Move value_counts for struct into only multi-index's (#1142)

This PR address the comment at #1116 (comment)

Author: HyukjinKwon

databricks/koalas/base.py

@@ -20,9 +20,7 @@
 
 from functools import wraps, partial
 from typing import Union, Callable, Any
-from distutils.version import LooseVersion
 
-import pyspark
 import numpy as np
 import pandas as pd
 from pandas.api.types import is_list_like
@@ -35,7 +33,7 @@
 from databricks.koalas import numpy_compat
 from databricks.koalas.internal import _InternalFrame, SPARK_INDEX_NAME_FORMAT
 from databricks.koalas.typedef import pandas_wraps, spark_type_to_pandas_dtype
-from databricks.koalas.utils import align_diff_series, scol_for, validate_axis, default_session
+from databricks.koalas.utils import align_diff_series, scol_for, validate_axis
 from databricks.koalas.frame import DataFrame
 
 
@@ -948,14 +946,8 @@ def value_counts(self, normalize=False, sort=True, ascending=False, bins=None, d
         3    1
         Name: koalas, dtype: int64
         """
-        from databricks.koalas.series import Series, _col
-        from databricks.koalas.indexes import MultiIndex
-        if LooseVersion(pyspark.__version__) < LooseVersion("2.4") and \
-                default_session().conf.get("spark.sql.execution.arrow.enabled") == "true" and \
-                isinstance(self, MultiIndex):
-            raise RuntimeError("if you're using pyspark < 2.4, set conf "
-                               "'spark.sql.execution.arrow.enabled' to 'false' "
-                               "for using this function with MultiIndex")
+        from databricks.koalas.series import _col
+
         if bins is not None:
             raise NotImplementedError("value_counts currently does not support bins")
 

databricks/koalas/indexes.py

@@ -17,8 +17,8 @@
 """
 Wrappers for Indexes to behave similar to pandas Index, MultiIndex.
 """
-
-from functools import partial, reduce
+from distutils.version import LooseVersion
+from functools import partial
 from typing import Any, List, Optional, Tuple, Union
 
 import pandas as pd
@@ -27,6 +27,7 @@
     is_categorical_dtype, is_integer_dtype, is_float_dtype, is_numeric_dtype, is_object_dtype
 from pandas.io.formats.printing import pprint_thing
 
+import pyspark
 from pyspark import sql as spark
 from pyspark.sql import functions as F
 
@@ -35,10 +36,9 @@
 from databricks.koalas.exceptions import PandasNotImplementedError
 from databricks.koalas.base import IndexOpsMixin
 from databricks.koalas.frame import DataFrame
-from databricks.koalas.internal import _InternalFrame
 from databricks.koalas.missing.indexes import _MissingPandasLikeIndex, _MissingPandasLikeMultiIndex
 from databricks.koalas.series import Series
-from databricks.koalas.utils import name_like_string
+from databricks.koalas.utils import name_like_string, default_session
 from databricks.koalas.internal import _InternalFrame
 
 
@@ -1159,6 +1159,18 @@ def symmetric_difference(self, other, result_name=None, sort=None):
 
         return result
 
+    def value_counts(self, normalize=False, sort=True, ascending=False, bins=None, dropna=True):
+        if LooseVersion(pyspark.__version__) < LooseVersion("2.4") and \
+                default_session().conf.get("spark.sql.execution.arrow.enabled") == "true" and \
+                isinstance(self, MultiIndex):
+            raise RuntimeError("if you're using pyspark < 2.4, set conf "
+                               "'spark.sql.execution.arrow.enabled' to 'false' "
+                               "for using this function with MultiIndex")
+        return super(MultiIndex, self).value_counts(
+            normalize=normalize, sort=sort, ascending=ascending, bins=bins, dropna=dropna)
+
+    value_counts.__doc__ = IndexOpsMixin.value_counts.__doc__
+
     def __getattr__(self, item: str) -> Any:
         if hasattr(_MissingPandasLikeMultiIndex, item):
             property_or_func = getattr(_MissingPandasLikeMultiIndex, item)

databricks/koalas/tests/test_series.py

@@ -33,7 +33,6 @@
 from databricks.koalas.testing.utils import ReusedSQLTestCase, SQLTestUtils
 from databricks.koalas.exceptions import PandasNotImplementedError
 from databricks.koalas.missing.series import _MissingPandasLikeSeries
-from databricks.koalas.config import set_option, reset_option
 from databricks.koalas.utils import default_session