import woe.feature_process as fp
import woe.eval as eval
 
#%% woe分箱, iv and transform
data_woe = data #用于存储所有数据的woe值
civ_list = []
n_positive = sum(data['target'])
n_negtive = len(data) - n_positive
for column in list(data.columns[1:]):
 if data[column].dtypes == 'object':
 civ = fp.proc_woe_discrete(data, column, n_positive, n_negtive, 0.05*len(data), alpha=0.05)
 else:  
 civ = fp.proc_woe_continuous(data, column, n_positive, n_negtive, 0.05*len(data), alpha=0.05)
 civ_list.append(civ)
 data_woe[column] = fp.woe_trans(data[column], civ)
 
civ_df = eval.eval_feature_detail(civ_list,'output_feature_detail_0315.csv')
#删除iv值过小的变量
iv_thre = 0.001
iv = civ_df[['var_name','iv']].drop_duplicates()
x_columns = iv.var_name[iv.iv > iv_thre]

proc_woe_discrete(df,var,global_bt,global_gt,min_sample,alpha=0.01)

proc_woe_continuous(df,var,global_bt,global_gt,min_sample,alpha=0.01)

class InfoValue(object):
 '''
 InfoValue Class
 '''
 def __init__(self):
 self.var_name = []
 self.split_list = []
 self.iv = 0
 self.woe_list = []
 self.iv_list = []
 self.is_discrete = 0
 self.sub_total_sample_num = []
 self.positive_sample_num = []
 self.negative_sample_num = []
 self.sub_total_num_percentage = []
 self.positive_rate_in_sub_total = []
 self.negative_rate_in_sub_total = []
 
 def init(self,civ):
 self.var_name = civ.var_name
 self.split_list = civ.split_list
 self.iv = civ.iv
 self.woe_list = civ.woe_list
 self.iv_list = civ.iv_list
 self.is_discrete = civ.is_discrete
 self.sub_total_sample_num = civ.sub_total_sample_num
 self.positive_sample_num = civ.positive_sample_num
 self.negative_sample_num = civ.negative_sample_num
 self.sub_total_num_percentage = civ.sub_total_num_percentage
 self.positive_rate_in_sub_total = civ.positive_rate_in_sub_total
 self.negative_rate_in_sub_total = civ.negative_rate_in_sub_total

eval.eval_feature_detail(Info_Value_list,out_path=False)