Expand test

Author: kotamatsuoka

pandas/core/algorithms.py

@@ -727,6 +727,8 @@ def value_counts(
         if not isinstance(counts, np.ndarray):
             counts = counts.to_numpy()
         result = result / float(counts.sum())
+    else:
+        result = result.astype("Int64")
 
     return result
 

pandas/tests/arrays/string_/test_string.py

@@ -277,13 +277,3 @@ def test_value_counts_na():
     result = arr.value_counts(dropna=True)
     expected = pd.Series([2, 1], index=["a", "b"], dtype="Int64")
     tm.assert_series_equal(result, expected)
-
-
-def test_normalize_value_counts():
-    result = (
-        pd.Series(list("abcd"), dtype="string")
-        .value_counts(normalize=True)
-        .sort_index()
-    )
-    expected = pd.Series([0.25, 0.25, 0.25, 0.25], index=["a", "b", "c", "d"])
-    tm.assert_series_equal(expected, result)

pandas/tests/extension/base/methods.py

@@ -3,12 +3,10 @@
 import numpy as np
 import pytest
 
-from pandas.core.dtypes.common import is_bool_dtype
-
 import pandas as pd
 import pandas._testing as tm
+from pandas.core.dtypes.common import is_bool_dtype
 from pandas.core.sorting import nargsort
-
 from .base import BaseExtensionTests
 
 
@@ -17,7 +15,7 @@ class BaseMethodsTests(BaseExtensionTests):
 
     @pytest.mark.parametrize("dropna", [True, False])
     def test_value_counts(self, all_data, dropna):
-        all_data = all_data[:10]
+        all_data = all_data[:5]
         if dropna:
             other = np.array(all_data[~all_data.isna()])
         else:
@@ -28,6 +26,15 @@ def test_value_counts(self, all_data, dropna):
 
         self.assert_series_equal(result, expected)
 
+        result = (
+            pd.Series(all_data, dtype=all_data.dtype)
+                .value_counts(dropna=dropna, normalize=True)
+                .sort_index()
+        )
+
+        expected = pd.Series([1 / len(other)] * len(other), index=result.index)
+        tm.assert_series_equal(expected, result)
+
     def test_count(self, data_missing):
         df = pd.DataFrame({"A": data_missing})
         result = df.count(axis="columns")

pandas/tests/extension/test_datetime.py

@@ -90,10 +90,6 @@ class TestGetitem(BaseDatetimeTests, base.BaseGetitemTests):
 
 
 class TestMethods(BaseDatetimeTests, base.BaseMethodsTests):
-    @pytest.mark.skip(reason="Incorrect expected")
-    def test_value_counts(self, all_data, dropna):
-        pass
-
     def test_combine_add(self, data_repeated):
         # Timestamp.__add__(Timestamp) not defined
         pass

pandas/tests/extension/test_string.py

@@ -81,9 +81,7 @@ class TestNoReduce(base.BaseNoReduceTests):
 
 
 class TestMethods(base.BaseMethodsTests):
-    @pytest.mark.skip(reason="returns nullable")
-    def test_value_counts(self, all_data, dropna):
-        return super().test_value_counts(all_data, dropna)
+    pass
 
 
 class TestCasting(base.BaseCastingTests):