评分卡模型阈值表（接上篇）

前言

接上篇：评分卡模型案例（GiveMeSomeCredit，kaggle数据）（自己练习版本）-优快云博客

通过评分卡，可以对数据记录进行评分。模型投产时，需要设定一个评分阈值，将低于评分阈值的客户拒绝。

一、计算信用评分

全量样本进行打分

# 本段代码的目的是把输入数据映射到分箱，并且选取相应的分值来计算最后的信用评分
def str_to_int(s):
    if s == '-inf':
        return -999999999.0
    elif s=='inf':
        return 999999999.0
    else:
        return float(s)
    
def map_value_to_bin(feature_value,feature_to_bin):
    for idx, row in feature_to_bin.iterrows():
        bins = str(row['Binning'])
        left_open = bins[0]=="("
        right_open = bins[-1]==")"
        binnings = bins[1:-1].split(',')
        in_range = True
        # check left bound
        if left_open:
            if feature_value<= str_to_int(binnings[0]):
                in_range = False   
        else:
            if feature_value< str_to_int(binnings[0]):
                in_range = False   
        #check right bound
        if right_open:
            if feature_value>= str_to_int(binnings[1]):
                in_range = False 
        else:
            if feature_value> str_to_int(binnings[1]):
                in_range = False   
        if in_range:
            return row['Binning']
    return null

def map_to_score(df,score_card):
    scored_columns = list(score_card['Variable'].unique())
    score = 0
    for col in scored_columns:
        feature_to_bin = score_card[score_card['Variable']==col]
        feature_value = df[col]
        selected_bin = map_value_to_bin(feature_value,feature_to_bin)
        selected_record_in_scorecard = feature_to_bin[feature_to_bin['Binning'] == selected_bin]
        score += selected_record_in_scorecard['Score'].iloc[0]
    return score  

def calculate_score_with_card(df,score_card,A):
    df['score'] = df.apply(map_to_score,args=(score_card,),axis=1)
    df['score'] = df['score']+A
    df['score'] = df['score'].astype(int)
    return df

df_score001 = calculate_score_with_card(df_train,score_card,A)

二、计算阈值表

#----阈值表计算函数-----
def cal_score_threshold_tb(score_df,bin_step=10,is_bad_col_name='SeriousDlqin2yrs',score_col_name='score'):
    # -----计算分组起始结束字段--------------
    bin_start = math.trunc(score_df[score_col_name].min()/bin_step)*bin_step                     
    bin_end   =  math.trunc(score_df[score_col_name].max()/bin_step+1)*bin_step
    score_thd = pd.DataFrame(columns=['分组名称','本组客户','本组好客户','本组坏客户'])         
    #-----统计分组内的好坏客户个数-------
    for cur_bin in range(bin_start,bin_end,bin_step):
        cur_bin_name ='['+str(cur_bin)+'-'+str(cur_bin+bin_step)+')'
        cur_score_df = score_df[(score_df[score_col_name]>=cur_bin)&(score_df[score_col_name]<cur_bin+bin_step)][is_bad_col_name]
        bad_cn       = cur_score_df.sum()
        cn           = cur_score_df.shape[0]
        score_thd.loc[score_thd.shape[0]]=[cur_bin_name,cn,cn-bad_cn,bad_cn]
    #------计算阈值表其它字段-------------------    
    score_thd['总客户']      = score_thd['本组客户'].sum()
    score_thd['总好客户']    = score_thd['本组好客户'].sum()
    score_thd['总坏客户']    = score_thd['本组坏客户'].sum()
    score_thd['阈值']        = score_thd['分组名称'].apply(lambda x: '<'+x.split('-')[1].replace(')',''))  
    score_thd['损失客户']    = score_thd['本组客户'].cumsum()
    score_thd['损失客户%']   = score_thd['损失客户']/score_thd['总客户']
    score_thd['损失好客户']  = score_thd['本组好客户'].cumsum()
    score_thd['损失好客户%'] = score_thd['损失好客户']/score_thd['总好客户']
    score_thd['剔除坏客户']  = score_thd['本组坏客户'].cumsum()
    score_thd['剔除坏客户%'] = score_thd['剔除坏客户']/score_thd['总坏客户']
    tmp = score_thd['本组客户'].copy()
    tmp[tmp==0] = 1
    score_thd['本组坏客户占比']       = score_thd['本组坏客户']/tmp
    score_thd['损失客户中坏客户占比'] = score_thd['剔除坏客户']/score_thd['损失客户']
    return score_thd

# --------计算分数阈值表---------------
score_df  = df_score001[['score','SeriousDlqin2yrs']]
score_thd = cal_score_threshold_tb(score_df,bin_step=20)

输出如下： 

	分组名称	本组客户	本组好客户	本组坏客户	阈值	损失客户	损失客户%	损失好客户	损失好客户%	剔除坏客户	剔除坏客户%	本组坏客户占比	损失客户中坏客户占比
0	[300-320)	15	4	11	<320	15	0.01%	4	0.00%	11	0.11%	73.33%	73.33%
1	[320-340)	163	40	123	<340	178	0.12%	44	0.03%	134	1.36%	75.46%	75.28%
2	[340-360)	257