BUG: Series.asof fails for all NaN Series (GH15713)

closes bug pandas-dev#15713

Added the test if the series is all nans  Added the code that check if
that's the case: if yes, return the expected output

Author: Carlos Souza <[email protected]>

Closes pandas-dev#15758 from ucals/bug-fix-15713 and squashes the following commits:

0765108 [Carlos Souza] First simplification, code-block in the same place
bb63964 [Carlos Souza] Propagating Series name
af9a29b [Carlos Souza] Setting name of asof result when scalar input and all nan
b8f078a [Carlos Souza] Small code standard change
7448b96 [Carlos Souza] Fixing scalar input
a080b9b [Carlos Souza] Making scalar input return in a Series
04b7306 [Carlos Souza] Removing .values and formating code PEP8
3f9c7fd [Carlos Souza] Minor comments
70c958f [Carlos Souza] Added tests for non-default indexes, scalar and multiple inputs, and results preserve columns
6b745af [Carlos Souza] Adding DataFrame tests & support, and optimizing the code
89fb6cf [Carlos Souza] BUG pandas-dev#15713 fixing failing tests
17d1d77 [Carlos Souza] BUG pandas-dev#15713 Series.asof return nan when series is all nans!
4e26ab8 [Carlos Souza] BUG pandas-dev#15713 Series.asof return nan when series is all nans.
c78d687 [Carlos Souza] BUG pandas-dev#15713 Series.asof return nan when series is all nans
676a4e5 [Carlos Souza] Test

Author: Carlos Souza

doc/source/whatsnew/v0.20.0.txt

@@ -868,6 +868,7 @@ Bug Fixes
 - Bug in ``pd.cut()`` with a single bin on an all 0s array (:issue:`15428`)
 - Bug in ``pd.qcut()`` with a single quantile and an array with identical values (:issue:`15431`)
 - Compat with SciPy 0.19.0 for testing on ``.interpolate()`` (:issue:`15662`)
+- Bug in ``Series.asof`` which raised if the series contained all ``np.nan`` (:issue:`15713`)
 
 - Compat for 32-bit platforms for ``.qcut/cut``; bins will now be ``int64`` dtype (:issue:`14866`)
 

pandas/core/generic.py

@@ -3972,6 +3972,16 @@ def asof(self, where, subset=None):
             where = Index(where) if is_list else Index([where])
 
         nulls = self.isnull() if is_series else self[subset].isnull().any(1)
+        if nulls.all():
+            if is_series:
+                return self._constructor(np.nan, index=where, name=self.name)
+            elif is_list:
+                from pandas import DataFrame
+                return DataFrame(np.nan, index=where, columns=self.columns)
+            else:
+                from pandas import Series
+                return Series(np.nan, index=self.columns, name=where[0])
+
         locs = self.index.asof_locs(where, ~(nulls.values))
 
         # mask the missing

pandas/tests/frame/test_asof.py

@@ -4,22 +4,19 @@
 from pandas import (DataFrame, date_range, Timestamp, Series,
                     to_datetime)
 
-from pandas.util.testing import assert_frame_equal, assert_series_equal
 import pandas.util.testing as tm
 
 from .common import TestData
 
 
 class TestFrameAsof(TestData, tm.TestCase):
-
     def setUp(self):
         self.N = N = 50
-        rng = date_range('1/1/1990', periods=N, freq='53s')
+        self.rng = date_range('1/1/1990', periods=N, freq='53s')
         self.df = DataFrame({'A': np.arange(N), 'B': np.arange(N)},
-                            index=rng)
+                            index=self.rng)
 
     def test_basic(self):
-
         df = self.df.copy()
         df.loc[15:30, 'A'] = np.nan
         dates = date_range('1/1/1990', periods=self.N * 3,
@@ -39,7 +36,6 @@ def test_basic(self):
         self.assertTrue((rs == 14).all(1).all())
 
     def test_subset(self):
-
         N = 10
         rng = date_range('1/1/1990', periods=N, freq='53s')
         df = DataFrame({'A': np.arange(N), 'B': np.arange(N)},
@@ -51,19 +47,19 @@ def test_subset(self):
         # with a subset of A should be the same
         result = df.asof(dates, subset='A')
         expected = df.asof(dates)
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
 
