[style] Modify data/

[style] Modify data/base_feature_validator.py

[style] Modify data/base_validator.py and base_target_validator.py

[style] Modify data/base_validator.py and tabular_xxx_validator.py

[style] Modify base_validator.py

Author: nabenabe0928

autoPyTorch/data/base_feature_validator.py

@@ -1,5 +1,5 @@
 import logging
-import typing
+from typing import List, Optional, Set, Tuple, Union
 
 import numpy as np
 
@@ -12,8 +12,8 @@
 from autoPyTorch.utils.logging_ import PicklableClientLogger
 
 
-SUPPORTED_FEAT_TYPES = typing.Union[
-    typing.List,
+SUPPORTED_FEAT_TYPES = Union[
+    List,
     pd.DataFrame,
     np.ndarray,
     scipy.sparse.bsr_matrix,
@@ -29,58 +29,57 @@
 class BaseFeatureValidator(BaseEstimator):
     """
     A class to pre-process features. In this regards, the format of the data is checked,
-    and if applicable, features are encoded
+    and if applicable, features are encoded.
+
     Attributes:
         feat_type (List[str]):
             List of the column types found by this estimator during fit.
         data_type (str):
             Class name of the data type provided during fit.
-        encoder (typing.Optional[BaseEstimator])
+        encoder (Optional[BaseEstimator])
             Host a encoder object if the data requires transformation (for example,
-            if provided a categorical column in a pandas DataFrame)
-        enc_columns (typing.List[str])
-            List of columns that were encoded.
+            if provided a categorical column in a pandas DataFrame).
     """
-    def __init__(self,
-                 logger: typing.Optional[typing.Union[PicklableClientLogger, logging.Logger
-                                                      ]] = None,
-                 ) -> None:
+    def __init__(
+        self,
+        logger: Optional[Union[PicklableClientLogger, logging.Logger]] = None,
+    ):
         # Register types to detect unsupported data format changes
-        self.feat_type = None  # type: typing.Optional[typing.List[str]]
-        self.data_type = None  # type: typing.Optional[type]
-        self.dtypes = []  # type: typing.List[str]
-        self.column_order = []  # type: typing.List[str]
+        self.feat_type: Optional[List[str]] = None
+        self.data_type: Optional[type] = None
+        self.dtypes: List[str] = []
+        self.column_order: List[str] = []
 
-        self.encoder = None  # type: typing.Optional[BaseEstimator]
-        self.enc_columns = []  # type: typing.List[str]
+        self.encoder = None  # type: Optional[BaseEstimator]
+        self.enc_columns = []  # type: List[str]
 
-        self.logger: typing.Union[
+        self.logger: Union[
             PicklableClientLogger, logging.Logger
         ] = logger if logger is not None else logging.getLogger(__name__)
 
         # Required for dataset properties
-        self.num_features = None  # type: typing.Optional[int]
-        self.categories = []  # type: typing.List[typing.List[int]]
-        self.categorical_columns: typing.List[int] = []
-        self.numerical_columns: typing.List[int] = []
+        self.num_features: Optional[int] = None
+        self.categories: List[List[int]] = []
+        self.categorical_columns: List[int] = []
+        self.numerical_columns: List[int] = []
 
         self._is_fitted = False
 
     def fit(
         self,
         X_train: SUPPORTED_FEAT_TYPES,
-        X_test: typing.Optional[SUPPORTED_FEAT_TYPES] = None,
+        X_test: Optional[SUPPORTED_FEAT_TYPES] = None,
     ) -> BaseEstimator:
         """
         Validates and fit a categorical encoder (if needed) to the features.
         The supported data types are List, numpy arrays and pandas DataFrames.
         CSR sparse data types are also supported
 
-        Arguments:
+        Args:
             X_train (SUPPORTED_FEAT_TYPES):
                 A set of features that are going to be validated (type and dimensionality
                 checks) and a encoder fitted in the case the data needs encoding
-            X_test (typing.Optional[SUPPORTED_FEAT_TYPES]):
+            X_test (Optional[SUPPORTED_FEAT_TYPES]):
                 A hold out set of data used for checking
         """
 
