Fix spelling mistake

src/gui_version/compatibility_of_input_datasets.py

@@ -213,14 +213,14 @@ class comparison_training_prediction_dataset:
     
         columns = self.pred.columns
         # Regular expression to match "<feature>_<value>_encoded"
-        pattern = re.compile(r"^(.*?)(_?\d+)?_encoded$")
+        pattern = re.compile(r"^(.*?)(_?\d+)?_encode$")
         encoded_features = {pattern.match(col).group(1) for col in columns if pattern.match(col)}
         
         self.logger.info('Identified encoded features: ' + str(encoded_features))
         count = 0
         for feature in encoded_features:
             
-            feature_cols = [col for col in self.pred.columns if col.startswith(feature) and col.endswith("_encoded")]
+            feature_cols = [col for col in self.pred.columns if col.startswith(feature) and col.endswith("_encode")]
             all_zero_rows = (self.pred[feature_cols] == 0).all(axis=1)
             all_zero_rows = self.pred.index[all_zero_rows].tolist()
             self.idx = list(set(self.idx + all_zero_rows))
@@ -235,6 +235,9 @@ class comparison_training_prediction_dataset:
         """
 
         self.pred = pd.concat([self.xy, self.pred], axis=1)
+        
+        self.logger.info('Features in the prediction dataset: ' + str(self.pred.columns.tolist()))
+        
         pred = self.pred.to_numpy()
         char_features = features_to_char(self.pred.columns)
 
@@ -272,7 +275,7 @@ class comparison_training_prediction_dataset:
             os.remove(outfile)
             
         self.train = pd.concat([self.xy_train, self.train], axis=1)
-
+        self.logger.info('Features in the training dataset: ' + str(self.train.columns.tolist()))
         # Save dataframe as csv
         self.train.to_csv(outfile, sep=',', index=False)
         self.logger.info('Training dataset saved')

src/plain_scripts/compatibility_of_input_datasets.py

@@ -193,14 +193,14 @@ class comparison_training_prediction_dataset:
     
         columns = self.pred.columns
         # Regular expression to match "<feature>_<value>_encoded"
-        pattern = re.compile(r"^(.*?)(_?\d+)?_encoded$")
+        pattern = re.compile(r"^(.*?)(_?\d+)?_encode$")
         encoded_features = {pattern.match(col).group(1) for col in columns if pattern.match(col)}
-        
+        print(encoded_features)
         self.logger.info('Identified encoded features: ' + str(encoded_features))
         count = 0
         for feature in encoded_features:
             
-            feature_cols = [col for col in self.pred.columns if col.startswith(feature) and col.endswith("_encoded")]
+            feature_cols = [col for col in self.pred.columns if col.startswith(feature) and col.endswith("_encode")]
             all_zero_rows = (self.pred[feature_cols] == 0).all(axis=1)
             all_zero_rows = self.pred.index[all_zero_rows].tolist()
             self.idx = list(set(self.idx + all_zero_rows))
@@ -215,6 +215,7 @@ class comparison_training_prediction_dataset:
         """
 
         self.pred = pd.concat([self.xy, self.pred], axis=1)
+        self.logger.info('Features in the prediction dataset: ' + str(self.pred.columns.tolist()))
         pred = self.pred.to_numpy()
         char_features = features_to_char(self.pred.columns)
 
@@ -252,6 +253,7 @@ class comparison_training_prediction_dataset:
             os.remove(outfile)
 
         self.train = pd.concat([self.xy_train, self.train], axis=1)
+        self.logger.info('Features in the training dataset: ' + str(self.train.columns.tolist()))
 
         # Save dataframe as csv
         self.train.to_csv(outfile, sep=',', index=False)