Merge branch 'main' into patch-1

datapythonista · web-flow · commit d356286cec0e · 2024-01-15T14:54:17.000+07:00
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -76,41 +76,25 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.errors.DatabaseError \
         pandas.errors.IndexingError \
         pandas.errors.InvalidColumnName \
-        pandas.errors.PossibleDataLossError \
-        pandas.errors.PossiblePrecisionLoss \
-        pandas.errors.SettingWithCopyError \
         pandas.errors.SettingWithCopyWarning \
         pandas.errors.SpecificationError \
         pandas.errors.UndefinedVariableError \
-        pandas.errors.ValueLabelTypeMismatch \
         pandas.Timestamp.ceil \
         pandas.Timestamp.floor \
         pandas.Timestamp.round \
-        pandas.ExcelWriter \
         pandas.read_json \
         pandas.io.json.build_table_schema \
         pandas.io.formats.style.Styler.to_latex \
         pandas.read_parquet \
         pandas.DataFrame.to_sql \
         pandas.read_stata \
-        pandas.core.resample.Resampler.interpolate \
         pandas.plotting.scatter_matrix \
-        pandas.pivot \
-        pandas.merge_asof \
-        pandas.wide_to_long \
-        pandas.Index.rename \
         pandas.Index.droplevel \
-        pandas.Index.isin \
-        pandas.IndexSlice \
         pandas.Grouper \
         pandas.io.formats.style.Styler.map \
         pandas.io.formats.style.Styler.apply_index \
         pandas.io.formats.style.Styler.map_index \
         pandas.io.formats.style.Styler.format \
-        pandas.io.formats.style.Styler.format_index \
-        pandas.io.formats.style.Styler.relabel_index \
-        pandas.io.formats.style.Styler.hide \
-        pandas.io.formats.style.Styler.set_td_classes \
         pandas.io.formats.style.Styler.set_tooltips \
         pandas.io.formats.style.Styler.set_uuid \
         pandas.io.formats.style.Styler.pipe \
@@ -120,9 +104,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.io.formats.style.Styler.text_gradient \
         pandas.DataFrame.values \
         pandas.DataFrame.groupby \
-        pandas.DataFrame.idxmax \
-        pandas.DataFrame.idxmin \
-        pandas.DataFrame.pivot \
         pandas.DataFrame.sort_values \
         pandas.DataFrame.plot.hexbin \
         pandas.DataFrame.plot.line \
diff --git a/pandas/core/indexes/base.py b/pandas/core/indexes/base.py
@@ -1953,7 +1953,7 @@ def rename(self, name, inplace: bool = False) -> Self | None:
 
         >>> idx = pd.MultiIndex.from_product([['python', 'cobra'],
         ...                                   [2018, 2019]],
-        ...                                   names=['kind', 'year'])
+        ...                                  names=['kind', 'year'])
         >>> idx
         MultiIndex([('python', 2018),
                     ('python', 2019),
@@ -6576,7 +6576,7 @@ def isin(self, values, level=None) -> npt.NDArray[np.bool_]:
 
         Examples
         --------
-        >>> idx = pd.Index([1,2,3])
+        >>> idx = pd.Index([1, 2, 3])
         >>> idx
         Index([1, 2, 3], dtype='int64')
 
@@ -6585,7 +6585,7 @@ def isin(self, values, level=None) -> npt.NDArray[np.bool_]:
         >>> idx.isin([1, 4])
         array([ True, False, False])
 
-        >>> midx = pd.MultiIndex.from_arrays([[1,2,3],
+        >>> midx = pd.MultiIndex.from_arrays([[1, 2, 3],
         ...                                  ['red', 'blue', 'green']],
         ...                                  names=('number', 'color'))
         >>> midx
diff --git a/pandas/core/indexing.py b/pandas/core/indexing.py
@@ -121,7 +121,7 @@ class _IndexSlice:
 
