in tests, change pd.arrays.SparseArray to SparseArray (#30765)

pandas/tests/arrays/test_array.py

@@ -11,6 +11,15 @@
 import pandas._testing as tm
 from pandas.api.extensions import register_extension_dtype
 from pandas.api.types import is_scalar
+from pandas.arrays import (
+    BooleanArray,
+    DatetimeArray,
+    IntegerArray,
+    IntervalArray,
+    SparseArray,
+    StringArray,
+    TimedeltaArray,
+)
 from pandas.core.arrays import PandasArray, integer_array, period_array
 from pandas.tests.extension.decimal import DecimalArray, DecimalDtype, to_decimal
 
@@ -19,18 +28,14 @@
     "data, dtype, expected",
     [
         # Basic NumPy defaults.
-        ([1, 2], None, pd.arrays.IntegerArray._from_sequence([1, 2])),
+        ([1, 2], None, IntegerArray._from_sequence([1, 2])),
         ([1, 2], object, PandasArray(np.array([1, 2], dtype=object))),
         (
             [1, 2],
             np.dtype("float32"),
             PandasArray(np.array([1.0, 2.0], dtype=np.dtype("float32"))),
         ),
-        (
-            np.array([1, 2], dtype="int64"),
-            None,
-            pd.arrays.IntegerArray._from_sequence([1, 2]),
-        ),
+        (np.array([1, 2], dtype="int64"), None, IntegerArray._from_sequence([1, 2]),),
         # String alias passes through to NumPy
         ([1, 2], "float32", PandasArray(np.array([1, 2], dtype="float32"))),
         # Period alias
@@ -49,55 +54,51 @@
         (
             [1, 2],
             np.dtype("datetime64[ns]"),
-            pd.arrays.DatetimeArray._from_sequence(
-                np.array([1, 2], dtype="datetime64[ns]")
-            ),
+            DatetimeArray._from_sequence(np.array([1, 2], dtype="datetime64[ns]")),
         ),
         (
             np.array([1, 2], dtype="datetime64[ns]"),
             None,
-            pd.arrays.DatetimeArray._from_sequence(
-                np.array([1, 2], dtype="datetime64[ns]")
-            ),
+            DatetimeArray._from_sequence(np.array([1, 2], dtype="datetime64[ns]")),
         ),
         (
             pd.DatetimeIndex(["2000", "2001"]),
             np.dtype("datetime64[ns]"),
-            pd.arrays.DatetimeArray._from_sequence(["2000", "2001"]),
+            DatetimeArray._from_sequence(["2000", "2001"]),
         ),
         (
             pd.DatetimeIndex(["2000", "2001"]),
             None,
-            pd.arrays.DatetimeArray._from_sequence(["2000", "2001"]),
+            DatetimeArray._from_sequence(["2000", "2001"]),
         ),
         (
             ["2000", "2001"],
             np.dtype("datetime64[ns]"),
-            pd.arrays.DatetimeArray._from_sequence(["2000", "2001"]),
+            DatetimeArray._from_sequence(["2000", "2001"]),
         ),
         # Datetime (tz-aware)
         (
             ["2000", "2001"],
             pd.DatetimeTZDtype(tz="CET"),
-            pd.arrays.DatetimeArray._from_sequence(
+            DatetimeArray._from_sequence(
                 ["2000", "2001"], dtype=pd.DatetimeTZDtype(tz="CET")
             ),
         ),
         # Timedelta
         (
             ["1H", "2H"],
             np.dtype("timedelta64[ns]"),
-            pd.arrays.TimedeltaArray._from_sequence(["1H", "2H"]),
+            TimedeltaArray._from_sequence(["1H", "2H"]),
         ),
         (
             pd.TimedeltaIndex(["1H", "2H"]),
             np.dtype("timedelta64[ns]"),
-            pd.arrays.TimedeltaArray._from_sequence(["1H", "2H"]),
+            TimedeltaArray._from_sequence(["1H", "2H"]),
         ),
         (
             pd.TimedeltaIndex(["1H", "2H"]),
             None,
-            pd.arrays.TimedeltaArray._from_sequence(["1H", "2H"]),
+            TimedeltaArray._from_sequence(["1H", "2H"]),
         ),
         # Category
         (["a", "b"], "category", pd.Categorical(["a", "b"])),
@@ -110,27 +111,19 @@
         (
             [pd.Interval(1, 2), pd.Interval(3, 4)],
             "interval",
-            pd.arrays.IntervalArray.from_tuples([(1, 2), (3, 4)]),
+            IntervalArray.from_tuples([(1, 2), (3, 4)]),
         ),
         # Sparse
-        ([0, 1], "Sparse[int64]", pd.arrays.SparseArray([0, 1], dtype="int64")),
+        ([0, 1], "Sparse[int64]", SparseArray([0, 1], dtype="int64")),
         # IntegerNA
         ([1, None], "Int16", integer_array([1, None], dtype="Int16")),
         (pd.Series([1, 2]), None, PandasArray(np.array([1, 2], dtype=np.int64))),
         # String
