fix: move third_party.bigframes_vendored to bigframes_vendored (#424

)

This will avoid potential conflicts when run from a location that contains the commonly named `third_party` directory.

Note: I followed the instructions here: https://stackoverflow.com/a/17179022/101923 but I also had to add a `pyproject.toml` file to support editable installations (see: https://togithub.com/pypa/setuptools/issues/230#issuecomment-1473278299).

Fixes internal issue 328781348.
🦕

MANIFEST.in

@@ -16,7 +16,7 @@
 
 # Generated by synthtool. DO NOT EDIT!
 include README.rst LICENSE
-recursive-include third_party *
+recursive-include third_party/bigframes_vendored *
 recursive-include bigframes *.json *.proto py.typed
 recursive-include tests *
 global-exclude *.py[co]

bigframes/_config/__init__.py

@@ -17,11 +17,12 @@
 DataFrames from this package.
 """
 
+import bigframes_vendored.pandas._config.config as pandas_config
+
 import bigframes._config.bigquery_options as bigquery_options
 import bigframes._config.compute_options as compute_options
 import bigframes._config.display_options as display_options
 import bigframes._config.sampling_options as sampling_options
-import third_party.bigframes_vendored.pandas._config.config as pandas_config
 
 
 class Options:

bigframes/_config/display_options.py

@@ -18,10 +18,9 @@
 import dataclasses
 from typing import Literal, Optional
 
+import bigframes_vendored.pandas.core.config_init as vendored_pandas_config
 import pandas as pd
 
-import third_party.bigframes_vendored.pandas.core.config_init as vendored_pandas_config
-
 
 @dataclasses.dataclass
 class DisplayOptions:

bigframes/_config/sampling_options.py

@@ -19,7 +19,7 @@
 import dataclasses
 from typing import Literal, Optional
 
-import third_party.bigframes_vendored.pandas.core.config_init as vendored_pandas_config
+import bigframes_vendored.pandas.core.config_init as vendored_pandas_config
 
 
 @dataclasses.dataclass

bigframes/core/blocks.py

@@ -29,6 +29,7 @@
 from typing import Iterable, List, Mapping, Optional, Sequence, Tuple
 import warnings
 
+import bigframes_vendored.pandas.io.common as vendored_pandas_io_common
 import google.cloud.bigquery as bigquery
 import pandas as pd
 
@@ -45,7 +46,6 @@
 import bigframes.operations as ops
 import bigframes.operations.aggregations as agg_ops
 import bigframes.session._io.pandas
-import third_party.bigframes_vendored.pandas.io.common as vendored_pandas_io_common
 
 # Type constraint for wherever column labels are used
 Label = typing.Hashable

bigframes/core/compile/aggregate_compiler.py

@@ -15,6 +15,7 @@
 import typing
 from typing import cast, Optional
 
+import bigframes_vendored.ibis.expr.operations as vendored_ibis_ops
 import ibis
 import ibis.expr.datatypes as ibis_dtypes
 import ibis.expr.types as ibis_types
@@ -26,7 +27,6 @@
 import bigframes.core.window_spec as window_spec
 import bigframes.dtypes as dtypes
 import bigframes.operations.aggregations as agg_ops
-import third_party.bigframes_vendored.ibis.expr.operations as vendored_ibis_ops
 
 scalar_compiler = scalar_compilers.scalar_op_compiler
 

bigframes/core/groupby/__init__.py

@@ -16,6 +16,7 @@
 
 import typing
 
+import bigframes_vendored.pandas.core.groupby as vendored_pandas_groupby
 import pandas as pd
 
 import bigframes.constants as constants
@@ -30,7 +31,6 @@
 import bigframes.dtypes as dtypes
 import bigframes.operations.aggregations as agg_ops
 import bigframes.series as series
-import third_party.bigframes_vendored.pandas.core.groupby as vendored_pandas_groupby
 
 
 @log_adapter.class_logger

bigframes/core/indexes/index.py

@@ -19,6 +19,7 @@
 import typing
 from typing import Hashable, Optional, Sequence, Union
 
