[ci skip] MAINT Changed the use of ColumnTransformer to make_column_transformer (#831)

* changed besides to additionally for better phrasing

* Apply suggestions from code review

* Changed the use of ColumnTransformer to make_column_transformer

* fixed format

* fixed format

* changed additional mentions of ColumnTransformer

* Rerender notebooks

---------

Co-authored-by: SebastienMelo <seastien.melo@polytechnique.edu>
Co-authored-by: Arturo Amor <86408019+ArturoAmorQ@users.noreply.github.com>
Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org> 6625d0c

Author: 3 people

_sources/appendix/glossary.md

@@ -368,7 +368,7 @@ The dataset used to train the [model](#model).
 
 An [estimator](#estimator) (i.e. an object that has a `fit` method) supporting
 `transform` and/or `fit_transform`. Examples for transformers are
-`StandardScaler` or `ColumnTransformer`.
+`StandardScaler` or `OneHotEncoder`.
 
 ### underfitting
 

_sources/python_scripts/03_categorical_pipeline_column_transformer.py

@@ -74,9 +74,10 @@
 #   categories.
 # * **numerical scaling** numerical features which will be standardized.
 #
-# Now, we create our `ColumnTransfomer` by specifying three values: the
-# preprocessor name, the transformer, and the columns. First, let's create the
-# preprocessors for the numerical and categorical parts.
+# Now, we create our `ColumnTransfomer` using the helper function
+# `make_column_transformer`. We specify two values: the transformer, and the
+# columns. First, let's create the preprocessors for the numerical and
+# categorical parts.
 
 # %%
 from sklearn.preprocessing import OneHotEncoder, StandardScaler
@@ -89,13 +90,11 @@
 # their respective columns.
 
 # %%
-from sklearn.compose import ColumnTransformer
+from sklearn.compose import make_column_transformer
 
-preprocessor = ColumnTransformer(
-    [
-        ("one-hot-encoder", categorical_preprocessor, categorical_columns),
-        ("standard_scaler", numerical_preprocessor, numerical_columns),
-    ]
+preprocessor = make_column_transformer(
+    (categorical_preprocessor, categorical_columns),
+    (numerical_preprocessor, numerical_columns),
 )
 
 # %% [markdown]
@@ -234,8 +233,8 @@
     handle_unknown="use_encoded_value", unknown_value=-1
 )
 
-preprocessor = ColumnTransformer(
-    [("categorical", categorical_preprocessor, categorical_columns)],
+preprocessor = make_column_transformer(
+    (categorical_preprocessor, categorical_columns),
     remainder="passthrough",
 )
 

_sources/python_scripts/03_categorical_pipeline_ex_02.py

@@ -58,18 +58,19 @@
 
 from sklearn.model_selection import cross_validate
 from sklearn.pipeline import make_pipeline
-from sklearn.compose import ColumnTransformer
+from sklearn.compose import make_column_transformer
 from sklearn.preprocessing import OrdinalEncoder
 from sklearn.ensemble import HistGradientBoostingClassifier
 
 categorical_preprocessor = OrdinalEncoder(
     handle_unknown="use_encoded_value", unknown_value=-1
 )
-preprocessor = ColumnTransformer(
-    [("categorical", categorical_preprocessor, categorical_columns)],
+preprocessor = make_column_transformer(
+    (categorical_preprocessor, categorical_columns),
     remainder="passthrough",
 )
 
+
 model = make_pipeline(preprocessor, HistGradientBoostingClassifier())
 
 start = time.time()

_sources/python_scripts/03_categorical_pipeline_sol_02.py

@@ -52,18 +52,19 @@
 
 from sklearn.model_selection import cross_validate
 from sklearn.pipeline import make_pipeline
-from sklearn.compose import ColumnTransformer
+from sklearn.compose import make_column_transformer
 from sklearn.preprocessing import OrdinalEncoder
 from sklearn.ensemble import HistGradientBoostingClassifier
 
 categorical_preprocessor = OrdinalEncoder(
     handle_unknown="use_encoded_value", unknown_value=-1
 )
-preprocessor = ColumnTransformer(
-    [("categorical", categorical_preprocessor, categorical_columns)],
+preprocessor = make_column_transformer(
+    (categorical_preprocessor, categorical_columns),
     remainder="passthrough",
 )
 
+
 model = make_pipeline(preprocessor, HistGradientBoostingClassifier())
 
 start = time.time()
@@ -90,17 +91,12 @@
 
 from sklearn.preprocessing import StandardScaler
 
-preprocessor = ColumnTransformer(
-    [
-        ("numerical", StandardScaler(), numerical_columns),
-        (
-            "categorical",
-            OrdinalEncoder(
-                handle_unknown="use_encoded_value", unknown_value=-1
-            ),
-            categorical_columns,
-        ),
-    ]
+preprocessor = make_column_transformer(
+    (StandardScaler(), numerical_columns),
+    (
+        OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1),
+        categorical_columns,
+    ),
 )
 
 model = make_pipeline(preprocessor, HistGradientBoostingClassifier())
@@ -151,8 +147,8 @@
 categorical_preprocessor = OneHotEncoder(
     handle_unknown="ignore", sparse_output=False
 )
-preprocessor = ColumnTransformer(
-    [("one-hot-encoder", categorical_preprocessor, categorical_columns)],
+preprocessor = make_column_transformer(
+    (categorical_preprocessor, categorical_columns),
     remainder="passthrough",
 )
 

_sources/python_scripts/parameter_tuning_ex_02.py

@@ -37,21 +37,15 @@
 )
 
