Renaming

skrub/_drop_column_if_null.py → skrub/_drop_if_too_many_nulls.py

@@ -5,10 +5,10 @@
 from . import _dataframe as sbd
 from ._on_each_column import SingleColumnTransformer
 
-__all__ = ["DropColumnIfNull"]
+__all__ = ["DropIfTooManyNulls"]
 
 
-class DropColumnIfNull(SingleColumnTransformer):
+class DropIfTooManyNulls(SingleColumnTransformer):
     """Drop a single column if the fraction of Null or NaN values in the column
     is larger than the given threshold.
 

skrub/_table_vectorizer.py

@@ -16,7 +16,7 @@
 from ._clean_categories import CleanCategories
 from ._clean_null_strings import CleanNullStrings
 from ._datetime_encoder import DatetimeEncoder
-from ._drop_column_if_null import DropColumnIfNull
+from ._drop_if_too_many_nulls import DropIfTooManyNulls
 from ._gap_encoder import GapEncoder
 from ._on_each_column import SingleColumnTransformer
 from ._select_cols import Drop
@@ -192,12 +192,12 @@ class TableVectorizer(TransformerMixin, BaseEstimator):
         similar functionality to what is offered by scikit-learn's
         :class:`~sklearn.compose.ColumnTransformer`.
 
-    null_threshold : float or None, default=1.0
-        Fraction of null above which the column is dropped. If `null_threshold` is
+    drop_null_fraction : float or None, default=1.0
+        Fraction of null above which the column is dropped. If `drop_null_fraction` is
         set to ``1.0``, the column is dropped if it contains only
-        nulls or NaNs (this is the default behavior). If `null_threshold` is a
+        nulls or NaNs (this is the default behavior). If `drop_null_fraction` is a
         number in ``[0.0, 1.0)``, the column is dropped if the fraction of nulls
-        is strictly larger than `null_threshold`. If `null_threshold` is ``None``,
+        is strictly larger than `drop_null_fraction`. If `drop_null_fraction` is ``None``,
         this selection is disabled: no columns are dropped based on the number
         of null values they contain.
 
@@ -325,7 +325,7 @@ class TableVectorizer(TransformerMixin, BaseEstimator):
     We can inspect all the processing steps that were applied to a given column:
 
     >>> vectorizer.all_processing_steps_['B']
-    [CleanNullStrings(), DropColumnIfNull(), ToDatetime(), DatetimeEncoder(), {'B_day': ToFloat32(), 'B_month': ToFloat32(), ...}]
+    [CleanNullStrings(), DropIfTooManyNulls(), ToDatetime(), DatetimeEncoder(), {'B_day': ToFloat32(), 'B_month': ToFloat32(), ...}]
 
     Note that as the encoder (``DatetimeEncoder()`` above) produces multiple
     columns, the last processing step is not described by a single transformer
@@ -400,7 +400,7 @@ class TableVectorizer(TransformerMixin, BaseEstimator):
     ``ToDatetime()``:
 
     >>> vectorizer.all_processing_steps_
-    {'A': [Drop()], 'B': [OrdinalEncoder()], 'C': [CleanNullStrings(), DropColumnIfNull(), ToFloat32(), PassThrough(), {'C': ToFloat32()}]}
+    {'A': [Drop()], 'B': [OrdinalEncoder()], 'C': [CleanNullStrings(), DropIfTooManyNulls(), ToFloat32(), PassThrough(), {'C': ToFloat32()}]}
 
     Specifying several ``specific_transformers`` for the same column is not allowed.
 
@@ -423,7 +423,7 @@ def __init__(
         numeric=NUMERIC_TRANSFORMER,
         datetime=DATETIME_TRANSFORMER,
         specific_transformers=(),
-        null_threshold=1.0,
+        drop_null_fraction=1.0,
         n_jobs=None,
     ):
         self.cardinality_threshold = cardinality_threshold
@@ -437,7 +437,7 @@ def __init__(
         self.datetime = _utils.clone_if_default(datetime, DATETIME_TRANSFORMER)
         self.specific_transformers = specific_transformers
         self.n_jobs = n_jobs
-        self.null_threshold = null_threshold
+        self.drop_null_fraction = drop_null_fraction
 
     def fit(self, X, y=None):
         """Fit transformer.
@@ -551,7 +551,7 @@ def add_step(steps, transformer, cols, allow_reject=False):
         self._preprocessors = [CheckInputDataFrame()]
 
         transformer_list = [CleanNullStrings()]
-        transformer_list.append(DropColumnIfNull(self.null_threshold))
+        transformer_list.append(DropIfTooManyNulls(self.drop_null_fraction))
 
         transformer_list += [
             ToDatetime(),