Skip to content

fix: null_rep mat should calculate even if datetime #933

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
taylorfturner merged 1 commit into from
Jun 29, 2023
Merged

fix: null_rep mat should calculate even if datetime #933

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 @@ -2469,7 +2469,7 @@ def _update_null_replication_metrics(self, clean_samples: dict) -> None:
total_row_sum = np.asarray(
[
get_data_type_profiler(profile).sum
if get_data_type(profile)
if get_data_type(profile) not in [None, "datetime"]
else np.nan
for profile in self._profile
]
Expand Down
28 changes: 27 additions & 1 deletion dataprofiler/tests/profilers/test_profile_builder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,9 @@ def setUpClass(cls):
)
cls.aws_dataset = pd.read_csv(cls.input_file_path)
profiler_options = ProfilerOptions()
profiler_options.set({"data_labeler.is_enabled": False})
profiler_options.set(
{"data_labeler.is_enabled": False, "multiprocess.is_enabled": False}
)
with test_utils.mock_timeit():
cls.trained_schema = dp.StructuredProfiler(
cls.aws_dataset, len(cls.aws_dataset), options=profiler_options
Expand Down Expand Up @@ -2301,6 +2303,30 @@ def test_null_replication_metrics_calculation(self):
np.testing.assert_array_almost_equal([[20], [0]], column["class_sum"])
np.testing.assert_array_almost_equal([[10], [0]], column["class_mean"])

# account for datetime
data = pd.DataFrame(
{
"a": [3, 2, np.nan, 7, None],
"b": [10, 10, 1, 4, 2],
"c": ["2/2/2021", "2/5/2021", "2/9/2021", "2/21/2021", None],
}
)
profiler = dp.StructuredProfiler(data, options=profile_options)
expected_null_rep = {
0: {
"class_prior": [0.6, 0.4],
"class_sum": [[24.0, np.nan], [3.0, 0.0]],
"class_mean": [[8.0, np.nan], [1.5, 0.0]],
},
# 1: has not values bc none to replicate 100% real
2: {
"class_prior": [0.8, 0.2],
"class_sum": [[12.0, 25.0], [0.0, 2.0]],
"class_mean": [[3.0, 6.25], [0.0, 2.0]],
},
}
np.testing.assert_equal(expected_null_rep, profiler._null_replication_metrics)

def test_column_level_invalid_values(self):
data = pd.DataFrame([[1, 1], [9999999, 2], [3, 3]])

Expand Down