Cocktail hotfixes (#245)

* Fixes for the development branch and regularization cocktails

* Update implementation

* Fix unit tests temporarily

* Implementation update and bug fixes

* Removing unecessary code

* Addressing Ravin's comments

[refactor] Address Shuhei's comments

[refactor] Address Shuhei's comments

[refactor] Address Shuhei's comments

[refactor] Address Shuhei's comments

Author: ArlindKadra

autoPyTorch/api/base_task.py

@@ -407,7 +407,7 @@ def set_pipeline_config(self, **pipeline_config_kwargs: Any) -> None:
             None
         """
         unknown_keys = []
-        for option, value in pipeline_config_kwargs.items():
+        for option in pipeline_config_kwargs.keys():
             if option in self.pipeline_options.keys():
                 pass
             else:

autoPyTorch/api/tabular_classification.py

@@ -389,7 +389,16 @@ def search(
             y_test=y_test,
             resampling_strategy=self.resampling_strategy,
             resampling_strategy_args=self.resampling_strategy_args,
-            dataset_name=dataset_name)
+            dataset_name=dataset_name
+        )
+
+        if not isinstance(self.resampling_strategy, (CrossValTypes, HoldoutValTypes)):
+            raise ValueError(
+                'Hyperparameter optimization requires a validation split. '
+                'Expected `self.resampling_strategy` to be either '
+                '(CrossValTypes, HoldoutValTypes), but got {}'.format(self.resampling_strategy)
+            )
+
 
         return self._search(
             dataset=self.dataset,
@@ -430,23 +439,23 @@ def predict(
             raise ValueError("predict() is only supported after calling search. Kindly call first "
                              "the estimator search() method.")
 
-        X_test = self.InputValidator.feature_validator.transform(X_test)
+        X_test = self.input_validator.feature_validator.transform(X_test)
         predicted_probabilities = super().predict(X_test, batch_size=batch_size,
                                                   n_jobs=n_jobs)
 
-        if self.InputValidator.target_validator.is_single_column_target():
+        if self.input_validator.target_validator.is_single_column_target():
             predicted_indexes = np.argmax(predicted_probabilities, axis=1)
         else:
             predicted_indexes = (predicted_probabilities > 0.5).astype(int)
 
         # Allow to predict in the original domain -- that is, the user is not interested
         # in our encoded values
-        return self.InputValidator.target_validator.inverse_transform(predicted_indexes)
+        return self.input_validator.target_validator.inverse_transform(predicted_indexes)
 
     def predict_proba(self,
                       X_test: Union[np.ndarray, pd.DataFrame, List],
                       batch_size: Optional[int] = None, n_jobs: int = 1) -> np.ndarray:
-        if self.InputValidator is None or not self.InputValidator._is_fitted:
+        if self.input_validator is None or not self.input_validator._is_fitted:
             raise ValueError("predict() is only supported after calling search. Kindly call first "
                              "the estimator search() method.")
         X_test = self.InputValidator.feature_validator.transform(X_test)

autoPyTorch/api/tabular_regression.py

@@ -389,7 +389,16 @@ def search(
             y_test=y_test,
             resampling_strategy=self.resampling_strategy,
             resampling_strategy_args=self.resampling_strategy_args,
-            dataset_name=dataset_name)
+            dataset_name=dataset_name
+        )
+
+        if not isinstance(self.resampling_strategy, (CrossValTypes, HoldoutValTypes)):
+            raise ValueError(
+                'Hyperparameter optimization requires a validation split. '
+                'Expected `self.resampling_strategy` to be either '
+                '(CrossValTypes, HoldoutValTypes), but got {}'.format(self.resampling_strategy)
+            )
+
 
         return self._search(
             dataset=self.dataset,
@@ -416,14 +425,14 @@ def predict(
             batch_size: Optional[int] = None,
             n_jobs: int = 1
     ) -> np.ndarray:
-        if self.InputValidator is None or not self.InputValidator._is_fitted:
+        if self.input_validator is None or not self.input_validator._is_fitted:
             raise ValueError("predict() is only supported after calling search. Kindly call first "
                              "the estimator search() method.")
 
-        X_test = self.InputValidator.feature_validator.transform(X_test)
+        X_test = self.input_validator.feature_validator.transform(X_test)
         predicted_values = super().predict(X_test, batch_size=batch_size,
                                            n_jobs=n_jobs)
 
         # Allow to predict in the original domain -- that is, the user is not interested
         # in our encoded values
-        return self.InputValidator.target_validator.inverse_transform(predicted_values)
+        return self.input_validator.target_validator.inverse_transform(predicted_values)

autoPyTorch/data/tabular_feature_validator.py

@@ -391,7 +391,7 @@ def _get_columns_to_encode(
         feat_type = []
 
         # Make sure each column is a valid type
-        for i, column in enumerate(X.columns):
+        for column in X.columns:
             if X[column].dtype.name in ['category', 'bool']:
 
                 transformed_columns.append(column)
@@ -512,7 +512,7 @@ def infer_objects(self, X: pd.DataFrame) -> pd.DataFrame:
                     X[key] = X[key].astype(dtype.name)
                 except Exception as e:
                     # Try inference if possible
-                    self.logger.warning(f"Tried to cast column {key} to {dtype} caused {e}")
+                    self.logger.warning(f'Casting the column {key} to {dtype} caused the exception {e}')
                     pass
         else:
             X = X.infer_objects()