CLN: Make first argument in IO writers keyword only; remove gbq (#57279)

Author: mroeschke

asv_bench/benchmarks/io/hdf.py

@@ -123,12 +123,12 @@ def setup(self, format):
             index=date_range("20000101", periods=N, freq="h"),
         )
         self.df["object"] = Index([f"i-{i}" for i in range(N)], dtype=object)
-        self.df.to_hdf(self.fname, "df", format=format)
+        self.df.to_hdf(self.fname, key="df", format=format)
 
         # Numeric df
         self.df1 = self.df.copy()
         self.df1 = self.df1.reset_index()
-        self.df1.to_hdf(self.fname, "df1", format=format)
+        self.df1.to_hdf(self.fname, key="df1", format=format)
 
     def time_read_hdf(self, format):
         read_hdf(self.fname, "df")
@@ -137,7 +137,7 @@ def peakmem_read_hdf(self, format):
         read_hdf(self.fname, "df")
 
     def time_write_hdf(self, format):
-        self.df.to_hdf(self.fname, "df", format=format)
+        self.df.to_hdf(self.fname, key="df", format=format)
 
 
 from ..pandas_vb_common import setup  # noqa: F401 isort:skip

doc/redirects.csv

@@ -495,7 +495,6 @@ generated/pandas.DataFrame.to_csv,../reference/api/pandas.DataFrame.to_csv
 generated/pandas.DataFrame.to_dict,../reference/api/pandas.DataFrame.to_dict
 generated/pandas.DataFrame.to_excel,../reference/api/pandas.DataFrame.to_excel
 generated/pandas.DataFrame.to_feather,../reference/api/pandas.DataFrame.to_feather
-generated/pandas.DataFrame.to_gbq,../reference/api/pandas.DataFrame.to_gbq
 generated/pandas.DataFrame.to_hdf,../reference/api/pandas.DataFrame.to_hdf
 generated/pandas.DataFrame.to,../reference/api/pandas.DataFrame.to
 generated/pandas.DataFrame.to_json,../reference/api/pandas.DataFrame.to_json
@@ -890,7 +889,6 @@ generated/pandas.read_csv,../reference/api/pandas.read_csv
 generated/pandas.read_excel,../reference/api/pandas.read_excel
 generated/pandas.read_feather,../reference/api/pandas.read_feather
 generated/pandas.read_fwf,../reference/api/pandas.read_fwf
-generated/pandas.read_gbq,../reference/api/pandas.read_gbq
 generated/pandas.read_hdf,../reference/api/pandas.read_hdf
 generated/pandas.read,../reference/api/pandas.read
 generated/pandas.read_json,../reference/api/pandas.read_json

doc/source/conf.py

@@ -323,7 +323,6 @@
     ("pandas.io.clipboard.read_clipboard", "pandas.read_clipboard"),
     ("pandas.io.excel.ExcelFile.parse", "pandas.ExcelFile.parse"),
     ("pandas.io.excel.read_excel", "pandas.read_excel"),
-    ("pandas.io.gbq.read_gbq", "pandas.read_gbq"),
     ("pandas.io.html.read_html", "pandas.read_html"),
     ("pandas.io.json.read_json", "pandas.read_json"),
     ("pandas.io.parsers.read_csv", "pandas.read_csv"),
@@ -812,8 +811,6 @@ def setup(app) -> None:
         for link in [
             "http://scatterci.github.io/pydata/pandas",
             "http://specs.frictionlessdata.io/json-table-schema/",
-            "https://cloud.google.com/bigquery/docs/access-control#roles",
-            "https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs#configuration.query",
             "https://crates.io/crates/calamine",
             "https://devguide.python.org/setup/#macos",
             "https://en.wikipedia.org/wiki/Imputation_statistics",
@@ -829,7 +826,6 @@ def setup(app) -> None:
             "https://nipunbatra.github.io/blog/visualisation/2013/05/01/aggregation-timeseries.html",
             "https://nbviewer.ipython.org/gist/metakermit/5720498",
             "https://numpy.org/doc/stable/user/basics.byteswapping.html",
-            "https://pandas-gbq.readthedocs.io/en/latest/changelog.html#changelog-0-8-0",
             "https://pandas.pydata.org/pandas-docs/stable/io.html#io-chunking",
             "https://pandas.pydata.org/pandas-docs/stable/ecosystem.html",
             "https://sqlalchemy.readthedocs.io/en/latest/dialects/index.html",

doc/source/getting_started/install.rst

@@ -386,7 +386,6 @@ Dependency                Minimum Version    pip extra       Notes
 fsspec                    2022.11.0          fss, gcp, aws   Handling files aside from simple local and HTTP (required
                                                              dependency of s3fs, gcsfs).
 gcsfs                     2022.11.0          gcp             Google Cloud Storage access
-pandas-gbq                0.19.0             gcp             Google Big Query access
 s3fs                      2022.11.0          aws             Amazon S3 access
 ========================= ================== =============== =============================================================
 

