P Addressed review comments on f483d6a

Author: blalterman

doc/source/whatsnew/v0.24.0.txt

@@ -236,6 +236,7 @@ Other Enhancements
 - Compatibility with Matplotlib 3.0 (:issue:`22790`).
 - Added :meth:`Interval.overlaps`, :meth:`IntervalArray.overlaps`, and :meth:`IntervalIndex.overlaps` for determining overlaps between interval-like objects (:issue:`21998`)
 - :meth:`Timestamp.tz_localize`, :meth:`DatetimeIndex.tz_localize`, and :meth:`Series.tz_localize` have gained the ``nonexistent`` argument for alternative handling of nonexistent times. See :ref:`timeseries.timezone_nonexsistent` (:issue:`8917`)
+- :func: `~cut` `bins` kwarg now accepts a string, which is dispatched to `numpy.histogram_bin_edges`. (:issue:`14627`)
 
 .. _whatsnew_0240.api_breaking:
 

pandas/core/reshape/tile.py

@@ -13,6 +13,8 @@
     is_scalar, is_timedelta64_dtype)
 from pandas.core.dtypes.missing import isna
 
+from pandas.compat import string_types
+
 from pandas import (
     Categorical, Index, Interval, IntervalIndex, Series, Timedelta, Timestamp,
     to_datetime, to_timedelta)
@@ -42,7 +44,7 @@ def cut(x, bins, right=True, labels=None, retbins=False, precision=3,
           range of `x` is extended by .1% on each side to include the minimum
           and maximum values of `x`.
         * str : Bin calculaton dispatched to `np.histogram_bin_edges`. See that
-          documentation for details.
+          documentation for details. (versionadded:: 0.24.0)
         * sequence of scalars : Defines the bin edges allowing for non-uniform
           width. No extension of the range of `x` is done.
         * IntervalIndex : Defines the exact bins to be used.
@@ -87,9 +89,9 @@ def cut(x, bins, right=True, labels=None, retbins=False, precision=3,
 
     bins : numpy.ndarray or IntervalIndex
         The computed or specified bins. Only returned when `retbins=True`.
-        For scalar or sequence `bins`, this is an ndarray with the computed
-        bins. If set `duplicates=drop`, `bins` will drop non-unique bin. For
-        an IntervalIndex `bins`, this is equal to `bins`.
+        For scalar, str, or sequence `bins`, this is an ndarray with the 
+        computed bins. If set `duplicates=drop`, `bins` will drop non-unique 
+        bin. For an IntervalIndex `bins`, this is equal to `bins`.
 
     See Also
     --------
@@ -100,6 +102,8 @@ def cut(x, bins, right=True, labels=None, retbins=False, precision=3,
     Series : One-dimensional array with axis labels (including time series).
     pandas.IntervalIndex : Immutable Index implementing an ordered,
         sliceable set.
+    numpy.histogram_bin_edges : Bin calculation dispatched to this method when
+        `bins` is a string.
 
     Notes
     -----
@@ -185,7 +189,7 @@ def cut(x, bins, right=True, labels=None, retbins=False, precision=3,
     Categories (3, interval[int64]): [(0, 1] < (2, 3] < (4, 5]]
 
     Passng a string for `bins` dispatches the bin calculation to numpy's
-    `histogram_bin_edges`.
+    `histogram_bin_edges`. (Starting in version 0.24.)
     >>> pd.cut(array([0.1, 0.1, 0.2, 0.5, 0.5, 0.9, 1.0]),
     ...        bins="auto")
     ... # doctest: +ELLIPSIS`
@@ -200,7 +204,8 @@ def cut(x, bins, right=True, labels=None, retbins=False, precision=3,
     x_is_series, series_index, name, x = _preprocess_for_cut(x)
     x, dtype = _coerce_to_type(x)
 
-    if isinstance(bins, str):
+    if isinstance(bins, string_types):
+        # GH 14627
         bins = np.histogram_bin_edges(x, bins)
         mn, mx = bins[0], bins[-1]
         adj = (mx - mn)

pandas/tests/reshape/test_tile.py

@@ -16,8 +16,6 @@
 from pandas.core.algorithms import quantile
 import pandas.core.reshape.tile as tmod
 
-import pdb
-
 class TestCut(object):
 
     def test_simple(self):
@@ -39,6 +37,7 @@ def test_bins(self):
                                                6.53333333, 9.7]))
 
     def test_str_bins(self):
+        # GH 14627
         data = np.array([0.1, 0.1, 0.2, 0.5, 0.5, 0.9, 1.0])
         result, bins_cut = cut(data, bins="auto",
                                retbins=True)
@@ -55,6 +54,13 @@ def test_str_bins(self):
         expected = Categorical(intervals, ordered=True)
         tm.assert_index_equal(result.categories,
                               expected.categories)
+        
+        
+        # Test that a `bin` string not present in `np.histogram_bin_edges`
+        # throws a ValueError.
+        tm.assert_raises_regex(ValueError, 
+            "'*' is not a valid estimator for `bins`", 
+            cut, data, "bad bins")
 
     def test_right(self):
         data = np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1, 2.575])