Improved docstrings, formatting

src/sensai/data_transformation/dft.py

@@ -816,7 +816,7 @@ def info(self):
 
 class DFTSkLearnTransformer(InvertibleDataFrameTransformer):
     """
-    Applies a transformer from sklearn.preprocessing to (a subset of the columns of) a data frame.
+    Applies a transformer from sklearn.preprocessing to (a subset of) the columns of a data frame.
     If multiple columns are transformed, they are transformed independently (i.e. each column uses a separately trained transformation).
     """
     def __init__(self,

src/sensai/featuregen/feature_generator.py

@@ -2,7 +2,7 @@
 import logging
 import re
 from abc import ABC, abstractmethod
-from typing import Sequence, List, Union, Callable, Any, Dict, TYPE_CHECKING, Optional, Hashable
+from typing import Sequence, List, Union, Callable, Any, Dict, TYPE_CHECKING, Optional
 
 import numpy as np
 import pandas as pd
@@ -43,7 +43,7 @@ def __init__(self,
         :param normalisation_rules: Rules to be used by DFTNormalisation (e.g. for constructing an input transformer for a model).
             These rules are only relevant if a DFTNormalisation object consuming them is instantiated and used
             within a data processing pipeline. They do not affect feature generation.
-        :param normalisation_rule_template: This parameter can be supplied instead of normalisationRules for the case where
+        :param normalisation_rule_template: This parameter can be supplied instead of normalisation_rules for the case where
             there shall be a single rule that applies to all columns generated by this feature generator that were not labeled as
             categorical.
         :param add_categorical_default_rules:
@@ -56,7 +56,7 @@ def __init__(self,
         # and can provide them directly in the subclass constructor implementation. Thus it would enable
         # non-sensical settings which should be avoided.
         if len(normalisation_rules) > 0 and normalisation_rule_template is not None:
-            raise ValueError(f"normalisationRules should be empty when a normalisationRuleTemplate is provided")
+            raise ValueError(f"Normalisation rules should be empty when a rule template is provided")
 
         self._generatedColumnNames = None
         self.__categoricalFeatureNames = categorical_feature_names
@@ -700,9 +700,11 @@ def _generate(self, df: pd.DataFrame, ctx=None) -> pd.DataFrame:
             if self.flatten:
                 for target_value in self._targetColumnValues:
                     # Important: pd.Series.apply should not be used here, as it would label the resulting column as categorical
-                    result_df[f"{column}_{self.targetColumn}_distribution_{target_value}"] = [target_distribution_by_value[value].get(target_value, 0.0) for value in df[column]]
+                    result_df[f"{column}_{self.targetColumn}_distribution_{target_value}"] = \
+                        [target_distribution_by_value[value].get(target_value, 0.0) for value in df[column]]
             else:
-                distributions = [[target_distribution_by_value[value].get(targetValue, 0.0) for targetValue in self._targetColumnValues] for value in df[column]]
+                distributions = [[target_distribution_by_value[value].get(targetValue, 0.0) for targetValue in self._targetColumnValues]
+                                 for value in df[column]]
                 result_df[f"{column}_{self.targetColumn}_distribution"] = pd.Series(distributions, index=df[column].index)
         return result_df