8000 TST: Add tests for duplicated and drop_duplicates by mproszewska · Pull Request #32575 · pandas-dev/pandas · GitHub
[go: up one dir, main page]
Skip to content

TST: Add tests for duplicated and drop_duplicates #32575

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 14 commits into from
Apr 6, 2020
Merged

TST: Add tests for duplicated and drop_duplicates #32575

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
d70d860
TST: Add tests for duplicated and drop_duplicates
mproszewska Mar 9, 2020
59d9119
TST: Fix syntax
mproszewska Mar 10, 2020
dc6b993
TST: Fix indent
mproszewska Mar 10, 2020
8e9e0ad
TST: Fix trailing whitespaces
mproszewska Mar 10, 2020
ed3798f
TST: Delete numpy testing
mproszewska Mar 10, 2020
e7d3882
TST: Fix test
mproszewska Mar 10, 2020
8b09450
TST: Delete negative values in period
mproszewska Mar 10, 2020
0067641
TST: Fix categorical tests
mproszewska Mar 10, 2020
79cba23
TST: Fix format with black
mproszewska Mar 10, 2020
5931a48
TST: Apply requested changes
mproszewska Mar 14, 2020
d228fd2
TST: Fix syntax
mproszewska Mar 14, 2020
444c081
TST: Fix indentation
mproszewska Mar 21, 2020
815c0ee
TST: Reformat conftest file with black
mproszewska Mar 21, 2020
b2b6e02
Merge branch 'master' into duplicated-tests
mproszewska Apr 3, 2020
File filter 8000

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
Prev Previous commit
Next Next commit
TST: Apply requested changes
  • Loading branch information
@mproszewska
mproszewska committed Mar 14, 2020
commit 5931a48dd243d24b6c2b6cf7ab9f460ff5dcfdb5
104 changes: 48 additions & 56 deletions pandas/tests/indexes/categorical/test_category.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -365,66 +365,58 @@ def test_has_duplicates(self):
assert idx.is_unique is True
assert idx.has_duplicates is False

def _test_drop_duplicates(self, idx, keep, expected, index):
for k, e, i in zip(keep, expected, index):
tm.assert_numpy_array_equal(idx.duplicated(keep=k), e)
e = idx[~e]

result = idx.drop_duplicates(keep=k)
tm.assert_index_equal(result, e)

result = Series(idx).drop_duplicates(keep=k)
tm.assert_series_equal(result, Series(e, i))

def test_drop_duplicates(self):
keep = ["first", "last", False]

categories = [[1, 2, 3], list("abc")]
expected = [
np.array([False, True, True]),
np.array([True, True, False]),
np.array([True, True, True]),
]
index = [[0], [2], np.empty(shape=(0), dtype=int)]
for c in categories:
idx = pd.CategoricalIndex([1, 1, 1], categories=c, name="foo")
self._test_drop_duplicates(idx, keep, expected, index)

categories = ["a", "b", "c"]
idx = CategoricalIndex([2, "a", "b"], categories=categories, name="foo")
expected = np.zeros(shape=(3, 3), dtype=np.bool)
index = [[0, 1, 2], [0, 1, 2], [0, 1, 2]]
self._test_drop_duplicates(idx, keep, expected, index)

idx = CategoricalIndex(list("abb"), categories=categories, name="foo")
expected = [
np.array([False, False, True]),
np.array([False, True, False]),
np.array([False, True, True]),
]
index = [[0, 1], [0, 2], [0]]
self._test_drop_duplicates(idx, keep, expected, index)

def test_unique(self):

categories = [1, 2, 3]
idx = CategoricalIndex([1, 1, 1], categories=categories)
expected = CategoricalIndex([1], categories=[1])
tm.assert_index_equal(idx.unique(), expected)
@pytest.mark.parametrize(
"data, categories, expected",
[
([1, 1, 1], [1, 2, 3],
{
"first" : np.array([False, True, True]),
"last" : np.array([True, True, False]),
False : np.array([True, True, True]),
}),
([1, 1, 1], list("abc"),
{
"first" : np.array([False, True, True]),
"last" : np.array([True, True, False]),
False : np.array([True, True, True]),
}),
([2, "a", "b"], list('abc'),
{
"first" : np.zeros(shape=(3), dtype=np.bool),
"last" : np.zeros(shape=(3), dtype=np.bool),
False : np.zeros(shape=(3), dtype=np.bool),
}),
(list("abb"), list('abc'),
{
"first" : np.array([False, False, True]),
"last" : np.array([False, True, False]),
False : np.array([False, True, True]),
}),
],
)
def test_drop_duplicates(self, data, categories, expected):

