docs: link to ML.EVALUATE BQML page for score() methods

bigframes/ml/ensemble.py

@@ -507,6 +507,12 @@ def score(
     ):
         """Calculate evaluation metrics of the model.
 
+        .. note::
+
+            Output matches that of the BigQuery ML.EVALUTE function.
+            See: https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-evaluate#regression_models
+            for the outputs relevant to this model type.
+
         Args:
             X (bigframes.dataframe.DataFrame or bigframes.series.Series):
                 A BigQuery DataFrame as evaluation data.
@@ -676,6 +682,12 @@ def score(
     ):
         """Calculate evaluation metrics of the model.
 
+        .. note::
+
+            Output matches that of the BigQuery ML.EVALUTE function.
+            See: https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-evaluate#classification_models
+            for the outputs relevant to this model type.
+
         Args:
             X (bigframes.dataframe.DataFrame or bigframes.series.Series):
                 A BigQuery DataFrame as evaluation data.

bigframes/ml/forecasting.py

@@ -112,6 +112,12 @@ def score(
     ) -> bpd.DataFrame:
         """Calculate evaluation metrics of the model.
 
+        .. note::
+
+            Output matches that of the BigQuery ML.EVALUTE function.
+            See: https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-evaluate#time_series_models
+            for the outputs relevant to this model type.
+
         Args:
             X (bigframes.dataframe.DataFrame or bigframes.series.Series):
                 A BigQuery DataFrame only contains 1 column as

third_party/bigframes_vendored/sklearn/base.py

@@ -85,6 +85,12 @@ def score(self, X, y):
         which is a harsh metric since you require for each sample that
         each label set be correctly predicted.
 
+        .. note::
+
+            Output matches that of the BigQuery ML.EVALUTE function.
+            See: https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-evaluate#classification_models
+            for the outputs relevant to this model type.
+
         Args:
             X (bigframes.dataframe.DataFrame or bigframes.series.Series):
                 DataFrame of shape (n_samples, n_features). Test samples.
@@ -105,7 +111,13 @@ class RegressorMixin:
     _estimator_type = "regressor"
 
     def score(self, X, y):
-        """Return the evaluation metrics of the model.
+        """Calculate evaluation metrics of the model.
+
+        .. note::
+
+            Output matches that of the BigQuery ML.EVALUTE function.
+            See: https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-evaluate#regression_models
+            for the outputs relevant to this model type.
 
         Args:
             X (bigframes.dataframe.DataFrame or bigframes.series.Series):

third_party/bigframes_vendored/sklearn/cluster/_kmeans.py

@@ -12,7 +12,6 @@
 # License: BSD 3 clause
 
 from abc import ABC
-from typing import List, Optional
 
 from bigframes import constants
 from third_party.bigframes_vendored.sklearn.base import BaseEstimator
@@ -83,7 +82,13 @@ def score(
         X,
         y=None,
     ):
-        """Metrics of the model.
+        """Calculate evaluation metrics of the model.
+
+        .. note::
+
+            Output matches that of the BigQuery ML.EVALUTE function.
+            See: https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-evaluate#k-means_models
+            for the outputs relevant to this model type.
 
         Args:
             X (bigframes.dataframe.DataFrame or bigframes.series.Series):

third_party/bigframes_vendored/sklearn/decomposition/_pca.py

@@ -55,7 +55,13 @@ def fit(self, X, y=None):
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 
     def score(self, X=None, y=None):
-        """Return the metrics of the model.
+        """Calculate evaluation metrics of the model.
+
+        .. note::
+
+            Output matches that of the BigQuery ML.EVALUTE function.
+            See: https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-evaluate#pca_models
+            for the outputs relevant to this model type.
 
         Args:
             X (default None):