[back] Get back to the original name to make the PR review procedure easier

Author: nabenabe0928

autoPyTorch/api/base_task.py

@@ -34,7 +34,7 @@
     STRING_TO_TASK_TYPES,
 )
 from autoPyTorch.datasets.base_dataset import BaseDataset
-from autoPyTorch.datasets.resampling_strategy import CrossValTypes, HoldoutTypes
+from autoPyTorch.datasets.resampling_strategy import CrossValTypes, HoldoutValTypes
 from autoPyTorch.ensemble.ensemble_builder import EnsembleBuilderManager
 from autoPyTorch.ensemble.ensemble_selection import EnsembleSelection
 from autoPyTorch.ensemble.singlebest_ensemble import SingleBest
@@ -138,7 +138,7 @@ def __init__(
         include_components: Optional[Dict] = None,
         exclude_components: Optional[Dict] = None,
         backend: Optional[Backend] = None,
-        resampling_strategy: Union[CrossValTypes, HoldoutTypes] = HoldoutTypes.holdout,
+        resampling_strategy: Union[CrossValTypes, HoldoutValTypes] = HoldoutValTypes.holdout_validation,
         resampling_strategy_args: Optional[Dict[str, Any]] = None,
         search_space_updates: Optional[HyperparameterSearchSpaceUpdates] = None,
         task_type: Optional[str] = None
@@ -1171,7 +1171,7 @@ def predict(
         assert self.ensemble_ is not None, "Load models should error out if no ensemble"
         self.ensemble_ = cast(Union[SingleBest, EnsembleSelection], self.ensemble_)
 
-        if isinstance(self.resampling_strategy, HoldoutTypes):
+        if isinstance(self.resampling_strategy, HoldoutValTypes):
             models = self.models_
         elif isinstance(self.resampling_strategy, CrossValTypes):
             models = self.cv_models_

autoPyTorch/api/tabular_classification.py

@@ -15,7 +15,7 @@
 from autoPyTorch.datasets.base_dataset import BaseDataset
 from autoPyTorch.datasets.resampling_strategy import (
     CrossValTypes,
-    HoldoutTypes,
+    HoldoutValTypes,
 )
 from autoPyTorch.datasets.tabular_dataset import TabularDataset
 from autoPyTorch.pipeline.tabular_classification import TabularClassificationPipeline
@@ -72,7 +72,7 @@ def __init__(
         delete_output_folder_after_terminate: bool = True,
         include_components: Optional[Dict] = None,
         exclude_components: Optional[Dict] = None,
-        resampling_strategy: Union[CrossValTypes, HoldoutTypes] = HoldoutTypes.holdout,
+        resampling_strategy: Union[CrossValTypes, HoldoutValTypes] = HoldoutValTypes.holdout_validation,
         resampling_strategy_args: Optional[Dict[str, Any]] = None,
         backend: Optional[Backend] = None,
         search_space_updates: Optional[HyperparameterSearchSpaceUpdates] = None

autoPyTorch/api/tabular_regression.py

@@ -15,7 +15,7 @@
 from autoPyTorch.datasets.base_dataset import BaseDataset
 from autoPyTorch.datasets.resampling_strategy import (
     CrossValTypes,
-    HoldoutTypes,
+    HoldoutValTypes,
 )
 from autoPyTorch.datasets.tabular_dataset import TabularDataset
 from autoPyTorch.pipeline.tabular_regression import TabularRegressionPipeline
@@ -64,7 +64,7 @@ def __init__(
             delete_output_folder_after_terminate: bool = True,
             include_components: Optional[Dict] = None,
             exclude_components: Optional[Dict] = None,
-            resampling_strategy: Union[CrossValTypes, HoldoutTypes] = HoldoutTypes.holdout,
+            resampling_strategy: Union[CrossValTypes, HoldoutValTypes] = HoldoutValTypes.holdout_validation,
             resampling_strategy_args: Optional[Dict[str, Any]] = None,
             backend: Optional[Backend] = None,
             search_space_updates: Optional[HyperparameterSearchSpaceUpdates] = None

autoPyTorch/datasets/base_dataset.py

@@ -14,7 +14,7 @@
 import torchvision
 
 from autoPyTorch.constants import CLASSIFICATION_OUTPUTS, STRING_TO_OUTPUT_TYPES
-from autoPyTorch.datasets.resampling_strategy import CrossValTypes, HoldoutTypes
+from autoPyTorch.datasets.resampling_strategy import CrossValTypes, HoldoutValTypes
 from autoPyTorch.utils.common import FitRequirement
 