categories = list("abc")
idx = CategoricalIndex([1, 1, 1], categories=categories)
expected = CategoricalIndex([np.nan], categories=[])
tm.assert_index_equal(idx.unique(), expected)
idx = CategoricalIndex(data, categories=categories, name="foo")
for keep, e in expected.items():
tm.assert_numpy_array_equal(idx.duplicated(keep=keep), e)
e = idx[~e]
result = idx.drop_duplicates(keep=keep)
tm.assert_index_equal(result, e)

categories = [1, 2, 3]
idx = CategoricalIndex([1, 2, "a"], categories=categories)
expected = CategoricalIndex([1, 2, np.nan], categories=[1, 2])
tm.assert_index_equal(idx.unique(), expected)
@pytest.mark.parametrize(
"data, categories, expected_data, expected_categories",
[
([1, 1, 1], [1, 2, 3], [1], [1]),
([1, 1, 1], list('abc'), [np.nan], []),
([1, 2, "a"], [1, 2, 3], [1, 2, np.nan], [1, 2]),
([2, "a", "b"], list("abc"), [np.nan, "a", "b"], ["a", "b"]),
],
)
def test_unique(self, data, categories, expected_data, expected_categories):

categories = list("abc")
idx = CategoricalIndex([2, "a", "b"], categories=categories)
expected = CategoricalIndex([np.nan, "a", "b"], categories=["a", "b"])
idx = CategoricalIndex(data, categories=categories)
expected = CategoricalIndex(expected_data, categories=expected_categories)
tm.assert_index_equal(idx.unique(), expected)

def test_repr_roundtrip(self):
Expand Down
10 changes: 10 additions & 0 deletions pandas/tests/indexes/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,3 +16,13 @@ def sort(request):
in in the Index setops methods.
"""
return request.param

@pytest.fixture(
params=["D", "3D", "-3D", "H", "2H", "-2H", "T", "2T", "S", "-3S"]
)
def freq_sample(request):
"""
Valid values for 'freq' parameter used to create date_range and
timedelta_range..
"""
return request.param
44 changes: 7 additions & 37 deletions pandas/tests/indexes/datetimes/test_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -259,12 +259,9 @@ def test_order_without_freq(self, index_dates, expected_dates, tz_naive_fixture)
tm.assert_numpy_array_equal(indexer, exp, check_dtype=False)
assert ordered.freq is None

@pytest.mark.parametrize(
"freq", ["D", "3D", "-3D", "H", "2H", "-2H", "T", "2T", "S", "-3S"]
)
def test_drop_duplicates_metadata(self, freq):
def test_drop_duplicates_metadata(self, freq_sample):
# GH 10115
idx = pd.date_range("2011-01-01", freq=freq, periods=10, name="idx")
idx = pd.date_range("2011-01-01", freq=freq_sample, periods=10, name="idx")
result = idx.drop_duplicates()
tm.assert_index_equal(idx, result)
assert idx.freq == result.freq
Expand All @@ -275,9 +272,6 @@ def test_drop_duplicates_metadata(self, freq):
tm.assert_index_equal(idx, result)
assert result.freq is None

