fix: address more technical writers feedback

bigframes/_config/compute_options.py

@@ -21,7 +21,7 @@
 @dataclasses.dataclass
 class ComputeOptions:
     """
-    Encapsulates configuration for compute options.
+    Encapsulates the configuration for compute options.
 
     **Examples:**
 
@@ -39,7 +39,7 @@ class ComputeOptions:
             Limits the bytes billed for query jobs. Queries that will have
             bytes billed beyond this limit will fail (without incurring a
             charge). If unspecified, this will be set to your project default.
-            See `maximum_bytes_billed <https://cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.job.QueryJobConfig#google_cloud_bigquery_job_QueryJobConfig_maximum_bytes_billed>`_.
+            See `maximum_bytes_billed`: https://cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.job.QueryJobConfig#google_cloud_bigquery_job_QueryJobConfig_maximum_bytes_billed.
         enable_multi_query_execution (bool, Options):
             If enabled, large queries may be factored into multiple smaller queries
             in order to avoid generating queries that are too complex for the query

bigframes/ml/base.py

@@ -193,7 +193,7 @@ def to_gbq(self: _T, model_name: str, replace: bool = False) -> _T:
             model_name (str):
                 The name of the model.
             replace (bool, default False):
-                Whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
             Saved transformer."""

bigframes/ml/cluster.py

@@ -177,7 +177,7 @@ def to_gbq(self, model_name: str, replace: bool = False) -> KMeans:
             model_name (str):
                 the name of the model.
             replace (bool, default False):
-                whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
             KMeans: saved model."""

bigframes/ml/decomposition.py

@@ -171,7 +171,7 @@ def to_gbq(self, model_name: str, replace: bool = False) -> PCA:
             model_name (str):
                 the name of the model.
             replace (bool, default False):
-                whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
             PCA: saved model."""

bigframes/ml/ensemble.py

@@ -192,9 +192,9 @@ def to_gbq(self, model_name: str, replace: bool = False) -> XGBRegressor:
             model_name (str):
                 The name of the model.
             replace (bool, default False):
-                Whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
-        Returns: saved model."""
+        Returns: Saved model."""
         if not self._bqml_model:
             raise RuntimeError("A model must be fitted before it can be saved")
 
@@ -345,10 +345,10 @@ def to_gbq(self, model_name: str, replace: bool = False) -> XGBClassifier:
             model_name (str):
                 The name of the model.
             replace (bool, default False):
-                Whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
-            XGBClassifier: saved model."""
+            XGBClassifier: Saved model."""
         if not self._bqml_model:
             raise RuntimeError("A model must be fitted before it can be saved")
 
@@ -508,10 +508,10 @@ def to_gbq(self, model_name: str, replace: bool = False) -> RandomForestRegresso
             model_name (str):
                 The name of the model.
             replace (bool, default False):
-                Whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
-            RandomForestRegressor: saved model."""
+            RandomForestRegressor: Saved model."""
         if not self._bqml_model:
             raise RuntimeError("A model must be fitted before it can be saved")
 
@@ -671,10 +671,10 @@ def to_gbq(self, model_name: str, replace: bool = False) -> RandomForestClassifi
             model_name (str):
                 The name of the model.
             replace (bool, default False):
-                Whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
-            RandomForestClassifier: saved model."""
+            RandomForestClassifier: Saved model."""
         if not self._bqml_model:
             raise RuntimeError("A model must be fitted before it can be saved")
 

bigframes/ml/forecasting.py

@@ -363,10 +363,10 @@ def to_gbq(self, model_name: str, replace: bool = False) -> ARIMAPlus:
             model_name (str):
                 the name of the model.
             replace (bool, default False):
-                whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
-            ARIMAPlus: saved model."""
+            ARIMAPlus: Saved model."""
         if not self._bqml_model:
             raise RuntimeError("A model must be fitted before it can be saved")
 

bigframes/ml/imported.py

@@ -32,7 +32,7 @@ class TensorFlowModel(base.Predictor):
 
     Args:
         model_path (str):
-            GCS path that holds the model files.
+            Cloud Storage path that holds the model files.
         session (BigQuery Session):
             BQ session to create the model.
     """
@@ -69,10 +69,10 @@ def predict(self, X: Union[bpd.DataFrame, bpd.Series]) -> bpd.DataFrame:
 
         Args:
             X (bigframes.dataframe.DataFrame):
-                Input DataFrame, schema is defined by the model.
+                Input DataFrame. Schema is defined by the model.
 