 BaseDatasetInputType = Union[Tuple[np.ndarray, np.ndarray], Dataset]
@@ -69,7 +69,7 @@ def __init__(
         dataset_name: Optional[str] = None,
         val_tensors: Optional[BaseDatasetInputType] = None,
         test_tensors: Optional[BaseDatasetInputType] = None,
-        resampling_strategy: Union[CrossValTypes, HoldoutTypes] = HoldoutTypes.holdout,
+        resampling_strategy: Union[CrossValTypes, HoldoutValTypes] = HoldoutValTypes.holdout_validation,
         resampling_strategy_args: Optional[Dict[str, Any]] = None,
         seed: Optional[int] = 42,
         train_transforms: Optional[torchvision.transforms.Compose] = None,
@@ -85,8 +85,8 @@ def __init__(
                 validation data
             test_tensors (An optional tuple of objects that have a __len__ and a __getitem__ attribute):
                 test data
-            resampling_strategy (Union[CrossValTypes, HoldoutTypes]),
-                (default=HoldoutTypes.holdout):
+            resampling_strategy (Union[CrossValTypes, HoldoutValTypes]),
+                (default=HoldoutValTypes.holdout_validation):
                 strategy to split the training data.
             resampling_strategy_args (Optional[Dict[str, Any]]):
                 arguments required for the chosen resampling strategy.
@@ -196,7 +196,7 @@ def _get_indices(self) -> np.ndarray:
 
     def _process_resampling_strategy_args(self) -> None:
         if not any(isinstance(self.resampling_strategy, val_type)
-                   for val_type in [HoldoutTypes, CrossValTypes]):
+                   for val_type in [HoldoutValTypes, CrossValTypes]):
             raise ValueError(f"resampling_strategy {self.resampling_strategy} is not supported.")
 
         if self.resampling_strategy_args is not None and \
@@ -229,7 +229,7 @@ def get_splits_from_resampling_strategy(self) -> List[Tuple[List[int], List[int]
 
         labels_to_stratify = self.train_tensors[-1] if self.is_stratify else None
 
-        if isinstance(self.resampling_strategy, HoldoutTypes):
+        if isinstance(self.resampling_strategy, HoldoutValTypes):
             val_share = self.resampling_strategy_args['val_share']
 
             return self.resampling_strategy(

autoPyTorch/datasets/image_dataset.py

@@ -23,7 +23,7 @@
 from autoPyTorch.datasets.base_dataset import BaseDataset
 from autoPyTorch.datasets.resampling_strategy import (
     CrossValTypes,
-    HoldoutTypes,
+    HoldoutValTypes,
 )
 
 IMAGE_DATASET_INPUT = Union[Dataset, Tuple[Union[np.ndarray, List[str]], np.ndarray]]
@@ -39,8 +39,8 @@ class ImageDataset(BaseDataset):
             validation data
         test (Union[Dataset, Tuple[Union[np.ndarray, List[str]], np.ndarray]]):
             testing data
-        resampling_strategy (Union[CrossValTypes, HoldoutTypes]),
-            (default=HoldoutTypes.holdout):
+        resampling_strategy (Union[CrossValTypes, HoldoutValTypes]),
+            (default=HoldoutValTypes.holdout_validation):
             strategy to split the training data.
         resampling_strategy_args (Optional[Dict[str, Any]]):
             arguments required for the chosen resampling strategy.
@@ -56,7 +56,7 @@ def __init__(self,
                  train: IMAGE_DATASET_INPUT,
                  val: Optional[IMAGE_DATASET_INPUT] = None,
                  test: Optional[IMAGE_DATASET_INPUT] = None,
-                 resampling_strategy: Union[CrossValTypes, HoldoutTypes] = HoldoutTypes.holdout,
+                 resampling_strategy: Union[CrossValTypes, HoldoutValTypes] = HoldoutValTypes.holdout_validation,
                  resampling_strategy_args: Optional[Dict[str, Any]] = None,
                  seed: Optional[int] = 42,
                  train_transforms: Optional[torchvision.transforms.Compose] = None,

autoPyTorch/datasets/resampling_strategy.py

@@ -25,7 +25,7 @@ class _ResamplingStrategyArgs(NamedTuple):
 
 class HoldoutFuncs():
     @staticmethod
-    def holdout(
+    def holdout_validation(
         random_state: np.random.RandomState,
         val_share: float,
         indices: np.ndarray,
@@ -51,7 +51,7 @@ class CrossValFuncs():
     }
 
     @staticmethod
-    def k_fold(
+    def k_fold_cross_validation(
         random_state: np.random.RandomState,
         num_splits: int,
         indices: np.ndarray,
@@ -106,18 +106,18 @@ class CrossValTypes(Enum):
     and is not supposed to be instantiated.
 
