Merge branch 'main' into merge_ordered_validation

doc/source/whatsnew/index.rst

@@ -24,6 +24,7 @@ Version 2.1
 .. toctree::
    :maxdepth: 2
 
+   v2.1.4
    v2.1.3
    v2.1.2
    v2.1.1

doc/source/whatsnew/v2.1.4.rst

@@ -0,0 +1,41 @@
+.. _whatsnew_214:
+
+What's new in 2.1.4 (December ??, 2023)
+---------------------------------------
+
+These are the changes in pandas 2.1.4. See :ref:`release` for a full changelog
+including other versions of pandas.
+
+{{ header }}
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_214.regressions:
+
+Fixed regressions
+~~~~~~~~~~~~~~~~~
+-
+-
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_214.bug_fixes:
+
+Bug fixes
+~~~~~~~~~
+-
+-
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_214.other:
+
+Other
+~~~~~
+-
+-
+
+.. ---------------------------------------------------------------------------
+.. _whatsnew_214.contributors:
+
+Contributors
+~~~~~~~~~~~~
+
+.. contributors:: v2.1.3..v2.1.4|HEAD

pandas/_libs/lib.pyi

@@ -63,7 +63,11 @@ def is_string_array(values: np.ndarray, skipna: bool = ...): ...
 def is_float_array(values: np.ndarray, skipna: bool = ...): ...
 def is_integer_array(values: np.ndarray, skipna: bool = ...): ...
 def is_bool_array(values: np.ndarray, skipna: bool = ...): ...
-def fast_multiget(mapping: dict, keys: np.ndarray, default=...) -> np.ndarray: ...
+def fast_multiget(
+    mapping: dict,
+    keys: np.ndarray,  # object[:]
+    default=...,
+) -> np.ndarray: ...
 def fast_unique_multiple_list_gen(gen: Generator, sort: bool = ...) -> list: ...
 def fast_unique_multiple_list(lists: list, sort: bool | None = ...) -> list: ...
 def map_infer(

pandas/_libs/lib.pyx

@@ -2520,6 +2520,7 @@ def maybe_convert_objects(ndarray[object] objects,
         ndarray[int64_t] ints
         ndarray[uint64_t] uints
         ndarray[uint8_t] bools
+        ndarray[uint8_t] mask
         Seen seen = Seen()
         object val
         _TSObject tsobj
@@ -3088,7 +3089,7 @@ def to_object_array_tuples(rows: object) -> np.ndarray:
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def fast_multiget(dict mapping, ndarray keys, default=np.nan) -> np.ndarray:
+def fast_multiget(dict mapping, object[:] keys, default=np.nan) -> np.ndarray:
     cdef:
         Py_ssize_t i, n = len(keys)
         object val

pandas/core/indexers/objects.py

@@ -102,7 +102,7 @@ def get_window_bounds(
         closed: str | None = None,
         step: int | None = None,
     ) -> tuple[np.ndarray, np.ndarray]:
-        if center:
+        if center or self.window_size == 0:
             offset = (self.window_size - 1) // 2
         else:
             offset = 0

pandas/plotting/_matplotlib/boxplot.py

@@ -10,6 +10,7 @@
 from matplotlib.artist import setp
 import numpy as np
 
+from pandas._libs import lib
 from pandas.util._decorators import cache_readonly
 from pandas.util._exceptions import find_stack_level
 
@@ -113,26 +114,26 @@ def _plot(  # type: ignore[override]
         else:
             return ax, bp
 
-    def _validate_color_args(self):
-        if "color" in self.kwds:
-            if self.colormap is not None:
-                warnings.warn(
-                    "'color' and 'colormap' cannot be used "
-                    "simultaneously. Using 'color'",
-                    stacklevel=find_stack_level(),
-                )
-            self.color = self.kwds.pop("color")
+    def _validate_color_args(self, color, colormap):
+        if color is lib.no_default:
+            return None
 
-            if isinstance(self.color, dict):
-                valid_keys = ["boxes", "whiskers", "medians", "caps"]
-                for key in self.color:
-                    if key not in valid_keys:
-                        raise ValueError(
-                            f"color dict contains invalid key '{key}'. "
-                            f"The key must be either {valid_keys}"
-                        )
-        else:
-            self.color = None
+        if colormap is not None:
+            warnings.warn(
+                "'color' and 'colormap' cannot be used "
+                "simultaneously. Using 'color'",
+                stacklevel=find_stack_level(),
+            )
+
+        if isinstance(color, dict):
+            valid_keys = ["boxes", "whiskers", "medians", "caps"]
+            for key in color:
+                if key not in valid_keys:
+                    raise ValueError(
+                        f"color dict contains invalid key '{key}'. "
+                        f"The key must be either {valid_keys}"
+                    )
+        return color
 
