Merge branch 'master' into Fix_support_for_matplotlib_s_constrained_layout_25261

Author: mdruiter

.github/ISSUE_TEMPLATE/documentation_improvement.md

@@ -9,7 +9,7 @@ labels: "Docs, Needs Triage"
 
 #### Location of the documentation
 
-[this should provide the location of the documentation, e.g. "pandas.read_csv" or the URL of the documentation, e.g. "https://dev.pandas.io/docs/reference/api/pandas.read_csv.html"]
+[this should provide the location of the documentation, e.g. "pandas.read_csv" or the URL of the documentation, e.g. "https://pandas.pydata.org/docs/reference/api/pandas.read_csv.html"]
 
 **Note**: You can check the latest versions of the docs on `master` [here](https://pandas.pydata.org/docs/dev/).
 

.pre-commit-config.yaml

@@ -60,11 +60,11 @@ repos:
         entry: |
             (?x)
             # Check for imports from pandas.core.common instead of `import pandas.core.common as com`
-            from\ pandas\.core\.common\ import|
-            from\ pandas\.core\ import\ common|
+            from\ pandas\.core\.common\ import
+            |from\ pandas\.core\ import\ common
 
             # Check for imports from collections.abc instead of `from collections import abc`
-            from\ collections\.abc\ import
+            |from\ collections\.abc\ import
 
     -   id: non-standard-numpy.random-related-imports
         name: Check for non-standard numpy.random-related imports excluding pandas/_testing.py
@@ -73,24 +73,24 @@ repos:
         entry: |
             (?x)
             # Check for imports from np.random.<method> instead of `from numpy import random` or `from numpy.random import <method>`
-            from\ numpy\ import\ random|
-            from\ numpy.random\ import
+            from\ numpy\ import\ random
+            |from\ numpy.random\ import
         types: [python]
     -   id: non-standard-imports-in-tests
         name: Check for non-standard imports in test suite
         language: pygrep
         entry: |
             (?x)
             # Check for imports from pandas._testing instead of `import pandas._testing as tm`
-            from\ pandas\._testing\ import|
-            from\ pandas\ import\ _testing\ as\ tm|
+            from\ pandas\._testing\ import
+            |from\ pandas\ import\ _testing\ as\ tm
 
             # No direct imports from conftest
-            conftest\ import|
-            import\ conftest
+            |conftest\ import
+            |import\ conftest
 
             # Check for use of pandas.testing instead of tm
-            pd\.testing\.
+            |pd\.testing\.
         types: [python]
         files: ^pandas/tests/
     -   id: incorrect-code-directives
@@ -135,7 +135,7 @@ repos:
         files: ^pandas/tests/
     -   id: FrameOrSeriesUnion
         name: Check for use of Union[Series, DataFrame] instead of FrameOrSeriesUnion alias
-        entry: Union\[.*(Series.*DataFrame|DataFrame.*Series).*\]
+        entry: Union\[.*(Series,.*DataFrame|DataFrame,.*Series).*\]
         language: pygrep
         types: [python]
         exclude: ^pandas/_typing\.py$
@@ -148,9 +148,8 @@ repos:
         name: Check for outdated annotation syntax and missing error codes
         entry: |
             (?x)
-            \#\ type:\ (?!ignore)|
-            \#\ type:\s?ignore(?!\[)|
-            \)\ ->\ \"
+            \#\ type:\ (?!ignore)
+            |\#\ type:\s?ignore(?!\[)
         language: pygrep
         types: [python]
     -   id: np-bool
@@ -166,9 +165,15 @@ repos:
         files: ^pandas/tests/
         exclude: |
             (?x)^
-            pandas/tests/io/excel/test_writers\.py|
-            pandas/tests/io/pytables/common\.py|
-            pandas/tests/io/pytables/test_store\.py$
+            pandas/tests/io/excel/test_writers\.py
+            |pandas/tests/io/pytables/common\.py
+            |pandas/tests/io/pytables/test_store\.py$
+    -   id: no-pandas-api-types
+        name: Check code for instances of pd.api.types
+        entry: (pd|pandas)\.api\.types\.
+        language: pygrep
+        types: [python]
+        files: ^pandas/tests/
 -   repo: https://github.com/asottile/yesqa
     rev: v1.2.2
     hooks:
@@ -184,4 +189,9 @@ repos:
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown]
-        files: ^pandas/core/
+        files: ^pandas/
+        exclude: ^pandas/tests/
+-   repo: https://github.com/MarcoGorelli/no-string-hints
+    rev: v0.1.6
+    hooks:
+    -   id: no-string-hints

README.md

@@ -1,5 +1,5 @@
 <div align="center">
-  <img src="https://dev.pandas.io/static/img/pandas.svg"><br>
+  <img src="https://pandas.pydata.org/static/img/pandas.svg"><br>
 </div>
 
 -----------------

asv_bench/benchmarks/indexing.py

@@ -243,6 +243,20 @@ def time_loc_list(self, monotonic):
         monotonic.loc[80000:]
 
 
+class DatetimeIndexIndexing:
+    def setup(self):
+        dti = date_range("2016-01-01", periods=10000, tz="US/Pacific")
+        dti2 = dti.tz_convert("UTC")
+        self.dti = dti
+        self.dti2 = dti2
+
+    def time_get_indexer_mismatched_tz(self):
+        # reached via e.g.
+        #  ser = Series(range(len(dti)), index=dti)
+        #  ser[dti2]
+        self.dti.get_indexer(self.dti2)
+
+
 class CategoricalIndexIndexing:
 
     params = ["monotonic_incr", "monotonic_decr", "non_monotonic"]

asv_bench/benchmarks/io/csv.py

@@ -76,6 +76,54 @@ def time_frame(self, obs):
         self.data.to_csv(self.fname)
 
