[ENH] Drop numpy array input support

benchmarks/bench_gap_divergence.py

@@ -208,7 +208,7 @@ def benchmark(max_iter_e_step: int, dataset_name: str):
                 (
                     "encoding",
                     TableVectorizer(
-                        high_card_cat_transformer=ModifiedGapEncoder(
+                        high_cardinality_transformer=ModifiedGapEncoder(
                             min_iter=5,
                             max_iter=5,
                             max_iter_e_step=max_iter_e_step,
@@ -234,7 +234,7 @@ def benchmark(max_iter_e_step: int, dataset_name: str):
     results = []
     for pipeline, (_, cv_results) in zip(pipelines, cv_df.iterrows()):
         for modified_gap_encoder in (
-            pipeline["encoding"].named_transformers_["high_card_cat"].fitted_models_
+            pipeline["encoding"].named_transformers_["high_cardinality"].fitted_models_
         ):
             for gap_iter, inner_results in enumerate(
                 modified_gap_encoder.benchmark_results_

benchmarks/bench_tablevectorizer_tuning.py

@@ -59,7 +59,7 @@ def benchmark(
 ):
     tv = TableVectorizer(
         cardinality_threshold=tv_cardinality_threshold,
-        high_card_cat_transformer=MinHashEncoder(n_components=minhash_n_components),
+        high_cardinality_transformer=MinHashEncoder(n_components=minhash_n_components),
     )
 
     dataset = dataset_map[dataset_name]

benchmarks/run_on_openml_datasets.py

@@ -45,14 +45,14 @@
 
 classification_pipeline = Pipeline(
     [
-        ("vectorizer", TableVectorizer(high_card_cat_transformer=MinHashEncoder())),
+        ("vectorizer", TableVectorizer(high_cardinality_transformer=MinHashEncoder())),
         ("classifier", HistGradientBoostingClassifier()),
     ]
 )
 
 regression_pipeline = Pipeline(
     [
-        ("vectorizer", TableVectorizer(high_card_cat_transformer=MinHashEncoder())),
+        ("vectorizer", TableVectorizer(high_cardinality_transformer=MinHashEncoder())),
         ("regressor", HistGradientBoostingRegressor()),
     ]
 )

examples/01_encodings.py

@@ -94,14 +94,14 @@
 #     - The |OneHotEncoder| for low cardinality string variables, the columns
 #       ``'gender'``, ``'department'``, ``'department_name'`` and ``'assignment_category'``.
 
-tv.named_transformers_["low_card_cat"].get_feature_names_out()
+tv.named_transformers_["low_cardinality"].get_feature_names_out()
 
 ###############################################################################
 #     - The |GapEncoder| for high cardinality string columns, ``'employee_position_title'``
 #       and ``'division'``. The |GapEncoder| is a powerful encoder that can handle dirty
 #       categorical columns.
 
-tv.named_transformers_["high_card_cat"].get_feature_names_out()
+tv.named_transformers_["high_cardinality"].get_feature_names_out()
 
 ###############################################################################
 #     - The |DatetimeEncoder| to the ``'date_first_hired'`` column. The |DatetimeEncoder|

examples/FIXME/07_grid_searching_with_the_tablevectorizer.py

@@ -62,7 +62,7 @@
 from skrub import MinHashEncoder
 
 tv = TableVectorizer(
-    high_card_cat_transformer=MinHashEncoder(),
+    high_cardinality_transformer=MinHashEncoder(),
 )
 tv.fit(X)
 
@@ -101,8 +101,8 @@
 # For that, we use the dunder separator, which indicates a nesting layer.
 # That means that for tuning the parameter ``n_components`` of the
 # |GapEncoder| saved in the |TableVectorizer| attribute
-# ``high_card_cat_transformer``, we use the syntax
-# ``tablevectorizer__high_card_cat_transformer__n_components``.
+# ``high_cardinality_transformer``, we use the syntax
+# ``tablevectorizer__high_cardinality_transformer__n_components``.
 #
 # We recommend using the 3-tuple syntax for the column-specific transformers,
 # which allows us to give a name to the assignment (here ``mh_dep_name``).
@@ -114,7 +114,7 @@
 
 pipeline = make_pipeline(
     TableVectorizer(
-        high_card_cat_transformer=GapEncoder(),
+        high_cardinality_transformer=GapEncoder(),
         specific_transformers=[
             ("mh_dep_name", MinHashEncoder(), ["department_name"]),
         ],
@@ -123,7 +123,7 @@
 )
 
 params = {
-    "tablevectorizer__high_card_cat_transformer__n_components": [10, 30, 50],
+    "tablevectorizer__high_cardinality_transformer__n_components": [10, 30, 50],
     "tablevectorizer__mh_dep_name__n_components": [25, 50],
 }