         Returns:
-            bigframes.dataframe.DataFrame: Output DataFrame, schema is defined by the model."""
+            bigframes.dataframe.DataFrame: Output DataFrame. Schema is defined by the model."""
 
         if not self._bqml_model:
             if self.model_path is None:
@@ -91,10 +91,10 @@ def to_gbq(self, model_name: str, replace: bool = False) -> TensorFlowModel:
             model_name (str):
                 the name of the model.
             replace (bool, default False):
-                whether to replace if the model already exists. Default to False.
+                 Default to False.
 
         Returns:
-            TensorFlowModel: saved model."""
+            TensorFlowModel: Saved model."""
         if not self._bqml_model:
             if self.model_path is None:
                 raise ValueError("Model GCS path must be provided.")
@@ -146,7 +146,7 @@ def predict(self, X: Union[bpd.DataFrame, bpd.Series]) -> bpd.DataFrame:
 
         Args:
             X (bigframes.dataframe.DataFrame or bigframes.series.Series):
-                Input DataFrame or Series, schema is defined by the model.
+                Input DataFrame or Series. Schema is defined by the model.
 
         Returns:
             bigframes.dataframe.DataFrame: Output DataFrame, schema is defined by the model."""
@@ -168,10 +168,10 @@ def to_gbq(self, model_name: str, replace: bool = False) -> ONNXModel:
             model_name (str):
                 the name of the model.
             replace (bool, default False):
-                whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
-            ONNXModel: saved model."""
+            ONNXModel: Saved model."""
         if not self._bqml_model:
             if self.model_path is None:
                 raise ValueError("Model GCS path must be provided.")
@@ -262,10 +262,10 @@ def predict(self, X: Union[bpd.DataFrame, bpd.Series]) -> bpd.DataFrame:
 
         Args:
             X (bigframes.dataframe.DataFrame or bigframes.series.Series):
-                Input DataFrame or Series, schema is defined by the model.
+                Input DataFrame or Series. Schema is defined by the model.
 
         Returns:
-            bigframes.dataframe.DataFrame: Output DataFrame, schema is defined by the model."""
+            bigframes.dataframe.DataFrame: Output DataFrame. Schema is defined by the model."""
 
         if not self._bqml_model:
             if self.model_path is None:
@@ -284,10 +284,10 @@ def to_gbq(self, model_name: str, replace: bool = False) -> XGBoostModel:
             model_name (str):
                 the name of the model.
             replace (bool, default False):
-                whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
-            XGBoostModel: saved model."""
+            XGBoostModel: Saved model."""
         if not self._bqml_model:
             if self.model_path is None:
                 raise ValueError("Model GCS path must be provided.")

bigframes/ml/linear_model.py

@@ -184,7 +184,7 @@ def to_gbq(self, model_name: str, replace: bool = False) -> LinearRegression:
             model_name (str):
                 the name of the model.
             replace (bool, default False):
-                whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
             LinearRegression: saved model."""
@@ -349,7 +349,7 @@ def to_gbq(self, model_name: str, replace: bool = False) -> LogisticRegression:
             model_name (str):
                 the name of the model.
             replace (bool, default False):
-                whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
             LogisticRegression: saved model."""

bigframes/ml/llm.py

@@ -248,7 +248,7 @@ def to_gbq(self, model_name: str, replace: bool = False) -> PaLM2TextGenerator:
             model_name (str):
                 the name of the model.
             replace (bool, default False):
-                whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
             PaLM2TextGenerator: saved model."""
@@ -415,7 +415,7 @@ def to_gbq(
             model_name (str):
                 the name of the model.
             replace (bool, default False):
-                whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
             PaLM2TextEmbeddingGenerator: saved model."""
@@ -595,7 +595,7 @@ def to_gbq(self, model_name: str, replace: bool = False) -> GeminiTextGenerator:
             model_name (str):
                 the name of the model.
             replace (bool, default False):
-                whether to replace if the model already exists. Default to False.
+                Determine whether to replace if the model already exists. Default to False.
 
         Returns:
             GeminiTextGenerator: saved model."""

third_party/bigframes_vendored/pandas/core/config_init.py

@@ -13,7 +13,7 @@
 from __future__ import annotations
 
 display_options_doc = """
-Encapsulates configuration for displaying objects.
+Encapsulates the configuration for displaying objects.
 
 **Examples:**
 
@@ -79,7 +79,7 @@
 """
 
 sampling_options_doc = """
-Encapsulates configuration for data sampling.
+Encapsulates the configuration for data sampling.
 
