Skip to content

TST: #15752 Add test_drop_duplicates for Categorical dtypes #18072

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
Nov 6, 2017
Merged

TST: #15752 Add test_drop_duplicates for Categorical dtypes #18072

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
e3cdb6e
Add test_drop_duplicates for Categorical dtypes
Nov 2, 2017
289ad35
Fix PEP8 issue
Nov 2, 2017
e1dc3c9
Parameterize dtypes
jamestran201-alt Nov 3, 2017
20c41e3
Fix PEP8 issue
jamestran201-alt Nov 3, 2017
7b7e577
Fix PEP8 issue
jamestran201-alt Nov 4, 2017
f9c65c7
Use datetime64[D] and mark it as xfail
jamestran201-alt Nov 6, 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
91 changes: 91 additions & 0 deletions pandas/tests/test_categorical.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -797,6 +797,97 @@ def test_set_categories_inplace(self):
cat.set_categories(['a', 'b', 'c', 'd'], inplace=True)
tm.assert_index_equal(cat.categories, pd.Index(['a', 'b', 'c', 'd']))

@pytest.mark.parametrize(
Copy link
Contributor

Choose a reason for hiding this comment

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

can you add an xfail with datetime64[D], something like this

"timedelta64[h]", pytest.param('datetime64[D]', marks=pytest.mark.xfail(
                         reason='write the issue number'))

Copy link
Author

Choose a reason for hiding this comment

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

yup, just added it

"dtype",
["int_", "uint", "float_", "unicode_", "timedelta64[h]",
pytest.param("datetime64[D]",
marks=pytest.mark.xfail(reason="issue7996"))]
)
@pytest.mark.parametrize("is_ordered", [True, False])
def test_drop_duplicates_non_bool(self, dtype, is_ordered):
cat_array = np.array([1, 2, 3, 4, 5], dtype=np.dtype(dtype))

# Test case 1
input1 = np.array([1, 2, 3, 3], dtype=np.dtype(dtype))
tc1 = Series(Categorical(input1, categories=cat_array,
ordered=is_ordered))

expected = Series([False, False, False, True])
tm.assert_series_equal(tc1.duplicated(), expected)
tm.assert_series_equal(tc1.drop_duplicates(), tc1[~expected])
sc = tc1.copy()
sc.drop_duplicates(inplace=True)
tm.assert_series_equal(sc, tc1[~expected])

expected = Series([False, False, True, False])
tm.assert_series_equal(tc1.duplicated(keep='last'), expected)
tm.assert_series_equal(tc1.drop_duplicates(keep='last'),
tc1[~expected])
sc = tc1.copy()
sc.drop_duplicates(keep='last', inplace=True)
tm.assert_series_equal(sc, tc1[~expected])

expected = Series([False, False, True, True])
tm.assert_series_equal(tc1.duplicated(keep=False), expected)
tm.assert_series_equal(tc1.drop_duplicates(keep=False), tc1[~expected])
sc = tc1.copy()
sc.drop_duplicates(keep=False, inplace=True)
tm.assert_series_equal(sc, tc1[~expected])

# Test case 2
input2 = np.array([1, 2, 3, 5, 3, 2, 4], dtype=np.dtype(dtype))
tc2 = Series(Categorical(
input2, categories=cat_array, ordered=is_ordered)
)

expected = Series([False, False, False, False, True, True, False])
tm.assert_series_equal(tc2.duplicated(), expected)
tm.assert_series_equal(tc2.drop_duplicates(), tc2[~expected])
sc = tc2.copy()
sc.drop_duplicates(inplace=True)
tm.assert_series_equal(sc, tc2[~expected])

expected = Series([False, True, True, False, False, False, False])
tm.assert_series_equal(tc2.duplicated(keep='last'), expected)
tm.assert_series_equal(tc2.drop_duplicates(keep='last'),
tc2[~expected])
sc = tc2.copy()
sc.drop_duplicates(keep='last', inplace=True)
tm.assert_series_equal(sc, tc2[~expected])

expected = Series([False, True, True, False, True, True, False])
tm.assert_series_equal(tc2.duplicated(keep=False), expected)
tm.assert_series_equal(tc2.drop_duplicates(keep=False), tc2[~expected])
sc = tc2.copy()
sc.drop_duplicates(keep=False, inplace=True)
tm.assert_series_equal(sc, tc2[~expected])

@pytest.mark.parametrize("is_ordered", [True, False])
def test_drop_duplicates_bool(self, is_ordered):
tc = Series(Categorical([True, False, True, False],
categories=[True, False], ordered=is_ordered))

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

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

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

def test_describe(self):
# string type
desc = self.factor.describe()
Expand Down