'Tag','ip2_sub','time',50)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计每个用户最常出现的经纬度
# temp = _F.PositionWS(df)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 地理位置聚类
data = data.fillna(0)
return data
def ProcessTrans(df):
data = pd.DataFrame()
data[pri_id] = pd.concat((_train[pri_id], _test[pri_id]))
# channel 统计次数
temp = _F.CatRowsToCols(df, pri_id, 'channel', 'day')
data = pd.merge(data, temp, on=pri_id, how='left')
# day
temp = _F.MonthCount(df, pri_id)
data = pd.merge(data, temp, on=pri_id, how='left')
# time
df['day_period'] = df['time'].apply(_F.TimeInterval)
temp = _F.CatRowsToCols(df, pri_id, 'day_period', 'day')
data = pd.merge(data, temp, on=pri_id, how='left')
# trans_amt (交易金额)(最大值，最小值，平均值)
# temp = _F.GetValMaxMin(df,pri_id,'trans_amt')
# data = pd.merge(data,temp,on=pri_id,how='left')
# temp = _F.GetValAvg(df,pri_id,'trans_amt')
# data = pd.merge(data,temp,on=pri_id,how='left')
# temp = _F.GetValSum(df,pri_id,'trans_amt')
# data = pd.merge(data,temp,on=pri_id,how='left')
# 计算不同的次数
cols = [
'device2', 'ip1', 'mac1', 'device_code1', 'device_code2',
'device_code3', 'amt_src1', 'amt_src2', 'merchant', 'trans_type1',
'trans_type2', 'acc_id1', 'market_type', 'market_code'
]
for col in cols:
temp = _F.GetCount(df, pri_id, col, 'day')
data = pd.merge(data, temp, on=pri_id, how='left')
# 脱敏后的余额(最大值，最小值，平均值)
# temp = _F.GetValMaxMin(df,pri_id,'bal')
# data = pd.merge(data,temp,on=pri_id,how='left')
# temp = _F.GetValAvg(df,pri_id,'bal')
# data = pd.merge(data,temp,on=pri_id,how='left')
# temp = _F.GetValSum(df,pri_id,'bal')
# data = pd.merge(data,temp,on=pri_id,how='left')
# 危险设备（安卓）
# temp = _F.CountDangerous(df,label,pri_id,'Tag','device_code1','time',100)
# data = pd.merge(data,temp,on=pri_id,how='left')
#
# # 危险设备（安卓）
# temp = _F.CountDangerous(df,label,pri_id,'Tag','device_code2','time',100)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 危险设备（苹果）
# temp = _F.CountDangerous(df,label,pri_id,'Tag','device_code3','time',80)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计危险地理位置
# temp = _F.CountDangerous(df,label,pri_id,'Tag','geo_code','time',200)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计危险商家
# temp = _F.CountDangerous(df,label,pri_id,'Tag','merchant','time',1000)
# data = pd.merge(data,temp,on=pri_id,how='left')
#
# # 统计地理位置次数
temp = _F.CountWS(df)
data = pd.merge(data, temp, on=pri_id, how='left')
#
# 统计危险mac1地址
# temp = _F.CountDangerous(df,label,pri_id,'Tag','mac1','time',600)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计危险ip1地址
# temp = _F.CountDangerous(df,label,pri_id,'Tag','ip1','time',1000)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计危险ip1_sub地址
# temp = _F.CountDangerous(df,label,pri_id,'Tag','ip1_sub','time',1000)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计危险交易账户
# temp = _F.CountDangerous(df,label,pri_id,'Tag','acc_id1','time',200)
# data = pd.merge(data,temp,on=pri_id,how='left')
#
# # 统计危险转出账户
# temp = _F.CountDangerous(df,label,pri_id,'Tag','acc_id2','time',100)
# data = pd.merge(data,temp,on=pri_id,how='left')
#
# # 统计危险转入账户
# temp = _F.CountDangerous(df,label,pri_id,'Tag','acc_id3','time',100)
# data = pd.merge(data,temp,on=pri_id,how='left')
# 统计每个用户最常出现的经纬度
# temp = _F.PositionWS(df)
# data = pd.merge(data,temp,on=pri_id,how='left')
data = data.fillna(0)
return data
