覆盖率

data/analyis/datacal.py

@@ -147,7 +147,7 @@ def cal_miss(df,feature,classes=[]):
     tmp.loc[tmp[feature] == 0, 'flag'] = '0值'
     tmp.loc[tmp[feature] > 0, 'flag'] = '非0值'
 
-    headers = classes+['flag', 'cnt', 'miss_rate']
+    headers = classes+['flag', 'cnt', 'match_rate']
     if len(classes) > 0:
         # == 分类型
         df_gp = pd.merge(
@@ -155,12 +155,12 @@ def cal_miss(df,feature,classes=[]):
             tmp.groupby(classes+['flag'])[feature].count().reset_index().rename(columns={feature: "cnt1"}),
             on=classes, how='left'
         )
-        df_gp['miss_rate'] = np.round(1-df_gp.cnt1 / df_gp.cnt, 3)
+        df_gp['match_rate'] = np.round(df_gp.cnt1 / df_gp.cnt, 3)
         df_out = df_gp
     else:
-        all = [[ '非0值', tmp.shape[0], round(1 - tmp[tmp[feature] > 0].shape[0] / tmp.shape[0], 3)],
-               [ '0值', tmp.shape[0], round(1 - tmp[tmp[feature] == 0].shape[0] / tmp.shape[0], 3)],
-               ['缺失值', tmp.shape[0], round(1 - tmp[(tmp[feature] < 0)].shape[0] / tmp.shape[0], 3)]]
+        all = [[ '非0值', tmp.shape[0], round(tmp[tmp[feature] > 0].shape[0] / tmp.shape[0], 3)],
+               [ '0值', tmp.shape[0], round( tmp[tmp[feature] == 0].shape[0] / tmp.shape[0], 3)],
+               ['缺失值', tmp.shape[0], round(tmp[(tmp[feature] < 0)].shape[0] / tmp.shape[0], 3)]]
         df_all = pd.DataFrame(all, columns=headers)
         df_out=df_all
     return df_out[headers]
\ No newline at end of file