 Attributes:
     max_download_size (int, default 500):

third_party/bigframes_vendored/pandas/core/groupby/__init__.py

@@ -24,7 +24,7 @@ def any(self):
         Returns:
             Series or DataFrame: DataFrame or Series of boolean values,
                 where a value is True if any element is True within its
-                respective group, False otherwise.
+                respective group; otherwise False.
         """
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 
@@ -35,7 +35,7 @@ def all(self):
         Returns:
             Series or DataFrame: DataFrame or Series of boolean values,
                 where a value is True if all elements are True within its
-                respective group, False otherwise.
+                respective group; otherwise False.
         """
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 
@@ -339,7 +339,7 @@ def expanding(self, *args, **kwargs):
         Provides expanding functionality.
 
         Returns:
-            Series or DataFrame: A expanding grouper, providing expanding functionality per group.
+            Series or DataFrame: An expanding grouper, providing expanding functionality per group.
         """
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 

third_party/bigframes_vendored/pandas/core/indexes/base.py

@@ -83,7 +83,7 @@ def copy(
             name (Label, optional):
                 Set name for new object.
         Returns:
-            Index: Index refer to new object which is a copy of this object.
+            Index: Index reference to new object, which is a copy of this object.
         """
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 
@@ -148,7 +148,7 @@ def isin(self, values):
         """
         Return a boolean array where the index values are in `values`.
 
-        Compute boolean array of whether each index value is found in the
+        Compute boolean array to check whether each index value is found in the
         passed set of values. The length of the returned boolean array matches
         the length of the index.
 
@@ -195,7 +195,7 @@ def max(self):
 
     def argmin(self) -> int:
         """
-        Return int position of the smallest value in the Series.
+        Return int position of the smallest value in the series.
 
         If the minimum is achieved in multiple locations,
         the first row position is returned.
@@ -264,7 +264,7 @@ def value_counts(
 
         Args:
             normalize (bool, default False):
-                If True then the object returned will contain the relative
+                If True, then the object returned will contain the relative
                 frequencies of the unique values.
             sort (bool, default True):
                 Sort by frequencies.
@@ -316,7 +316,7 @@ def drop(self, labels) -> Index:
             labels (array-like or scalar):
 
         Returns:
-            Index: Will be same type as self
+            Index: Will be same type as self.
         """
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 

third_party/bigframes_vendored/pandas/core/series.py

@@ -2836,7 +2836,7 @@ def unstack(self, level):
 
     def argmax(self):
         """
-        Return int position of the smallest value in the Series.
+        Return int position of the smallest value in the series.
 
         If the minimum is achieved in multiple locations, the first row position is returned.
 

third_party/bigframes_vendored/sklearn/base.py

@@ -81,9 +81,9 @@ class ClassifierMixin:
     def score(self, X, y):
         """Return the mean accuracy on the given test data and labels.
 
-        In multi-label classification, this is the subset accuracy
-        which is a harsh metric since you require for each sample that
-        each label set be correctly predicted.
+        In multi-label classification, this is the subset accuracy,
+        which is a harsh metric since you require that
+        each label set be correctly predicted for each sample.
 
         .. note::
 

third_party/bigframes_vendored/sklearn/decomposition/_pca.py

@@ -22,7 +22,7 @@ class PCA(BaseEstimator, metaclass=ABCMeta):
 
     Args:
         n_components (int, float or None, default None):
-            Number of components to keep. If n_components is not set all
+            Number of components to keep. If n_components is not set, all
             components are kept, n_components = min(n_samples, n_features).
             If 0 < n_components < 1, select the number of components such that the amount of variance that needs to be explained is greater than the percentage specified by n_components.
         svd_solver ("full", "randomized" or "auto", default "auto"):
@@ -75,7 +75,7 @@ def predict(self, X):
                 Series or a DataFrame to predict.
 
         Returns:
-            bigframes.dataframe.DataFrame: predicted DataFrames."""
+            bigframes.dataframe.DataFrame: Predicted DataFrames."""
         raise NotImplementedError(constants.ABSTRACT_METHOD_ERROR_MESSAGE)
 
     @property
@@ -90,7 +90,7 @@ def components_(self):
 
                 numerical_value: If feature is numeric, the value of feature for the principal component that principal_component_id identifies. If feature isn't numeric, the value is NULL.
 
-                categorical_value: An list of mappings containing information about categorical features. Each mapping contains the following fields:
+                categorical_value: A list of mappings containing information about categorical features. Each mapping contains the following fields:
                     categorical_value.category: The name of each category.
 
                     categorical_value.value: The value of categorical_value.category for the centroid that centroid_id identifies.