pass through allow dups

Author: jorisvandenbossche

.github/workflows/ci.yml

@@ -157,4 +157,4 @@ jobs:
       run: |
         source activate pandas-dev
         pytest pandas/tests/frame/methods --array-manager
-        pytest pandas/tests/reshape/concat/ --array-manager
+        pytest pandas/tests/reshape --array-manager

pandas/core/internals/concat.py

@@ -59,7 +59,12 @@ def concatenate_array_managers(
     for mgr, indexers in mgrs_indexers:
         for ax, indexer in indexers.items():
             mgr = mgr.reindex_indexer(
-                axes[ax], indexer, axis=ax, do_integrity_check=False, use_na_proxy=True
+                axes[ax],
+                indexer,
+                axis=ax,
+                allow_dups=True,
+                do_integrity_check=False,
+                use_na_proxy=True,
             )
         mgrs.append(mgr)
 

pandas/tests/frame/methods/test_explode.py

@@ -1,14 +1,9 @@
 import numpy as np
 import pytest
 
-import pandas.util._test_decorators as td
-
 import pandas as pd
 import pandas._testing as tm
 
-# TODO(ArrayManager) concat reindex with duplicates
-pytestmark = td.skip_array_manager_not_yet_implemented
-
 
 def test_error():
     df = pd.DataFrame(

pandas/tests/frame/methods/test_join.py

@@ -3,8 +3,6 @@
 import numpy as np
 import pytest
 
-import pandas.util._test_decorators as td
-
 import pandas as pd
 from pandas import DataFrame, Index, MultiIndex, date_range, period_range
 import pandas._testing as tm
@@ -180,7 +178,6 @@ def test_join_period_index(frame_with_period_index):
     tm.assert_frame_equal(joined, expected)
 
 
-@td.skip_array_manager_not_yet_implemented  # TODO(ArrayManager) concat with duplicates
 def test_join_left_sequence_non_unique_index():
     # https://github.com/pandas-dev/pandas/issues/19607
     df1 = DataFrame({"a": [0, 10, 20]}, index=[1, 2, 3])

pandas/tests/reshape/merge/test_join.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+import pandas.util._test_decorators as td
+
 import pandas as pd
 from pandas import (
     Categorical,
@@ -547,6 +549,7 @@ def test_join_non_unique_period_index(self):
         )
         tm.assert_frame_equal(result, expected)
 
+    @td.skip_array_manager_not_yet_implemented  # TODO(ArrayManager) groupby
     def test_mixed_type_join_with_suffix(self):
         # GH #916
         df = DataFrame(np.random.randn(20, 6), columns=["a", "b", "c", "d", "e", "f"])

pandas/tests/reshape/merge/test_merge.py

@@ -5,6 +5,8 @@
 import numpy as np
 import pytest
 
+import pandas.util._test_decorators as td
+
 from pandas.core.dtypes.common import is_categorical_dtype, is_object_dtype
 from pandas.core.dtypes.dtypes import CategoricalDtype
 
@@ -277,6 +279,7 @@ def test_merge_copy(self):
         merged["d"] = "peekaboo"
         assert (right["d"] == "bar").all()
 
+    @td.skip_array_manager_invalid_test  # TODO(ArrayManager) join copy behaviour
     def test_merge_nocopy(self):
         left = DataFrame({"a": 0, "b": 1}, index=range(10))
         right = DataFrame({"c": "foo", "d": "bar"}, index=range(10))
@@ -656,7 +659,7 @@ def _constructor(self):
 
         assert isinstance(result, NotADataFrame)
 
-    def test_join_append_timedeltas(self):
+    def test_join_append_timedeltas(self, using_array_manager):
         # timedelta64 issues with join/merge
         # GH 5695
 
@@ -670,6 +673,8 @@ def test_join_append_timedeltas(self):
                 "t": [timedelta(0, 22500), timedelta(0, 22500)],
             }
         )
+        if using_array_manager:
+            expected = expected.astype(object)
         tm.assert_frame_equal(result, expected)
 
         td = np.timedelta64(300000000)
@@ -1362,6 +1367,7 @@ def test_merge_take_missing_values_from_index_of_other_dtype(self):
         expected = expected.reindex(columns=["a", "key", "b"])
         tm.assert_frame_equal(result, expected)
 
+    @td.skip_array_manager_invalid_test  # TODO(ArrayManager) rewrite test
     def test_merge_readonly(self):
         # https://github.com/pandas-dev/pandas/issues/27943
         data1 = DataFrame(

pandas/tests/reshape/test_crosstab.py

@@ -1,11 +1,15 @@
 import numpy as np
 import pytest
 
+import pandas.util._test_decorators as td
+
 from pandas.core.dtypes.common import is_categorical_dtype
 
 from pandas import CategoricalIndex, DataFrame, Index, MultiIndex, Series, crosstab
 import pandas._testing as tm
 
+pytestmark = td.skip_array_manager_not_yet_implemented  # TODO(ArrayManager) groupby
+
 
 class TestCrosstab:
     def setup_method(self, method):

pandas/tests/reshape/test_pivot.py

@@ -4,6 +4,8 @@
 import numpy as np
 import pytest
 
+import pandas.util._test_decorators as td
+
 import pandas as pd
 from pandas import (
     Categorical,
@@ -19,6 +21,8 @@
 from pandas.api.types import CategoricalDtype as CDT
 from pandas.core.reshape.pivot import pivot_table
 
+pytestmark = td.skip_array_manager_not_yet_implemented  # TODO(ArrayManager) groupby
+
 
 @pytest.fixture(params=[True, False])
 def dropna(request):

pandas/tests/reshape/test_pivot_multilevel.py

@@ -192,7 +192,7 @@ def test_pivot_list_like_columns(
     tm.assert_frame_equal(result, expected)
 
 
-def test_pivot_multiindexed_rows_and_cols():
+def test_pivot_multiindexed_rows_and_cols(using_array_manager):
     # GH 36360
 
     df = pd.DataFrame(
@@ -214,11 +214,14 @@ def test_pivot_multiindexed_rows_and_cols():
     )
 
     expected = pd.DataFrame(
-        data=[[5.0, np.nan], [10.0, 7.0]],
+        data=[[5, np.nan], [10, 7.0]],
         columns=MultiIndex.from_tuples(
             [(0, 1, 0), (0, 1, 1)], names=["col_L0", "col_L1", "idx_L1"]
         ),
         index=Int64Index([0, 1], dtype="int64", name="idx_L0"),
     )
+    if not using_array_manager:
+        # BlockManager does not preserve the dtypes
+        expected = expected.astype("float64")
 
     tm.assert_frame_equal(res, expected)