Skip to content

TST: #15752 Add drop_duplicates tests for uint, float and bool for Series #17974

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 6 commits into from
Oct 31, 2017
Merged

TST: #15752 Add drop_duplicates tests for uint, float and bool for Series #17974

Changes from 5 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
194d7cd
Add drop_duplicates test for uint, float and bool
Oct 25, 2017
888e937
TST: #15752 resolve PEP8 issues in test_analytics.py
Oct 25, 2017
523ac99
TST: #15752 resolve PEP8 issues in test_analytics.py
Oct 25, 2017
897b09e
TST: #15752 parametrized test_drop_duplicates and removed duplicate code
Oct 26, 2017
1952ba3
TST #15752 Re-parametrize test_drop_duplicates
Oct 27, 2017
7b035e4
TST #15752: create separate method to test drop duplicates for bools …
Oct 28, 2017
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
113 changes: 67 additions & 46 deletions pandas/tests/series/test_analytics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -873,52 +873,73 @@ def test_unique(self):
expected = np.array([1, 2, 3, None], dtype=object)
tm.assert_numpy_array_equal(result, expected)

def test_drop_duplicates(self):
# check both int and object
for s in [Series([1, 2, 3, 3]), Series(['1', '2', '3', '3'])]:
expected = Series([False, False, False, True])
assert_series_equal(s.duplicated(), expected)
assert_series_equal(s.drop_duplicates(), s[~expected])
sc = s.copy()
sc.drop_duplicates(inplace=True)
assert_series_equal(sc, s[~expected])

expected = Series([False, False, True, False])
assert_series_equal(s.duplicated(keep='last'), expected)
assert_series_equal(s.drop_duplicates(keep='last'), s[~expected])
sc = s.copy()
sc.drop_duplicates(keep='last', inplace=True)
assert_series_equal(sc, s[~expected])

expected = Series([False, False, True, True])
assert_series_equal(s.duplicated(keep=False), expected)
assert_series_equal(s.drop_duplicates(keep=False), s[~expected])
sc = s.copy()
sc.drop_duplicates(keep=False, inplace=True)
assert_series_equal(sc, s[~expected])

for s in [Series([1, 2, 3, 5, 3, 2, 4]),
Series(['1', '2', '3', '5', '3', '2', '4'])]:
expected = Series([False, False, False, False, True, True, False])
assert_series_equal(s.duplicated(), expected)
assert_series_equal(s.drop_duplicates(), s[~expected])
sc = s.copy()
sc.drop_duplicates(inplace=True)
assert_series_equal(sc, s[~expected])

expected = Series([False, True, True, False, False, False, False])
assert_series_equal(s.duplicated(keep='last'), expected)
assert_series_equal(s.drop_duplicates(keep='last'), s[~expected])
sc = s.copy()
sc.drop_duplicates(keep='last', inplace=True)
assert_series_equal(sc, s[~expected])

expected = Series([False, True, True, False, True, True, False])
assert_series_equal(s.duplicated(keep=False), expected)
assert_series_equal(s.drop_duplicates(keep=False), s[~expected])
sc = s.copy()
sc.drop_duplicates(keep=False, inplace=True)
assert_series_equal(sc, s[~expected])
@pytest.mark.parametrize(
"tc",
[
Series([1, 2, 3, 3], dtype=np.dtype('int_')),
Series([1, 2, 3, 5, 3, 2, 4], dtype=np.dtype('int_')),
Series([1, 2, 3, 3], dtype=np.dtype('uint')),
Series([1, 2, 3, 5, 3, 2, 4], dtype=np.dtype('uint')),
Series([1, 2, 3, 3], dtype=np.dtype('float_')),
Series([1, 2, 3, 5, 3, 2, 4], dtype=np.dtype('float_')),
Series([1, 2, 3, 3], dtype=np.dtype('unicode_')),
Series([1, 2, 3, 5, 3, 2, 4], dtype=np.dtype('unicode_')),
Series([True, False, False]),
Series([True, False, True, False])
]
)
Copy link
Contributor

Choose a reason for hiding this comment

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

I would pull the bool tests out and do them separately (as they are simpler and don't need as much checking);
also just in-ilne the expected results, don't use an if for that. the way to do this is to pass in things as a pair

e.g.

@pytest.mark.parametrize("tc1, tc2",
[
   (Series(1,2, 3, 3, dtype='int_'), Series([1, 2, 3, 5,3 ,2, 4])),
.....
])
def test_drop_duplicates(self, tc1, tc2)

def test_drop_duplicates(self, tc):
expected_results = {
"shorter_series_non_bool": [
Series([False, False, False, True]),
Series([False, False, True, False]),
Series([False, False, True, True])
],
"longer_series_non_bool": [
Series([False, False, False, False, True, True, False]),
Series([False, True, True, False, False, False, False]),
Series([False, True, True, False, True, True, False])
],
"shorter_series_bool": [
Series([False, False, True]),
Series([False, True, False]),
Series([False, True, True])
],
"longer_series_bool": [
Series([False, False, True, True]),
Series([True, True, False, False]),
Series([True, True, True, True])
]
}

if (tc.dtype != "bool"):
if (tc.size == 7):
expected = expected_results["longer_series_non_bool"]
else:
expected = expected_results["shorter_series_non_bool"]
else:
if (tc.size == 4):
expected = expected_results["longer_series_bool"]
else:
expected = expected_results["shorter_series_bool"]

assert_series_equal(tc.duplicated(), expected[0])
assert_series_equal(tc.drop_duplicates(), tc[~expected[0]])
sc = tc.copy()
sc.drop_duplicates(inplace=True)
assert_series_equal(sc, tc[~expected[0]])

assert_series_equal(tc.duplicated(keep='last'), expected[1])
assert_series_equal(tc.drop_duplicates(keep='last'), tc[~expected[1]])
sc = tc.copy()
sc.drop_duplicates(keep='last', inplace=True)
assert_series_equal(sc, tc[~expected[1]])

assert_series_equal(tc.duplicated(keep=False), expected[2])
assert_series_equal(tc.drop_duplicates(keep=False), tc[~expected[2]])
sc = tc.copy()
sc.drop_duplicates(keep=False, inplace=True)
assert_series_equal(sc, tc[~expected[2]])

def test_clip(self):
val = self.ts.median()
Expand Down