@@ -112,7 +111,7 @@ def _fit(
         X: SUPPORTED_FEAT_TYPES,
     ) -> BaseEstimator:
         """
-        Arguments:
+        Args:
             X (SUPPORTED_FEAT_TYPES):
                 A set of features that are going to be validated (type and dimensionality
                 checks) and a encoder fitted in the case the data needs encoding
@@ -127,7 +126,7 @@ def transform(
         X: SUPPORTED_FEAT_TYPES,
     ) -> np.ndarray:
         """
-        Arguments:
+        Args:
             X_train (SUPPORTED_FEAT_TYPES):
                 A set of features, whose categorical features are going to be
                 transformed

autoPyTorch/data/base_target_validator.py

@@ -1,5 +1,5 @@
 import logging
-import typing
+from typing import List, Optional, Union, cast
 
 import numpy as np
 
@@ -12,8 +12,8 @@
 from autoPyTorch.utils.logging_ import PicklableClientLogger
 
 
-SUPPORTED_TARGET_TYPES = typing.Union[
-    typing.List,
+SUPPORTED_TARGET_TYPES = Union[
+    List,
     pd.Series,
     pd.DataFrame,
     np.ndarray,
@@ -35,48 +35,50 @@ class BaseTargetValidator(BaseEstimator):
         is_classification (bool):
             A bool that indicates if the validator should operate in classification mode.
             During classification, the targets are encoded.
-        encoder (typing.Optional[BaseEstimator]):
+        encoder (Optional[BaseEstimator]):
             Host a encoder object if the data requires transformation (for example,
             if provided a categorical column in a pandas DataFrame)
-        enc_columns (typing.List[str])
+        enc_columns (List[str])
             List of columns that where encoded
     """
     def __init__(self,
                  is_classification: bool = False,
-                 logger: typing.Optional[typing.Union[PicklableClientLogger, logging.Logger
-                                                      ]] = None,
-                 ) -> None:
+                 logger: Optional[Union[PicklableClientLogger,
+                                        logging.Logger
+                                        ]
+                                  ] = None,
+                 ):
         self.is_classification = is_classification
 
-        self.data_type = None  # type: typing.Optional[type]
+        self.data_type: Optional[type] = None
 
-        self.encoder = None  # type: typing.Optional[BaseEstimator]
+        self.encoder: Optional[BaseEstimator] = None
 
-        self.out_dimensionality = None  # type: typing.Optional[int]
-        self.type_of_target = None  # type: typing.Optional[str]
+        self.out_dimensionality: Optional[int] = None
+        self.type_of_target: Optional[str] = None
 
-        self.logger: typing.Union[
+        self.logger: Union[
             PicklableClientLogger, logging.Logger
         ] = logger if logger is not None else logging.getLogger(__name__)
 
         # Store the dtype for remapping to correct type
-        self.dtype = None  # type: typing.Optional[type]
+        self.dtype: Optional[type] = None
 
         self._is_fitted = False
 
     def fit(
         self,
         y_train: SUPPORTED_TARGET_TYPES,
-        y_test: typing.Optional[SUPPORTED_TARGET_TYPES] = None,
+        y_test: Optional[SUPPORTED_TARGET_TYPES] = None,
     ) -> BaseEstimator:
         """
         Validates and fit a categorical encoder (if needed) to the targets
         The supported data types are List, numpy arrays and pandas DataFrames.
 
-        Arguments:
+        Args:
             y_train (SUPPORTED_TARGET_TYPES)
                 A set of targets set aside for training
-            y_test (typing.Union[SUPPORTED_TARGET_TYPES])
+            y_test (Union[SUPPORTED_TARGET_TYPES])
                 A hold out set of data used of the targets. It is also used to fit the
                 categories of the encoder.
         """
@@ -95,7 +97,8 @@ def fit(
                                      np.shape(y_test)
                                  ))
             if isinstance(y_train, pd.DataFrame):
-                y_test = typing.cast(pd.DataFrame, y_test)
+                y_train = cast(pd.DataFrame, y_train)
+                y_test = cast(pd.DataFrame, y_test)
                 if y_train.columns.tolist() != y_test.columns.tolist():
                     raise ValueError(
                         "Train and test targets must both have the same columns, yet "
@@ -126,24 +129,24 @@ def fit(
     def _fit(
         self,
         y_train: SUPPORTED_TARGET_TYPES,
-        y_test: typing.Optional[SUPPORTED_TARGET_TYPES] = None,
+        y_test: Optional[SUPPORTED_TARGET_TYPES] = None,
     ) -> BaseEstimator:
         """
-        Arguments:
+        Args:
             y_train (SUPPORTED_TARGET_TYPES)
                 The labels of the current task. They are going to be encoded in case
                 of classification
-            y_test (typing.Optional[SUPPORTED_TARGET_TYPES])
+            y_test (Optional[SUPPORTED_TARGET_TYPES])
                 A holdout set of labels
         """
         raise NotImplementedError()
 