+import bigframes_vendored.pandas.core.indexes.base as vendored_pandas_index
 import google.cloud.bigquery as bigquery
 import numpy as np
 import pandas
@@ -33,7 +34,6 @@
 import bigframes.formatting_helpers as formatter
 import bigframes.operations as ops
 import bigframes.operations.aggregations as agg_ops
-import third_party.bigframes_vendored.pandas.core.indexes.base as vendored_pandas_index
 
 if typing.TYPE_CHECKING:
     import bigframes.dataframe

bigframes/core/tools/datetimes.py

@@ -16,14 +16,14 @@
 from datetime import datetime
 from typing import Optional, Union
 
+import bigframes_vendored.pandas.core.tools.datetimes as vendored_pandas_datetimes
 import pandas as pd
 
 import bigframes.constants as constants
 import bigframes.core.global_session as global_session
 import bigframes.dataframe
 import bigframes.operations as ops
 import bigframes.series
-import third_party.bigframes_vendored.pandas.core.tools.datetimes as vendored_pandas_datetimes
 
 
 def to_datetime(

bigframes/core/utils.py

@@ -15,11 +15,10 @@
 import typing
 from typing import Hashable, Iterable, List
 
+import bigframes_vendored.pandas.io.common as vendored_pandas_io_common
 import pandas as pd
 import typing_extensions
 
-import third_party.bigframes_vendored.pandas.io.common as vendored_pandas_io_common
-
 UNNAMED_COLUMN_ID = "bigframes_unnamed_column"
 UNNAMED_INDEX_ID = "bigframes_unnamed_index"
 

bigframes/core/window/__init__.py

@@ -16,11 +16,12 @@
 
 import typing
 
+import bigframes_vendored.pandas.core.window.rolling as vendored_pandas_rolling
+
 from bigframes.core import log_adapter
 import bigframes.core as core
 import bigframes.core.blocks as blocks
 import bigframes.operations.aggregations as agg_ops
-import third_party.bigframes_vendored.pandas.core.window.rolling as vendored_pandas_rolling
 
 
 @log_adapter.class_logger

bigframes/dataframe.py

@@ -34,6 +34,8 @@
     Union,
 )
 
+import bigframes_vendored.pandas.core.frame as vendored_pandas_frame
+import bigframes_vendored.pandas.pandas._typing as vendored_pandas_typing
 import google.api_core.exceptions
 import google.cloud.bigquery as bigquery
 import numpy
@@ -63,8 +65,6 @@
 import bigframes.series
 import bigframes.series as bf_series
 import bigframes.session._io.bigquery
-import third_party.bigframes_vendored.pandas.core.frame as vendored_pandas_frame
-import third_party.bigframes_vendored.pandas.pandas._typing as vendored_pandas_typing
 
 if typing.TYPE_CHECKING:
     import bigframes.session

bigframes/dtypes.py

@@ -20,6 +20,9 @@
 import typing
 from typing import Any, Dict, Iterable, Literal, Tuple, Union
 
+import bigframes_vendored.google_cloud_bigquery._pandas_helpers as gcb3p_pandas_helpers
+import bigframes_vendored.ibis.backends.bigquery.datatypes as third_party_ibis_bqtypes
+import bigframes_vendored.ibis.expr.operations as vendored_ibis_ops
 import geopandas as gpd  # type: ignore
 import google.cloud.bigquery as bigquery
 import ibis
@@ -31,9 +34,6 @@
 import pyarrow as pa
 
 import bigframes.constants as constants
-import third_party.bigframes_vendored.google_cloud_bigquery._pandas_helpers as gcb3p_pandas_helpers
-import third_party.bigframes_vendored.ibis.backends.bigquery.datatypes as third_party_ibis_bqtypes
-import third_party.bigframes_vendored.ibis.expr.operations as vendored_ibis_ops
 
