BUG-26214 fix colors parameter in DataFrame.boxplot (#26456)

Author: JustinZhengBC

doc/source/whatsnew/v1.0.0.rst

@@ -231,6 +231,7 @@ Plotting
 - Bug in :meth:`DataFrame.plot` producing incorrect legend markers when plotting multiple series on the same axis (:issue:`18222`)
 - Bug in :meth:`DataFrame.plot` when ``kind='box'`` and data contains datetime or timedelta data. These types are now automatically dropped (:issue:`22799`)
 - Bug in :meth:`DataFrame.plot.line` and :meth:`DataFrame.plot.area` produce wrong xlim in x-axis (:issue:`27686`, :issue:`25160`, :issue:`24784`)
+- Bug where :meth:`DataFrame.boxplot` would not accept a `color` parameter like `DataFrame.plot.box` (:issue:`26214`)
 - :func:`set_option` now validates that the plot backend provided to ``'plotting.backend'`` implements the backend when the option is set, rather than when a plot is created (:issue:`28163`)
 
 Groupby/resample/rolling

pandas/plotting/_matplotlib/boxplot.py

@@ -4,6 +4,7 @@
 from matplotlib.artist import setp
 import numpy as np
 
+from pandas.core.dtypes.common import is_dict_like
 from pandas.core.dtypes.generic import ABCSeries
 from pandas.core.dtypes.missing import remove_na_arraylike
 
@@ -250,13 +251,38 @@ def boxplot(
     def _get_colors():
         #  num_colors=3 is required as method maybe_color_bp takes the colors
         #  in positions 0 and 2.
-        return _get_standard_colors(color=kwds.get("color"), num_colors=3)
+        #  if colors not provided, use same defaults as DataFrame.plot.box
+        result = _get_standard_colors(num_colors=3)
+        result = np.take(result, [0, 0, 2])
+        result = np.append(result, "k")
+
+        colors = kwds.pop("color", None)
+        if colors:
+            if is_dict_like(colors):
+                # replace colors in result array with user-specified colors
+                # taken from the colors dict parameter
+                # "boxes" value placed in position 0, "whiskers" in 1, etc.
+                valid_keys = ["boxes", "whiskers", "medians", "caps"]
+                key_to_index = dict(zip(valid_keys, range(4)))
+                for key, value in colors.items():
+                    if key in valid_keys:
+                        result[key_to_index[key]] = value
+                    else:
+                        raise ValueError(
+                            "color dict contains invalid "
+                            "key '{0}' "
+                            "The key must be either {1}".format(key, valid_keys)
+                        )
+            else:
+                result.fill(colors)
+
+        return result
 
     def maybe_color_bp(bp):
-        if "color" not in kwds:
-            setp(bp["boxes"], color=colors[0], alpha=1)
-            setp(bp["whiskers"], color=colors[0], alpha=1)
-            setp(bp["medians"], color=colors[2], alpha=1)
+        setp(bp["boxes"], color=colors[0], alpha=1)
+        setp(bp["whiskers"], color=colors[1], alpha=1)
+        setp(bp["medians"], color=colors[2], alpha=1)
+        setp(bp["caps"], color=colors[3], alpha=1)
 
     def plot_group(keys, values, ax):
         keys = [pprint_thing(x) for x in keys]

pandas/tests/plotting/test_boxplot_method.py

@@ -175,6 +175,34 @@ def test_boxplot_numeric_data(self):
         ax = df.plot(kind="box")
         assert [x.get_text() for x in ax.get_xticklabels()] == ["b", "c"]
 
+    @pytest.mark.parametrize(
+        "colors_kwd, expected",
+        [
+            (
+                dict(boxes="r", whiskers="b", medians="g", caps="c"),
+                dict(boxes="r", whiskers="b", medians="g", caps="c"),
+            ),
+            (dict(boxes="r"), dict(boxes="r")),
+            ("r", dict(boxes="r", whiskers="r", medians="r", caps="r")),
+        ],
+    )
+    def test_color_kwd(self, colors_kwd, expected):
+        # GH: 26214
+        df = DataFrame(random.rand(10, 2))
+        result = df.boxplot(color=colors_kwd, return_type="dict")
+        for k, v in expected.items():
+            assert result[k][0].get_color() == v
+
+    @pytest.mark.parametrize(
+        "dict_colors, msg",
+        [(dict(boxes="r", invalid_key="r"), "invalid key 'invalid_key'")],
+    )
+    def test_color_kwd_errors(self, dict_colors, msg):
+        # GH: 26214
+        df = DataFrame(random.rand(10, 2))
+        with pytest.raises(ValueError, match=msg):
+            df.boxplot(color=dict_colors, return_type="dict")
+
 
 @td.skip_if_no_mpl
 class TestDataFrameGroupByPlots(TestPlotBase):