-        (["a", None], "string", pd.arrays.StringArray._from_sequence(["a", None])),
-        (
-            ["a", None],
-            pd.StringDtype(),
-            pd.arrays.StringArray._from_sequence(["a", None]),
-        ),
+        (["a", None], "string", StringArray._from_sequence(["a", None])),
+        (["a", None], pd.StringDtype(), StringArray._from_sequence(["a", None]),),
         # Boolean
-        ([True, None], "boolean", pd.arrays.BooleanArray._from_sequence([True, None])),
-        (
-            [True, None],
-            pd.BooleanDtype(),
-            pd.arrays.BooleanArray._from_sequence([True, None]),
-        ),
+        ([True, None], "boolean", BooleanArray._from_sequence([True, None])),
+        ([True, None], pd.BooleanDtype(), BooleanArray._from_sequence([True, None]),),
         # Index
         (pd.Index([1, 2]), None, PandasArray(np.array([1, 2], dtype=np.int64))),
         # Series[EA] returns the EA
@@ -181,31 +174,28 @@ def test_array_copy():
             period_array(["2000", "2001"], freq="D"),
         ),
         # interval
-        (
-            [pd.Interval(0, 1), pd.Interval(1, 2)],
-            pd.arrays.IntervalArray.from_breaks([0, 1, 2]),
-        ),
+        ([pd.Interval(0, 1), pd.Interval(1, 2)], IntervalArray.from_breaks([0, 1, 2]),),
         # datetime
         (
             [pd.Timestamp("2000"), pd.Timestamp("2001")],
-            pd.arrays.DatetimeArray._from_sequence(["2000", "2001"]),
+            DatetimeArray._from_sequence(["2000", "2001"]),
         ),
         (
             [datetime.datetime(2000, 1, 1), datetime.datetime(2001, 1, 1)],
-            pd.arrays.DatetimeArray._from_sequence(["2000", "2001"]),
+            DatetimeArray._from_sequence(["2000", "2001"]),
         ),
         (
             np.array([1, 2], dtype="M8[ns]"),
-            pd.arrays.DatetimeArray(np.array([1, 2], dtype="M8[ns]")),
+            DatetimeArray(np.array([1, 2], dtype="M8[ns]")),
         ),
         (
             np.array([1, 2], dtype="M8[us]"),
-            pd.arrays.DatetimeArray(np.array([1000, 2000], dtype="M8[ns]")),
+            DatetimeArray(np.array([1000, 2000], dtype="M8[ns]")),
         ),
         # datetimetz
         (
             [pd.Timestamp("2000", tz="CET"), pd.Timestamp("2001", tz="CET")],
-            pd.arrays.DatetimeArray._from_sequence(
+            DatetimeArray._from_sequence(
                 ["2000", "2001"], dtype=pd.DatetimeTZDtype(tz="CET")
             ),
         ),
@@ -214,30 +204,30 @@ def test_array_copy():
                 datetime.datetime(2000, 1, 1, tzinfo=cet),
                 datetime.datetime(2001, 1, 1, tzinfo=cet),
             ],
-            pd.arrays.DatetimeArray._from_sequence(["2000", "2001"], tz=cet),
+            DatetimeArray._from_sequence(["2000", "2001"], tz=cet),
         ),
         # timedelta
         (
             [pd.Timedelta("1H"), pd.Timedelta("2H")],
-            pd.arrays.TimedeltaArray._from_sequence(["1H", "2H"]),
+            TimedeltaArray._from_sequence(["1H", "2H"]),
         ),
         (
             np.array([1, 2], dtype="m8[ns]"),
-            pd.arrays.TimedeltaArray(np.array([1, 2], dtype="m8[ns]")),
+            TimedeltaArray(np.array([1, 2], dtype="m8[ns]")),
         ),
         (
             np.array([1, 2], dtype="m8[us]"),
-            pd.arrays.TimedeltaArray(np.array([1000, 2000], dtype="m8[ns]")),
+            TimedeltaArray(np.array([1000, 2000], dtype="m8[ns]")),
         ),
         # integer
-        ([1, 2], pd.arrays.IntegerArray._from_sequence([1, 2])),
-        ([1, None], pd.arrays.IntegerArray._from_sequence([1, None])),
+        ([1, 2], IntegerArray._from_sequence([1, 2])),
+        ([1, None], IntegerArray._from_sequence([1, None])),
         # string
-        (["a", "b"], pd.arrays.StringArray._from_sequence(["a", "b"])),
-        (["a", None], pd.arrays.StringArray._from_sequence(["a", None])),
+        (["a", "b"], StringArray._from_sequence(["a", "b"])),
+        (["a", None], StringArray._from_sequence(["a", None])),
         # Boolean
-        ([True, False], pd.arrays.BooleanArray._from_sequence([True, False])),
-        ([True, None], pd.arrays.BooleanArray._from_sequence([True, None])),
+        ([True, False], BooleanArray._from_sequence([True, False])),
+        ([True, None], BooleanArray._from_sequence([True, None])),
     ],
 )
 def test_array_inference(data, expected):

