Skip to content
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

List now maintains same visual data representation #363

Merged
merged 3 commits into from
Jul 28, 2021
Merged

List now maintains same visual data representation #363

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0227c03
fix: list now maintains same visual data representation
JGSweets Jul 27, 2021
f2c2865
fix: to account for multi col lists
JGSweets Jul 27, 2021
1e5face
fix: bug bc my test data was float, comment was wrong
JGSweets Jul 27, 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
2 changes: 1 addition & 1 deletion dataprofiler/profilers/profile_builder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1849,7 +1849,7 @@ def _update_profile_from_chunk(self, data, sample_size,
if isinstance(data, pd.Series):
data = data.to_frame()
elif isinstance(data, list):
data = pd.DataFrame(data)
data = pd.DataFrame(data, dtype=object)

# Calculate schema of incoming data
mapping_given = defaultdict(list)
Expand Down
15 changes: 13 additions & 2 deletions dataprofiler/tests/profilers/test_profile_builder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,7 +86,13 @@ def test_bad_input_data(self, *mocks):
@mock.patch('dataprofiler.profilers.profile_builder.'
'StructuredProfiler._update_correlation')
def test_list_data(self, *mocks):
data = [1, None, 3, 4, 5, None, 1]
data = [[1, 1],
[None, None],
[3, 3],
[4, 4],
[5, 5],
[None, None],
[1, 1]]
with test_utils.mock_timeit():
profiler = dp.StructuredProfiler(data)

Expand All @@ -97,10 +103,15 @@ def test_list_data(self, *mocks):
self.assertEqual(2, profiler.row_is_null_count)
self.assertEqual(7, profiler.total_samples)
self.assertEqual(5, len(profiler.hashed_row_dict))
self.assertListEqual([0], list(profiler._col_name_to_idx.keys()))
self.assertListEqual([0, 1], list(profiler._col_name_to_idx.keys()))
self.assertIsNone(profiler.correlation_matrix)
self.assertDictEqual({'row_stats': 1}, profiler.times)

# validates the sample out maintains the same visual data format as the
# input.
self.assertListEqual(['5', '1', '1', '3', '4'],
profiler.profile[0].sample)

@mock.patch('dataprofiler.profilers.profile_builder.'
'ColumnPrimitiveTypeProfileCompiler')
@mock.patch('dataprofiler.profilers.profile_builder.'
Expand Down