The indexes of DataFrame.describe(percentiles=[0.29, 0.57, 0.58]) are incorrect (#48298)

Khor Chean Wei · mroeschke · web-flow · commit 82ce975b1619 · 2022-09-06T10:31:40.000-07:00
* add test

* add test

* add

* Update doc/source/whatsnew/v1.6.0.rst

Co-authored-by: Matthew Roeschke &lt;10647082+mroeschke@users.noreply.github.com&gt;

* add

Co-authored-by: Matthew Roeschke &lt;10647082+mroeschke@users.noreply.github.com&gt;
diff --git a/doc/source/whatsnew/v1.6.0.rst b/doc/source/whatsnew/v1.6.0.rst
@@ -154,7 +154,7 @@ Indexing
 ^^^^^^^^
 - Bug in :meth:`DataFrame.reindex` filling with wrong values when indexing columns and index for ``uint`` dtypes (:issue:`48184`)
 - Bug in :meth:`DataFrame.reindex` casting dtype to ``object`` when :class:`DataFrame` has single extension array column when re-indexing ``columns`` and ``index`` (:issue:`48190`)
--
+- Bug in :func:`~DataFrame.describe` when formatting percentiles in the resulting index showed more decimals than needed (:issue:`46362`)
 
 Missing
 ^^^^^^^
diff --git a/pandas/io/formats/format.py b/pandas/io/formats/format.py
@@ -1720,11 +1720,12 @@ def format_percentiles(
             raise ValueError("percentiles should all be in the interval [0,1]")
 
     percentiles = 100 * percentiles
+    percentiles_round_type = percentiles.round().astype(int)
 
-    int_idx = np.isclose(percentiles.astype(int), percentiles)
+    int_idx = np.isclose(percentiles_round_type, percentiles)
 
     if np.all(int_idx):
-        out = percentiles.astype(int).astype(str)
+        out = percentiles_round_type.astype(str)
         return [i + "%" for i in out]
 
     unique_pcts = np.unique(percentiles)
@@ -1737,7 +1738,7 @@ def format_percentiles(
     ).astype(int)
     prec = max(1, prec)
     out = np.empty_like(percentiles, dtype=object)
-    out[int_idx] = percentiles[int_idx].astype(int).astype(str)
+    out[int_idx] = percentiles[int_idx].round().astype(int).astype(str)
 
     out[~int_idx] = percentiles[~int_idx].round(prec).astype(str)
     return [i + "%" for i in out]
diff --git a/pandas/tests/io/formats/test_format.py b/pandas/tests/io/formats/test_format.py
@@ -3306,24 +3306,34 @@ def test_nat_representations(self):
             assert f(NaT) == "NaT"
 
 
-def test_format_percentiles():
-    result = fmt.format_percentiles([0.01999, 0.02001, 0.5, 0.666666, 0.9999])
-    expected = ["1.999%", "2.001%", "50%", "66.667%", "99.99%"]
+@pytest.mark.parametrize(
+    "percentiles, expected",
+    [
+        (
+            [0.01999, 0.02001, 0.5, 0.666666, 0.9999],
+            ["1.999%", "2.001%", "50%", "66.667%", "99.99%"],
+        ),
+        (
+            [0, 0.5, 0.02001, 0.5, 0.666666, 0.9999],
+            ["0%", "50%", "2.0%", "50%", "66.67%", "99.99%"],
+        ),
+        ([0.281, 0.29, 0.57, 0.58], ["28.1%", "29%", "57%", "58%"]),
+        ([0.28, 0.29, 0.57, 0.58], ["28%", "29%", "57%", "58%"]),
+    ],
+)
+def test_format_percentiles(percentiles, expected):
+    result = fmt.format_percentiles(percentiles)
     assert result == expected
 
-    result = fmt.format_percentiles([0, 0.5, 0.02001, 0.5, 0.666666, 0.9999])
-    expected = ["0%", "50%", "2.0%", "50%", "66.67%", "99.99%"]
-    assert result == expected
 
+@pytest.mark.parametrize(
+    "percentiles",
+    [([0.1, np.nan, 0.5]), ([-0.001, 0.1, 0.5]), ([2, 0.1, 0.5]), ([0.1, 0.5, "a"])],
+)
+def test_error_format_percentiles(percentiles):
     msg = r"percentiles should all be in the interval \[0,1\]"
     with pytest.raises(ValueError, match=msg):
-        fmt.format_percentiles([0.1, np.nan, 0.5])
-    with pytest.raises(ValueError, match=msg):
-        fmt.format_percentiles([-0.001, 0.1, 0.5])
-    with pytest.raises(ValueError, match=msg):
-        fmt.format_percentiles([2, 0.1, 0.5])
-    with pytest.raises(ValueError, match=msg):
-        fmt.format_percentiles([0.1, 0.5, "a"])
+        fmt.format_percentiles(percentiles)
 
 
 def test_format_percentiles_integer_idx():