 # %%
-from sklearn.compose import ColumnTransformer
+from sklearn.compose import make_column_transformer
 from sklearn.compose import make_column_selector as selector
 from sklearn.preprocessing import OrdinalEncoder
 
 categorical_preprocessor = OrdinalEncoder(
     handle_unknown="use_encoded_value", unknown_value=-1
 )
-preprocessor = ColumnTransformer(
-    [
-        (
-            "cat_preprocessor",
-            categorical_preprocessor,
-            selector(dtype_include=object),
-        )
-    ],
+preprocessor = make_column_transformer(
+    (categorical_preprocessor, selector(dtype_include=object)),
     remainder="passthrough",
 )
 
@@ -88,3 +82,5 @@
 
 # %%
 # Write your code here.
+
+# %%

_sources/python_scripts/parameter_tuning_grid_search.py

@@ -80,14 +80,14 @@
 )
 
 # %% [markdown]
-# We then use a `ColumnTransformer` to select the categorical columns and apply
+# We then use `make_column_transformer` to select the categorical columns and apply
 # the `OrdinalEncoder` to them.
 
 # %%
-from sklearn.compose import ColumnTransformer
+from sklearn.compose import make_column_transformer
 
-preprocessor = ColumnTransformer(
-    [("cat_preprocessor", categorical_preprocessor, categorical_columns)],
+preprocessor = make_column_transformer(
+    (categorical_preprocessor, categorical_columns),
     remainder="passthrough",
     # Silence a deprecation warning in scikit-learn v1.6 related to how the
     # ColumnTransformer stores an attribute that we do not use in this notebook

_sources/python_scripts/parameter_tuning_nested.py

@@ -41,7 +41,7 @@
 # pipeline is identical to the one we used in the previous notebook.
 
 # %%
-from sklearn.compose import ColumnTransformer
+from sklearn.compose import make_column_transformer
 from sklearn.preprocessing import OrdinalEncoder
 from sklearn.compose import make_column_selector as selector
 
@@ -51,10 +51,8 @@
 categorical_preprocessor = OrdinalEncoder(
     handle_unknown="use_encoded_value", unknown_value=-1
 )
-preprocessor = ColumnTransformer(
-    [
-        ("cat_preprocessor", categorical_preprocessor, categorical_columns),
-    ],
+preprocessor = make_column_transformer(
+    (categorical_preprocessor, categorical_columns),
     remainder="passthrough",
     force_int_remainder_cols=False,  # Silence a warning in scikit-learn v1.6.
 )

_sources/python_scripts/parameter_tuning_randomized_search.py

@@ -60,7 +60,7 @@
 # We create the same predictive pipeline as done for the grid-search section.
 
 # %%
-from sklearn.compose import ColumnTransformer
+from sklearn.compose import make_column_transformer
 from sklearn.preprocessing import OrdinalEncoder
 from sklearn.compose import make_column_selector as selector
 
@@ -70,8 +70,8 @@
 categorical_preprocessor = OrdinalEncoder(
     handle_unknown="use_encoded_value", unknown_value=-1
 )
-preprocessor = ColumnTransformer(
-    [("cat_preprocessor", categorical_preprocessor, categorical_columns)],
+preprocessor = make_column_transformer(
+    (categorical_preprocessor, categorical_columns),
     remainder="passthrough",
     force_int_remainder_cols=False,  # Silence a warning in scikit-learn v1.6.
 )

_sources/python_scripts/parameter_tuning_sol_02.py

@@ -31,21 +31,15 @@
 )
 
 # %%
-from sklearn.compose import ColumnTransformer
+from sklearn.compose import make_column_transformer
 from sklearn.compose import make_column_selector as selector
 from sklearn.preprocessing import OrdinalEncoder
 
 categorical_preprocessor = OrdinalEncoder(
     handle_unknown="use_encoded_value", unknown_value=-1
 )
-preprocessor = ColumnTransformer(
-    [
-        (
-            "cat_preprocessor",
-            categorical_preprocessor,
-            selector(dtype_include=object),
-        )
-    ],
+preprocessor = make_column_transformer(
+    (categorical_preprocessor, selector(dtype_include=object)),
     remainder="passthrough",
 )
 
@@ -121,3 +115,5 @@
 test_score = model.score(data_test, target_test)
 
 print(f"Test score after the parameter tuning: {test_score:.3f}")
+
+# %%

appendix/glossary.html

@@ -1040,7 +1040,7 @@ <h3>train set<a class="headerlink" href="#train-set" title="Link to this heading
 <h3>transformer<a class="headerlink" href="#transformer" title="Link to this heading">#</a></h3>
 <p>An <a class="reference internal" href="#estimator"><span class="xref myst">estimator</span></a> (i.e. an object that has a <code class="docutils literal notranslate"><span class="pre">fit</span></code> method) supporting
 <code class="docutils literal notranslate"><span class="pre">transform</span></code> and/or <code class="docutils literal notranslate"><span class="pre">fit_transform</span></code>. Examples for transformers are
-<code class="docutils literal notranslate"><span class="pre">StandardScaler</span></code> or <code class="docutils literal notranslate"><span class="pre">ColumnTransformer</span></code>.</p>
+<code class="docutils literal notranslate"><span class="pre">StandardScaler</span></code> or <code class="docutils literal notranslate"><span class="pre">OneHotEncoder</span></code>.</p>
 </section>
 <section id="underfitting">
 <h3>underfitting<a class="headerlink" href="#underfitting" title="Link to this heading">#</a></h3>