 # Type hints for Pandas dtypes supported by BigQuery DataFrame
 Dtype = Union[

bigframes/functions/remote_function.py

@@ -32,6 +32,7 @@
 if TYPE_CHECKING:
     from bigframes.session import Session
 
+import bigframes_vendored.ibis.backends.bigquery.datatypes as third_party_ibis_bqtypes
 import cloudpickle
 import google.api_core.exceptions
 import google.api_core.retry
@@ -47,7 +48,6 @@
 from bigframes import clients
 import bigframes.constants as constants
 import bigframes.dtypes
-import third_party.bigframes_vendored.ibis.backends.bigquery.datatypes as third_party_ibis_bqtypes
 
 logger = logging.getLogger(__name__)
 

bigframes/ml/base.py

@@ -24,12 +24,13 @@
 import abc
 from typing import cast, Optional, TypeVar, Union
 
+import bigframes_vendored.sklearn.base
+
 from bigframes.ml import core
 import bigframes.pandas as bpd
-import third_party.bigframes_vendored.sklearn.base
 
 
-class BaseEstimator(third_party.bigframes_vendored.sklearn.base.BaseEstimator, abc.ABC):
+class BaseEstimator(bigframes_vendored.sklearn.base.BaseEstimator, abc.ABC):
     """
     A BigQuery DataFrames machine learning component following the SKLearn API
     design Ref: https://bit.ly/3NyhKjN
@@ -80,7 +81,7 @@ def __repr__(self):
 
         # Estimator pretty printer adapted from Sklearn's, which is in turn an adaption of
         # the inbuilt pretty-printer in CPython
-        import third_party.bigframes_vendored.cpython._pprint as adapted_pprint
+        import bigframes_vendored.cpython._pprint as adapted_pprint
 
         prettyprinter = adapted_pprint._EstimatorPrettyPrinter(
             compact=True, indent=1, indent_at_name=True, n_max_elements_to_show=30

bigframes/ml/cluster.py

@@ -19,22 +19,22 @@
 
 from typing import Dict, List, Optional, Union
 
+import bigframes_vendored.sklearn.cluster._kmeans
 from google.cloud import bigquery
 
 import bigframes
 from bigframes.core import log_adapter
 from bigframes.ml import base, core, globals, utils
 import bigframes.pandas as bpd
-import third_party.bigframes_vendored.sklearn.cluster._kmeans
 
 
 @log_adapter.class_logger
 class KMeans(
     base.UnsupervisedTrainablePredictor,
-    third_party.bigframes_vendored.sklearn.cluster._kmeans.KMeans,
+    bigframes_vendored.sklearn.cluster._kmeans.KMeans,
 ):
 
-    __doc__ = third_party.bigframes_vendored.sklearn.cluster._kmeans.KMeans.__doc__
+    __doc__ = bigframes_vendored.sklearn.cluster._kmeans.KMeans.__doc__
 
     def __init__(self, n_clusters: int = 8):
         self.n_clusters = n_clusters

bigframes/ml/compose.py

@@ -21,11 +21,12 @@
 import typing
 from typing import List, Optional, Tuple, Union
 
+import bigframes_vendored.sklearn.compose._column_transformer
+
 from bigframes import constants
 from bigframes.core import log_adapter
 from bigframes.ml import base, core, globals, preprocessing, utils
 import bigframes.pandas as bpd
-import third_party.bigframes_vendored.sklearn.compose._column_transformer
 
 CompilablePreprocessorType = Union[
     preprocessing.OneHotEncoder,
@@ -40,10 +41,10 @@
 @log_adapter.class_logger
 class ColumnTransformer(
     base.Transformer,
-    third_party.bigframes_vendored.sklearn.compose._column_transformer.ColumnTransformer,
+    bigframes_vendored.sklearn.compose._column_transformer.ColumnTransformer,
 ):
     __doc__ = (
-        third_party.bigframes_vendored.sklearn.compose._column_transformer.ColumnTransformer.__doc__
+        bigframes_vendored.sklearn.compose._column_transformer.ColumnTransformer.__doc__
     )
 
     def __init__(

bigframes/ml/decomposition.py

@@ -19,21 +19,21 @@
 
 from typing import List, Optional, Union
 
+import bigframes_vendored.sklearn.decomposition._pca
 from google.cloud import bigquery
 
 import bigframes
 from bigframes.core import log_adapter
 from bigframes.ml import base, core, globals, utils
 import bigframes.pandas as bpd
-import third_party.bigframes_vendored.sklearn.decomposition._pca
 
