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.

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
Changes from 3 commits
Commits
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
192 changes: 146 additions & 46 deletions pandas/tests/series/test_analytics.py
Original file line number Diff line number Diff line change
Expand Up @@ -873,52 +873,152 @@ 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('dtype', ['int_', 'uint', 'float_'])
Copy link
Contributor

Choose a reason for hiding this comment

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

so the parametrization is good here, just pull all dtypes to here to avoid repeating all of this code multiple times.

@pytest.mark.parametrize('arg',
    [
        (Series([1, 2, 3,3 ], dtype='int_'),
        (Series([1, 2, 3,3 ], dtype='uint'),
        .....
        (Series(['1', '2', '3', '4',])
])

Copy link
Contributor

Choose a reason for hiding this comment

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

and if you have different expected values, just add antother parameter (and expand the tuple to multiple values)

def test_drop_duplicates_with_numeric(self, dtype):
# Test case 1
tc_1 = Series([1, 2, 3, 3], dtype=np.dtype(dtype))

expected = Series([False, False, False, True])
assert_series_equal(tc_1.duplicated(), expected)
assert_series_equal(tc_1.drop_duplicates(), tc_1[~expected])
sc = tc_1.copy()
sc.drop_duplicates(inplace=True)
assert_series_equal(sc, tc_1[~expected])

expected = Series([False, False, True, False])
assert_series_equal(tc_1.duplicated(keep='last'), expected)
assert_series_equal(tc_1.drop_duplicates(keep='last'), tc_1[~expected])
sc = tc_1.copy()
sc.drop_duplicates(keep='last', inplace=True)
assert_series_equal(sc, tc_1[~expected])

expected = Series([False, False, True, True])
assert_series_equal(tc_1.duplicated(keep=False), expected)
assert_series_equal(tc_1.drop_duplicates(keep=False), tc_1[~expected])
sc = tc_1.copy()
sc.drop_duplicates(keep=False, inplace=True)
assert_series_equal(sc, tc_1[~expected])

# Test case 2
tc_2 = Series([1, 2, 3, 5, 3, 2, 4], dtype=np.dtype(dtype))

expected = Series([False, False, False, False, True, True, False])
assert_series_equal(tc_2.duplicated(), expected)
assert_series_equal(tc_2.drop_duplicates(), tc_2[~expected])
sc = tc_2.copy()
sc.drop_duplicates(inplace=True)
assert_series_equal(sc, tc_2[~expected])

expected = Series([False, True, True, False, False, False, False])
assert_series_equal(tc_2.duplicated(keep='last'), expected)
assert_series_equal(tc_2.drop_duplicates(keep='last'), tc_2[~expected])
sc = tc_2.copy()
sc.drop_duplicates(keep='last', inplace=True)
assert_series_equal(sc, tc_2[~expected])

expected = Series([False, True, True, False, True, True, False])
assert_series_equal(tc_2.duplicated(keep=False), expected)
assert_series_equal(tc_2.drop_duplicates(keep=False), tc_2[~expected])
sc = tc_2.copy()
sc.drop_duplicates(keep=False, inplace=True)
assert_series_equal(sc, tc_2[~expected])

def test_drop_duplicates_with_object(self):
# Test case 1
tc_1 = Series(['1', '2', '3', '3'])

expected = Series([False, False, False, True])
assert_series_equal(tc_1.duplicated(), expected)
assert_series_equal(tc_1.drop_duplicates(), tc_1[~expected])
sc = tc_1.copy()
sc.drop_duplicates(inplace=True)
assert_series_equal(sc, tc_1[~expected])

expected = Series([False, False, True, False])
assert_series_equal(tc_1.duplicated(keep='last'), expected)
assert_series_equal(tc_1.drop_duplicates(keep='last'), tc_1[~expected])
sc = tc_1.copy()
sc.drop_duplicates(keep='last', inplace=True)
assert_series_equal(sc, tc_1[~expected])

expected = Series([False, False, True, True])
assert_series_equal(tc_1.duplicated(keep=False), expected)
assert_series_equal(tc_1.drop_duplicates(keep=False), tc_1[~expected])
sc = tc_1.copy()
sc.drop_duplicates(keep=False, inplace=True)
assert_series_equal(sc, tc_1[~expected])

# Test case 2
tc_2 = Series(['1', '2', '3', '5', '3', '2', '4'])

expected = Series([False, False, False, False, True, True, False])
assert_series_equal(tc_2.duplicated(), expected)
assert_series_equal(tc_2.drop_duplicates(), tc_2[~expected])
sc = tc_2.copy()
sc.drop_duplicates(inplace=True)
assert_series_equal(sc, tc_2[~expected])

expected = Series([False, True, True, False, False, False, False])
assert_series_equal(tc_2.duplicated(keep='last'), expected)
assert_series_equal(tc_2.drop_duplicates(keep='last'), tc_2[~expected])
sc = tc_2.copy()
sc.drop_duplicates(keep='last', inplace=True)
assert_series_equal(sc, tc_2[~expected])

expected = Series([False, True, True, False, True, True, False])
assert_series_equal(tc_2.duplicated(keep=False), expected)
assert_series_equal(tc_2.drop_duplicates(keep=False), tc_2[~expected])
sc = tc_2.copy()
sc.drop_duplicates(keep=False, inplace=True)
assert_series_equal(sc, tc_2[~expected])

def test_drop_duplicates_with_bool(self):
# Test case 1
tc_1 = Series([True, False, False])

expected = Series([False, False, True])
assert_series_equal(tc_1.duplicated(), expected)
assert_series_equal(tc_1.drop_duplicates(), tc_1[~expected])
sc = tc_1.copy()
sc.drop_duplicates(inplace=True)
assert_series_equal(sc, tc_1[~expected])

expected = Series([False, True, False])
assert_series_equal(tc_1.duplicated(keep='last'), expected)
assert_series_equal(tc_1.drop_duplicates(keep='last'), tc_1[~expected])
sc = tc_1.copy()
sc.drop_duplicates(keep='last', inplace=True)
assert_series_equal(sc, tc_1[~expected])

expected = Series([False, True, True])
assert_series_equal(tc_1.duplicated(keep=False), expected)
assert_series_equal(tc_1.drop_duplicates(keep=False), tc_1[~expected])
sc = tc_1.copy()
sc.drop_duplicates(keep=False, inplace=True)
assert_series_equal(sc, tc_1[~expected])

# Test case 2
tc_2 = Series([True, False, True, False])
expected = Series([False, False, True, True])
assert_series_equal(tc_2.duplicated(), expected)
assert_series_equal(tc_2.drop_duplicates(), tc_2[~expected])
sc = tc_2.copy()
sc.drop_duplicates(inplace=True)
assert_series_equal(sc, tc_2[~expected])

expected = Series([True, True, False, False])
assert_series_equal(tc_2.duplicated(keep='last'), expected)
assert_series_equal(tc_2.drop_duplicates(keep='last'), tc_2[~expected])
sc = tc_2.copy()
sc.drop_duplicates(keep='last', inplace=True)
assert_series_equal(sc, tc_2[~expected])

expected = Series([True, True, True, True])
assert_series_equal(tc_2.duplicated(keep=False), expected)
assert_series_equal(tc_2.drop_duplicates(keep=False), tc_2[~expected])
sc = tc_2.copy()
sc.drop_duplicates(keep=False, inplace=True)
assert_series_equal(sc, tc_2[~expected])

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