 
+class ToCSVIndexes(BaseIO):
+
+    fname = "__test__.csv"
+
+    @staticmethod
+    def _create_df(rows, cols):
+        index_cols = {
+            "index1": np.random.randint(0, rows, rows),
+            "index2": np.full(rows, 1, dtype=np.int),
+            "index3": np.full(rows, 1, dtype=np.int),
+        }
+        data_cols = {
+            f"col{i}": np.random.uniform(0, 100000.0, rows) for i in range(cols)
+        }
+        df = DataFrame({**index_cols, **data_cols})
+        return df
+
+    def setup(self):
+        ROWS = 100000
+        COLS = 5
+        # For tests using .head(), create an initial dataframe with this many times
+        # more rows
+        HEAD_ROW_MULTIPLIER = 10
+
+        self.df_standard_index = self._create_df(ROWS, COLS)
+
+        self.df_custom_index_then_head = (
+            self._create_df(ROWS * HEAD_ROW_MULTIPLIER, COLS)
+            .set_index(["index1", "index2", "index3"])
+            .head(ROWS)
+        )
+
+        self.df_head_then_custom_index = (
+            self._create_df(ROWS * HEAD_ROW_MULTIPLIER, COLS)
+            .head(ROWS)
+            .set_index(["index1", "index2", "index3"])
+        )
+
+    def time_standard_index(self):
+        self.df_standard_index.to_csv(self.fname)
+
+    def time_multiindex(self):
+        self.df_head_then_custom_index.to_csv(self.fname)
+
+    def time_head_of_multiindex(self):
+        self.df_custom_index_then_head.to_csv(self.fname)
+
+
 class StringIORewind:
     def data(self, stringio_object):
         stringio_object.seek(0)

asv_bench/benchmarks/reshape.py

@@ -5,6 +5,7 @@
 
 import pandas as pd
 from pandas import DataFrame, MultiIndex, date_range, melt, wide_to_long
+from pandas.api.types import CategoricalDtype
 
 
 class Melt:
@@ -196,7 +197,7 @@ def setup(self):
         categories = list(string.ascii_letters[:12])
         s = pd.Series(
             np.random.choice(categories, size=1000000),
-            dtype=pd.api.types.CategoricalDtype(categories),
+            dtype=CategoricalDtype(categories),
         )
         self.s = s
 

doc/source/conf.py

@@ -164,7 +164,7 @@
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
-# language = None
+language = "en"
 
 # There are two options for replacing |today|: either, you set today to some
 # non-false value, then it is used:

doc/source/getting_started/comparison/comparison_with_spreadsheets.rst

@@ -89,13 +89,6 @@ Both `Excel <https://support.microsoft.com/en-us/office/import-data-from-externa
 and :ref:`pandas <10min_tut_02_read_write>` can import data from various sources in various
 formats.
 
-Excel files
-'''''''''''
-
-Excel opens `various Excel file formats <https://support.microsoft.com/en-us/office/file-formats-that-are-supported-in-excel-0943ff2c-6014-4e8d-aaea-b83d51d46247>`_
-by double-clicking them, or using `the Open menu <https://support.microsoft.com/en-us/office/open-files-from-the-file-menu-97f087d8-3136-4485-8e86-c5b12a8c4176>`_.
-In pandas, you use :ref:`special methods for reading and writing from/to Excel files <io.excel>`.
-
 CSV
 '''
 
@@ -125,6 +118,27 @@ would be:
    # alternatively, read_table is an alias to read_csv with tab delimiter
    tips = pd.read_table("tips.csv", header=None)
 
+Excel files
+'''''''''''
+
+Excel opens `various Excel file formats <https://support.microsoft.com/en-us/office/file-formats-that-are-supported-in-excel-0943ff2c-6014-4e8d-aaea-b83d51d46247>`_
+by double-clicking them, or using `the Open menu <https://support.microsoft.com/en-us/office/open-files-from-the-file-menu-97f087d8-3136-4485-8e86-c5b12a8c4176>`_.
+In pandas, you use :ref:`special methods for reading and writing from/to Excel files <io.excel>`.
+
+Let's first :ref:`create a new Excel file <io.excel_writer>` based on the ``tips`` dataframe in the above example:
+
+.. code-block:: python
+
+    tips.to_excel("./tips.xlsx")
+
+Should you wish to subsequently access the data in the ``tips.xlsx`` file, you can read it into your module using
+
+.. code-block:: python
+
+    tips_df = pd.read_excel("./tips.xlsx", index_col=0)
+
+You have just read in an Excel file using pandas!
+
 
 Limiting output
 ~~~~~~~~~~~~~~~

doc/source/user_guide/io.rst

@@ -2853,7 +2853,7 @@ See the :ref:`cookbook<cookbook.excel>` for some advanced strategies.
    The `xlrd <https://xlrd.readthedocs.io/en/latest/>`__ package is now only for reading
    old-style ``.xls`` files.
 
-   Previously, the default argument ``engine=None`` to :func:`~pandas.read_excel`
+   Before pandas 1.2.0, the default argument ``engine=None`` to :func:`~pandas.read_excel`
    would result in using the ``xlrd`` engine in many cases, including new
    Excel 2007+ (``.xlsx``) files.
    If `openpyxl <https://openpyxl.readthedocs.io/en/stable/>`__  is installed,