     def transform(
         self,
-        y: typing.Union[SUPPORTED_TARGET_TYPES],
+        y: Union[SUPPORTED_TARGET_TYPES],
     ) -> np.ndarray:
         """
-        Arguments:
+        Args:
             y (SUPPORTED_TARGET_TYPES)
                 A set of targets that are going to be encoded if the current task
                 is classification
@@ -160,8 +163,8 @@ def inverse_transform(
         """
         Revert any encoding transformation done on a target array
 
-        Arguments:
-            y (typing.Union[np.ndarray, pd.DataFrame, pd.Series]):
+        Args:
+            y (Union[np.ndarray, pd.DataFrame, pd.Series]):
                 Target array to be transformed back to original form before encoding
         Returns:
             np.ndarray:

autoPyTorch/data/base_validator.py

@@ -1,6 +1,6 @@
 # -*- encoding: utf-8 -*-
 import logging.handlers
-import typing
+from typing import Optional, Tuple
 
 import numpy as np
 
@@ -34,16 +34,16 @@ class BaseInputValidator(BaseEstimator):
     def __init__(
         self,
         is_classification: bool = False,
-        logger_port: typing.Optional[int] = logging.handlers.DEFAULT_TCP_LOGGING_PORT,
+        logger_port: Optional[int] = logging.handlers.DEFAULT_TCP_LOGGING_PORT,
     ) -> None:
         raise NotImplementedError()
 
     def fit(
         self,
         X_train: SUPPORTED_FEAT_TYPES,
         y_train: SUPPORTED_TARGET_TYPES,
-        X_test: typing.Optional[SUPPORTED_FEAT_TYPES] = None,
-        y_test: typing.Optional[SUPPORTED_TARGET_TYPES] = None,
+        X_test: Optional[SUPPORTED_FEAT_TYPES] = None,
+        y_test: Optional[SUPPORTED_TARGET_TYPES] = None,
     ) -> BaseEstimator:
         """
         Validates and fit a categorical encoder (if needed) to the features, and
@@ -58,14 +58,14 @@ def fit(
             + Checks for dimensionality as well as missing values are performed.
             + If performing a classification task, the data is going to be encoded
 
-        Arguments:
+        Args:
             X_train (SUPPORTED_FEAT_TYPES):
                 A set of features that are going to be validated (type and dimensionality
                 checks). If this data contains categorical columns, an encoder is going to
                 be instantiated and trained with this data.
             y_train (SUPPORTED_TARGET_TYPES):
                 A set of targets that are going to be encoded if the task is for classification
-            X_test (typing.Optional[SUPPORTED_FEAT_TYPES]):
+            X_test (Optional[SUPPORTED_FEAT_TYPES]):
                 A hold out set of features used for checking
             y_test (SUPPORTED_TARGET_TYPES):
                 A hold out set of targets used for checking. Additionally, if the current task
@@ -97,15 +97,15 @@ def fit(
     def transform(
         self,
         X: SUPPORTED_FEAT_TYPES,
-        y: typing.Optional[SUPPORTED_TARGET_TYPES] = None,
-    ) -> typing.Tuple[np.ndarray, typing.Optional[np.ndarray]]:
+        y: Optional[SUPPORTED_TARGET_TYPES] = None,
+    ) -> Tuple[np.ndarray, Optional[np.ndarray]]:
         """
         Transform the given target or features to a numpy array
 
-        Arguments:
+        Args:
             X (SUPPORTED_FEAT_TYPES):
                 A set of features to transform
-            y (typing.Optional[SUPPORTED_TARGET_TYPES]):
+            y (Optional[SUPPORTED_TARGET_TYPES]):
                 A set of targets to transform
 
         Returns: