Skip to content

TST/CLN: deduplicate troublesome rank values #38894

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

Merged
merged 7 commits into from
Jan 4, 2021
Merged

TST/CLN: deduplicate troublesome rank values #38894

Show file tree
Hide file tree
Changes from 6 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
b6e52de
WIP
mzeitlin11 Dec 31, 2020
c43318c
Merge remote-tracking branch 'upstream/master' into ref/rank_fixture
mzeitlin11 Jan 2, 2021
863e4d6
TST/CLN: deduplicate troublesome rank values
mzeitlin11 Jan 2, 2021
da4c76b
Remove unneeded imports
mzeitlin11 Jan 2, 2021
b816586
Merge remote-tracking branch 'upstream/master' into ref/rank_fixture
mzeitlin11 Jan 3, 2021
c77a84f
Address comments
mzeitlin11 Jan 3, 2021
4961e38
Use frame_or_series instead
mzeitlin11 Jan 3, 2021
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
87 changes: 87 additions & 0 deletions pandas/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,8 @@
import pytest
from pytz import FixedOffset, utc

from pandas._libs import iNaT
from pandas._libs.algos import Infinity, NegInfinity
import pandas.util._test_decorators as td

from pandas.core.dtypes.dtypes import DatetimeTZDtype, IntervalDtype
Expand Down Expand Up @@ -591,6 +593,91 @@ def narrow_series(request):
return _narrow_series[request.param].copy()


# Used in tests in (series|frame)/methods/test_rank.py
_nuisance_arr_for_rank_by_dtype = {
"float64": [
-np.inf,
-50,
-1,
-1e-20,
-1e-25,
-1e-50,
0,
1e-40,
1e-20,
1e-10,
2,
40,
np.inf,
],
"float32": [
-np.inf,
-50,
-1,
-1e-20,
-1e-25,
-1e-45,
0,
1e-40,
1e-20,
1e-10,
2,
40,
np.inf,
],
"uint8": [np.iinfo(np.uint8).min, 1, 2, 100, np.iinfo(np.uint8).max],
"int64": [
np.iinfo(np.int64).min,
-100,
0,
1,
9999,
100000,
1e10,
np.iinfo(np.int64).max,
],
"object": [NegInfinity(), "1", "A", "BA", "Ba", "C", Infinity()],
}


@pytest.fixture(params=_nuisance_arr_for_rank_by_dtype.keys())
def nuisance_rank_series_and_expected(request):
"""
Fixture for Series with troublesome values for rank
algorithms
"""
_dtype_na_map = {
"float64": np.nan,
"float32": np.nan,
"int64": iNaT,
"object": None,
}
dtype = request.param
if dtype == "int64":
mark = pytest.mark.xfail(
reason="iNaT is equivalent to minimum value of dtype"
"int64 pending issue GH#16674"
)
request.node.add_marker(mark)
data = _nuisance_arr_for_rank_by_dtype[dtype]
values = np.array(data, dtype=dtype)
exp_order = np.array(range(len(values)), dtype="float64") + 1.0
# Insert nans at random positions if underlying dtype has missing
# value. Then adjust the expected order by adding nans accordingly
# This is for testing whether rank calculation is affected
# when values are interwined with nan values.
if dtype in _dtype_na_map:
na_value = _dtype_na_map[dtype]
nan_indices = np.random.choice(range(len(values)), 5)
values = np.insert(values, nan_indices, na_value)
exp_order = np.insert(exp_order, nan_indices, np.nan)
# shuffle the testing array and expected results in the same way
random_order = np.random.permutation(len(values))
iseries = Series(values[random_order])
exp = Series(exp_order[random_order], dtype="float64")
return iseries, exp


_index_or_series_objs = {**indices_dict, **_series, **_narrow_series}


Expand Down
88 changes: 4 additions & 84 deletions pandas/tests/frame/methods/test_rank.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,6 @@
import numpy as np
import pytest

from pandas._libs import iNaT
from pandas._libs.algos import Infinity, NegInfinity
import pandas.util._test_decorators as td

from pandas import DataFrame, Series
Expand Down Expand Up @@ -332,88 +330,10 @@ def test_pct_max_many_rows(self):
result = df.rank(pct=True).max()
assert (result == 1).all()

