Added 'allow' duplicates option to _bins_to_cuts

Author: luca-s

pandas/tests/tools/test_tile.py

@@ -3,7 +3,7 @@
 import numpy as np
 from pandas.compat import zip
 
-from pandas import Series, Index
+from pandas import Series, Index, Categorical
 import pandas.util.testing as tm
 from pandas.util.testing import assertRaisesRegexp
 import pandas.core.common as com
@@ -239,7 +239,6 @@ def test_qcut_binning_issues(self):
             self.assertTrue(ep <= sn)
 
     def test_cut_return_categorical(self):
-        from pandas import Categorical
         s = Series([0, 1, 2, 3, 4, 5, 6, 7, 8])
         res = cut(s, 3)
         exp = Series(Categorical.from_codes([0, 0, 0, 1, 1, 1, 2, 2, 2],
@@ -249,7 +248,6 @@ def test_cut_return_categorical(self):
         tm.assert_series_equal(res, exp)
 
     def test_qcut_return_categorical(self):
-        from pandas import Categorical
         s = Series([0, 1, 2, 3, 4, 5, 6, 7, 8])
         res = qcut(s, [0, 0.333, 0.666, 1])
         exp = Series(Categorical.from_codes([0, 0, 0, 1, 1, 1, 2, 2, 2],
@@ -292,28 +290,52 @@ def test_single_quantile(self):
         s = Series([9., 9.])
         result = qcut(s, 1, labels=False)
         tm.assert_series_equal(result, expected)
+        result = qcut(s, 1)
+        exp_lab = Series(Categorical.from_codes([0, 0], ["[9, 9]"],
+                                                ordered=True))
+        tm.assert_series_equal(result, exp_lab)
 
         s = Series([-9., -9.])
         result = qcut(s, 1, labels=False)
         tm.assert_series_equal(result, expected)
+        result = qcut(s, 1)
+        exp_lab = Series(Categorical.from_codes([0, 0], ["[-9, -9]"],
+                                                ordered=True))
+        tm.assert_series_equal(result, exp_lab)
 
         s = Series([0., 0.])
         result = qcut(s, 1, labels=False)
         tm.assert_series_equal(result, expected)
+        result = qcut(s, 1)
+        exp_lab = Series(Categorical.from_codes([0, 0], ["[0, 0]"],
+                                                ordered=True))
+        tm.assert_series_equal(result, exp_lab)
 
         expected = Series([0])
 
         s = Series([9])
         result = qcut(s, 1, labels=False)
         tm.assert_series_equal(result, expected)
+        result = qcut(s, 1)
+        exp_lab = Series(Categorical.from_codes([0], ["[9, 9]"],
+                                                ordered=True))
+        tm.assert_series_equal(result, exp_lab)
 
         s = Series([-9])
         result = qcut(s, 1, labels=False)
         tm.assert_series_equal(result, expected)
+        result = qcut(s, 1)
+        exp_lab = Series(Categorical.from_codes([0], ["[-9, -9]"],
+                                                ordered=True))
+        tm.assert_series_equal(result, exp_lab)
 
         s = Series([0])
         result = qcut(s, 1, labels=False)
         tm.assert_series_equal(result, expected)
+        result = qcut(s, 1)
+        exp_lab = Series(Categorical.from_codes([0], ["[0, 0]"],
+                                                ordered=True))
+        tm.assert_series_equal(result, exp_lab)
 
     def test_single_bin(self):
         # issue 14652

pandas/tools/tile.py

@@ -186,16 +186,13 @@ def qcut(x, q, labels=None, retbins=False, precision=3, duplicates='raise'):
 
     if is_integer(q):
         quantiles = np.linspace(0, 1, q + 1)
+
+        if q == 1:
+            duplicates = 'allow'
     else:
         quantiles = q
     bins = algos.quantile(x, quantiles)
 
-    # fix special case: q=1 and all identical values
-    if q == 1 and len(bins) == 2 and bins[0] == bins[1]:
-        bins = np.asarray(bins, np.float64)
-        bins[0] -= .001 * abs(bins[0]) if bins[0] != 0 else .001
-        bins[1] += .001 * abs(bins[1]) if bins[1] != 0 else .001
-
     fac, bins = _bins_to_cuts(x, bins, labels=labels,
                               precision=precision, include_lowest=True,
                               dtype=dtype, duplicates=duplicates)
@@ -208,7 +205,7 @@ def _bins_to_cuts(x, bins, right=True, labels=None,
                   precision=3, include_lowest=False,
                   dtype=None, duplicates='raise'):
 
-    if duplicates not in ['raise', 'drop']:
+    if duplicates not in ['raise', 'drop', 'allow']:
         raise ValueError("invalid value for 'duplicates' parameter, "
                          "valid options are: raise, drop")
 
@@ -218,7 +215,7 @@ def _bins_to_cuts(x, bins, right=True, labels=None,
             raise ValueError("Bin edges must be unique: {}.\nYou "
                              "can drop duplicate edges by setting "
                              "the 'duplicates' kwarg".format(repr(bins)))
-        else:
+        elif duplicates == 'drop':
             bins = unique_bins
 
     side = 'left' if right else 'right'