Merge branch 'where_bool_broadcast' of https://github.com/SleepingPills/pandas into SleepingPills-where_bool_broadcast

Conflicts:
	doc/source/release.rst

Author: jreback

doc/source/release.rst

@@ -72,11 +72,11 @@ pandas 0.12
     - support python3 (via ``PyTables 3.0.0``) (:issue:`3750`)
   - Add modulo operator to Series, DataFrame
   - Add ``date`` method to DatetimeIndex
-  - Add ``dropna`` argument to pivot_table (:issue: `3820`) 
+  - Add ``dropna`` argument to pivot_table (:issue: `3820`)
   - Simplified the API and added a describe method to Categorical
   - ``melt`` now accepts the optional parameters ``var_name`` and ``value_name``
     to specify custom column names of the returned DataFrame (:issue:`3649`),
-    thanks @hoechenberger. If ``var_name`` is not specified and ``dataframe.columns.name`` 
+    thanks @hoechenberger. If ``var_name`` is not specified and ``dataframe.columns.name``
     is not None, then this will be used as the ``var_name`` (:issue:`4144`).
   - clipboard functions use pyperclip (no dependencies on Windows, alternative
     dependencies offered for Linux) (:issue:`3837`).
@@ -322,10 +322,13 @@ pandas 0.12
     object Series/Frame was not converting properly (:issue:`4119`)
   - Fixed bugs in multi-index selection with column multi-index and duplicates
     (:issue:`4145`, :issue:`4146`)
-  - Fixed bug in the parsing of microseconds when using the ``format`` 
+  - Fixed bug in the parsing of microseconds when using the ``format``
     argument in ``to_datetime`` (:issue:`4152`)
   - Fixed bug in ``PandasAutoDateLocator`` where ``invert_xaxis`` triggered
     incorrectly ``MilliSecondLocator``  (:issue:`3990`)
+  - Fixed bug in ``Series.where`` where broadcasting a single element input vector
+    to the length of the series resulted in multiplying the value
+    inside the input (:issue:`4192`)
 
 pandas 0.11.0
 =============

pandas/core/series.py

@@ -755,7 +755,7 @@ def where(self, cond, other=nan, inplace=False):
             # GH 2745
             # treat like a scalar
             if len(other) == 1:
-                other = np.array(other[0]*len(ser))
+                other = np.array(other[0])
 
             # GH 3235
             # match True cond to other

pandas/tests/test_series.py

@@ -1090,11 +1090,6 @@ def test_where(self):
         expected = Series([0,2])
         assert_series_equal(s,expected)
 
-        s = Series([1,2])
-        s[[True, False]] = [0]
-        expected = Series([0,2])
-        assert_series_equal(s,expected)
-
         # failures
         self.assertRaises(ValueError, s.__setitem__, tuple([[[True, False]]]), [0,2,3])
         self.assertRaises(ValueError, s.__setitem__, tuple([[[True, False]]]), [])
@@ -1142,6 +1137,24 @@ def test_where(self):
         s = Series(np.arange(10))
         mask = s > 5
         self.assertRaises(ValueError, s.__setitem__, mask, ([0]*5,))
+        
+    def test_where_broadcast(self):
+        # Test a variety of differently sized series
+        for size in range(2, 6):
+            # Test a variety of boolean indices
+            for selection in [np.resize([True, False, False, False, False], size), # First element should be set
+                              np.resize([True, False], size), # Set alternating elements]
+                              np.resize([False], size)]: # No element should be set
+                # Test a variety of different numbers as content
+                for item in [2.0, np.nan, np.finfo(np.float).max, np.finfo(np.float).min]:
+                    # Test numpy arrays, lists and tuples as the input to be broadcast
+                    for arr in [np.array([item]), [item], (item,)]:
+                        data = np.arange(size, dtype=float)
+                        s = Series(data)
+                        s[selection] = arr
+                        # Construct the expected series by taking the source data or item based on the selection
+                        expected = Series([item if use_item else data[i] for i, use_item in enumerate(selection)])
+                        assert_series_equal(s,expected)
 
     def test_where_inplace(self):
         s = Series(np.random.randn(5))