def _F_nunique_ratio(n=3):
if os.path.exists(data_path + "data/_F_nunique_ratio.feather"):
df = feather.read_dataframe(data_path +
"data/_F_nunique_ratio.feather")
return df
temp = pd.DataFrame()
temp[pri_id] = pd.concat((_train[pri_id], _test[pri_id]))
# 增加天和月份的片
df = pd.concat((op_info[[pri_id, 'day']], trans_info[[pri_id, 'day']]))
month = _F.Day2Month(df, 'day')
temp = pd.merge(temp,
_F.TopN_col_distinct_ratio(month[[pri_id, 'month', 'day']],
pri_id, 'month', 'day', n),
on=pri_id,
how='left')
df = pd.concat((op_info[[pri_id, 'time',
'day']], trans_info[[pri_id, 'time', 'day']]))
df['day_period'] = df['time'].apply(_F.TimeInterval)
temp = pd.merge(
temp,
_F.TopN_col_distinct_ratio(df[[pri_id, 'day_period', 'day']], pri_id,
'day_period', 'day', n))
# topN ratio
for col in [
'geo_code', 'ip1', 'ip1_sub', 'mac1', 'merchant', 'ip2', 'ip2_sub',
'mode', 'mac2', 'os', 'channel', 'trans_type1', 'trans_type2',
'code1', 'code2', 'market_code', 'market_type', 'device_code1',
'device_code2', 'device_code3', 'wifi'
]:
if col in [
'merchant', 'channel', 'trans_type1', 'trans_type2', 'code1',
'code2', 'market_code', 'market_type'
]:
df = trans_info[[pri_id, col, 'day']]
elif col in ['ip2', 'ip2_sub', 'mode', 'mac2', 'os', 'wifi']:
df = op_info[[pri_id, col, 'day']]
else:
df = pd.concat((op_info[[pri_id, col,
'day']], trans_info[[pri_id, col,
'day']]))
temp = pd.merge(temp,
_F.TopN_col_distinct_ratio(df, pri_id, col, 'day', n),
on=pri_id,
how='left')
feather.write_dataframe(temp, data_path + "data/_F_nunique_ratio.feather")
return temp