         # same with A/B
         result = df.asof(dates, subset=['A', 'B'])
         expected = df.asof(dates)
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
 
         # B gives self.df.asof
         result = df.asof(dates, subset='B')
         expected = df.resample('25s', closed='right').ffill().reindex(dates)
         expected.iloc[20:] = 9
 
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
 
     def test_missing(self):
         # GH 15118
@@ -75,9 +71,38 @@ def test_missing(self):
         result = df.asof('1989-12-31')
 
         expected = Series(index=['A', 'B'], name=Timestamp('1989-12-31'))
-        assert_series_equal(result, expected)
+        tm.assert_series_equal(result, expected)
 
         result = df.asof(to_datetime(['1989-12-31']))
         expected = DataFrame(index=to_datetime(['1989-12-31']),
                              columns=['A', 'B'], dtype='float64')
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
+
+    def test_all_nans(self):
+        # GH 15713
+        # DataFrame is all nans
+        result = DataFrame([np.nan]).asof([0])
+        expected = DataFrame([np.nan])
+        tm.assert_frame_equal(result, expected)
+
+        # testing non-default indexes, multiple inputs
+        dates = date_range('1/1/1990', periods=self.N * 3, freq='25s')
+        result = DataFrame(np.nan, index=self.rng, columns=['A']).asof(dates)
+        expected = DataFrame(np.nan, index=dates, columns=['A'])
+        tm.assert_frame_equal(result, expected)
+
+        # testing multiple columns
+        dates = date_range('1/1/1990', periods=self.N * 3, freq='25s')
+        result = DataFrame(np.nan, index=self.rng,
+                           columns=['A', 'B', 'C']).asof(dates)
+        expected = DataFrame(np.nan, index=dates, columns=['A', 'B', 'C'])
+        tm.assert_frame_equal(result, expected)
+
+        # testing scalar input
+        result = DataFrame(np.nan, index=[1, 2], columns=['A', 'B']).asof([3])
+        expected = DataFrame(np.nan, index=[3], columns=['A', 'B'])
+        tm.assert_frame_equal(result, expected)
+
+        result = DataFrame(np.nan, index=[1, 2], columns=['A', 'B']).asof(3)
+        expected = Series(np.nan, index=['A', 'B'], name=3)
+        tm.assert_series_equal(result, expected)

pandas/tests/series/test_asof.py

@@ -148,3 +148,29 @@ def test_errors(self):
         s = Series(np.random.randn(N), index=rng)
         with self.assertRaises(ValueError):
             s.asof(s.index[0], subset='foo')
+
+    def test_all_nans(self):
+        # GH 15713
+        # series is all nans
+        result = Series([np.nan]).asof([0])
+        expected = Series([np.nan])
+        tm.assert_series_equal(result, expected)
+
+        # testing non-default indexes
+        N = 50
+        rng = date_range('1/1/1990', periods=N, freq='53s')
+
+        dates = date_range('1/1/1990', periods=N * 3, freq='25s')
+        result = Series(np.nan, index=rng).asof(dates)
+        expected = Series(np.nan, index=dates)
+        tm.assert_series_equal(result, expected)
+
+        # testing scalar input
+        date = date_range('1/1/1990', periods=N * 3, freq='25s')[0]
+        result = Series(np.nan, index=rng).asof(date)
+        assert isnull(result)
+
+        # test name is propagated
+        result = Series(np.nan, index=[1, 2, 3, 4], name='test').asof([4, 5])
+        expected = Series(np.nan, index=[4, 5], name='test')
+        tm.assert_series_equal(result, expected)