made nan count when dropna=False

Author: DataInformer

doc/source/whatsnew/v1.0.3.rst

@@ -22,6 +22,7 @@ Fixed regressions
 
 Bug fixes
 ~~~~~~~~~
+:issue: `25970` Fixed Series.value_counts so that normalize excludes NA values when dropna=False.
 
 Contributors
 ~~~~~~~~~~~~

pandas/core/algorithms.py

@@ -695,16 +695,15 @@ def value_counts(
 
         # count, remove nulls (from the index), and but the bins
         result = ii.value_counts(dropna=dropna)
-        result = result[result.index.notna()]
         result.index = result.index.astype("interval")
         result = result.sort_index()
 
         # if we are dropna and we have NO values
         if dropna and (result._values == 0).all():
             result = result.iloc[0:0]
 
-        # normalizing is by len of all (regardless of dropna)
-        counts = np.array([len(ii)])
+        # normalizing is by len of what gets included in the bins
+        counts = result._values
 
     else:
 

pandas/core/groupby/generic.py

@@ -675,7 +675,7 @@ def value_counts(
         from pandas.core.reshape.tile import cut
         from pandas.core.reshape.merge import _get_join_indexers
 
-        if bins is not None and not np.iterable(bins):
+        if bins is not None:# and not np.iterable(bins):
             # scalar bins cannot be done at top level
             # in a backward compatible way
             return self.apply(
@@ -684,6 +684,7 @@ def value_counts(
                 sort=sort,
                 ascending=ascending,
                 bins=bins,
+                dropna=dropna
             )
 
         ids, _, _ = self.grouper.group_info

pandas/tests/base/test_value_counts.py

@@ -190,6 +190,14 @@ def test_value_counts_bins(index_or_series):
 
     assert s.nunique() == 0
 
+    # handle normalizing bins with NA's properly
+    # see GH25970
+    s2 = Series([1,2,2,3,3,3, np.nan, np.nan, 4, 5])
+    intervals = IntervalIndex.from_breaks([0.995, 2.333, 3.667, 5.0])
+    expected_dropna = Series([0.375, 0.375, 0.25], intervals.take([1,0,2]))
+    expected_keepna_vals = np.array([0.3, 0.3, 0.2, 0.2])
+    tm.assert_series_equal(s2.value_counts(dropna=True, normalize=True, bins=3), expected_dropna)
+    tm.assert_numpy_array_equal(s2.value_counts(dropna=False, normalize=True, bins=3).values, expected_keepna_vals)
 
 def test_value_counts_datetime64(index_or_series):
     klass = index_or_series