BUG: Comparisons result in different dtypes for empty DataFrames #15077

closes #15077

Author: Giacomo Ferroni <[email protected]>
Author: Giacomo Ferroni <[email protected]>
Author: mralgos <[email protected]>

Closes #15115 from mralgos/gh15077 and squashes the following commits:

a5ca359 [mralgos] Merge branch 'master' into gh15077
dc0803b [Giacomo Ferroni] Merge branch 'master' into gh15077
b2f2d1e [Giacomo Ferroni] Merge branch 'gh15077' of https://github.com/mralgos/pandas into gh15077
fcbcb5b [Giacomo Ferroni] Apply review changes
9723c5d [Giacomo Ferroni] Merge branch 'master' into gh15077
eb7d9fd [Giacomo Ferroni] Delete blank lines
28437bb [Giacomo Ferroni] Check for bool dtype return added also for Series. Minor update to whatsnew
19296f1 [Giacomo Ferroni] Added test for gh15077 (cf. gh15115) and whatsnew note
ea11867 [Giacomo Ferroni] [gh15077] Bugfix

Author: Giacomo Ferroni

doc/source/whatsnew/v0.20.0.txt

@@ -437,9 +437,10 @@ Bug Fixes
 
 - Bug in ``Series`` constructor when both ``copy=True`` and ``dtype`` arguments are provided (:issue:`15125`)
 - Bug in ``pd.read_csv()`` for the C engine where ``usecols`` were being indexed incorrectly with ``parse_dates`` (:issue:`14792`)
-
+- Incorrect dtyped ``Series`` was returned by comparison methods (e.g., ``lt``, ``gt``, ...) against a constant for an empty ``DataFrame`` (:issue:`15077`)
 - Bug in ``Series.dt.round`` inconsistent behaviour on NAT's with different arguments (:issue:`14940`)
 
+
 - Bug in ``.read_json()`` for Python 2 where ``lines=True`` and contents contain non-ascii unicode characters (:issue:`15132`)
 
 - Bug in ``pd.read_csv()`` with ``float_precision='round_trip'`` which caused a segfault when a text entry is parsed (:issue:`15140`)

pandas/core/frame.py

@@ -3595,9 +3595,6 @@ def _combine_match_columns(self, other, func, level=None, fill_value=None):
         return self._constructor(new_data)
 
     def _combine_const(self, other, func, raise_on_error=True):
-        if self.empty:
-            return self
-
         new_data = self._data.eval(func=func, other=other,
                                    raise_on_error=raise_on_error)
         return self._constructor(new_data)

pandas/tests/frame/test_operators.py

@@ -671,6 +671,22 @@ def _test_seq(df, idx_ser, col_ser):
         exp = DataFrame({'col': [False, True, False]})
         assert_frame_equal(result, exp)
 
+    def test_return_dtypes_bool_op_costant(self):
+        # GH15077
+        df = DataFrame({'x': [1, 2, 3], 'y': [1., 2., 3.]})
+        const = 2
+
+        # not empty DataFrame
+        for op in ['eq', 'ne', 'gt', 'lt', 'ge', 'le']:
+            result = getattr(df, op)(const).get_dtype_counts()
+            self.assert_series_equal(result, Series([2], ['bool']))
+
+        # empty DataFrame
+        empty = df.iloc[:0]
+        for op in ['eq', 'ne', 'gt', 'lt', 'ge', 'le']:
+            result = getattr(empty, op)(const).get_dtype_counts()
+            self.assert_series_equal(result, Series([2], ['bool']))
+
     def test_dti_tz_convert_to_utc(self):
         base = pd.DatetimeIndex(['2011-01-01', '2011-01-02',
                                  '2011-01-03'], tz='UTC')

pandas/tests/series/test_operators.py

@@ -1294,6 +1294,20 @@ def test_comparison_flex_alignment_fill(self):
         exp = pd.Series([True, True, False, False], index=list('abcd'))
         assert_series_equal(left.gt(right, fill_value=0), exp)
 
+    def test_return_dtypes_bool_op_costant(self):
+        # gh15115
+        s = pd.Series([1, 3, 2], index=range(3))
+        const = 2
+        for op in ['eq', 'ne', 'gt', 'lt', 'ge', 'le']:
+            result = getattr(s, op)(const).get_dtype_counts()
+            self.assert_series_equal(result, Series([1], ['bool']))
+
+        # empty Series
+        empty = s.iloc[:0]
+        for op in ['eq', 'ne', 'gt', 'lt', 'ge', 'le']:
+            result = getattr(empty, op)(const).get_dtype_counts()
+            self.assert_series_equal(result, Series([1], ['bool']))
+
     def test_operators_bitwise(self):
         # GH 9016: support bitwise op for integer types
         index = list('bca')