     Examples: This class is supposed to be used as follows
-    >>> cv_type = CrossValTypes.k_fold
+    >>> cv_type = CrossValTypes.k_fold_cross_validation
     >>> print(cv_type.name)
 
-    k_fold
+    k_fold_cross_validation
 
     >>> for cross_val_type in CrossValTypes:
             print(cross_val_type.name, cross_val_type.value)
 
-    k_fold functools.partial(<function CrossValFuncs.k_fold at ...>)
+    k_fold_cross_validation functools.partial(<function CrossValFuncs.k_fold_cross_validation at ...>)
     time_series <function CrossValFuncs.time_series>
     """
-    k_fold = partial(CrossValFuncs.k_fold)
+    k_fold_cross_validation = partial(CrossValFuncs.k_fold_cross_validation)
     time_series = partial(CrossValFuncs.time_series)
 
     def __call__(
@@ -153,31 +153,31 @@ def __call__(
         )
 
 
-class HoldoutTypes(Enum):
+class HoldoutValTypes(Enum):
     """The type of holdout validation
 
     This class is used to specify the holdout validation function
     and is not supposed to be instantiated.
 
     Examples: This class is supposed to be used as follows
-    >>> holdout_type = HoldoutTypes.holdout
+    >>> holdout_type = HoldoutValTypes.holdout_validation
     >>> print(holdout_type.name)
 
-    holdout
+    holdout_validation
 
     >>> print(holdout_type.value)
 
-    functools.partial(<function HoldoutTypes.holdout at ...>)
+    functools.partial(<function HoldoutValTypes.holdout_validation at ...>)
 
-    >>> for holdout_type in HoldoutTypes:
+    >>> for holdout_type in HoldoutValTypes:
             print(holdout_type.name)
 
-    holdout
+    holdout_validation
 
-    Additionally, HoldoutTypes.<function> can be called directly.
+    Additionally, HoldoutValTypes.<function> can be called directly.
     """
 
-    holdout = partial(HoldoutFuncs.holdout)
+    holdout = partial(HoldoutFuncs.holdout_validation)
 
     def __call__(
         self,

autoPyTorch/datasets/tabular_dataset.py

@@ -20,7 +20,7 @@
 from autoPyTorch.datasets.base_dataset import BaseDataset
 from autoPyTorch.datasets.resampling_strategy import (
     CrossValTypes,
-    HoldoutTypes,
+    HoldoutValTypes,
 )
 
 
@@ -44,8 +44,8 @@ class TabularDataset(BaseDataset):
             Y (Union[np.ndarray, pd.Series]): training data targets.
             X_test (Optional[Union[np.ndarray, pd.DataFrame]]):  input testing data.
             Y_test (Optional[Union[np.ndarray, pd.DataFrame]]): testing data targets
-            resampling_strategy (Union[CrossValTypes, HoldoutTypes]),
-                (default=HoldoutTypes.holdout):
+            resampling_strategy (Union[CrossValTypes, HoldoutValTypes]),
+                (default=HoldoutValTypes.holdout_validation):
                 strategy to split the training data.
             resampling_strategy_args (Optional[Dict[str, Any]]):
                 arguments required for the chosen resampling strategy.
@@ -66,7 +66,7 @@ def __init__(self,
                  Y: Union[np.ndarray, pd.Series],
                  X_test: Optional[Union[np.ndarray, pd.DataFrame]] = None,
                  Y_test: Optional[Union[np.ndarray, pd.DataFrame]] = None,
-                 resampling_strategy: Union[CrossValTypes, HoldoutTypes] = HoldoutTypes.holdout,
+                 resampling_strategy: Union[CrossValTypes, HoldoutValTypes] = HoldoutValTypes.holdout_validation,
                  resampling_strategy_args: Optional[Dict[str, Any]] = None,
                  seed: Optional[int] = 42,
                  train_transforms: Optional[torchvision.transforms.Compose] = None,

autoPyTorch/datasets/time_series_dataset.py

@@ -5,7 +5,7 @@
 import torchvision.transforms
 
 from autoPyTorch.datasets.base_dataset import BaseDataset
-from autoPyTorch.datasets.resampling_strategy import CrossValTypes, HoldoutTypes
+from autoPyTorch.datasets.resampling_strategy import CrossValTypes, HoldoutValTypes
 
