Merge branch 'main' into BUG-56994/pyarrow-assignment-unexpected-dtypes

Author: droussea2001

ci/code_checks.sh

@@ -89,7 +89,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
         -i "pandas.arrays.IntegerArray SA01" \
-        -i "pandas.arrays.IntervalArray.left SA01" \
         -i "pandas.arrays.IntervalArray.length SA01" \
         -i "pandas.arrays.IntervalArray.right SA01" \
         -i "pandas.arrays.NumpyExtensionArray SA01" \

doc/source/whatsnew/v3.0.0.rst

@@ -740,6 +740,7 @@ Reshaping
 - Bug in :meth:`DataFrame.join` when a :class:`DataFrame` with a :class:`MultiIndex` would raise an ``AssertionError`` when :attr:`MultiIndex.names` contained ``None``. (:issue:`58721`)
 - Bug in :meth:`DataFrame.merge` where merging on a column containing only ``NaN`` values resulted in an out-of-bounds array access (:issue:`59421`)
 - Bug in :meth:`DataFrame.unstack` producing incorrect results when ``sort=False`` (:issue:`54987`, :issue:`55516`)
+- Bug in :meth:`DataFrame.merge` when merging two :class:`DataFrame` on ``intc`` or ``uintc`` types on Windows (:issue:`60091`, :issue:`58713`)
 - Bug in :meth:`DataFrame.pivot_table` incorrectly subaggregating results when called without an ``index`` argument (:issue:`58722`)
 - Bug in :meth:`DataFrame.unstack` producing incorrect results when manipulating empty :class:`DataFrame` with an :class:`ExtentionDtype` (:issue:`59123`)
 

pandas/core/arrays/interval.py

@@ -1233,6 +1233,22 @@ def left(self) -> Index:
         """
         Return the left endpoints of each Interval in the IntervalArray as an Index.
 
+        This property provides access to the left endpoints of the intervals
+        contained within the IntervalArray. This can be useful for analyses where
+        the starting point of each interval is of interest, such as in histogram
+        creation, data aggregation, or any scenario requiring the identification
+        of the beginning of defined ranges. This property returns a ``pandas.Index``
+        object containing the midpoint for each interval.
+
+        See Also
+        --------
+        arrays.IntervalArray.right : Return the right endpoints of each Interval in
+            the IntervalArray as an Index.
+        arrays.IntervalArray.mid : Return the midpoint of each Interval in the
+            IntervalArray as an Index.
+        arrays.IntervalArray.contains : Check elementwise if the Intervals contain
+            the value.
+
         Examples
         --------
 

pandas/core/generic.py

@@ -3324,9 +3324,9 @@ def to_latex(
         r"""
         Render object to a LaTeX tabular, longtable, or nested table.
 
-        Requires ``\usepackage{{booktabs}}``.  The output can be copy/pasted
+        Requires ``\usepackage{booktabs}``.  The output can be copy/pasted
         into a main LaTeX document or read from an external file
-        with ``\input{{table.tex}}``.
+        with ``\input{table.tex}``.
 
         .. versionchanged:: 2.0.0
            Refactored to use the Styler implementation via jinja2 templating.
@@ -3344,13 +3344,13 @@ def to_latex(
             Write row names (index).
         na_rep : str, default 'NaN'
             Missing data representation.
-        formatters : list of functions or dict of {{str: function}}, optional
+        formatters : list of functions or dict of {str: function}, optional
             Formatter functions to apply to columns' elements by position or
             name. The result of each function must be a unicode string.
             List must be of length equal to the number of columns.
         float_format : one-parameter function or str, optional, default None
             Formatter for floating point numbers. For example
-            ``float_format="%.2f"`` and ``float_format="{{:0.2f}}".format`` will
+            ``float_format="%.2f"`` and ``float_format="{:0.2f}".format`` will
             both result in 0.1234 being formatted as 0.12.
         sparsify : bool, optional
             Set to False for a DataFrame with a hierarchical index to print
@@ -3367,7 +3367,7 @@ def to_latex(
             columns of numbers, which default to 'r'.
         longtable : bool, optional
             Use a longtable environment instead of tabular. Requires
-            adding a \usepackage{{longtable}} to your LaTeX preamble.
+            adding a \usepackage{longtable} to your LaTeX preamble.
             By default, the value will be read from the pandas config
             module, and set to `True` if the option ``styler.latex.environment`` is
             `"longtable"`.
@@ -3405,7 +3405,7 @@ def to_latex(
                default value to "r".
         multirow : bool, default True
             Use \multirow to enhance MultiIndex rows. Requires adding a
-            \usepackage{{multirow}} to your LaTeX preamble. Will print
+            \usepackage{multirow} to your LaTeX preamble. Will print
             centered labels (instead of top-aligned) across the contained
             rows, separating groups via clines. The default will be read
             from the pandas config module, and is set as the option
@@ -3416,15 +3416,15 @@ def to_latex(
                default value to `True`.
         caption : str or tuple, optional
             Tuple (full_caption, short_caption),
-            which results in ``\caption[short_caption]{{full_caption}}``;
+            which results in ``\caption[short_caption]{full_caption}``;
             if a single string is passed, no short caption will be set.
         label : str, optional
-            The LaTeX label to be placed inside ``\label{{}}`` in the output.
-            This is used with ``\ref{{}}`` in the main ``.tex`` file.
+            The LaTeX label to be placed inside ``\label{}`` in the output.
+            This is used with ``\ref{}`` in the main ``.tex`` file.
 
