fix tests

Author: ravinkohli

autoPyTorch/api/base_task.py

@@ -256,6 +256,7 @@ def __init__(
         self.input_validator: Optional[BaseInputValidator] = None
 
         self.search_space_updates = search_space_updates
+
         if search_space_updates is not None:
             if not isinstance(self.search_space_updates,
                               HyperparameterSearchSpaceUpdates):

autoPyTorch/evaluation/train_evaluator.py

@@ -196,24 +196,24 @@ def fit_predict_and_loss(self) -> None:
             additional_run_info = pipeline.get_additional_run_info() if hasattr(
                 pipeline, 'get_additional_run_info') else {}
 
-            # add learning curve of configurations to additional_run_info
-            if isinstance(pipeline, TabularClassificationPipeline):
-                if hasattr(pipeline.named_steps['trainer'], 'run_summary'):
-                    run_summary = pipeline.named_steps['trainer'].run_summary
-                    split_types = ['train', 'val', 'test']
-                    run_summary_dict = dict(
-                        run_summary={},
-                        budget=self.budget,
-                        seed=self.seed,
-                        config_id=self.configuration.config_id,
-                        num_run=self.num_run
-                        )
-                    for split_type in split_types:
-                        run_summary_dict['run_summary'][f'{split_type}_loss'] = run_summary.performance_tracker.get(f'{split_type}_loss', None)
-                        run_summary_dict['run_summary'][f'{split_type}_metrics'] = run_summary.performance_tracker.get(f'{split_type}_metrics', None)
-                    self.logger.debug(f"run_summary_dict {json.dumps(run_summary_dict)}")
-                    with open(os.path.join(self.backend.temporary_directory, 'run_summary.txt'), 'a') as file:
-                        file.write(f"{json.dumps(run_summary_dict)}\n")
+            # # add learning curve of configurations to additional_run_info
+            # if isinstance(pipeline, TabularClassificationPipeline):
+            #     if hasattr(pipeline.named_steps['trainer'], 'run_summary'):
+            #         run_summary = pipeline.named_steps['trainer'].run_summary
+            #         split_types = ['train', 'val', 'test']
+            #         run_summary_dict = dict(
+            #             run_summary={},
+            #             budget=self.budget,
+            #             seed=self.seed,
+            #             config_id=self.configuration.config_id,
+            #             num_run=self.num_run
+            #             )
+            #         for split_type in split_types:
+            #             run_summary_dict['run_summary'][f'{split_type}_loss'] = run_summary.performance_tracker.get(f'{split_type}_loss', None)
+            #             run_summary_dict['run_summary'][f'{split_type}_metrics'] = run_summary.performance_tracker.get(f'{split_type}_metrics', None)
+            #         self.logger.debug(f"run_summary_dict {json.dumps(run_summary_dict)}")
+            #         with open(os.path.join(self.backend.temporary_directory, 'run_summary.txt'), 'a') as file:
+            #             file.write(f"{json.dumps(run_summary_dict)}\n")
 
             status = StatusType.SUCCESS
 

autoPyTorch/pipeline/components/preprocessing/tabular_preprocessing/coalescer/base_coalescer.py

@@ -12,7 +12,6 @@ def __init__(self) -> None:
         self._processing = True
         self.add_fit_requirements([
             FitRequirement('categorical_columns', (List,), user_defined=True, dataset_property=True),
-            FitRequirement('categories', (List,), user_defined=True, dataset_property=True)
         ])
 
     def transform(self, X: Dict[str, Any]) -> Dict[str, Any]:

autoPyTorch/pipeline/components/preprocessing/tabular_preprocessing/feature_preprocessing/utils.py

@@ -82,17 +82,15 @@ def percentage_value_range_to_integer_range(
         else:
             log = hyperparameter_search_space.log
 
-        min_hyperparameter_value = hyperparameter_search_space.value_range[0]
-        if len(hyperparameter_search_space.value_range) > 1:
-            max_hyperparameter_value = hyperparameter_search_space.value_range[1]
-        else:
-            max_hyperparameter_value = hyperparameter_search_space.value_range[0]
+        value_range = (
+            floor(float(hyperparameter_search_space.value_range[0]) * n_features),
+            floor(float(hyperparameter_search_space.value_range[-1]) * n_features)) \
+            if len(hyperparameter_search_space.value_range) == 2 else \
+                (floor(float(hyperparameter_search_space.value_range[0]) * n_features),)
 
         hyperparameter_search_space = HyperparameterSearchSpace(
             hyperparameter=hyperparameter_name,
-            value_range=(
-                floor(float(min_hyperparameter_value) * n_features),
-                floor(float(max_hyperparameter_value) * n_features)),
+            value_range=value_range,
             default_value=ceil(float(hyperparameter_search_space.default_value) * n_features),
             log=log)
     else:

autoPyTorch/pipeline/components/training/trainer/__init__.py

@@ -453,7 +453,7 @@ def _fit(self, X: Dict[str, Any], y: Any = None, **kwargs: Any) -> 'TrainerChoic
 
             # change model
             update_model_state_dict_from_swa(X['network'], self.choice.swa_model.state_dict())
-            if self.choice.use_snapshot_ensemble:
+            if self.choice.use_snapshot_ensemble and len(self.choice.model_snapshots) > 0:
                 # we update only the last network which pertains to the stochastic weight averaging model
                 swa_utils.update_bn(X['train_data_loader'], self.choice.model_snapshots[-1].double())
 

autoPyTorch/pipeline/tabular_regression.py

@@ -17,6 +17,9 @@
 from autoPyTorch.pipeline.components.preprocessing.tabular_preprocessing.TabularColumnTransformer import (
     TabularColumnTransformer
 )
+from autoPyTorch.pipeline.components.preprocessing.tabular_preprocessing.column_splitting.ColumnSplitter import (
+    ColumnSplitter
+)
 from autoPyTorch.pipeline.components.preprocessing.tabular_preprocessing.coalescer import (
     CoalescerChoice
 )
@@ -234,8 +237,9 @@ def _get_pipeline_steps(
 
         steps.extend([
             ("imputer", SimpleImputer(random_state=self.random_state)),
-            ("variance_threshold", VarianceThreshold(random_state=self.random_state)),
-            ("coalescer", CoalescerChoice(default_dataset_properties, random_state=self.random_state)),
+            # ("variance_threshold", VarianceThreshold(random_state=self.random_state)),
+            # ("coalescer", CoalescerChoice(default_dataset_properties, random_state=self.random_state)),
+            ("column_splitter", ColumnSplitter(random_state=self.random_state)),
             ("encoder", EncoderChoice(default_dataset_properties, random_state=self.random_state)),
             ("scaler", ScalerChoice(default_dataset_properties, random_state=self.random_state)),
             ("feature_preprocessor", FeatureProprocessorChoice(default_dataset_properties,