 
 @log_adapter.class_logger
 class PCA(
     base.UnsupervisedTrainablePredictor,
-    third_party.bigframes_vendored.sklearn.decomposition._pca.PCA,
+    bigframes_vendored.sklearn.decomposition._pca.PCA,
 ):
-    __doc__ = third_party.bigframes_vendored.sklearn.decomposition._pca.PCA.__doc__
+    __doc__ = bigframes_vendored.sklearn.decomposition._pca.PCA.__doc__
 
     def __init__(self, n_components: int = 3):
         self.n_components = n_components

bigframes/ml/ensemble.py

@@ -19,14 +19,14 @@
 
 from typing import Dict, List, Literal, Optional, Union
 
+import bigframes_vendored.sklearn.ensemble._forest
+import bigframes_vendored.xgboost.sklearn
 from google.cloud import bigquery
 
 import bigframes
 from bigframes.core import log_adapter
 from bigframes.ml import base, core, globals, utils
 import bigframes.pandas as bpd
-import third_party.bigframes_vendored.sklearn.ensemble._forest
-import third_party.bigframes_vendored.xgboost.sklearn
 
 _BQML_PARAMS_MAPPING = {
     "booster": "boosterType",
@@ -51,9 +51,9 @@
 @log_adapter.class_logger
 class XGBRegressor(
     base.SupervisedTrainablePredictor,
-    third_party.bigframes_vendored.xgboost.sklearn.XGBRegressor,
+    bigframes_vendored.xgboost.sklearn.XGBRegressor,
 ):
-    __doc__ = third_party.bigframes_vendored.xgboost.sklearn.XGBRegressor.__doc__
+    __doc__ = bigframes_vendored.xgboost.sklearn.XGBRegressor.__doc__
 
     def __init__(
         self,
@@ -208,10 +208,10 @@ def to_gbq(self, model_name: str, replace: bool = False) -> XGBRegressor:
 @log_adapter.class_logger
 class XGBClassifier(
     base.SupervisedTrainablePredictor,
-    third_party.bigframes_vendored.xgboost.sklearn.XGBClassifier,
+    bigframes_vendored.xgboost.sklearn.XGBClassifier,
 ):
 
-    __doc__ = third_party.bigframes_vendored.xgboost.sklearn.XGBClassifier.__doc__
+    __doc__ = bigframes_vendored.xgboost.sklearn.XGBClassifier.__doc__
 
     def __init__(
         self,
@@ -364,12 +364,10 @@ def to_gbq(self, model_name: str, replace: bool = False) -> XGBClassifier:
 @log_adapter.class_logger
 class RandomForestRegressor(
     base.SupervisedTrainablePredictor,
-    third_party.bigframes_vendored.sklearn.ensemble._forest.RandomForestRegressor,
+    bigframes_vendored.sklearn.ensemble._forest.RandomForestRegressor,
 ):
 
-    __doc__ = (
-        third_party.bigframes_vendored.sklearn.ensemble._forest.RandomForestRegressor.__doc__
-    )
+    __doc__ = bigframes_vendored.sklearn.ensemble._forest.RandomForestRegressor.__doc__
 
     def __init__(
         self,
@@ -531,12 +529,10 @@ def to_gbq(self, model_name: str, replace: bool = False) -> RandomForestRegresso
 @log_adapter.class_logger
 class RandomForestClassifier(
     base.SupervisedTrainablePredictor,
-    third_party.bigframes_vendored.sklearn.ensemble._forest.RandomForestClassifier,
+    bigframes_vendored.sklearn.ensemble._forest.RandomForestClassifier,
 ):
 
-    __doc__ = (
-        third_party.bigframes_vendored.sklearn.ensemble._forest.RandomForestClassifier.__doc__
-    )
+    __doc__ = bigframes_vendored.sklearn.ensemble._forest.RandomForestClassifier.__doc__
 
     def __init__(
         self,