Skip to content

Quick Test update #893

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
JGSweets merged 3 commits into from
Jun 22, 2023
Merged

Quick Test update #893

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ce1fc8e
update
taylorfturner Jun 21, 2023
e9f5da7
string in list
taylorfturner Jun 22, 2023
3c3c07c
formatting
taylorfturner Jun 22, 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
34 changes: 8 additions & 26 deletions dataprofiler/tests/profilers/test_column_profile_compilers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -774,7 +774,7 @@ def test_json_decode_after_update(self, mock_instance):
self._setup_data_labeler_mock(mock_instance)
mock_instance._default_model_loc = "structured_model"

data = pd.Series(["-2", "-1", "1", "15"], name="test")
data = pd.Series(["2", "-1", "1", "2"], name="test")
with test_utils.mock_timeit():
expected_compiler = col_pro_compilers.ColumnDataLabelerCompiler(data)

Expand All @@ -784,36 +784,18 @@ def test_json_decode_after_update(self, mock_instance):
test_utils.assert_profiles_equal(deserialized, expected_compiler)
# assert before update
assert deserialized.report().get("data_label", None) == "a|b"
assert (
sum(
[
v
for k, v in deserialized.report()
.get("statistics", None)
.get("avg_predictions", None)
.items()
]
)
== 1.0
)
assert deserialized.report().get("statistics", {}).get(
"data_label_representation", None
) == {"a": 0.5, "b": 0.5}

new_data = pd.Series(list(range(100))).apply(str)
new_data = pd.Series(["100"])

# validating update after deserialization with a few small tests
deserialized.update_profile(new_data)
assert deserialized.report().get("data_label", None) == "a|b"
assert (
sum(
[
v
for k, v in deserialized.report()
.get("statistics", None)
.get("avg_predictions", None)
.items()
]
)
== 1.0
)
assert deserialized.report().get("statistics", {}).get(
"data_label_representation", None
) == {"a": 0.6, "b": 0.4}


class TestUnstructuredCompiler(unittest.TestCase):
Expand Down