         position : str, optional
             The LaTeX positional argument for tables, to be placed after
-            ``\begin{{}}`` in the output.
+            ``\begin{}`` in the output.
 
         Returns
         -------

pandas/core/reshape/merge.py

@@ -123,7 +123,17 @@
 
 # See https://github.com/pandas-dev/pandas/issues/52451
 if np.intc is not np.int32:
-    _factorizers[np.intc] = libhashtable.Int64Factorizer
+    if np.dtype(np.intc).itemsize == 4:
+        _factorizers[np.intc] = libhashtable.Int32Factorizer
+    else:
+        _factorizers[np.intc] = libhashtable.Int64Factorizer
+
+if np.uintc is not np.uint32:
+    if np.dtype(np.uintc).itemsize == 4:
+        _factorizers[np.uintc] = libhashtable.UInt32Factorizer
+    else:
+        _factorizers[np.uintc] = libhashtable.UInt64Factorizer
+
 
 _known = (np.ndarray, ExtensionArray, Index, ABCSeries)
 

pandas/tests/reshape/merge/test_merge.py

@@ -1843,6 +1843,41 @@ def test_merge_empty(self, left_empty, how, exp):
 
         tm.assert_frame_equal(result, expected)
 
+    def test_merge_with_uintc_columns(self):
+        df1 = DataFrame({"a": ["foo", "bar"], "b": np.array([1, 2], dtype=np.uintc)})
+        df2 = DataFrame({"a": ["foo", "baz"], "b": np.array([3, 4], dtype=np.uintc)})
+        result = df1.merge(df2, how="outer")
+        expected = DataFrame(
+            {
+                "a": ["bar", "baz", "foo", "foo"],
+                "b": np.array([2, 4, 1, 3], dtype=np.uintc),
+            }
+        )
+        tm.assert_frame_equal(result.reset_index(drop=True), expected)
+
+    def test_merge_with_intc_columns(self):
+        df1 = DataFrame({"a": ["foo", "bar"], "b": np.array([1, 2], dtype=np.intc)})
+        df2 = DataFrame({"a": ["foo", "baz"], "b": np.array([3, 4], dtype=np.intc)})
+        result = df1.merge(df2, how="outer")
+        expected = DataFrame(
+            {
+                "a": ["bar", "baz", "foo", "foo"],
+                "b": np.array([2, 4, 1, 3], dtype=np.intc),
+            }
+        )
+        tm.assert_frame_equal(result.reset_index(drop=True), expected)
+
+    def test_merge_intc_non_monotonic(self):
+        df = DataFrame({"join_key": Series([0, 2, 1], dtype=np.intc)})
+        df_details = DataFrame(
+            {"join_key": Series([0, 1, 2], dtype=np.intc), "value": ["a", "b", "c"]}
+        )
+        merged = df.merge(df_details, on="join_key", how="left")
+        expected = DataFrame(
+            {"join_key": np.array([0, 2, 1], dtype=np.intc), "value": ["a", "c", "b"]}
+        )
+        tm.assert_frame_equal(merged.reset_index(drop=True), expected)
+
 
 @pytest.fixture
 def left():