@pytest.mark.parametrize(
"freq", ["D", "3D", "-3D", "H", "2H", "-2H", "T", "2T", "S", "-3S"]
)
@pytest.mark.parametrize(
"keep, expected, index",
[
Expand All @@ -290,9 +284,9 @@ def test_drop_duplicates_metadata(self, freq):
),
],
)
def test_drop_duplicates(self, freq, keep, expected, index):
def test_drop_duplicates(self, freq_sample, keep, expected, index):
# to check Index/Series compat
idx = pd.date_range("2011-01-01", freq=freq, periods=10, name="idx")
idx = pd.date_range("2011-01-01", freq=freq_sample, periods=10, name="idx")
idx = idx.append(idx[:5])

tm.assert_numpy_array_equal(idx.duplicated(keep=keep), expected)
Expand All @@ -304,36 +298,12 @@ def test_drop_duplicates(self, freq, keep, expected, index):
result = Series(idx).drop_duplicates(keep=keep)
tm.assert_series_equal(result, Series(expected, index=index))

@pytest.mark.parametrize(
"freq",
[
"A",
"2A",
"-2A",
"Q",
"-1Q",
"M",
"-1M",
"D",
"3D",
"-3D",
"W",
"-1W",
"H",
"2H",
"-2H",
"T",
"2T",
"S",
"-3S",
],
)
def test_infer_freq(self, freq):
def test_infer_freq(self, freq_sample):
# GH 11018
idx = pd.date_range("2011-01-01 09:00:00", freq=freq, periods=10)
idx = pd.date_range("2011-01-01 09:00:00", freq=freq_sample, periods=10)
result = pd.DatetimeIndex(idx.asi8, freq="infer")
tm.assert_index_equal(idx, result)
assert result.freq == freq
assert result.freq == freq_sample

def test_nat(self, tz_naive_fixture):
tz = tz_naive_fixture
Expand Down
23 changes: 7 additions & 16 deletions pandas/tests/indexes/timedeltas/test_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,12 +136,9 @@ def test_order(self):
tm.assert_numpy_array_equal(indexer, exp, check_dtype=False)
assert ordered.freq is None

@pytest.mark.parametrize(
"freq", ["D", "3D", "-3D", "H", "2H", "-2H", "T", "2T", "S", "-3S"]
)
def test_drop_duplicates_metadata(self, freq):
def test_drop_duplicates_metadata(self, freq_sample):
# GH 10115
idx = pd.timedelta_range("1 day", periods=10, freq=freq, name="idx")
idx = pd.timedelta_range("1 day", periods=10, freq=freq_sample, name="idx")
result = idx.drop_duplicates()
tm.assert_index_equal(idx, result)
assert idx.freq == result.freq
Expand All @@ -152,9 +149,6 @@ def test_drop_duplicates_metadata(self, freq):
tm.assert_index_equal(idx, result)
assert result.freq is None

@pytest.mark.parametrize(
"freq", ["D", "3D", "-3D", "H", "2H", "-2H", "T", "2T", "S", "-3S"]
)
@pytest.mark.parametrize(
"keep, expected, index",
[
Expand All @@ -167,9 +161,9 @@ def test_drop_duplicates_metadata(self, freq):
),
],
)
def test_drop_duplicates(self, freq, keep, expected, index):
def test_drop_duplicates(self, freq_sample, keep, expected, index):
# to check Index/Series compat
idx = pd.timedelta_range("1 day", periods=10, freq=freq, name="idx")
idx = pd.timedelta_range("1 day", periods=10, freq=freq_sample, name="idx")
idx = idx.append(idx[:5])

tm.assert_numpy_array_equal(idx.duplicated(keep=keep), expected)
Expand All @@ -181,15 +175,12 @@ def test_drop_duplicates(self, freq, keep, expected, index):
result = Series(idx).drop_duplicates(keep=keep)
tm.assert_series_equal(result, Series(expected, index=index))

@pytest.mark.parametrize(
"freq", ["D", "3D", "-3D", "H", "2H", "-2H", "T", "2T", "S", "-3S"]
)
def test_infer_freq(self, freq):
def test_infer_freq(self, freq_sample):
# GH#11018
idx = pd.timedelta_range("1", freq=freq, periods=10)
idx = pd.timedelta_range("1", freq=freq_sample, periods=10)
result = pd.TimedeltaIndex(idx.asi8, freq="infer")
tm.assert_index_equal(idx, result)
assert result.freq == freq
assert result.freq == freq_sample

def test_repeat(self):
index = pd.timedelta_range("1 days", periods=2, freq="D")
Expand Down
0