     @cache_readonly
     def _color_attrs(self):
@@ -182,16 +183,8 @@ def maybe_color_bp(self, bp) -> None:
             medians = self.color or self._medians_c
             caps = self.color or self._caps_c
 
-        # GH 30346, when users specifying those arguments explicitly, our defaults
-        # for these four kwargs should be overridden; if not, use Pandas settings
-        if not self.kwds.get("boxprops"):
-            setp(bp["boxes"], color=boxes, alpha=1)
-        if not self.kwds.get("whiskerprops"):
-            setp(bp["whiskers"], color=whiskers, alpha=1)
-        if not self.kwds.get("medianprops"):
-            setp(bp["medians"], color=medians, alpha=1)
-        if not self.kwds.get("capprops"):
-            setp(bp["caps"], color=caps, alpha=1)
+        color_tup = (boxes, whiskers, medians, caps)
+        maybe_color_bp(bp, color_tup=color_tup, **self.kwds)
 
     def _make_plot(self, fig: Figure) -> None:
         if self.subplots:
@@ -276,6 +269,19 @@ def result(self):
             return self._return_obj
 
 
+def maybe_color_bp(bp, color_tup, **kwds) -> None:
+    # GH#30346, when users specifying those arguments explicitly, our defaults
+    # for these four kwargs should be overridden; if not, use Pandas settings
+    if not kwds.get("boxprops"):
+        setp(bp["boxes"], color=color_tup[0], alpha=1)
+    if not kwds.get("whiskerprops"):
+        setp(bp["whiskers"], color=color_tup[1], alpha=1)
+    if not kwds.get("medianprops"):
+        setp(bp["medians"], color=color_tup[2], alpha=1)
+    if not kwds.get("capprops"):
+        setp(bp["caps"], color=color_tup[3], alpha=1)
+
+
 def _grouped_plot_by_column(
     plotf,
     data,
@@ -389,18 +395,6 @@ def _get_colors():
 
         return result
 
-    def maybe_color_bp(bp, **kwds) -> None:
-        # GH 30346, when users specifying those arguments explicitly, our defaults
-        # for these four kwargs should be overridden; if not, use Pandas settings
-        if not kwds.get("boxprops"):
-            setp(bp["boxes"], color=colors[0], alpha=1)
-        if not kwds.get("whiskerprops"):
-            setp(bp["whiskers"], color=colors[1], alpha=1)
-        if not kwds.get("medianprops"):
-            setp(bp["medians"], color=colors[2], alpha=1)
-        if not kwds.get("capprops"):
-            setp(bp["caps"], color=colors[3], alpha=1)
-
     def plot_group(keys, values, ax: Axes, **kwds):
         # GH 45465: xlabel/ylabel need to be popped out before plotting happens
         xlabel, ylabel = kwds.pop("xlabel", None), kwds.pop("ylabel", None)
@@ -419,7 +413,7 @@ def plot_group(keys, values, ax: Axes, **kwds):
         _set_ticklabels(
             ax=ax, labels=keys, is_vertical=kwds.get("vert", True), rotation=rot
         )
-        maybe_color_bp(bp, **kwds)
+        maybe_color_bp(bp, color_tup=colors, **kwds)
 
         # Return axes in multiplot case, maybe revisit later # 985
         if return_type == "dict":

pandas/plotting/_matplotlib/core.py

@@ -271,7 +271,10 @@ def __init__(
 
         self.kwds = kwds
 
-        self._validate_color_args()
+        color = kwds.pop("color", lib.no_default)
+        self.color = self._validate_color_args(color, self.colormap)
+        assert "color" not in self.kwds
+
         self.data = self._ensure_frame(self.data)
 
     @final
@@ -396,34 +399,31 @@ def _validate_subplots_kwarg(
             out.append((idx_loc,))
         return out
 
-    def _validate_color_args(self):
-        if (
-            "color" in self.kwds
-            and self.nseries == 1
-            and self.kwds["color"] is not None
-            and not is_list_like(self.kwds["color"])
-        ):
+    def _validate_color_args(self, color, colormap):
+        if color is lib.no_default:
+            # It was not provided by the user
+            if "colors" in self.kwds and colormap is not None:
+                warnings.warn(
+                    "'color' and 'colormap' cannot be used simultaneously. "
+                    "Using 'color'",
+                    stacklevel=find_stack_level(),
+                )
+            return None
+        if self.nseries == 1 and color is not None and not is_list_like(color):
             # support series.plot(color='green')
-            self.kwds["color"] = [self.kwds["color"]]
+            color = [color]
 