     Examples
     --------
-    >>> midx = pd.MultiIndex.from_product([['A0','A1'], ['B0','B1','B2','B3']])
+    >>> midx = pd.MultiIndex.from_product([['A0', 'A1'], ['B0', 'B1', 'B2', 'B3']])
     >>> columns = ['foo', 'bar']
     >>> dfmi = pd.DataFrame(np.arange(16).reshape((len(midx), len(columns))),
     ...                     index=midx, columns=columns)
diff --git a/pandas/core/reshape/melt.py b/pandas/core/reshape/melt.py
@@ -295,7 +295,7 @@ def wide_to_long(
     ...                    "B1970" : {0 : 2.5, 1 : 1.2, 2 : .7},
     ...                    "B1980" : {0 : 3.2, 1 : 1.3, 2 : .1},
     ...                    "X"     : dict(zip(range(3), np.random.randn(3)))
-    ...                   })
+    ...                    })
     >>> df["id"] = df.index
     >>> df
       A1970 A1980  B1970  B1980         X  id
@@ -332,8 +332,8 @@ def wide_to_long(
     6      3      1  2.2  3.3
     7      3      2  2.3  3.4
     8      3      3  2.1  2.9
-    >>> l = pd.wide_to_long(df, stubnames='ht', i=['famid', 'birth'], j='age')
-    >>> l
+    >>> long_format = pd.wide_to_long(df, stubnames='ht', i=['famid', 'birth'], j='age')
+    >>> long_format
     ... # doctest: +NORMALIZE_WHITESPACE
                       ht
     famid birth age
@@ -358,9 +358,9 @@ def wide_to_long(
 
     Going from long back to wide just takes some creative use of `unstack`
 
-    >>> w = l.unstack()
-    >>> w.columns = w.columns.map('{0[0]}{0[1]}'.format)
-    >>> w.reset_index()
+    >>> wide_format = long_format.unstack()
+    >>> wide_format.columns = wide_format.columns.map('{0[0]}{0[1]}'.format)
+    >>> wide_format.reset_index()
        famid  birth  ht1  ht2
     0      1      1  2.8  3.4
     1      1      2  2.9  3.8
@@ -381,7 +381,7 @@ def wide_to_long(
     ...                    'B(weekly)-2011': np.random.rand(3),
     ...                    'X' : np.random.randint(3, size=3)})
     >>> df['id'] = df.index
-    >>> df # doctest: +NORMALIZE_WHITESPACE, +ELLIPSIS
+    >>> df  # doctest: +NORMALIZE_WHITESPACE, +ELLIPSIS
        A(weekly)-2010  A(weekly)-2011  B(weekly)-2010  B(weekly)-2011  X  id
     0        0.548814        0.544883        0.437587        0.383442  0   0
     1        0.715189        0.423655        0.891773        0.791725  1   1
@@ -430,9 +430,9 @@ def wide_to_long(
     7      3      2     2.3     3.4
     8      3      3     2.1     2.9
 
-    >>> l = pd.wide_to_long(df, stubnames='ht', i=['famid', 'birth'], j='age',
-    ...                     sep='_', suffix=r'\w+')
-    >>> l
+    >>> long_format = pd.wide_to_long(df, stubnames='ht', i=['famid', 'birth'], j='age',
+    ...                               sep='_', suffix=r'\w+')
+    >>> long_format
     ... # doctest: +NORMALIZE_WHITESPACE
                       ht
     famid birth age
diff --git a/pandas/core/reshape/merge.py b/pandas/core/reshape/merge.py
@@ -601,17 +601,17 @@ def merge_asof(
     ...             pd.Timestamp("2016-05-25 13:30:00.075")
     ...         ],
     ...         "ticker": [
-    ...                "GOOG",
-    ...                "MSFT",
-    ...                "MSFT",
-    ...                "MSFT",
-    ...                "GOOG",
-    ...                "AAPL",
-    ...                "GOOG",
-    ...                "MSFT"
-    ...            ],
-    ...            "bid": [720.50, 51.95, 51.97, 51.99, 720.50, 97.99, 720.50, 52.01],
-    ...            "ask": [720.93, 51.96, 51.98, 52.00, 720.93, 98.01, 720.88, 52.03]
+    ...             "GOOG",
+    ...             "MSFT",
+    ...             "MSFT",
+    ...             "MSFT",
+    ...             "GOOG",
+    ...             "AAPL",
+    ...             "GOOG",
+    ...             "MSFT"
+    ...         ],
+    ...         "bid": [720.50, 51.95, 51.97, 51.99, 720.50, 97.99, 720.50, 52.01],
+    ...         "ask": [720.93, 51.96, 51.98, 52.00, 720.93, 98.01, 720.88, 52.03]
     ...     }
     ... )
     >>> quotes
@@ -626,19 +626,19 @@ def merge_asof(
     7 2016-05-25 13:30:00.075   MSFT   52.01   52.03
 
