data-to-loacl

main_spider.py

@@ -54,6 +54,7 @@ class LightGBM(object):
         self.model = "models/lightgbm_0401_spider.bin"
         self.flag = flag
         self.dt = dt
+        self.label_mapping = {}
 
     def read_data(self, path, yc=None):
         """
@@ -75,6 +76,7 @@ class LightGBM(object):
             features[key] = pd.to_numeric(features[key], errors="coerce")
         for key in self.str_columns:
             features[key] = self.label_encoder.fit_transform(features[key])
+            # self.label_mapping[key] = dict(zip(self.label_encoder.classes_, self.label_encoder.transform(self.label_encoder.classes_)))
         return features, labels, video_ids, video_titles
 
     def best_params(self):
@@ -184,6 +186,8 @@ class LightGBM(object):
         fw.close()
         # 水平合并
         df_concatenated = pd.concat([ids, titles, x, true_label_df, pred_score_df, pred_label_df], axis=1)
+        for key in self.str_columns:
+            df_concatenated[key] = self.label_encoder.inverse_transform(df_concatenated[key])
         df_concatenated.to_excel("data/predict_data/spider_predict_result_{}.xlsx".format(dt), index=False)
 
     def feature_importance(self):