직접 만든 기능을 사용하여 모델 성능 향상

D_* = 拖欠变量
S_* = 支出变量
P_* = 支付变量
B_* = 平衡变量
R_* = 风险变量

# LOAD LIBRARIES
 import pandas as pd, numpy as np # CPU libraries
 import cudf # GPU libraries
 import matplotlib.pyplot as plt, gc, os
 
 df = cudf.read_parquet('./data.parquet')

cat_features = ["B_1","B_2","D_1","D_2","D_10","P_21","D_126","D_3","D_42","R_66","R_68"]
 num_features = [col for col in all_cols if col not in cat_features] #all features accept cateforical features.
 test_num_agg = df.groupby("customer_ID")[num_features].agg(['mean', 'std', 'min', 'max', 'last','median']) #grouping by customerID
 test_num_agg.columns = ['_'.join(x) for x in test_num_agg.columns]

cat_features = ["B_1","B_2","D_1","D_2","D_10","P_21","D_126","D_3","D_42","R_66","R_68"]
 test_cat_agg = df.groupby("customer_ID")[cat_features].agg(['count', 'last', 'nunique'])
 test_cat_agg.columns = ['_'.join(x) for x in test_cat_agg.columns]

df[feat+'_rank']=df[feat].rank(pct=True, method='min')

df[feat+'_rank']=df.groupby([cat_feat]).rank(pct=True, method='min')

features=[col for col in train.columns if col not in ['customer_ID',target]+cat_features]
 for feat1 in features:
for feat2 in features:
th=max(np.corr(feat1,Y)[0],np.corr(feat1,Y)[0]) #calculate threshold
feat3=df[feat1]-df[feat2] #difference feature
corr3=np.corr(feat3,Y)[0]
if(corr3>max(th,0.9)): #if correlation greater than max(th,0.9) we add it as feature
df[feat1+'_'+feat2]=feat3

features=[col for col in train.columns if col not in ['customer_ID',target]+cat_features]
 month_Agg=df.groupby([month])[features].agg('mean')#grouping based on month feature
 month_Agg.columns = ['_month_'.join(x) for x in month_Agg.columns]
 month_Agg.reset_index(inplace=True)
 df=df.groupby(month_Agg,notallow='month')
 for feat in features: #create composite features b taking difference
df[feat+'_'+feat+'_month_mean']=df[feat]-df[feat+'_month_mean']

features=[col for col in train.columns if col not in ['customer_ID',target]+cat_features]
 month_Agg=df.groupby([month])[features].rank(pct=True) #grouping based on month feature
 month_Agg.columns = ['_month_'.join(x) for x in month_Agg.columns]
 month_Agg.reset_index(inplace=True)
 df=pd.concat([df,month_Agg],axis=1) #concat to original dataframe

# difference function calculate the lag difference for numerical features
 #between last value and shift last value.
 def difference(groups,num_features,shift):
data=(groups[num_features].nth(-1)-groups[num_features].nth(-1*shift)).rename(columns={f: f"{f}_diff{shift}" for f in num_features})
return data
 #calculate diff features for last -2nd last, last -3rd last, last- 4th last
 def get_difference(data,num_features):
print("diff features...")
groups=data.groupby('customer_ID')
df1=difference(groups,num_features,2).fillna(0)
df2=difference(groups,num_features,3).fillna(0)
df3=difference(groups,num_features,4).fillna(0)
df1=pd.concat([df1,df2,df3],axis=1)
df1.reset_index(inplace=True)
df1.sort_values(by='customer_ID')
del df2,df3
gc.collect()
return df1train_diff = get_difference(df, num_features)

xth=3 #define the window size
 df["cumulative"]=df.groupby('customer_ID').sort_values(by=['time'],ascending=False).cumcount()
 last_info=df[df["cumulative"]<=xth]
 last_info = last_info.groupby("customer_ID")[num_features].agg(['mean', 'std', 'min', 'max', 'last','median']) #grouping by customerID
 last_info.columns = ['_'.join(x) for x in last_info.columns]

def calc_nan(df,features):
print("calculating nan_info...")
df_nan = (df[features].mul(0) + 1).fillna(0) #marke non_null values as 1 and null as zero
df_nan['customer_ID'] = df['customer_ID']
nan_sum = df_nan.groupby("customer_ID").sum().sum(axis=1) #total unknown values for a customer
nan_last = df_nan.groupby("customer_ID").last().sum(axis=1)#how many last values that are not known
del df_nan
gc.collect()
return nan_sum,nan_last