maintain: add more pre-commit hooks (#40)

.pre-commit-config.yaml

@@ -31,32 +31,66 @@ repos:
       - id: trailing-whitespace
       - id: end-of-file-fixer
       - id: check-yaml
+      - id: check-xml
       - id: mixed-line-ending
         args: ["--fix=lf"]
       - id: check-added-large-files
       - id: check-ast
+      - id: check-builtin-literals
       - id: check-case-conflict
       - id: check-docstring-first
       - id: check-merge-conflict
       - id: check-toml
       - id: debug-statements
       - id: fix-byte-order-marker
       - id: forbid-new-submodules
+      - id: forbid-submodules
+      - id: detect-private-key
+      - id: no-commit-to-branch
+        args: ["--branch=main", "--branch=develop"]
 
-  - repo: https://github.com/asottile/pyupgrade
-    rev: v3.3.1
+  - repo: https://github.com/pre-commit/pygrep-hooks
+    rev: v1.10.0
     hooks:
-      - id: pyupgrade
+      - id: python-use-type-annotations
+      - id: python-check-blanket-noqa
+      - id: python-check-mock-methods
+      - id: python-no-eval
+      - id: python-no-log-warn
+      - id: python-use-type-annotations
+      - id: text-unicode-replacement-char
+
+  - repo: https://github.com/PyCQA/docformatter
+    rev: v1.5.1
+    hooks:
+      - id: docformatter
+
+  - repo: https://github.com/nbQA-dev/nbQA
+    rev: 1.6.1
+    hooks:
+      - id: nbqa-check-ast
+      - id: nbqa-mypy
+        args: ["--config-file=pyproject.toml"]
+      - id: nbqa-pyupgrade
 
   - repo: https://github.com/bwhmather/ssort
     rev: v0.11.6
     hooks:
       - id: ssort
 
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.3.1
+    hooks:
+      - id: pyupgrade
+
   - repo: https://github.com/psf/black
     rev: 22.12.0
     hooks:
       - id: black
+        args: ["--config=pyproject.toml"]
+      - id: black-jupyter
+        args: ["--config=pyproject.toml"]
+        files: \.ipynb$
 
   - repo: https://github.com/PyCQA/isort
     rev: 5.11.4
@@ -65,7 +99,7 @@ repos:
         args: ["--profile=black"]
 
   - repo: https://github.com/PyCQA/pylint
-    rev: v2.15.9
+    rev: v2.15.10
     hooks:
       - id: pylint
         args: ["--rcfile=pyproject.toml"]
@@ -86,6 +120,11 @@ repos:
         args:
           - "-r"
 
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.6.1
+    hooks:
+      - id: nbstripout
+
   - repo: https://github.com/python-poetry/poetry
     rev: 1.3.0
     hooks:

src/sk_transformers/base_transformer.py

@@ -4,11 +4,14 @@
 
 
 class BaseTransformer(BaseEstimator, TransformerMixin):
-    """
-    Base class for all custom transformers. This class inherits from BaseEstimator and TransformerMixin.
-    Its main purpose is to provide an implementation of the `fit` method that does nothing except setting the `self.fitted_` to `True`.
-    Since most custom transformers do not need to implement a fit method, this class
-    can be used as a base class for all transformers not needing a `fit` method.
+    """Base class for all custom transformers.
+
+    This class inherits from BaseEstimator and TransformerMixin. Its
+    main purpose is to provide an implementation of the `fit` method
+    that does nothing except setting the `self.fitted_` to `True`. Since
+    most custom transformers do not need to implement a fit method, this
+    class can be used as a base class for all transformers not needing a
+    `fit` method.
     """
 
     def __init__(self) -> None:

src/sk_transformers/datetime_transformer.py

@@ -8,8 +8,7 @@
 
 
 class DurationCalculatorTransformer(BaseTransformer):
-    """
-    Calculates the duration between to given dates.
+    """Calculates the duration between to given dates.
 
     Example:
     ```python
@@ -50,8 +49,7 @@ def __init__(
         self.new_column_name = new_column_name
 
     def transform(self, X: pd.DataFrame) -> pd.DataFrame:
-        """
-        Transform method that calculates the duration between two dates.
+        """Transform method that calculates the duration between two dates.
 
