Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

TST (string dtype): un-xfail string tests specific to object dtype #59433

Merged
merged 4 commits into from
Nov 4, 2024
Merged

TST (string dtype): un-xfail string tests specific to object dtype #59433

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9bd4032
TST: fix xfailed algos tests
jbrockmendel Aug 6, 2024
beee346
TST: un-xfail string tests specific to object
jbrockmendel Aug 7, 2024
d89766b
Merge branch 'main' into tst-str-2
jbrockmendel Aug 13, 2024
4dd0aa8
Merge remote-tracking branch 'upstream/main' into tst-str-2
jorisvandenbossche Nov 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 2 additions & 6 deletions pandas/tests/copy_view/test_interp_fillna.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,6 @@
import numpy as np
import pytest

from pandas._config import using_string_dtype

from pandas.compat import HAS_PYARROW

from pandas import (
NA,
DataFrame,
Expand Down Expand Up @@ -114,18 +110,18 @@ def test_interp_fill_functions_inplace(func, dtype):
assert view._mgr._has_no_reference(0)


@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
def test_interpolate_cannot_with_object_dtype():
df = DataFrame({"a": ["a", np.nan, "c"], "b": 1})
df["a"] = df["a"].astype(object)

msg = "DataFrame cannot interpolate with object dtype"
with pytest.raises(TypeError, match=msg):
df.interpolate()


@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
def test_interpolate_object_convert_no_op():
df = DataFrame({"a": ["a", "b", "c"], "b": 1})
df["a"] = df["a"].astype(object)
arr_a = get_array(df, "a")

# Now CoW makes a copy, it should not!
Expand Down
3 changes: 1 addition & 2 deletions pandas/tests/copy_view/test_replace.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -259,10 +259,9 @@ def test_replace_empty_list():
assert not df2._mgr._has_no_reference(0)


@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
@pytest.mark.parametrize("value", ["d", None])
def test_replace_object_list_inplace(value):
df = DataFrame({"a": ["a", "b", "c"]})
df = DataFrame({"a": ["a", "b", "c"]}, dtype=object)
arr = get_array(df, "a")
df.replace(["c"], value, inplace=True)
assert np.shares_memory(arr, get_array(df, "a"))
Expand Down
28 changes: 18 additions & 10 deletions pandas/tests/test_algos.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,8 +4,6 @@
import numpy as np
import pytest

from pandas._config import using_string_dtype

from pandas._libs import (
algos as libalgos,
hashtable as ht,
Expand Down Expand Up @@ -1684,20 +1682,25 @@ def test_unique_complex_numbers(self, array, expected):


class TestHashTable:
@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
@pytest.mark.parametrize(
"htable, data",
[
(ht.PyObjectHashTable, [f"foo_{i}" for i in range(1000)]),
(ht.StringHashTable, [f"foo_{i}" for i in range(1000)]),
(
ht.PyObjectHashTable,
np.array([f"foo_{i}" for i in range(1000)], dtype=object),
),
(
ht.StringHashTable,
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I thought we added a hashtable for strings that didn't use Python objects. @phofl am I misremembering?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@WillAyd the StringHashTable is string specific, but still takes an object dtype array with Python strings as input (it just assumes the array only contains strings, and not any random Python object)

np.array([f"foo_{i}" for i in range(1000)], dtype=object),
),
(ht.Float64HashTable, np.arange(1000, dtype=np.float64)),
(ht.Int64HashTable, np.arange(1000, dtype=np.int64)),
(ht.UInt64HashTable, np.arange(1000, dtype=np.uint64)),
],
)
def test_hashtable_unique(self, htable, data, writable):
# output of maker has guaranteed unique elements
s = Series(data)
s = Series(data, dtype=data.dtype)
if htable == ht.Float64HashTable:
# add NaN for float column
s.loc[500] = np.nan
Expand All @@ -1724,20 +1727,25 @@ def test_hashtable_unique(self, htable, data, writable):
reconstr = result_unique[result_inverse]
tm.assert_numpy_array_equal(reconstr, s_duplicated.values)

@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
@pytest.mark.parametrize(
"htable, data",
[
(ht.PyObjectHashTable, [f"foo_{i}" for i in range(1000)]),
(ht.StringHashTable, [f"foo_{i}" for i in range(1000)]),
(
ht.PyObjectHashTable,
np.array([f"foo_{i}" for i in range(1000)], dtype=object),
),
(
ht.StringHashTable,
np.array([f"foo_{i}" for i in range(1000)], dtype=object),
),
(ht.Float64HashTable, np.arange(1000, dtype=np.float64)),
(ht.Int64HashTable, np.arange(1000, dtype=np.int64)),
(ht.UInt64HashTable, np.arange(1000, dtype=np.uint64)),
],
)
def test_hashtable_factorize(self, htable, writable, data):
# output of maker has guaranteed unique elements
s = Series(data)
s = Series(data, dtype=data.dtype)
if htable == ht.Float64HashTable:
# add NaN for float column
s.loc[500] = np.nan
Expand Down
Loading