split new test

Author: kotamatsuoka

pandas/core/arrays/string_.py

@@ -290,7 +290,7 @@ def _reduce(self, name, skipna=True, **kwargs):
     def value_counts(self, dropna=False):
         from pandas import value_counts
 
-        return value_counts(self._ndarray, dropna=dropna)
+        return value_counts(self._ndarray, dropna=dropna).astype("Int64")
 
     # Override parent because we have different return types.
     @classmethod

pandas/tests/arrays/string_/test_string.py

@@ -297,9 +297,9 @@ def test_arrow_roundtrip():
 def test_value_counts_na():
     arr = pd.array(["a", "b", "a", pd.NA], dtype="string")
     result = arr.value_counts(dropna=False)
-    expected = pd.Series([2, 1, 1], index=["a", "b", pd.NA])
+    expected = pd.Series([2, 1, 1], index=["a", "b", pd.NA], dtype="Int64")
     tm.assert_series_equal(result, expected)
 
     result = arr.value_counts(dropna=True)
-    expected = pd.Series([2, 1], index=["a", "b"])
+    expected = pd.Series([2, 1], index=["a", "b"], dtype="Int64")
     tm.assert_series_equal(result, expected)

pandas/tests/extension/base/methods.py

@@ -17,7 +17,7 @@ class BaseMethodsTests(BaseExtensionTests):
 
     @pytest.mark.parametrize("dropna", [True, False])
     def test_value_counts(self, all_data, dropna):
-        all_data = all_data[:10].unique()
+        all_data = all_data[:10]
         if dropna:
             other = np.array(all_data[~all_data.isna()])
         else:
@@ -28,13 +28,14 @@ def test_value_counts(self, all_data, dropna):
 
         self.assert_series_equal(result, expected)
 
+    def test_value_counts_with_normalize(self, data):
+        data = data[:10].unique()
+
         result = (
-            pd.Series(all_data, dtype=all_data.dtype)
-            .value_counts(dropna=dropna, normalize=True)
-            .sort_index()
+            pd.Series(data, dtype=data.dtype).value_counts(normalize=True).sort_index()
         )
 
-        expected = pd.Series([1 / len(other)] * len(other), index=result.index)
+        expected = pd.Series([1 / len(data)] * len(data), index=result.index)
         self.assert_series_equal(result, expected)
 
     def test_count(self, data_missing):

pandas/tests/extension/decimal/test_decimal.py

@@ -181,6 +181,10 @@ def test_value_counts(self, all_data, dropna):
 
         tm.assert_series_equal(result, expected)
 
+    @pytest.mark.xfail(reason="value_counts not implemented yet.")
+    def test_value_counts_with_normalize(self, data):
+        return super().test_value_counts_with_normalize(data)
+
 
 class TestCasting(BaseDecimal, base.BaseCastingTests):
     pass

pandas/tests/extension/json/test_json.py

@@ -193,6 +193,10 @@ class TestMethods(BaseJSON, base.BaseMethodsTests):
     def test_value_counts(self, all_data, dropna):
         pass
 
+    @unhashable
+    def test_value_counts_with_normalize(self, data):
+        pass
+
     @unhashable
     def test_sort_values_frame(self):
         # TODO (EA.factorize): see if _values_for_factorize allows this.

pandas/tests/extension/test_boolean.py

@@ -230,6 +230,10 @@ def test_searchsorted(self, data_for_sorting, as_series):
     def test_value_counts(self, all_data, dropna):
         return super().test_value_counts(all_data, dropna)
 
+    @pytest.mark.skip(reason="uses nullable integer")
+    def test_value_counts_with_normalize(self, data):
+        return super().test_value_counts_with_normalize(data)
+
 
 class TestCasting(base.BaseCastingTests):
     pass

pandas/tests/extension/test_integer.py

@@ -224,6 +224,10 @@ def test_value_counts(self, all_data, dropna):
 
         self.assert_series_equal(result, expected)
 
+    @pytest.mark.xfail(reason="not working with nan")
+    def test_value_counts_with_normalize(self, data):
+        super().test_value_counts_with_normalize(data)
+
 
 class TestCasting(base.BaseCastingTests):
     pass

pandas/tests/extension/test_numpy.py

@@ -199,6 +199,10 @@ class TestMethods(BaseNumPyTests, base.BaseMethodsTests):
     def test_value_counts(self, all_data, dropna):
         pass
 
+    @pytest.mark.xfail(reason="not working")
+    def test_value_counts_with_normalize(self, data):
+        return super().test_value_counts_with_normalize(data)
+
     @pytest.mark.skip(reason="Incorrect expected")
     # We have a bool dtype, so the result is an ExtensionArray
     # but expected is not

pandas/tests/extension/test_sparse.py

@@ -229,6 +229,10 @@ def test_fillna_frame(self, data_missing):
 
 
 class TestMethods(BaseSparseTests, base.BaseMethodsTests):
+    @pytest.mark.xfail(reason="not working with nan")
+    def test_value_counts_with_normalize(self):
+        super().test_value_counts_with_normalize(data)
+
     def test_combine_le(self, data_repeated):
         # We return a Series[SparseArray].__le__ returns a
         # Series[Sparse[bool]]

pandas/tests/extension/test_string.py

@@ -90,7 +90,9 @@ def test_reduce_series_numeric(self, data, all_numeric_reductions, skipna):
 
 
 class TestMethods(base.BaseMethodsTests):
-    pass
+    @pytest.mark.skip(reason="returns nullable")
+    def test_value_counts(self, all_data, dropna):
+        return super().test_value_counts(all_data, dropna)
 
 
 class TestCasting(base.BaseCastingTests):