     >>> trades = pd.DataFrame(
-    ...        {
-    ...            "time": [
-    ...                pd.Timestamp("2016-05-25 13:30:00.023"),
-    ...                pd.Timestamp("2016-05-25 13:30:00.038"),
-    ...                pd.Timestamp("2016-05-25 13:30:00.048"),
-    ...                pd.Timestamp("2016-05-25 13:30:00.048"),
-    ...                pd.Timestamp("2016-05-25 13:30:00.048")
-    ...            ],
-    ...            "ticker": ["MSFT", "MSFT", "GOOG", "GOOG", "AAPL"],
-    ...            "price": [51.95, 51.95, 720.77, 720.92, 98.0],
-    ...            "quantity": [75, 155, 100, 100, 100]
-    ...        }
-    ...    )
+    ...     {
+    ...         "time": [
+    ...             pd.Timestamp("2016-05-25 13:30:00.023"),
+    ...             pd.Timestamp("2016-05-25 13:30:00.038"),
+    ...             pd.Timestamp("2016-05-25 13:30:00.048"),
+    ...             pd.Timestamp("2016-05-25 13:30:00.048"),
+    ...             pd.Timestamp("2016-05-25 13:30:00.048")
+    ...         ],
+    ...         "ticker": ["MSFT", "MSFT", "GOOG", "GOOG", "AAPL"],
+    ...         "price": [51.95, 51.95, 720.77, 720.92, 98.0],
+    ...         "quantity": [75, 155, 100, 100, 100]
+    ...     }
+    ... )
     >>> trades
                          time ticker   price  quantity
     0 2016-05-25 13:30:00.023   MSFT   51.95        75
diff --git a/pandas/errors/__init__.py b/pandas/errors/__init__.py
@@ -425,7 +425,7 @@ class SettingWithCopyError(ValueError):
     --------
     >>> pd.options.mode.chained_assignment = 'raise'
     >>> df = pd.DataFrame({'A': [1, 1, 1, 2, 2]}, columns=['A'])
-    >>> df.loc[0:3]['A'] = 'a' # doctest: +SKIP
+    >>> df.loc[0:3]['A'] = 'a'  # doctest: +SKIP
     ... # SettingWithCopyError: A value is trying to be set on a copy of a...
     """
 
@@ -665,8 +665,8 @@ class PossibleDataLossError(Exception):
 
     Examples
     --------
-    >>> store = pd.HDFStore('my-store', 'a') # doctest: +SKIP
-    >>> store.open("w") # doctest: +SKIP
+    >>> store = pd.HDFStore('my-store', 'a')  # doctest: +SKIP
+    >>> store.open("w")  # doctest: +SKIP
     ... # PossibleDataLossError: Re-opening the file [my-store] with mode [a]...
     """
 
@@ -734,7 +734,7 @@ class PossiblePrecisionLoss(Warning):
     Examples
     --------
     >>> df = pd.DataFrame({"s": pd.Series([1, 2**53], dtype=np.int64)})
-    >>> df.to_stata('test') # doctest: +SKIP
+    >>> df.to_stata('test')  # doctest: +SKIP
     ... # PossiblePrecisionLoss: Column converted from int64 to float64...
     """
 
@@ -746,7 +746,7 @@ class ValueLabelTypeMismatch(Warning):
     Examples
     --------
     >>> df = pd.DataFrame({"categories": pd.Series(["a", 2], dtype="category")})
-    >>> df.to_stata('test') # doctest: +SKIP
+    >>> df.to_stata('test')  # doctest: +SKIP
     ... # ValueLabelTypeMismatch: Stata value labels (pandas categories) must be str...
     """
 
diff --git a/pandas/io/excel/_base.py b/pandas/io/excel/_base.py
@@ -935,7 +935,7 @@ class ExcelWriter(Generic[_WorkbookT]):
       is installed otherwise `openpyxl <https://pypi.org/project/openpyxl/>`__
     * `odswriter <https://pypi.org/project/odswriter/>`__ for ods files
 
-    See ``DataFrame.to_excel`` for typical usage.
+    See :meth:`DataFrame.to_excel` for typical usage.
 
