Skip to content

Commit 4a039c6

Browse files
Dr-Irvjreback
Dr-Irv
authored and
jreback
committed
in tests, change pd.arrays.SparseArray to SparseArray (pandas-dev#30765)
1 parent 08b70d8 commit 4a039c6

File tree

7 files changed

+84
-91
lines changed

7 files changed

+84
-91
lines changed

‎pandas/tests/arrays/test_array.py

+42-52
Original file line numberDiff line numberDiff line change
@@ -11,6 +11,15 @@
1111
import pandas._testing as tm
1212
from pandas.api.extensions import register_extension_dtype
1313
from pandas.api.types import is_scalar
14+
from pandas.arrays import (
15+
BooleanArray,
16+
DatetimeArray,
17+
IntegerArray,
18+
IntervalArray,
19+
SparseArray,
20+
StringArray,
21+
TimedeltaArray,
22+
)
1423
from pandas.core.arrays import PandasArray, integer_array, period_array
1524
from pandas.tests.extension.decimal import DecimalArray, DecimalDtype, to_decimal
1625

@@ -19,18 +28,14 @@
1928
"data, dtype, expected",
2029
[
2130
# Basic NumPy defaults.
22-
([1, 2], None, pd.arrays.IntegerArray._from_sequence([1, 2])),
31+
([1, 2], None, IntegerArray._from_sequence([1, 2])),
2332
([1, 2], object, PandasArray(np.array([1, 2], dtype=object))),
2433
(
2534
[1, 2],
2635
np.dtype("float32"),
2736
PandasArray(np.array([1.0, 2.0], dtype=np.dtype("float32"))),
2837
),
29-
(
30-
np.array([1, 2], dtype="int64"),
31-
None,
32-
pd.arrays.IntegerArray._from_sequence([1, 2]),
33-
),
38+
(np.array([1, 2], dtype="int64"), None, IntegerArray._from_sequence([1, 2]),),
3439
# String alias passes through to NumPy
3540
([1, 2], "float32", PandasArray(np.array([1, 2], dtype="float32"))),
3641
# Period alias
@@ -49,55 +54,51 @@
4954
(
5055
[1, 2],
5156
np.dtype("datetime64[ns]"),
52-
pd.arrays.DatetimeArray._from_sequence(
53-
np.array([1, 2], dtype="datetime64[ns]")
54-
),
57+
DatetimeArray._from_sequence(np.array([1, 2], dtype="datetime64[ns]")),
5558
),
5659
(
5760
np.array([1, 2], dtype="datetime64[ns]"),
5861
None,
59-
pd.arrays.DatetimeArray._from_sequence(
60-
np.array([1, 2], dtype="datetime64[ns]")
61-
),
62+
DatetimeArray._from_sequence(np.array([1, 2], dtype="datetime64[ns]")),
6263
),
6364
(
6465
pd.DatetimeIndex(["2000", "2001"]),
6566
np.dtype("datetime64[ns]"),
66-
pd.arrays.DatetimeArray._from_sequence(["2000", "2001"]),
67+
DatetimeArray._from_sequence(["2000", "2001"]),
6768
),
6869
(
6970
pd.DatetimeIndex(["2000", "2001"]),
7071
None,
71-
pd.arrays.DatetimeArray._from_sequence(["2000", "2001"]),
72+
DatetimeArray._from_sequence(["2000", "2001"]),
7273
),
7374
(
7475
["2000", "2001"],
7576
np.dtype("datetime64[ns]"),
76-
pd.arrays.DatetimeArray._from_sequence(["2000", "2001"]),
77+
DatetimeArray._from_sequence(["2000", "2001"]),
7778
),
7879
# Datetime (tz-aware)
7980
(
8081
["2000", "2001"],
8182
pd.DatetimeTZDtype(tz="CET"),
82-
pd.arrays.DatetimeArray._from_sequence(
83+
DatetimeArray._from_sequence(
8384
["2000", "2001"], dtype=pd.DatetimeTZDtype(tz="CET")
8485
),
8586
),
8687
# Timedelta
8788
(
8889
["1H", "2H"],
8990
np.dtype("timedelta64[ns]"),
90-
pd.arrays.TimedeltaArray._from_sequence(["1H", "2H"]),
91+
TimedeltaArray._from_sequence(["1H", "2H"]),
9192
),
9293
(
9394
pd.TimedeltaIndex(["1H", "2H"]),
9495
np.dtype("timedelta64[ns]"),
95-
pd.arrays.TimedeltaArray._from_sequence(["1H", "2H"]),
96+
TimedeltaArray._from_sequence(["1H", "2H"]),
9697
),
9798
(
9899
pd.TimedeltaIndex(["1H", "2H"]),
99100
None,
100-
pd.arrays.TimedeltaArray._from_sequence(["1H", "2H"]),
101+
TimedeltaArray._from_sequence(["1H", "2H"]),
101102
),
102103
# Category
103104
(["a", "b"], "category", pd.Categorical(["a", "b"])),
@@ -110,27 +111,19 @@
110111
(
111112
[pd.Interval(1, 2), pd.Interval(3, 4)],
112113
"interval",
113-
pd.arrays.IntervalArray.from_tuples([(1, 2), (3, 4)]),
114+
IntervalArray.from_tuples([(1, 2), (3, 4)]),
114115
),
115116
# Sparse
116-
([0, 1], "Sparse[int64]", pd.arrays.SparseArray([0, 1], dtype="int64")),
117+
([0, 1], "Sparse[int64]", SparseArray([0, 1], dtype="int64")),
117118
# IntegerNA
118119
([1, None], "Int16", integer_array([1, None], dtype="Int16")),
119120