pandas/tests/dtypes/test_common.py

@@ -19,6 +19,7 @@
 
 import pandas as pd
 import pandas._testing as tm
+from pandas.arrays import SparseArray
 from pandas.conftest import (
     ALL_EA_INT_DTYPES,
     ALL_INT_DTYPES,
@@ -182,7 +183,7 @@ def test_is_object():
     "check_scipy", [False, pytest.param(True, marks=td.skip_if_no_scipy)]
 )
 def test_is_sparse(check_scipy):
-    assert com.is_sparse(pd.arrays.SparseArray([1, 2, 3]))
+    assert com.is_sparse(SparseArray([1, 2, 3]))
 
     assert not com.is_sparse(np.array([1, 2, 3]))
 
@@ -198,7 +199,7 @@ def test_is_scipy_sparse():
 
     assert com.is_scipy_sparse(bsr_matrix([1, 2, 3]))
 
-    assert not com.is_scipy_sparse(pd.arrays.SparseArray([1, 2, 3]))
+    assert not com.is_scipy_sparse(SparseArray([1, 2, 3]))
 
 
 def test_is_categorical():
@@ -576,7 +577,7 @@ def test_is_extension_type(check_scipy):
     cat = pd.Categorical([1, 2, 3])
     assert com.is_extension_type(cat)
     assert com.is_extension_type(pd.Series(cat))
-    assert com.is_extension_type(pd.arrays.SparseArray([1, 2, 3]))
+    assert com.is_extension_type(SparseArray([1, 2, 3]))
     assert com.is_extension_type(pd.DatetimeIndex(["2000"], tz="US/Eastern"))
 
     dtype = DatetimeTZDtype("ns", tz="US/Eastern")
@@ -605,7 +606,7 @@ def test_is_extension_array_dtype(check_scipy):
     cat = pd.Categorical([1, 2, 3])
     assert com.is_extension_array_dtype(cat)
     assert com.is_extension_array_dtype(pd.Series(cat))
-    assert com.is_extension_array_dtype(pd.arrays.SparseArray([1, 2, 3]))
+    assert com.is_extension_array_dtype(SparseArray([1, 2, 3]))
     assert com.is_extension_array_dtype(pd.DatetimeIndex(["2000"], tz="US/Eastern"))
 
