Merge branch 'pandas-dev:main' into fix/combine_first-bug

Author: Lavishgangwani

.github/workflows/package-checks.yml

@@ -67,7 +67,7 @@ jobs:
           fetch-depth: 0
 
       - name: Set up Python
-        uses: mamba-org/setup-micromamba@v1
+        uses: mamba-org/setup-micromamba@v2
         with:
           environment-name: recipe-test
           create-args: >-

.github/workflows/wheels.yml

@@ -165,7 +165,7 @@ jobs:
           CIBW_PLATFORM: ${{ matrix.buildplat[1] == 'pyodide_wasm32' && 'pyodide' || 'auto' }}
 
       - name: Set up Python
-        uses: mamba-org/setup-micromamba@v1
+        uses: mamba-org/setup-micromamba@v2
         with:
           environment-name: wheel-env
           # Use a fixed Python, since we might have an unreleased Python not

ci/code_checks.sh

@@ -174,12 +174,10 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.errors.ValueLabelTypeMismatch SA01" \
         -i "pandas.infer_freq SA01" \
         -i "pandas.io.json.build_table_schema PR07,RT03,SA01" \
-        -i "pandas.io.stata.StataReader.value_labels RT03,SA01" \
         -i "pandas.io.stata.StataReader.variable_labels RT03,SA01" \
         -i "pandas.io.stata.StataWriter.write_file SA01" \
         -i "pandas.json_normalize RT03,SA01" \
         -i "pandas.plotting.andrews_curves RT03,SA01" \
-        -i "pandas.plotting.lag_plot RT03,SA01" \
         -i "pandas.plotting.scatter_matrix PR07,SA01" \
         -i "pandas.set_eng_float_format RT03,SA01" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \

pandas/_libs/tslibs/nattype.pyi

@@ -9,6 +9,7 @@ from typing import (
     Literal,
     NoReturn,
     TypeAlias,
+    overload,
 )
 
 import numpy as np
@@ -159,15 +160,31 @@ class NaTType:
     # inject Period properties
     @property
     def qyear(self) -> float: ...
+    # comparisons
     def __eq__(self, other: object) -> bool: ...
     def __ne__(self, other: object) -> bool: ...
     __lt__: _NatComparison
     __le__: _NatComparison
     __gt__: _NatComparison
     __ge__: _NatComparison
+    # unary operators
+    def __pos__(self) -> Self: ...
+    def __neg__(self) -> Self: ...
+    # binary operators
     def __sub__(self, other: Self | timedelta | datetime) -> Self: ...
     def __rsub__(self, other: Self | timedelta | datetime) -> Self: ...
     def __add__(self, other: Self | timedelta | datetime) -> Self: ...
     def __radd__(self, other: Self | timedelta | datetime) -> Self: ...
+    def __mul__(self, other: float) -> Self: ...  # analogous to timedelta
+    def __rmul__(self, other: float) -> Self: ...
+    @overload  # analogous to timedelta
+    def __truediv__(self, other: Self | timedelta) -> float: ...  # Literal[NaN]
+    @overload
+    def __truediv__(self, other: float) -> Self: ...
+    @overload  # analogous to timedelta
+    def __floordiv__(self, other: Self | timedelta) -> float: ...  # Literal[NaN]
+    @overload
+    def __floordiv__(self, other: float) -> Self: ...
+    # other
     def __hash__(self) -> int: ...
     def as_unit(self, unit: str, round_ok: bool = ...) -> NaTType: ...

pandas/core/groupby/ops.py

@@ -867,7 +867,7 @@ def _ob_index_and_ids(
             names=names,
             verify_integrity=False,
         )
-        if not consistent_sorting:
+        if not consistent_sorting and len(ob_index) > 0:
             # Sort by the levels where the corresponding sort argument is True
             n_levels = len(sorts)
             drop_levels = [

pandas/core/reshape/encoding.py

@@ -68,7 +68,8 @@ def get_dummies(
         If appending prefix, separator/delimiter to use. Or pass a
         list or dictionary as with `prefix`.
     dummy_na : bool, default False
-        Add a column to indicate NaNs, if False NaNs are ignored.
+        If True, a NaN indicator column will be added even if no NaN values are present.
+        If False, NA values are encoded as all zero.
     columns : list-like, default None
         Column names in the DataFrame to be encoded.
         If `columns` is None then all the columns with

pandas/io/stata.py

@@ -2076,9 +2076,19 @@ def value_labels(self) -> dict[str, dict[int, str]]:
         """
         Return a nested dict associating each variable name to its value and label.
 
+        This method retrieves the value labels from a Stata file. Value labels are
+        mappings between the coded values and their corresponding descriptive labels
+        in a Stata dataset.
+
         Returns
         -------
         dict
+            A python dictionary.
+
+        See Also
+        --------
+        read_stata : Read Stata file into DataFrame.
+        DataFrame.to_stata : Export DataFrame object to Stata dta format.
 
         Examples
         --------

pandas/plotting/_misc.py

@@ -549,6 +549,10 @@ def lag_plot(series: Series, lag: int = 1, ax: Axes | None = None, **kwds) -> Ax
     """
     Lag plot for time series.
 
+    A lag plot is a scatter plot of a time series against a lag of itself. It helps
+    in visualizing the temporal dependence between observations by plotting the values
+    at time `t` on the x-axis and the values at time `t + lag` on the y-axis.
+
     Parameters
     ----------
     series : Series
@@ -563,6 +567,13 @@ def lag_plot(series: Series, lag: int = 1, ax: Axes | None = None, **kwds) -> Ax
     Returns
     -------
     matplotlib.axes.Axes
+        The matplotlib Axes object containing the lag plot.
+
+    See Also
+    --------
+    plotting.autocorrelation_plot : Autocorrelation plot for time series.
+    matplotlib.pyplot.scatter : A scatter plot of y vs. x with varying marker size
+        and/or color in Matplotlib.
 
     Examples
     --------

pandas/tests/groupby/methods/test_value_counts.py

@@ -1219,3 +1219,25 @@ def test_value_counts_sort_categorical(sort, vc_sort, normalize):
     expected = expected.take(taker)
 
     tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("groupby_sort", [True, False])
+def test_value_counts_all_na(sort, dropna, groupby_sort):
+    # GH#59989
+    df = DataFrame({"a": [2, 1, 1], "b": np.nan})
+    gb = df.groupby("a", sort=groupby_sort)
+    result = gb.value_counts(sort=sort, dropna=dropna)
+
+    kwargs = {"levels": [[1, 2], [np.nan]], "names": ["a", "b"]}
+    if dropna:
+        data = []
+        index = MultiIndex(codes=[[], []], **kwargs)
+    elif not groupby_sort and not sort:
+        data = [1, 2]
+        index = MultiIndex(codes=[[1, 0], [0, 0]], **kwargs)
+    else:
+        data = [2, 1]
+        index = MultiIndex(codes=[[0, 1], [0, 0]], **kwargs)
+    expected = Series(data, index=index, dtype="int64", name="count")
+
+    tm.assert_series_equal(result, expected)