(pd.Series([1, 2]), None, PandasArray(np.array([1, 2], dtype=np.int64))),
120121
# String
121-
(["a", None], "string", pd.arrays.StringArray._from_sequence(["a", None])),
122-
(
123-
["a", None],
124-
pd.StringDtype(),
125-
pd.arrays.StringArray._from_sequence(["a", None]),
126-
),
122+
(["a", None], "string", StringArray._from_sequence(["a", None])),
123+
(["a", None], pd.StringDtype(), StringArray._from_sequence(["a", None]),),
127124
# Boolean
128-
([True, None], "boolean", pd.arrays.BooleanArray._from_sequence([True, None])),
129-
(
130-
[True, None],
131-
pd.BooleanDtype(),
132-
pd.arrays.BooleanArray._from_sequence([True, None]),
133-
),
125+
([True, None], "boolean", BooleanArray._from_sequence([True, None])),
126+
([True, None], pd.BooleanDtype(), BooleanArray._from_sequence([True, None]),),
134127
# Index
135128
(pd.Index([1, 2]), None, PandasArray(np.array([1, 2], dtype=np.int64))),
136129
# Series[EA] returns the EA
@@ -181,31 +174,28 @@ def test_array_copy():
181174
period_array(["2000", "2001"], freq="D"),
182175
),
183176
# interval
184-
(
185-
[pd.Interval(0, 1), pd.Interval(1, 2)],
186-
pd.arrays.IntervalArray.from_breaks([0, 1, 2]),
187-
),
177+
([pd.Interval(0, 1), pd.Interval(1, 2)], IntervalArray.from_breaks([0, 1, 2]),),
188178
# datetime
189179
(
190180
[pd.Timestamp("2000"), pd.Timestamp("2001")],
191-
pd.arrays.DatetimeArray._from_sequence(["2000", "2001"]),
181+
DatetimeArray._from_sequence(["2000", "2001"]),
192182
),
193183
(
194184
[datetime.datetime(2000, 1, 1), datetime.datetime(2001, 1, 1)],
195-
pd.arrays.DatetimeArray._from_sequence(["2000", "2001"]),
185+
DatetimeArray._from_sequence(["2000", "2001"]),
196186
),
197187
(
198188
np.array([1, 2], dtype="M8[ns]"),
199-
pd.arrays.DatetimeArray(np.array([1, 2], dtype="M8[ns]")),
189+
DatetimeArray(np.array([1, 2], dtype="M8[ns]")),
200190
),
201191
(
202192
np.array([1, 2], dtype="M8[us]"),
203-
pd.arrays.DatetimeArray(np.array([1000, 2000], dtype="M8[ns]")),
193+
DatetimeArray(np.array([1000, 2000], dtype="M8[ns]")),
204194
),
205195
# datetimetz
206196
(
207197
[pd.Timestamp("2000", tz="CET"), pd.Timestamp("2001", tz="CET")],
208-
pd.arrays.DatetimeArray._from_sequence(
198+
DatetimeArray._from_sequence(
209199
["2000", "2001"], dtype=pd.DatetimeTZDtype(tz="CET")
210200
),
211201
),
@@ -214,30 +204,30 @@ def test_array_copy():
214204
datetime.datetime(2000, 1, 1, tzinfo=cet),
215205
datetime.datetime(2001, 1, 1, tzinfo=cet),
216206
],
217-
pd.arrays.DatetimeArray._from_sequence(["2000", "2001"], tz=cet),
207+
DatetimeArray._from_sequence(["2000", "2001"], tz=cet),
218208
),
219209
# timedelta
220210
(
221211
[pd.Timedelta("1H"), pd.Timedelta("2H")],
222-
pd.arrays.TimedeltaArray._from_sequence(["1H", "2H"]),
212+
TimedeltaArray._from_sequence(["1H", "2H"]),
223213
),
224214
(
225215
np.array([1, 2], dtype="m8[ns]"),
226-
pd.arrays.TimedeltaArray(np.array([1, 2], dtype="m8[ns]")),
216+
TimedeltaArray(np.array([1, 2], dtype="m8[ns]")),
227217
),
228218
(
229219
np.array([1, 2], dtype="m8[us]"),
230-
pd.arrays.TimedeltaArray(np.array([1000, 2000], dtype="m8[ns]")),
220+
TimedeltaArray(np.array([1000, 2000], dtype="m8[ns]")),
231221
),
232222
# integer
233-
([1, 2], pd.arrays.IntegerArray._from_sequence([1, 2])),
234-
([1, None], pd.arrays.IntegerArray._from_sequence([1, None])),
223+
([1, 2], IntegerArray._from_sequence([1, 2])),
224+
([1, None], IntegerArray._from_sequence([1, None])),
235225
# string
236-
(["a", "b"], pd.arrays.StringArray._from_sequence(["a", "b"])),
237-
(["a", None], pd.arrays.StringArray._from_sequence(["a", None])),
226+
(["a", "b"], StringArray._from_sequence(["a", "b"])),
227+
(["a", None], StringArray._from_sequence(["a", None])),
238228
# Boolean
239-
([True, False], pd.arrays.BooleanArray._from_sequence([True, False])),
240-
([True, None], pd.arrays.BooleanArray._from_sequence([True, None])),
229+
([True, False], BooleanArray._from_sequence([True, False])),
230+
([True, None], BooleanArray._from_sequence([True, None])),
241231
],
242232
)
243233
def test_array_inference(data, expected):

