BUG: Coercing bool types to int in qcut

doc/source/whatsnew/v0.25.2.rst

@@ -103,6 +103,7 @@ Other
 - Compatibility with Python 3.8 in :meth:`DataFrame.query` (:issue:`27261`)
 - Fix to ensure that tab-completion in an IPython console does not raise
   warnings for deprecated attributes (:issue:`27900`).
+- :func:`qcut` now handles bool ndarray/Series (:issue:`20303`)
 
 .. _whatsnew_0.252.contributors:
 

pandas/core/reshape/tile.py

@@ -11,6 +11,7 @@
 from pandas.core.dtypes.common import (
     _NS_DTYPE,
     ensure_int64,
+    is_bool_dtype,
     is_categorical_dtype,
     is_datetime64_dtype,
     is_datetime64tz_dtype,
@@ -423,8 +424,8 @@ def _bins_to_cuts(
 
 def _coerce_to_type(x):
     """
-    if the passed data is of datetime/timedelta type,
-    this method converts it to numeric so that cut method can
+    if the passed data is of datetime/timedelta or bool type,
+    this method converts it to numeric so that cut or qcut method can
     handle it
     """
     dtype = None
@@ -437,10 +438,15 @@ def _coerce_to_type(x):
     elif is_timedelta64_dtype(x):
         x = to_timedelta(x)
         dtype = np.dtype("timedelta64[ns]")
+    elif is_bool_dtype(x):
+        dtype = x.dtype
 
     if dtype is not None:
         # GH 19768: force NaT to NaN during integer conversion
-        x = np.where(x.notna(), x.view(np.int64), np.nan)
+        if is_bool_dtype(x):
+            x = np.where(~np.isnan(x), x.astype(int), np.nan)
+        else:
+            x = np.where(x.notna(), x.view(np.int64), np.nan)
 
     return x, dtype
 

pandas/tests/reshape/test_cut.py

@@ -585,3 +585,17 @@ def test_timedelta_cut_roundtrip():
         ["0 days 23:57:07.200000", "2 days 00:00:00", "3 days 00:00:00"]
     )
     tm.assert_index_equal(result_bins, expected_bins)
+
+
+@pytest.mark.parametrize("bins", [6, 7])
+@pytest.mark.parametrize(
+    "box, compare",
+    [(Series, tm.assert_series_equal), (np.array, tm.assert_categorical_equal)],
+)
+def test_cut_bool_coercion_to_int(bins, box, compare):
+    # issue 20303
+    x = box(np.random.randint(2, size=200))
+    expected = cut(x, bins, duplicates="drop")
+    data = x.astype(bool)
+    result = cut(data, bins, duplicates="drop")
+    compare(result, expected)

pandas/tests/reshape/test_qcut.py

@@ -236,3 +236,17 @@ def test_date_like_qcut_bins(arg, expected_bins):
     ser = Series(arg)
     result, result_bins = qcut(ser, 2, retbins=True)
     tm.assert_index_equal(result_bins, expected_bins)
+
+
+@pytest.mark.parametrize("bins", [6, 7])
+@pytest.mark.parametrize(
+    "box, compare",
+    [(Series, tm.assert_series_equal), (np.array, tm.assert_categorical_equal)],
+)
+def test_qcut_bool_coercion_to_int(bins, box, compare):
+    # issue 20303
+    x = box(np.random.randint(2, size=200))
+    expected = qcut(x, bins, duplicates="drop")
+    data = x.astype(bool)
+    result = qcut(data, bins, duplicates="drop")
+    compare(result, expected)