     dtype = DatetimeTZDtype("ns", tz="US/Eastern")

pandas/tests/dtypes/test_dtypes.py

@@ -28,7 +28,7 @@
 import pandas as pd
 from pandas import Categorical, CategoricalIndex, IntervalIndex, Series, date_range
 import pandas._testing as tm
-from pandas.core.arrays.sparse import SparseDtype
+from pandas.core.arrays.sparse import SparseArray, SparseDtype
 
 
 class Base:
@@ -914,7 +914,7 @@ def test_registry_find(dtype, expected):
         (pd.Series([1, 2]), False),
         (np.array([True, False]), True),
         (pd.Series([True, False]), True),
-        (pd.arrays.SparseArray([True, False]), True),
+        (SparseArray([True, False]), True),
         (SparseDtype(bool), True),
     ],
 )
@@ -924,7 +924,7 @@ def test_is_bool_dtype(dtype, expected):
 
 
 def test_is_bool_dtype_sparse():
-    result = is_bool_dtype(pd.Series(pd.arrays.SparseArray([True, False])))
+    result = is_bool_dtype(pd.Series(SparseArray([True, False])))
     assert result is True
 
 

pandas/tests/frame/indexing/test_indexing.py

@@ -21,6 +21,7 @@
     notna,
 )
 import pandas._testing as tm
+from pandas.arrays import SparseArray
 import pandas.core.common as com
 from pandas.core.indexing import IndexingError
 
@@ -1776,7 +1777,7 @@ def test_getitem_ix_float_duplicates(self):
 
     def test_getitem_sparse_column(self):
         # https://github.com/pandas-dev/pandas/issues/23559
-        data = pd.arrays.SparseArray([0, 1])
+        data = SparseArray([0, 1])
         df = pd.DataFrame({"A": data})
         expected = pd.Series(data, name="A")
         result = df["A"]
@@ -1791,17 +1792,17 @@ def test_getitem_sparse_column(self):
     def test_setitem_with_sparse_value(self):
         # GH8131
         df = pd.DataFrame({"c_1": ["a", "b", "c"], "n_1": [1.0, 2.0, 3.0]})
-        sp_array = pd.arrays.SparseArray([0, 0, 1])
+        sp_array = SparseArray([0, 0, 1])
         df["new_column"] = sp_array
         tm.assert_series_equal(
             df["new_column"], pd.Series(sp_array, name="new_column"), check_names=False
         )
 
     def test_setitem_with_unaligned_sparse_value(self):
         df = pd.DataFrame({"c_1": ["a", "b", "c"], "n_1": [1.0, 2.0, 3.0]})
-        sp_series = pd.Series(pd.arrays.SparseArray([0, 0, 1]), index=[2, 1, 0])
+        sp_series = pd.Series(SparseArray([0, 0, 1]), index=[2, 1, 0])
         df["new_column"] = sp_series
-        exp = pd.Series(pd.arrays.SparseArray([1, 0, 0]), name="new_column")
+        exp = pd.Series(SparseArray([1, 0, 0]), name="new_column")
         tm.assert_series_equal(df["new_column"], exp)
 
     def test_setitem_with_unaligned_tz_aware_datetime_column(self):

pandas/tests/frame/test_constructors.py

@@ -26,7 +26,7 @@
     isna,
 )
 import pandas._testing as tm
-from pandas.arrays import IntervalArray, PeriodArray
+from pandas.arrays import IntervalArray, PeriodArray, SparseArray
 from pandas.core.construction import create_series_with_explicit_dtype
 
 MIXED_FLOAT_DTYPES = ["float16", "float32", "float64"]
@@ -2414,7 +2414,7 @@ class List(list):
         "extension_arr",
         [
             Categorical(list("aabbc")),
-            pd.arrays.SparseArray([1, np.nan, np.nan, np.nan]),
+            SparseArray([1, np.nan, np.nan, np.nan]),
             IntervalArray([pd.Interval(0, 1), pd.Interval(1, 5)]),
             PeriodArray(pd.period_range(start="1/1/2017", end="1/1/2018", freq="M")),
         ],