‎pandas/tests/dtypes/test_common.py

+5-4
Original file line numberDiff line numberDiff line change
@@ -19,6 +19,7 @@
1919

2020
import pandas as pd
2121
import pandas._testing as tm
22+
from pandas.arrays import SparseArray
2223
from pandas.conftest import (
2324
ALL_EA_INT_DTYPES,
2425
ALL_INT_DTYPES,
@@ -182,7 +183,7 @@ def test_is_object():
182183
"check_scipy", [False, pytest.param(True, marks=td.skip_if_no_scipy)]
183184
)
184185
def test_is_sparse(check_scipy):
185-
assert com.is_sparse(pd.arrays.SparseArray([1, 2, 3]))
186+
assert com.is_sparse(SparseArray([1, 2, 3]))
186187

187188
assert not com.is_sparse(np.array([1, 2, 3]))
188189

@@ -198,7 +199,7 @@ def test_is_scipy_sparse():
198199

199200
assert com.is_scipy_sparse(bsr_matrix([1, 2, 3]))
200201

201-
assert not com.is_scipy_sparse(pd.arrays.SparseArray([1, 2, 3]))
202+
assert not com.is_scipy_sparse(SparseArray([1, 2, 3]))
202203

203204

204205
def test_is_categorical():
@@ -576,7 +577,7 @@ def test_is_extension_type(check_scipy):
576577
cat = pd.Categorical([1, 2, 3])
577578
assert com.is_extension_type(cat)
578579
assert com.is_extension_type(pd.Series(cat))
579-
assert com.is_extension_type(pd.arrays.SparseArray([1, 2, 3]))
580+
assert com.is_extension_type(SparseArray([1, 2, 3]))
580581
assert com.is_extension_type(pd.DatetimeIndex(["2000"], tz="US/Eastern"))
581582

582583
dtype = DatetimeTZDtype("ns", tz="US/Eastern")
@@ -605,7 +606,7 @@ def test_is_extension_array_dtype(check_scipy):
605606
cat = pd.Categorical([1, 2, 3])
606607
assert com.is_extension_array_dtype(cat)
607608
assert com.is_extension_array_dtype(pd.Series(cat))
608-
assert com.is_extension_array_dtype(pd.arrays.SparseArray([1, 2, 3]))
609+
assert com.is_extension_array_dtype(SparseArray([1, 2, 3]))
609610
assert com.is_extension_array_dtype(pd.DatetimeIndex(["2000"], tz="US/Eastern"))
610611

611612
dtype = DatetimeTZDtype("ns", tz="US/Eastern")

