ENH: categorical scatter plot

pandas/plotting/_matplotlib/core.py

@@ -8,6 +8,7 @@
 from pandas.util._decorators import cache_readonly
 
 from pandas.core.dtypes.common import (
+    is_categorical_dtype,
     is_hashable,
     is_integer,
     is_iterator,
@@ -413,7 +414,8 @@ def _compute_plot_data(self):
         # np.ndarray before plot.
         numeric_data = numeric_data.copy()
         for col in numeric_data:
-            numeric_data[col] = np.asarray(numeric_data[col])
+            if not is_categorical_dtype(numeric_data[col]):
+                numeric_data[col] = np.asarray(numeric_data[col])
 
         self.data = numeric_data
 
@@ -965,7 +967,10 @@ def _make_plot(self):
         elif color is not None:
             c_values = color
         elif c_is_column:
-            c_values = self.data[c].values
+            if not is_categorical_dtype(self.data[c]):
+                c_values = self.data[c].values
+            else:
+                c_values = self.data[c].cat.codes
         else:
             c_values = c
 
@@ -983,7 +988,19 @@ def _make_plot(self):
         )
         if cb:
             cbar_label = c if c_is_column else ""
-            self._plot_colorbar(ax, label=cbar_label)
+            if not is_categorical_dtype(self.data[c]):
+                self._plot_colorbar(ax, label=cbar_label)
+            else:
+                handles = [
+                    self.plt.scatter(
+                        [],
+                        [],
+                        color=scatter.cmap(scatter.norm(i)),
+                        label=self.data[c].cat.categories[i],
+                    )
+                    for i in self.data[c].cat.codes.unique()
+                ]
+                ax.legend(handles=handles, title=cbar_label)
 
         if label is not None:
             self._add_legend_handle(scatter, label)

pandas/tests/plotting/test_frame.py

@@ -1190,6 +1190,16 @@ def test_scatterplot_object_data(self):
         _check_plot_works(df.plot.scatter, x="a", y="b")
         _check_plot_works(df.plot.scatter, x=0, y=1)
 
+    def test_scatterplot_color_by_categorical(self):
+        df = pd.DataFrame(
+            [[5.1, 3.5], [4.9, 3.0], [7.0, 3.2], [6.4, 3.2], [5.9, 3.0]],
+            columns=["length", "width"],
+        )
+        df["species"] = pd.Categorical(
+            ["setosa", "setosa", "virginica", "virginica", "versicolor"]
+        )
+        _check_plot_works(df.plot.scatter, x=0, y=1, c="species")
+
     @pytest.mark.slow
     def test_if_scatterplot_colorbar_affects_xaxis_visibility(self):
         # addressing issue #10611, to ensure colobar does not