-        if (
-            "color" in self.kwds
-            and isinstance(self.kwds["color"], tuple)
-            and self.nseries == 1
-            and len(self.kwds["color"]) in (3, 4)
-        ):
+        if isinstance(color, tuple) and self.nseries == 1 and len(color) in (3, 4):
             # support RGB and RGBA tuples in series plot
-            self.kwds["color"] = [self.kwds["color"]]
+            color = [color]
 
-        if (
-            "color" in self.kwds or "colors" in self.kwds
-        ) and self.colormap is not None:
+        if colormap is not None:
             warnings.warn(
                 "'color' and 'colormap' cannot be used simultaneously. Using 'color'",
                 stacklevel=find_stack_level(),
             )
 
-        if "color" in self.kwds and self.style is not None:
+        if self.style is not None:
             if is_list_like(self.style):
                 styles = self.style
             else:
@@ -436,6 +436,7 @@ def _validate_color_args(self):
                         "'color' keyword argument. Please use one or the "
                         "other or pass 'style' without a color symbol"
                     )
+        return color
 
     @final
     @staticmethod
@@ -1058,11 +1059,14 @@ def _get_colors(
     ):
         if num_colors is None:
             num_colors = self.nseries
-
+        if color_kwds == "color":
+            color = self.color
+        else:
+            color = self.kwds.get(color_kwds)
         return get_standard_colors(
             num_colors=num_colors,
             colormap=self.colormap,
-            color=self.kwds.get(color_kwds),
+            color=color,
         )
 
     # TODO: tighter typing for first return?
@@ -1302,7 +1306,7 @@ def _make_plot(self, fig: Figure):
             self.data[c].dtype, CategoricalDtype
         )
 
-        color = self.kwds.pop("color", None)
+        color = self.color
         c_values = self._get_c_values(color, color_by_categorical, c_is_column)
         norm, cmap = self._get_norm_and_cmap(c_values, color_by_categorical)
         cb = self._get_colorbar(c_values, c_is_column)
@@ -1487,6 +1491,8 @@ def _make_plot(self, fig: Figure) -> None:
         for i, (label, y) in enumerate(it):
             ax = self._get_ax(i)
             kwds = self.kwds.copy()
+            if self.color is not None:
+                kwds["color"] = self.color
             style, kwds = self._apply_style_colors(
                 colors,
                 kwds,
@@ -1998,8 +2004,9 @@ def __init__(self, data, kind=None, **kwargs) -> None:
         self.logx = False
         self.loglog = False
 
-    def _validate_color_args(self) -> None:
-        pass
+    def _validate_color_args(self, color, colormap) -> None:
+        # TODO: warn if color is passed and ignored?
+        return None
 
     def _make_plot(self, fig: Figure) -> None:
         colors = self._get_colors(num_colors=len(self.data), color_kwds="colors")

pandas/plotting/_matplotlib/hist.py

@@ -140,6 +140,8 @@ def _make_plot(self, fig: Figure) -> None:
             ax = self._get_ax(i)
 
             kwds = self.kwds.copy()
+            if self.color is not None:
+                kwds["color"] = self.color
 
             label = pprint_thing(label)
             label = self._mark_right_label(label, index=i)

pandas/tests/groupby/test_grouping.py

@@ -297,6 +297,23 @@ def test_grouper_creation_bug3(self):
         expected = ser.groupby(level="one").sum()
         tm.assert_series_equal(result, expected)
 
+    @pytest.mark.parametrize("func", [False, True])
+    def test_grouper_returning_tuples(self, func):
+        # GH 22257 , both with dict and with callable
+        df = DataFrame({"X": ["A", "B", "A", "B"], "Y": [1, 4, 3, 2]})
+        mapping = dict(zip(range(4), [("C", 5), ("D", 6)] * 2))
+
+        if func:
+            gb = df.groupby(by=lambda idx: mapping[idx], sort=False)
+        else:
+            gb = df.groupby(by=mapping, sort=False)
+
+        name, expected = next(iter(gb))
+        assert name == ("C", 5)
+        result = gb.get_group(name)
+
+        tm.assert_frame_equal(result, expected)
+
     def test_grouper_column_and_index(self):
         # GH 14327