‎pandas/tests/dtypes/test_dtypes.py

+3-3
Original file line numberDiff line numberDiff line change
@@ -28,7 +28,7 @@
2828
import pandas as pd
2929
from pandas import Categorical, CategoricalIndex, IntervalIndex, Series, date_range
3030
import pandas._testing as tm
31-
from pandas.core.arrays.sparse import SparseDtype
31+
from pandas.core.arrays.sparse import SparseArray, SparseDtype
3232

3333

3434
class Base:
@@ -914,7 +914,7 @@ def test_registry_find(dtype, expected):
914914
(pd.Series([1, 2]), False),
915915
(np.array([True, False]), True),
916916
(pd.Series([True, False]), True),
917-
(pd.arrays.SparseArray([True, False]), True),
917+
(SparseArray([True, False]), True),
918918
(SparseDtype(bool), True),
919919
],
920920
)
@@ -924,7 +924,7 @@ def test_is_bool_dtype(dtype, expected):
924924

925925

926926
def test_is_bool_dtype_sparse():
927-
result = is_bool_dtype(pd.Series(pd.arrays.SparseArray([True, False])))
927+
result = is_bool_dtype(pd.Series(SparseArray([True, False])))
928928
assert result is True
929929

930930

‎pandas/tests/frame/indexing/test_indexing.py

+5-4
Original file line numberDiff line numberDiff line change
@@ -21,6 +21,7 @@
2121
notna,
2222
)
2323
import pandas._testing as tm
24+
from pandas.arrays import SparseArray
2425
import pandas.core.common as com
2526
from pandas.core.indexing import IndexingError
2627

@@ -1776,7 +1777,7 @@ def test_getitem_ix_float_duplicates(self):
17761777

17771778
def test_getitem_sparse_column(self):
17781779
# https://github.com/pandas-dev/pandas/issues/23559
1779-
data = pd.arrays.SparseArray([0, 1])
1780+
data = SparseArray([0, 1])
17801781
df = pd.DataFrame({"A": data})
17811782
expected = pd.Series(data, name="A")
17821783
result = df["A"]
@@ -1791,17 +1792,17 @@ def test_getitem_sparse_column(self):
17911792
def test_setitem_with_sparse_value(self):
17921793
# GH8131
17931794
df = pd.DataFrame({"c_1": ["a", "b", "c"], "n_1": [1.0, 2.0, 3.0]})
1794-
sp_array = pd.arrays.SparseArray([0, 0, 1])
1795+
sp_array = SparseArray([0, 0, 1])
17951796
df["new_column"] = sp_array
17961797
tm.assert_series_equal(
17971798
df["new_column"], pd.Series(sp_array, name="new_column"), check_names=False
17981799
)
17991800

18001801
def test_setitem_with_unaligned_sparse_value(self):
18011802
df = pd.DataFrame({"c_1": ["a", "b", "c"], "n_1": [1.0, 2.0, 3.0]})
1802-
sp_series = pd.Series(pd.arrays.SparseArray([0, 0, 1]), index=[2, 1, 0])
1803+
sp_series = pd.Series(SparseArray([0, 0, 1]), index=[2, 1, 0])
18031804
df["new_column"] = sp_series
1804-
exp = pd.Series(pd.arrays.SparseArray([1, 0, 0]), name="new_column")
1805+
exp = pd.Series(SparseArray([1, 0, 0]), name="new_column")
18051806
tm.assert_series_equal(df["new_column"], exp)
18061807

18071808
def test_setitem_with_unaligned_tz_aware_datetime_column(self):

‎pandas/tests/frame/test_constructors.py

+2-2
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@
2626
isna,
2727
)
2828
import pandas._testing as tm
29-
from pandas.arrays import IntervalArray, PeriodArray
29+
from pandas.arrays import IntervalArray, PeriodArray, SparseArray
3030
from pandas.core.construction import create_series_with_explicit_dtype
3131

3232
MIXED_FLOAT_DTYPES = ["float16", "float32", "float64"]
@@ -2414,7 +2414,7 @@ class List(list):
24142414
"extension_arr",
24152415
[
24162416
Categorical(list("aabbc")),
2417-
pd.arrays.SparseArray([1, np.nan, np.nan, np.nan]),
2417+
SparseArray([1, np.nan, np.nan, np.nan]),
24182418
IntervalArray([pd.Interval(0, 1), pd.Interval(1, 5)]),
24192419
PeriodArray(pd.period_range(start="1/1/2017", end="1/1/2018", freq="M")),
24202420
],

0 commit comments

Comments
 (0)