         Args:
             X (pandas.DataFrame): The input DataFrame.
@@ -75,8 +73,8 @@ def transform(self, X: pd.DataFrame) -> pd.DataFrame:
 
 
 class TimestampTransformer(BaseTransformer):
-    """
-    Transforms a date column with a specified format into a timestamp column.
+    """Transforms a date column with a specified format into a timestamp
+    column.
 
     Example:
     ```python
@@ -109,8 +107,7 @@ def __init__(
         self.date_format = date_format
 
     def transform(self, X: pd.DataFrame) -> pd.DataFrame:
-        """
-        Transforms columns from the provided dataframe.
+        """Transforms columns from the provided dataframe.
 
         Args:
             X (pandas.DataFrame): Dataframe with columns to transform.

src/sk_transformers/deep_transformer.py

@@ -12,9 +12,12 @@
 
 
 class ToVecTransformer(BaseEstimator, TransformerMixin):
-    """
-    This transformer trains an [FT-Transformer](https://paperswithcode.com/method/ft-transformer)
-    using the [pytorch-widedeep package](https://github.com/jrzaurin/pytorch-widedeep) and extracts the embeddings
+    """This transformer trains an [FT-
+    Transformer](https://paperswithcode.com/method/ft-transformer) using the.
+
+    [pytorch-widedeep package](https://github.com/jrzaurin/pytorch-widedeep)
+    and extracts the embeddings.
+
     from its embedding layer. The output shape of the transformer is (number of rows,(`input_dim` * number of columns)).
     Please refer to [this example](https://pytorch-widedeep.readthedocs.io/en/latest/examples/09_extracting_embeddings.html)
     for pytorch_widedeep example on how to extract embeddings.
@@ -99,8 +102,8 @@ def __init__(
         self.tab_vec_: Optional[Tab2Vec] = None
 
     def fit(self, X: pd.DataFrame, y: NDArray) -> "ToVecTransformer":
-        """
-        Fits the `ToVecTransformer`. The `TabPreprocessor` is fitted and the `FTTransformer` is trained.
+        """Fits the `ToVecTransformer`. The `TabPreprocessor` is fitted and the
+        `FTTransformer` is trained.
 
         Args:
             X (pd.DataFrame): The input data.
@@ -151,8 +154,8 @@ def fit(self, X: pd.DataFrame, y: NDArray) -> "ToVecTransformer":
         return self
 
     def transform(self, X: pd.DataFrame) -> pd.DataFrame:
-        """
-        Transforms the input data and returns the embeddings.
+        """Transforms the input data and returns the embeddings.
+
         The output shape is (number of rows,(`input_dim` * number of columns)).
 
         Args:

src/sk_transformers/encoder_transformer.py

@@ -6,8 +6,8 @@
 
 
 class MeanEncoderTransformer(BaseEstimator, TransformerMixin):
-    """
-    Scikit-learn API for the [feature-engine MeanEncoder](https://feature-engine.readthedocs.io/en/latest/api_doc/encoding/MeanEncoder.html).
+    """Scikit-learn API for the [feature-engine MeanEncoder](https://feature-
+    engine.readthedocs.io/en/latest/api_doc/encoding/MeanEncoder.html).
 
     Example:
     ```python
@@ -44,8 +44,7 @@ def __init__(self, fill_na_value: Union[int, float] = -999) -> None:
         self.fill_na_value = fill_na_value
 
     def fit(self, X: pd.DataFrame, y: pd.Series) -> "MeanEncoderTransformer":
-        """
-        Fit the MeanEncoder to the data.
+        """Fit the MeanEncoder to the data.
 
         Args:
             X (pandas.DataFrame): DataFrame to fit the MeanEncoder to.
@@ -58,8 +57,7 @@ def fit(self, X: pd.DataFrame, y: pd.Series) -> "MeanEncoderTransformer":
         return self
 
     def transform(self, X: pd.DataFrame) -> pd.DataFrame:
-        """
-        Transform the data using the fitted MeanEncoder.
+        """Transform the data using the fitted MeanEncoder.
 
         Args:
             X (pandas.DataFrame): DataFrame to transform.