@pytest.mark.parametrize(
"contents,dtype",
[
(
[
-np.inf,
-50,
-1,
-1e-20,
-1e-25,
-1e-50,
0,
1e-40,
1e-20,
1e-10,
2,
40,
np.inf,
],
"float64",
),
(
[
-np.inf,
-50,
-1,
-1e-20,
-1e-25,
-1e-45,
0,
1e-40,
1e-20,
1e-10,
2,
40,
np.inf,
],
"float32",
),
([np.iinfo(np.uint8).min, 1, 2, 100, np.iinfo(np.uint8).max], "uint8"),
pytest.param(
[
np.iinfo(np.int64).min,
-100,
0,
1,
9999,
100000,
1e10,
np.iinfo(np.int64).max,
],
"int64",
marks=pytest.mark.xfail(
reason="iNaT is equivalent to minimum value of dtype"
"int64 pending issue GH#16674"
),
),
([NegInfinity(), "1", "A", "BA", "Ba", "C", Infinity()], "object"),
],
)
def test_rank_inf_and_nan(self, contents, dtype):
dtype_na_map = {
"float64": np.nan,
"float32": np.nan,
"int64": iNaT,
"object": None,
}
# Insert nans at random positions if underlying dtype has missing
# value. Then adjust the expected order by adding nans accordingly
# This is for testing whether rank calculation is affected
# when values are interwined with nan values.
values = np.array(contents, dtype=dtype)
exp_order = np.array(range(len(values)), dtype="float64") + 1.0
if dtype in dtype_na_map:
na_value = dtype_na_map[dtype]
nan_indices = np.random.choice(range(len(values)), 5)
values = np.insert(values, nan_indices, na_value)
exp_order = np.insert(exp_order, nan_indices, np.nan)
# shuffle the testing array and expected results in the same way
random_order = np.random.permutation(len(values))
df = DataFrame({"a": values[random_order]})
expected = DataFrame({"a": exp_order[random_order]}, dtype="float64")
def test_rank_inf_and_nan(self, nuisance_rank_series_and_expected):
series, expected = nuisance_rank_series_and_expected
df = DataFrame({"a": series})
expected = DataFrame({"a": expected})
result = df.rank()
tm.assert_frame_equal(result, expected)

Expand Down
89 changes: 4 additions & 85 deletions pandas/tests/series/methods/test_rank.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,6 @@
import numpy as np
import pytest

from pandas._libs import iNaT
from pandas._libs.algos import Infinity, NegInfinity
import pandas.util._test_decorators as td

Expand Down Expand Up @@ -206,90 +205,10 @@ def test_rank_signature(self):
with pytest.raises(ValueError, match=msg):
s.rank("average")

@pytest.mark.parametrize(
"contents,dtype",
[
(
[
-np.inf,
-50,
-1,
-1e-20,
-1e-25,
-1e-50,
0,
1e-40,
1e-20,
1e-10,
2,
40,
np.inf,
],
"float64",
),
(
[
-np.inf,
-50,
-1,
-1e-20,
-1e-25,
-1e-45,
0,
1e-40,
1e-20,
1e-10,
2,
40,
np.inf,
],
"float32",
),
([np.iinfo(np.uint8).min, 1, 2, 100, np.iinfo(np.uint8).max], "uint8"),
pytest.param(
[
np.iinfo(np.int64).min,
-100,
0,
1,
9999,
100000,
1e10,
np.iinfo(np.int64).max,
],
"int64",
marks=pytest.mark.xfail(
reason="iNaT is equivalent to minimum value of dtype"
"int64 pending issue GH#16674"
),
),
([NegInfinity(), "1", "A", "BA", "Ba", "C", Infinity()], "object"),
],
)
def test_rank_inf(self, contents, dtype):
dtype_na_map = {
"float64": np.nan,
"float32": np.nan,
"int64": iNaT,
"object": None,
}
# Insert nans at random positions if underlying dtype has missing
# value. Then adjust the expected order by adding nans accordingly
# This is for testing whether rank calculation is affected
# when values are interwined with nan values.
values = np.array(contents, dtype=dtype)
exp_order = np.array(range(len(values)), dtype="float64") + 1.0
if dtype in dtype_na_map:
na_value = dtype_na_map[dtype]
nan_indices = np.random.choice(range(len(values)), 5)
values = np.insert(values, nan_indices, na_value)
exp_order = np.insert(exp_order, nan_indices, np.nan)
# shuffle the testing array and expected results in the same way
random_order = np.random.permutation(len(values))
iseries = Series(values[random_order])
exp = Series(exp_order[random_order], dtype="float64")
iranks = iseries.rank()
tm.assert_series_equal(iranks, exp)
def test_rank_inf(self, nuisance_rank_series_and_expected):
series, expected = nuisance_rank_series_and_expected
Copy link
Contributor

Choose a reason for hiding this comment

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

actually an alternative here is simply to use frame_or_series fixture and leave the fixture in tests/frame/methods (e.g. this is what we do for things for both series & frame), i think in this case it makes more sense.

Copy link
Member

Choose a reason for hiding this comment

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

yah i think this makes a lot more sense than a relatively-complicated fixture in conftest

Copy link
Member Author

Choose a reason for hiding this comment

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

Thanks that is much nicer, good pattern to know

result = series.rank()
tm.assert_series_equal(result, expected)

def test_rank_tie_methods(self):
s = self.s
Expand Down