fix: LabelEncoder params consistent with Sklearn

bigframes/ml/base.py

@@ -195,3 +195,23 @@ def fit_transform(
         y: Optional[Union[bpd.DataFrame, bpd.Series]] = None,
     ) -> bpd.DataFrame:
         return self.fit(X, y).transform(X)
+
+
+class LabelTransformer(BaseEstimator):
+    """A BigQuery DataFrames Label Transformer base class that transforms data.
+
+    Also the transformers can be attached to a pipeline with a predictor."""
+
+    @abc.abstractmethod
+    def fit(self, y):
+        pass
+
+    @abc.abstractmethod
+    def transform(self, y):
+        pass
+
+    def fit_transform(
+        self,
+        y: Union[bpd.DataFrame, bpd.Series],
+    ) -> bpd.DataFrame:
+        return self.fit(y).transform(y)

bigframes/ml/preprocessing.py

@@ -315,7 +315,7 @@ def transform(self, X: Union[bpd.DataFrame, bpd.Series]) -> bpd.DataFrame:
 
 
 class LabelEncoder(
-    base.Transformer,
+    base.LabelTransformer,
     third_party.bigframes_vendored.sklearn.preprocessing._label.LabelEncoder,
 ):
     # BQML max value https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-one-hot-encoder#syntax
@@ -401,16 +401,15 @@ def _parse_from_sql(cls, sql: str) -> tuple[LabelEncoder, str]:
 
     def fit(
         self,
-        X: Union[bpd.DataFrame, bpd.Series],
-        y=None,  # ignored
+        y: Union[bpd.DataFrame, bpd.Series],
     ) -> LabelEncoder:
-        (X,) = utils.convert_to_dataframe(X)
+        (y,) = utils.convert_to_dataframe(y)
 
-        compiled_transforms = self._compile_to_sql(X.columns.tolist())
+        compiled_transforms = self._compile_to_sql(y.columns.tolist())
         transform_sqls = [transform_sql for transform_sql, _ in compiled_transforms]
 
         self._bqml_model = self._bqml_model_factory.create_model(
-            X,
+            y,
             options={"model_type": "transform_only"},
             transforms=transform_sqls,
         )
@@ -419,13 +418,13 @@ def fit(
         self._output_names = [name for _, name in compiled_transforms]
         return self
 
-    def transform(self, X: Union[bpd.DataFrame, bpd.Series]) -> bpd.DataFrame:
+    def transform(self, y: Union[bpd.DataFrame, bpd.Series]) -> bpd.DataFrame:
         if not self._bqml_model:
             raise RuntimeError("Must be fitted before transform")
 
-        (X,) = utils.convert_to_dataframe(X)
+        (y,) = utils.convert_to_dataframe(y)
 
-        df = self._bqml_model.transform(X)
+        df = self._bqml_model.transform(y)
         return typing.cast(
             bpd.DataFrame,
             df[self._output_names],

tests/system/small/ml/test_preprocessing.py

@@ -357,9 +357,9 @@ def test_one_hot_encoder_different_data(penguins_df_default_index, new_penguins_
 
 def test_label_encoder_default_params(new_penguins_df):
     encoder = bigframes.ml.preprocessing.LabelEncoder()
-    encoder.fit(new_penguins_df[["species", "sex"]])
+    encoder.fit(new_penguins_df["species"])
 
-    result = encoder.transform(new_penguins_df).to_pandas()
+    result = encoder.transform(new_penguins_df["species"]).to_pandas()
 
     # TODO: bug? feature columns seem to be in nondeterministic random order
     # workaround: sort columns by name. Can't repro it in pantheon, so could
@@ -368,11 +368,6 @@ def test_label_encoder_default_params(new_penguins_df):
 
     expected = pd.DataFrame(
         {
-            "labelencoded_sex": [
-                2,
-                1,
-                1,
-            ],
             "labelencoded_species": [
                 1,
                 1,
@@ -389,7 +384,7 @@ def test_label_encoder_default_params(new_penguins_df):
 def test_label_encoder_default_params_fit_transform(new_penguins_df):
     encoder = bigframes.ml.preprocessing.LabelEncoder()
 
-    result = encoder.fit_transform(new_penguins_df[["species", "sex"]]).to_pandas()
+    result = encoder.fit_transform(new_penguins_df[["species"]]).to_pandas()
 
     # TODO: bug? feature columns seem to be in nondeterministic random order
     # workaround: sort columns by name. Can't repro it in pantheon, so could
@@ -398,11 +393,6 @@ def test_label_encoder_default_params_fit_transform(new_penguins_df):
 
     expected = pd.DataFrame(
         {
-            "labelencoded_sex": [
-                2,
-                1,
-                1,
-            ],
             "labelencoded_species": [
                 1,
                 1,
@@ -444,7 +434,7 @@ def test_label_encoder_series_default_params(new_penguins_df):
 
 def test_label_encoder_params(new_penguins_df):
     encoder = bigframes.ml.preprocessing.LabelEncoder(100, 2)
-    encoder.fit(new_penguins_df[["species", "sex"]])
+    encoder.fit(new_penguins_df[["species"]])
 
     result = encoder.transform(new_penguins_df).to_pandas()
 
@@ -455,11 +445,6 @@ def test_label_encoder_params(new_penguins_df):
 
     expected = pd.DataFrame(
         {
-            "labelencoded_sex": [
-                0,
-                0,
-                0,
-            ],
             "labelencoded_species": [
                 0,
                 0,
@@ -475,7 +460,7 @@ def test_label_encoder_params(new_penguins_df):
 
 def test_label_encoder_different_data(penguins_df_default_index, new_penguins_df):
     encoder = bigframes.ml.preprocessing.LabelEncoder()
-    encoder.fit(penguins_df_default_index[["species", "sex"]])
+    encoder.fit(penguins_df_default_index[["species"]])
 
     result = encoder.transform(new_penguins_df).to_pandas()
 
@@ -486,11 +471,6 @@ def test_label_encoder_different_data(penguins_df_default_index, new_penguins_df
 
     expected = pd.DataFrame(
         {
-            "labelencoded_sex": [
-                3,
-                2,
-                2,
-            ],
             "labelencoded_species": [
                 1,
                 1,

third_party/bigframes_vendored/sklearn/preprocessing/_label.py

@@ -28,23 +28,23 @@ class LabelEncoder(BaseEstimator):
             Default None, set limit to 1,000,000.
     """
 
-    def fit(self, X):
-        """Fit LabelEncoder to X.
+    def fit(self, y):
+        """Fit label encoder.
 
         Args:
-            X (bigframes.dataframe.DataFrame or bigframes.series.Series):
+            y (bigframes.dataframe.DataFrame or bigframes.series.Series):
                 The DataFrame or Series with training data.
 
         Returns:
             LabelEncoder: Fitted encoder.
         """
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 
-    def transform(self, X):
-        """Transform X using label encoding.
+    def transform(self, y):
+        """Transform y using label encoding.
 
         Args:
-            X (bigframes.dataframe.DataFrame or bigframes.series.Series):
+            y (bigframes.dataframe.DataFrame or bigframes.series.Series):
                 The DataFrame or Series to be transformed.
 
         Returns: