TST (string): copy/view tests (#59702)

Author: jbrockmendel

pandas/core/dtypes/dtypes.py

@@ -455,7 +455,7 @@ def __eq__(self, other: object) -> bool:
                 # Because left and right have the same length and are unique,
                 #  `indexer` not having any -1s implies that there is a
                 #  bijection between `left` and `right`.
-                return (indexer != -1).all()
+                return bool((indexer != -1).all())
 
             # With object-dtype we need a comparison that identifies
             #  e.g. int(2) as distinct from float(2)

pandas/tests/copy_view/test_constructors.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -209,9 +207,8 @@ def test_dataframe_from_dict_of_series_with_reindex(dtype):
     assert np.shares_memory(arr_before, arr_after)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
-    "data, dtype", [([1, 2], None), ([1, 2], "int64"), (["a", "b"], None)]
+    "data, dtype", [([1, 2], None), ([1, 2], "int64"), (["a", "b"], object)]
 )
 def test_dataframe_from_series_or_index(data, dtype, index_or_series):
     obj = index_or_series(data, dtype=dtype)

pandas/tests/copy_view/test_functions.py

@@ -16,10 +16,9 @@
 from pandas.tests.copy_view.util import get_array
 
 
-@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 def test_concat_frames():
-    df = DataFrame({"b": ["a"] * 3})
-    df2 = DataFrame({"a": ["a"] * 3})
+    df = DataFrame({"b": ["a"] * 3}, dtype=object)
+    df2 = DataFrame({"a": ["a"] * 3}, dtype=object)
     df_orig = df.copy()
     result = concat([df, df2], axis=1)
 
@@ -35,10 +34,9 @@ def test_concat_frames():
     tm.assert_frame_equal(df, df_orig)
 
 
-@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 def test_concat_frames_updating_input():
-    df = DataFrame({"b": ["a"] * 3})
-    df2 = DataFrame({"a": ["a"] * 3})
+    df = DataFrame({"b": ["a"] * 3}, dtype=object)
+    df2 = DataFrame({"a": ["a"] * 3}, dtype=object)
     result = concat([df, df2], axis=1)
 
     assert np.shares_memory(get_array(result, "b"), get_array(df, "b"))
@@ -155,7 +153,7 @@ def test_concat_copy_keyword():
     assert np.shares_memory(get_array(df2, "b"), get_array(result, "b"))
 
 
-@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
+# @pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 @pytest.mark.parametrize(
     "func",
     [
@@ -164,8 +162,8 @@ def test_concat_copy_keyword():
     ],
 )
 def test_merge_on_key(func):
-    df1 = DataFrame({"key": ["a", "b", "c"], "a": [1, 2, 3]})
-    df2 = DataFrame({"key": ["a", "b", "c"], "b": [4, 5, 6]})
+    df1 = DataFrame({"key": Series(["a", "b", "c"], dtype=object), "a": [1, 2, 3]})
+    df2 = DataFrame({"key": Series(["a", "b", "c"], dtype=object), "b": [4, 5, 6]})
     df1_orig = df1.copy()
     df2_orig = df2.copy()
 
@@ -207,7 +205,6 @@ def test_merge_on_index():
     tm.assert_frame_equal(df2, df2_orig)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
     "func, how",
     [
@@ -216,8 +213,8 @@ def test_merge_on_index():
     ],
 )
 def test_merge_on_key_enlarging_one(func, how):
-    df1 = DataFrame({"key": ["a", "b", "c"], "a": [1, 2, 3]})
-    df2 = DataFrame({"key": ["a", "b"], "b": [4, 5]})
+    df1 = DataFrame({"key": Series(["a", "b", "c"], dtype=object), "a": [1, 2, 3]})
+    df2 = DataFrame({"key": Series(["a", "b"], dtype=object), "b": [4, 5]})
     df1_orig = df1.copy()
     df2_orig = df2.copy()
 
@@ -251,9 +248,13 @@ def test_merge_copy_keyword():
     assert np.shares_memory(get_array(df2, "b"), get_array(result, "b"))
 
 
-@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
+@pytest.mark.xfail(
+    using_string_dtype() and HAS_PYARROW,
+    reason="TODO(infer_string); result.index infers str dtype while both "
+    "df1 and df2 index are object.",
+)
 def test_join_on_key():
-    df_index = Index(["a", "b", "c"], name="key")
+    df_index = Index(["a", "b", "c"], name="key", dtype=object)
 
     df1 = DataFrame({"a": [1, 2, 3]}, index=df_index.copy(deep=True))
     df2 = DataFrame({"b": [4, 5, 6]}, index=df_index.copy(deep=True))
@@ -279,9 +280,8 @@ def test_join_on_key():
     tm.assert_frame_equal(df2, df2_orig)
 
 
-@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 def test_join_multiple_dataframes_on_key():
-    df_index = Index(["a", "b", "c"], name="key")
+    df_index = Index(["a", "b", "c"], name="key", dtype=object)
 
     df1 = DataFrame({"a": [1, 2, 3]}, index=df_index.copy(deep=True))
     dfs_list = [

pandas/tests/copy_view/test_internals.py

@@ -1,9 +1,10 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
-from pandas import DataFrame
+from pandas import (
+    DataFrame,
+    Series,
+)
 import pandas._testing as tm
 from pandas.tests.copy_view.util import get_array
 
@@ -42,7 +43,6 @@ def test_consolidate():
     assert df.loc[0, "b"] == 0.1
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("dtype", [np.intp, np.int8])
 @pytest.mark.parametrize(
     "locs, arr",
@@ -68,7 +68,7 @@ def test_iset_splits_blocks_inplace(locs, arr, dtype):
             "c": [7, 8, 9],
             "d": [10, 11, 12],
             "e": [13, 14, 15],
-            "f": ["a", "b", "c"],
+            "f": Series(["a", "b", "c"], dtype=object),
         },
     )
     arr = arr.astype(dtype)

pandas/tests/dtypes/test_dtypes.py

@@ -4,8 +4,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas._libs.tslibs.dtypes import NpyDatetimeUnit
 
 from pandas.core.dtypes.base import _registry as registry
@@ -961,7 +959,6 @@ def test_same_categories_different_order(self):
         c2 = CategoricalDtype(["b", "a"], ordered=True)
         assert c1 is not c2
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize("ordered2", [True, False, None])
     def test_categorical_equality(self, ordered, ordered2):
         # same categories, same order