doc/source/reference/frame.rst

@@ -381,7 +381,6 @@ Serialization / IO / conversion
    DataFrame.to_feather
    DataFrame.to_latex
    DataFrame.to_stata
-   DataFrame.to_gbq
    DataFrame.to_records
    DataFrame.to_string
    DataFrame.to_clipboard

doc/source/reference/io.rst

@@ -188,13 +188,6 @@ SQL
    read_sql
    DataFrame.to_sql
 
-Google BigQuery
-~~~~~~~~~~~~~~~
-.. autosummary::
-   :toctree: api/
-
-   read_gbq
-
 STATA
 ~~~~~
 .. autosummary::

doc/source/user_guide/io.rst

@@ -36,7 +36,6 @@ The pandas I/O API is a set of top level ``reader`` functions accessed like
     binary;`SPSS <https://en.wikipedia.org/wiki/SPSS>`__;:ref:`read_spss<io.spss_reader>`;
     binary;`Python Pickle Format <https://docs.python.org/3/library/pickle.html>`__;:ref:`read_pickle<io.pickle>`;:ref:`to_pickle<io.pickle>`
     SQL;`SQL <https://en.wikipedia.org/wiki/SQL>`__;:ref:`read_sql<io.sql>`;:ref:`to_sql<io.sql>`
-    SQL;`Google BigQuery <https://en.wikipedia.org/wiki/BigQuery>`__;:ref:`read_gbq<io.bigquery>`;:ref:`to_gbq<io.bigquery>`
 
 :ref:`Here <io.perf>` is an informal performance comparison for some of these IO methods.
 
@@ -6096,10 +6095,6 @@ Google BigQuery
 
 The ``pandas-gbq`` package provides functionality to read/write from Google BigQuery.
 
-pandas integrates with this external package. if ``pandas-gbq`` is installed, you can
-use the pandas methods ``pd.read_gbq`` and ``DataFrame.to_gbq``, which will call the
-respective functions from ``pandas-gbq``.
-
 Full documentation can be found `here <https://pandas-gbq.readthedocs.io/en/latest/>`__.
 
 .. _io.stata:

doc/source/whatsnew/v3.0.0.rst

@@ -102,12 +102,14 @@ Deprecations
 
 Removal of prior version deprecations/changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+- All arguments except the first ``path``-like argument in IO writers are now keyword only (:issue:`54229`)
 - Removed :meth:`DataFrame.first` and :meth:`DataFrame.last` (:issue:`53710`)
 - Removed :meth:`DataFrameGroupby.fillna` and :meth:`SeriesGroupBy.fillna` (:issue:`55719`)
 - Removed ``DataFrameGroupBy.grouper`` and ``SeriesGroupBy.grouper`` (:issue:`56521`)
 - Removed ``axis`` argument from :meth:`DataFrame.groupby`, :meth:`Series.groupby`, :meth:`DataFrame.rolling`, :meth:`Series.rolling`, :meth:`DataFrame.resample`, and :meth:`Series.resample` (:issue:`51203`)
 - Removed ``axis`` argument from all groupby operations (:issue:`50405`)
 - Removed ``pandas.io.sql.execute`` (:issue:`50185`)
+- Removed ``read_gbq`` and ``DataFrame.to_gbq``. Use ``pandas_gbq.read_gbq`` and ``pandas_gbq.to_gbq`` instead https://pandas-gbq.readthedocs.io/en/latest/api.html (:issue:`55525`)
 - Removed deprecated argument ``obj`` in :meth:`.DataFrameGroupBy.get_group` and :meth:`.SeriesGroupBy.get_group` (:issue:`53545`)
 - Removed the ``ArrayManager`` (:issue:`55043`)
 - Removed unused arguments ``*args`` and ``**kwargs`` in :class:`Resampler` methods (:issue:`50977`)

pandas/__init__.py

@@ -162,7 +162,6 @@
     read_parquet,
     read_orc,
     read_feather,
-    read_gbq,
     read_html,
     read_xml,
     read_json,
@@ -352,7 +351,6 @@
     "read_excel",
     "read_feather",
     "read_fwf",
-    "read_gbq",
     "read_hdf",
     "read_html",
     "read_json",

pandas/_typing.py

@@ -510,9 +510,6 @@ def closed(self) -> bool:
 # from_dict
 FromDictOrient = Literal["columns", "index", "tight"]
 
-# to_gbc
-ToGbqIfexist = Literal["fail", "replace", "append"]
-
 # to_stata
 ToStataByteorder = Literal[">", "<", "little", "big"]
 

pandas/compat/_optional.py

@@ -37,7 +37,6 @@
     "numexpr": "2.8.4",
     "odfpy": "1.4.1",
     "openpyxl": "3.1.0",
-    "pandas_gbq": "0.19.0",
     "psycopg2": "2.9.6",  # (dt dec pq3 ext lo64)
     "pymysql": "1.0.2",
     "pyarrow": "10.0.1",
@@ -68,7 +67,6 @@
     "jinja2": "Jinja2",
     "lxml.etree": "lxml",
     "odf": "odfpy",
-    "pandas_gbq": "pandas-gbq",
     "python_calamine": "python-calamine",
     "sqlalchemy": "SQLAlchemy",
     "tables": "pytables",