Skip to content

Added testing for values for test_json_decode_after_update #915

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 2 commits into from
Jun 27, 2023
Merged

Added testing for values for test_json_decode_after_update #915

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cea95f6
Added testing for values for test_json_decode_after_update
ksneab7 Jun 27, 2023
1427f18
Merge branch 'feature/profile-serialization' into more_in_depth_test
ksneab7 Jun 27, 2023
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
26 changes: 11 additions & 15 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 @@ -2275,12 +2275,7 @@ def test_json_decode_after_update(self, mock_DataLabeler, *mocks):
mock_DataLabeler.load_from_library.return_value = mock_labeler

fake_profile_name = None
df_structured = pd.DataFrame(
[
["-1.5", "3.0"],
["a", "z"],
]
).T
df_structured = pd.DataFrame([["1.5", "a", "4"], ["3.0", "z", 7]])

# update mock for 2 confidence values for 2 possible classes
mock_labeler.predict.side_effect = lambda *args, **kwargs: {
Expand All @@ -2299,20 +2294,21 @@ def test_json_decode_after_update(self, mock_DataLabeler, *mocks):

df_structured = pd.DataFrame(
[
[
4.0, # add existing
15.0, # add new
],
["c", "nan"],
[4.0, "nan", "15.0"], # partial nan row
["nan", "nan", "nan"], # Full nan row
["1.5", "a", "4"], # Repeated from previous update
]
).T
)

# validating update after deserialization
deserialized.update_profile(df_structured)

assert deserialized.total_samples == 4
assert deserialized.row_has_null_count == 1
assert deserialized.row_is_null_count == 0
assert deserialized.total_samples == 5
assert deserialized._max_col_samples_used == 5
assert deserialized._min_col_samples_used == 5
assert deserialized.row_has_null_count == 2
assert deserialized.row_is_null_count == 1
assert deserialized._get_unique_row_ratio() == 0.80
assert deserialized.file_type == "<class 'pandas.core.frame.DataFrame'>"


Expand Down