PSI-群体稳定性指标(离散型)

单个指标计算

• 代码

  import pandas as pddf = pd.read_csv('/Users/mengzhichao/Desktop/文件/图表/小微企业用电量数据.csv')X_train = df.sample(n=7000)
  X_test = df.sample(n=3000)
  

• 计算单个psi

  def psi_calculate_category(origin,new,feature_name):"""计算单个类别型变量的psiorigin为实际数据，new为预期数据Parameters----------------------------------------------------------------------:param               origin               DataFrame,实际数据:param               new                  DataFrame,预期数据:param               feature_name         string,需要计算PSI的字段(类别型)Returns----------------------------------------------------------------------psi:                  float,psi值psi_df:               DataFrame,psi详细Examples---------------------------------------------------------------------->>> psi,psi_df = psi_calculate_category(origin=X_train,new=X_test,feature_name='dimvl_name')"""origin_cut = origin[feature_name].value_counts(dropna=False).reset_index()origin_cut.columns = ['buckets','origin_cnt']origin_cut['feature'] = feature_nameorigin_cut = origin_cut[['feature','buckets','origin_cnt']]new_cut = new[feature_name].value_counts(dropna=False).reset_index()new_cut.columns = ['buckets','new_cnt']new_cut['feature'] = feature_namenew_cut = new_cut[['feature','buckets','new_cnt']]psi_df = pd.merge(origin_cut,new_cut,on=['feature','buckets'])# print(psi_df)# 计算占比，分子加1，防止计算PSI时分子为0（这里分母不可能为0）psi_df['origin_percent'] = (psi_df['origin_cnt'] + 1) / psi_df['origin_cnt'].sum()psi_df['new_percent']    = (psi_df['new_cnt'] + 1) / psi_df['new_cnt'].sum()psi_df['minus']          = psi_df.apply(lambda x: x['origin_percent']-x['new_percent'],axis=1)psi_df['log']            = psi_df.apply(lambda x: np.log(x['origin_percent']/x['new_percent']),axis=1)psi_df['psi_bucket']  = psi_df.apply(lambda x: x['minus'] * x['log'],axis=1)psi_df['psi']         = psi_df['psi_bucket'].sum() psi = psi_df['psi_bucket'].sum()return psi,psi_dfpsi,psi_df = psi,psi_df = psi_calculate_category(origin=X_train,new=X_test,feature_name='区域')
  

  

  

所有指标计算

• 计算所有类别型：

## 所有的类别型特征列表
all_category_feature_list = df.select_dtypes(include='object').columns.tolist()psi_list = []
psi_df_list = []
for feature in notebook.tqdm(all_category_feature_list):psi,psi_df = psi_calculate_category(X_train,X_test,feature_name=feature)psi_list.append((feature,psi))psi_df_list.append(psi_df)psi = pd.DataFrame(psi_list,columns=['feature','psi'])
psi_df = pd.concat(psi_df_list,ignore_index=False)

---