如何使用Python为数据添加标签？

本文共计246个文字，预计阅读时间需要1分钟。

python创建标签为1的顾客数据集odue_df=df_train_stmt.loc[(df_train_stmt['AGE3']==0) | (df_train_stmt['AGE4']==0) | (df_train_stmt['AGE5']==0) | (df_train_stmt['AGE6']==0), ['XACCOUNT']]odue_df['label']=1cust_df=df_acct[df_acct['XACCOUNT'].isin(odue_df['XACCOUNT'])]

普通打标签

odue_df=df_train_stmt.loc[(df_train_stmt.AGE3>0)|(df_train_stmt.AGE4>0)|(df_train_stmt.AGE5>0)|(df_train_stmt.AGE6>0),['XACCOUNT']].drop_duplicates()
odue_df['label']=1
cust_df=df_acct[['CUSTR_NBR','XACCOUNT']].drop_duplicates()
#做合并
df_y=pd.merge(cust_df,odue_df,how='left',on='XACCOUNT').groupby('CUSTR_NBR').agg({'label':max}).reset_index().fillna(0)

使用函数来打标签

#标注标签 Label
def label(row):
if row['Date_received'] == 'null':
return -1
if row['Date'] != 'null':
td = pd.to_datetime(row['Date'], format='%Y%m%d') - pd.to_datetime(row['Date_received'], format='%Y%m%d')
if td <= pd.Timedelta(15, 'D'):
return 1
return 0

dfoff['label'] = dfoff.apply(label, axis=1)


#打标签，判断天数
def get_label(s):
s = s.split(':')
if s[0]=='null':
return 0
elif (date(int(s[0][0:4]),int(s[0][4:6]),int(s[0][6:8]))-date(int(s[1][0:4]),int(s[1][4:6]),int(s[1][6:8]))).days<=15:
return 1
else:
return -1

dataset2.label = dataset2.label.apply(get_label)