change after review

Author: makbigc

pandas/core/reshape/merge.py

@@ -8,51 +8,19 @@
 
 import numpy as np
 
-<<<<<<< HEAD
 from pandas._libs import hashtable as libhashtable, join as libjoin, lib
 import pandas.compat as compat
 from pandas.compat import filter, lzip, map, range, zip
 from pandas.errors import MergeError
-=======
-from pandas import (Categorical, DataFrame,
- Index, MultiIndex, Timedelta, Series)
-from pandas.core.arrays.categorical import _recode_for_categories
-from pandas.core.frame import _merge_doc
-from pandas.core.dtypes.common import (
- is_datetime64tz_dtype,
- is_datetime64_dtype,
- needs_i8_conversion,
- is_int64_dtype,
- is_array_like,
- is_categorical_dtype,
- is_integer_dtype,
- is_float_dtype,
- is_number,
- is_numeric_dtype,
- is_integer,
- is_extension_array_dtype,
- is_int_or_datetime_dtype,
- is_dtype_equal,
- is_bool,
- is_bool_dtype,
- is_list_like,
- is_datetimelike,
- ensure_int64,
- ensure_float64,
- ensure_object,
- _get_dtype)
-from pandas.core.dtypes.missing import na_value_for_dtype
-from pandas.core.internals import (items_overlap_with_suffix,
- concatenate_block_managers)
->>>>>>> fix bug #GH23020
 from pandas.util._decorators import Appender, Substitution
 
 from pandas.core.dtypes.common import (
  ensure_float64, ensure_int64, ensure_object, is_array_like, is_bool,
  is_bool_dtype, is_categorical_dtype, is_datetime64_dtype,
  is_datetime64tz_dtype, is_datetimelike, is_dtype_equal, is_float_dtype,
  is_int64_dtype, is_int_or_datetime_dtype, is_integer, is_integer_dtype,
- is_list_like, is_number, is_numeric_dtype, needs_i8_conversion)
+ is_list_like, is_number, is_numeric_dtype, is_extension_array_dtype,
+ needs_i8_conversion)
 from pandas.core.dtypes.missing import isnull, na_value_for_dtype
 
 from pandas import Categorical, DataFrame, Index, MultiIndex, Series, Timedelta
@@ -1551,10 +1519,12 @@ def _factorize_keys(lk, rk, sort=True):
 
  lk = ensure_int64(lk.codes)
  rk = ensure_int64(rk)
- elif is_extension_array_dtype(lk) and is_extension_array_dtype(rk):
+ elif (is_extension_array_dtype(lk) and
+ is_extension_array_dtype(rk) and
+ lk.dtype == rk.dtype):
  klass = libhashtable.Factorizer
- lk = ensure_object(lk)
- rk = ensure_object(rk)
+ lk, _ = lk._values_for_factorize()
+ rk, _ = rk._values_for_factorize()
  elif is_int_or_datetime_dtype(lk) and is_int_or_datetime_dtype(rk):
  klass = libhashtable.Int64Factorizer
  lk = ensure_int64(com.values_from_object(lk))

pandas/tests/extension/base/reshaping.py

@@ -170,3 +170,11 @@ def test_merge(self, data, na_value):
  [data[0], data[0], data[1], data[2], na_value],
  dtype=data.dtype)})
  self.assert_frame_equal(res, exp[['ext', 'int1', 'key', 'int2']])
+
+ def test_merge_on_int_array(self, df_merge_on_int_array):
+ # GH 23020
+ result = pd.merge(df_merge_on_int_array, df_merge_on_int_array, on='A')
+ expected = pd.DataFrame({'A': pd.Series([1, 2, np.nan], dtype='Int64'),
+ 'B_x': 1,
+ 'B_y': 1})
+ self.assert_frame_equal(result, expected, check_dtype=True)

pandas/tests/extension/conftest.py

@@ -1,3 +1,5 @@
+import pandas as pd
+import numpy as np
 import operator
 
 import pytest
@@ -104,3 +106,9 @@ def data_for_grouping():
 def box_in_series(request):
  """Whether to box the data in a Series"""
  return request.param
+
+
+@pytest.fixture
+def df_merge_on_int_array():
+ return pd.DataFrame({'A': pd.Series([1, 2, np.nan], dtype='Int64'),
+ 'B': 1})

pandas/tests/reshape/merge/test_merge.py

@@ -1842,16 +1842,6 @@ def test_merging_with_bool_or_int_cateorical_column(self, category_column,
  CDT(categories, ordered=ordered))
  assert_frame_equal(expected, result)
 
- def test_merge_on_int_array(self):
- # GH 23020
- df = pd.DataFrame({'A': pd.Series([1, 2, np.nan], dtype='Int64'),
- 'B': 1})
- result = pd.merge(df, df, on='A')
- expected = pd.DataFrame({'A': pd.Series([1, 2, np.nan], dtype='Int64'),
- 'B_x': 1,
- 'B_y': 1})
- assert_frame_equal(result, expected, check_dtype=True)
-
 
 @pytest.fixture
 def left_df():