 TIME_SERIES_FORECASTING_INPUT = Tuple[np.ndarray, np.ndarray]  # currently only numpy arrays are supported
 TIME_SERIES_REGRESSION_INPUT = Tuple[np.ndarray, np.ndarray]
@@ -17,9 +17,9 @@ def _check_prohibited_resampling() -> None:
 
     Args:
         task_name (str): Typically the Dataset class name
-        resampling_strategy (Union[CrossValTypes, HoldoutTypes]):
+        resampling_strategy (Union[CrossValTypes, HoldoutValTypes]):
             The splitting function
-        args (Union[CrossValTypes, HoldoutTypes]):
+        args (Union[CrossValTypes, HoldoutValTypes]):
             The list of cross validation functions and
             holdout validation functions that are suitable for the given task
 
@@ -39,7 +39,7 @@ def __init__(self,
                  n_steps: int,
                  train: TIME_SERIES_FORECASTING_INPUT,
                  val: Optional[TIME_SERIES_FORECASTING_INPUT] = None,
-                 resampling_strategy: Union[CrossValTypes, HoldoutTypes] = HoldoutTypes.holdout,
+                 resampling_strategy: Union[CrossValTypes, HoldoutValTypes] = HoldoutValTypes.holdout_validation,
                  resampling_strategy_args: Optional[Dict[str, Any]] = None,
                  seed: Optional[int] = 42,
                  train_transforms: Optional[torchvision.transforms.Compose] = None,

autoPyTorch/optimizer/smbo.py

@@ -19,7 +19,7 @@
 from autoPyTorch.datasets.base_dataset import BaseDataset
 from autoPyTorch.datasets.resampling_strategy import (
     CrossValTypes,
-    HoldoutTypes,
+    HoldoutValTypes,
 )
 from autoPyTorch.ensemble.ensemble_builder import EnsembleBuilderManager
 from autoPyTorch.evaluation.tae import ExecuteTaFuncWithQueue, get_cost_of_crash
@@ -92,7 +92,7 @@ def __init__(self,
                  pipeline_config: typing.Dict[str, typing.Any],
                  start_num_run: int = 1,
                  seed: int = 1,
-                 resampling_strategy: typing.Union[HoldoutTypes, CrossValTypes] = HoldoutTypes.holdout,
+                 resampling_strategy: typing.Union[HoldoutValTypes, CrossValTypes] = HoldoutValTypes.holdout_validation,
                  resampling_strategy_args: typing.Optional[typing.Dict[str, typing.Any]] = None,
                  include: typing.Optional[typing.Dict[str, typing.Any]] = None,
                  exclude: typing.Optional[typing.Dict[str, typing.Any]] = None,

examples/tabular/40_advanced/example_resampling_strategy.py

@@ -24,7 +24,7 @@
 import sklearn.model_selection
 
 from autoPyTorch.api.tabular_classification import TabularClassificationTask
-from autoPyTorch.datasets.resampling_strategy import CrossValTypes, HoldoutTypes
+from autoPyTorch.datasets.resampling_strategy import CrossValTypes, HoldoutValTypes
 
 
 if __name__ == '__main__':
@@ -48,11 +48,11 @@
         # To maintain logs of the run, set the next two as False
         delete_tmp_folder_after_terminate=True,
         delete_output_folder_after_terminate=True,
-        # 'HoldoutTypes.holdout' with 'val_share': 0.33
+        # 'HoldoutValTypes.holdout_validation' with 'val_share': 0.33
         # is the default argument setting for TabularClassificationTask.
         # It is explicitly specified in this example for demonstrational
         # purpose.
-        resampling_strategy=HoldoutTypes.holdout,
+        resampling_strategy=HoldoutValTypes.holdout_validation,
         resampling_strategy_args={'val_share': 0.33}
     )
 
@@ -90,7 +90,7 @@
         # To maintain logs of the run, set the next two as False
         delete_tmp_folder_after_terminate=True,
         delete_output_folder_after_terminate=True,
-        resampling_strategy=CrossValTypes.k_fold,
+        resampling_strategy=CrossValTypes.k_fold_cross_validation,
         resampling_strategy_args={'num_splits': 3}
     )
 
@@ -130,8 +130,8 @@
         delete_output_folder_after_terminate=True,
         # For demonstration purposes, we use
         # Stratified hold out validation. However,
-        # one can also use CrossValTypes.k_fold.
-        resampling_strategy=HoldoutTypes.holdout,
+        # one can also use CrossValTypes.k_fold_cross_validation.
+        resampling_strategy=HoldoutValTypes.holdout_validation,
         resampling_strategy_args={'val_share': 0.33, 'stratify': True}
     )