BUG: scatter discarding string columns (#56142)

* BUG: scatter discarding string columns * Add test
pandas-dev · Nov 26, 2023 · 45b937d · 45b937d
1 parent 6d1b07f
commit 45b937d
Show file tree

Hide file tree

Showing 3 changed files with 12 additions and 5 deletions.
diff --git a/doc/source/whatsnew/v2.2.0.rst b/doc/source/whatsnew/v2.2.0.rst
@@ -546,8 +546,8 @@ Period
 Plotting
 ^^^^^^^^
 - Bug in :meth:`DataFrame.plot.box` with ``vert=False`` and a matplotlib ``Axes`` created with ``sharey=True`` (:issue:`54941`)
+- Bug in :meth:`DataFrame.plot.scatter` discaring string columns (:issue:`56142`)
 - Bug in :meth:`Series.plot` when reusing an ``ax`` object failing to raise when a ``how`` keyword is passed (:issue:`55953`)
--
 
 Groupby/resample/rolling
 ^^^^^^^^^^^^^^^^^^^^^^^^

diff --git a/pandas/plotting/_matplotlib/core.py b/pandas/plotting/_matplotlib/core.py
@@ -688,7 +688,7 @@ def _compute_plot_data(self):
 
         # GH 18755, include object and category type for scatter plot
         if self._kind == "scatter":
-            include_type.extend(["object", "category"])
+            include_type.extend(["object", "category", "string"])
 
         numeric_data = data.select_dtypes(include=include_type, exclude=exclude_type)
 

diff --git a/pandas/tests/plotting/frame/test_frame.py b/pandas/tests/plotting/frame/test_frame.py
@@ -12,6 +12,8 @@
 import numpy as np
 import pytest
 
+import pandas.util._test_decorators as td
+
 from pandas.core.dtypes.api import is_list_like
 
 import pandas as pd
@@ -22,6 +24,7 @@
     Series,
     bdate_range,
     date_range,
+    option_context,
     plotting,
 )
 import pandas._testing as tm
@@ -794,13 +797,17 @@ def test_scatterplot_datetime_data(self, x, y):
 
         _check_plot_works(df.plot.scatter, x=x, y=y)
 
+    @pytest.mark.parametrize(
+        "infer_string", [False, pytest.param(True, marks=td.skip_if_no("pyarrow"))]
+    )
     @pytest.mark.parametrize("x, y", [("a", "b"), (0, 1)])
     @pytest.mark.parametrize("b_col", [[2, 3, 4], ["a", "b", "c"]])
-    def test_scatterplot_object_data(self, b_col, x, y):
+    def test_scatterplot_object_data(self, b_col, x, y, infer_string):
         # GH 18755
-        df = DataFrame({"a": ["A", "B", "C"], "b": b_col})
+        with option_context("future.infer_string", infer_string):
+            df = DataFrame({"a": ["A", "B", "C"], "b": b_col})
 
-        _check_plot_works(df.plot.scatter, x=x, y=y)
+            _check_plot_works(df.plot.scatter, x=x, y=y)
 
     @pytest.mark.parametrize("ordered", [True, False])
     @pytest.mark.parametrize(