     The writer should be used as a context manager. Otherwise, call `close()` to save
     and close any opened file handles.
@@ -1031,7 +1031,7 @@ class ExcelWriter(Generic[_WorkbookT]):
     Here, the `if_sheet_exists` parameter can be set to replace a sheet if it
     already exists:
 
-    >>> with ExcelWriter(
+    >>> with pd.ExcelWriter(
     ...     "path_to_file.xlsx",
     ...     mode="a",
     ...     engine="openpyxl",
@@ -1042,7 +1042,8 @@ class ExcelWriter(Generic[_WorkbookT]):
     You can also write multiple DataFrames to a single sheet. Note that the
     ``if_sheet_exists`` parameter needs to be set to ``overlay``:
 
-    >>> with ExcelWriter("path_to_file.xlsx",
+    >>> with pd.ExcelWriter(
+    ...     "path_to_file.xlsx",
     ...     mode="a",
     ...     engine="openpyxl",
     ...     if_sheet_exists="overlay",
diff --git a/pandas/io/formats/style.py b/pandas/io/formats/style.py
@@ -1496,10 +1496,10 @@ def set_td_classes(self, classes: DataFrame) -> Styler:
         Using `MultiIndex` columns and a `classes` `DataFrame` as a subset of the
         underlying,
 
-        >>> df = pd.DataFrame([[1,2],[3,4]], index=["a", "b"],
-        ...     columns=[["level0", "level0"], ["level1a", "level1b"]])
+        >>> df = pd.DataFrame([[1, 2], [3, 4]], index=["a", "b"],
+        ...                   columns=[["level0", "level0"], ["level1a", "level1b"]])
         >>> classes = pd.DataFrame(["min-val"], index=["a"],
-        ...     columns=[["level0"],["level1a"]])
+        ...                        columns=[["level0"], ["level1a"]])
         >>> df.style.set_td_classes(classes)  # doctest: +SKIP
 
         Form of the output with new additional css classes,
@@ -2717,15 +2717,15 @@ def hide(
         --------
         Simple application hiding specific rows:
 
-        >>> df = pd.DataFrame([[1,2], [3,4], [5,6]], index=["a", "b", "c"])
+        >>> df = pd.DataFrame([[1, 2], [3, 4], [5, 6]], index=["a", "b", "c"])
         >>> df.style.hide(["a", "b"])  # doctest: +SKIP
              0    1
         c    5    6
 
         Hide the index and retain the data values:
 
         >>> midx = pd.MultiIndex.from_product([["x", "y"], ["a", "b", "c"]])
-        >>> df = pd.DataFrame(np.random.randn(6,6), index=midx, columns=midx)
+        >>> df = pd.DataFrame(np.random.randn(6, 6), index=midx, columns=midx)
         >>> df.style.format("{:.1f}").hide()  # doctest: +SKIP
                          x                    y
            a      b      c      a      b      c
@@ -2739,7 +2739,7 @@ def hide(
         Hide specific rows in a MultiIndex but retain the index:
 
         >>> df.style.format("{:.1f}").hide(subset=(slice(None), ["a", "c"]))
-        ...   # doctest: +SKIP
+        ... # doctest: +SKIP
                                  x                    y
                    a      b      c      a      b      c
         x   b    0.7    1.0    1.3    1.5   -0.0   -0.2
@@ -2748,7 +2748,7 @@ def hide(
         Hide specific rows and the index through chaining:
 
         >>> df.style.format("{:.1f}").hide(subset=(slice(None), ["a", "c"])).hide()
-        ...   # doctest: +SKIP
+        ... # doctest: +SKIP
                          x                    y
            a      b      c      a      b      c
          0.7    1.0    1.3    1.5   -0.0   -0.2
diff --git a/pandas/io/formats/style_render.py b/pandas/io/formats/style_render.py
