BUG: Retain timezone dtype with cut and qcut

Add aditional test

Author: mroeschke

doc/source/whatsnew/v0.23.0.txt

@@ -918,6 +918,7 @@ Reshaping
 - :func:`Series.rename` now accepts ``axis`` as a kwarg (:issue:`18589`)
 - Comparisons between :class:`Series` and :class:`Index` would return a ``Series`` with an incorrect name, ignoring the ``Index``'s name attribute (:issue:`19582`)
 - Bug in :func:`qcut` where datetime and timedelta data with ``NaT`` present raised a ``ValueError`` (:issue:`19768`)
+- Bug in :func:`cut` and :func:`qcut` where timezone information was dropped (:issue:`19872`)
 
 Other
 ^^^^^

pandas/core/reshape/tile.py

@@ -9,6 +9,7 @@
     is_categorical_dtype,
     is_datetime64_dtype,
     is_timedelta64_dtype,
+    is_datetime64tz_dtype,
     _ensure_int64)
 
 import pandas.core.algorithms as algos
@@ -284,7 +285,9 @@ def _coerce_to_type(x):
     """
     dtype = None
 
-    if is_timedelta64_dtype(x):
+    if is_datetime64tz_dtype(x):
+        dtype = x.dtype
+    elif is_timedelta64_dtype(x):
         x = to_timedelta(x)
         dtype = np.timedelta64
     elif is_datetime64_dtype(x):
@@ -333,7 +336,11 @@ def _format_labels(bins, precision, right=True,
 
     closed = 'right' if right else 'left'
 
-    if is_datetime64_dtype(dtype):
+    if is_datetime64tz_dtype(dtype):
+        from functools import partial
+        formatter = partial(Timestamp, tz=dtype.tz)
+        adjust = lambda x: x - Timedelta('1ns')
+    elif is_datetime64_dtype(dtype):
         formatter = Timestamp
         adjust = lambda x: x - Timedelta('1ns')
     elif is_timedelta64_dtype(dtype):
@@ -372,7 +379,11 @@ def _preprocess_for_cut(x):
         series_index = x.index
         name = x.name
 
-    x = np.asarray(x)
+    ndim = getattr(x, 'ndim', None)
+    if ndim is None:
+        x = np.asarray(x)
+    if x.ndim != 1:
+        raise ValueError("Input array must be 1 dimensional")
 
     return x_is_series, series_index, name, x
 

pandas/tests/reshape/test_tile.py

@@ -4,7 +4,7 @@
 import numpy as np
 from pandas.compat import zip
 
-from pandas import (Series, isna, to_datetime, DatetimeIndex,
+from pandas import (DataFrame, Series, isna, to_datetime, DatetimeIndex,
                     Timestamp, Interval, IntervalIndex, Categorical,
                     cut, qcut, date_range, NaT, TimedeltaIndex)
 from pandas.tseries.offsets import Nano, Day
@@ -104,6 +104,12 @@ def test_cut_corner(self):
 
         pytest.raises(ValueError, cut, [1, 2, 3], 0.5)
 
+    @pytest.mark.parametrize('arg', [2, np.eye(2), DataFrame(np.eye(2))])
+    @pytest.mark.parametrize('cut_func', [cut, qcut])
+    def test_cut_not_1d_arg(self, arg, cut_func):
+        with pytest.raises(ValueError):
+            cut_func(arg, 2)
+
     def test_cut_out_of_range_more(self):
         # #1511
         s = Series([0, -1, 0, 1, -3], name='x')
@@ -488,6 +494,34 @@ def test_datetime_cut(self):
         result, bins = cut(data, 3, retbins=True)
         tm.assert_series_equal(Series(result), expected)
 
+    def test_datetimetz_cut(self):
+        # GH 19872
+        tz = 'US/Eastern'
+        s = Series(date_range('20130101', periods=3, tz=tz))
+        result = cut(s, 3)
+        expected = (
+            Series(IntervalIndex([
+                Interval(Timestamp('2012-12-31 23:57:07.200000', tz=tz),
+                         Timestamp('2013-01-01 16:00:00', tz=tz)),
+                Interval(Timestamp('2013-01-01 16:00:00', tz=tz),
+                         Timestamp('2013-01-02 08:00:00', tz=tz)),
+                Interval(Timestamp('2013-01-02 08:00:00', tz=tz),
+                         Timestamp('2013-01-03 00:00:00', tz=tz))]))
+            .astype(CDT(ordered=True)))
+        tm.assert_series_equal(result, expected)
+
+        result = qcut(s, 3)
+        expected = (
+            Series(IntervalIndex([
+                Interval(Timestamp('2012-12-31 23:59:59.999999999', tz=tz),
+                         Timestamp('2013-01-01 16:00:00', tz=tz)),
+                Interval(Timestamp('2013-01-01 16:00:00', tz=tz),
+                         Timestamp('2013-01-02 08:00:00', tz=tz)),
+                Interval(Timestamp('2013-01-02 08:00:00', tz=tz),
+                         Timestamp('2013-01-03 00:00:00', tz=tz))]))
+            .astype(CDT(ordered=True)))
+        tm.assert_series_equal(result, expected)
+
     def test_datetime_bin(self):
         data = [np.datetime64('2012-12-13'), np.datetime64('2012-12-15')]
         bin_data = ['2012-12-12', '2012-12-14', '2012-12-16']