Skip to content

chore: update deps #3284

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
mikewilli merged 5 commits into from
Jul 2, 2026
Merged

chore: update deps #3284

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
281150d
chore: update deps
mikewilli Jun 30, 2026
d4847fd
fix dask plugin method
mikewilli Jun 30, 2026
33da5ea
fix test for new pandas version
mikewilli Jul 1, 2026
539c27a
fix integration tests for pandas v3
mikewilli Jul 1, 2026
059fd3f
bump mozanalysis to latest
mikewilli Jul 2, 2026
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 jetstream/analysis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1296,7 +1296,7 @@ def run(

if self.log_config:
log_plugin = LogPlugin(self.log_config)
client.register_worker_plugin(log_plugin)
client.register_plugin(log_plugin)

# add profiling plugins
# resource_profiling_plugin = ResourceProfilingPlugin(
Expand Down
41 changes: 23 additions & 18 deletions jetstream/tests/integration/test_analysis_integration.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
from metric_config_parser.statistic import Statistic
from mozanalysis.metrics import agg_sum
from mozilla_nimbus_schemas.experimenter_apis.experiments import RandomizationUnit
from mozilla_nimbus_schemas.jetstream import AnalysisBasis
from mozilla_nimbus_schemas.jetstream import AnalysisBasis, Statistics

from jetstream.analysis import Analysis
from jetstream.bigquery_client import BigQueryClient
Expand Down Expand Up @@ -229,14 +229,14 @@ def test_metrics(
).to_dataframe()

count_by_branch = stats.query("statistic == 'count'").set_index("branch")
assert count_by_branch.loc["branch1", "point"][0] == 1.0
assert count_by_branch.loc["branch2", "point"][0] == 1.0
assert count_by_branch.loc["branch1", "point"].iloc[0] == 1.0
assert count_by_branch.loc["branch2", "point"].iloc[0] == 1.0

if count_by_branch.loc["branch2", "analysis_basis"][0] == "exposures":
assert count_by_branch.loc["branch2", "analysis_basis"][1] == "enrollments"
if count_by_branch.loc["branch2", "analysis_basis"].iloc[0] == "exposures":
assert count_by_branch.loc["branch2", "analysis_basis"].iloc[1] == "enrollments"
else:
assert count_by_branch.loc["branch2", "analysis_basis"][0] == "enrollments"
assert count_by_branch.loc["branch2", "analysis_basis"][1] == "exposures"
assert count_by_branch.loc["branch2", "analysis_basis"].iloc[0] == "enrollments"
assert count_by_branch.loc["branch2", "analysis_basis"].iloc[1] == "exposures"

assert (
client.client.get_table(
Expand Down Expand Up @@ -396,14 +396,14 @@ def test_discrete_metrics(
assert len(stats[stats["metric"] == "active_hours_doubled"]) == 12

count_by_branch = stats.query("statistic == 'count'").set_index("branch")
assert count_by_branch.loc["branch1", "point"][0] == 1.0
assert count_by_branch.loc["branch2", "point"][0] == 1.0
assert count_by_branch.loc["branch1", "point"].iloc[0] == 1.0
assert count_by_branch.loc["branch2", "point"].iloc[0] == 1.0

if count_by_branch.loc["branch2", "analysis_basis"][0] == "exposures":
assert count_by_branch.loc["branch2", "analysis_basis"][1] == "enrollments"
if count_by_branch.loc["branch2", "analysis_basis"].iloc[0] == "exposures":
assert count_by_branch.loc["branch2", "analysis_basis"].iloc[1] == "enrollments"
else:
assert count_by_branch.loc["branch2", "analysis_basis"][0] == "enrollments"
assert count_by_branch.loc["branch2", "analysis_basis"][1] == "exposures"
assert count_by_branch.loc["branch2", "analysis_basis"].iloc[0] == "enrollments"
assert count_by_branch.loc["branch2", "analysis_basis"].iloc[1] == "exposures"

def test_metrics_preenrollment(
self,
Expand Down Expand Up @@ -870,10 +870,10 @@ def test_no_enrollments(
).to_dataframe()

count_by_branch = stats.query("statistic == 'count'").set_index("branch")
assert count_by_branch.loc["a", "point"][0] == 0.0
assert count_by_branch.loc["a", "point"][1] == 0.0
assert count_by_branch.loc["b", "point"][0] == 0.0
assert count_by_branch.loc["b", "point"][1] == 0.0
assert count_by_branch.loc["a", "point"].iloc[0] == 0.0
assert count_by_branch.loc["a", "point"].iloc[1] == 0.0
assert count_by_branch.loc["b", "point"].iloc[0] == 0.0
assert count_by_branch.loc["b", "point"].iloc[1] == 0.0
assert len(count_by_branch.loc["b", "analysis_basis"]) == 2

assert (
Expand Down Expand Up @@ -1302,11 +1302,16 @@ def test_statistics_export(
"""
)

statistics_export_data = query_job.to_dataframe().to_dict(orient="records")
# drop NaN before validation to match BQ NDJSON extract behavior
statistics_export_data = [
{k: v for k, v in record.items() if v == v}
for record in query_job.to_dataframe().to_dict(orient="records")
]
Comment on lines +1305 to +1309

@mikewilli mikewilli Jul 2, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

This appears to cover a scenario that won't happen because to_dict already converts pd.NA to None. We can revisit if the test starts failing, but I'm satisfied that this covers the expectation here.

schema = json.loads(
(Path(__file__).parent.parent / "data/Statistics_v1.0.json").read_text()
)
jsonschema.validate(statistics_export_data, schema)
Statistics.model_validate(statistics_export_data)

def test_subset_metric_table(
self,
Expand Down
2 changes: 1 addition & 1 deletion jetstream/tests/test_statistics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -655,7 +655,7 @@ def test_population_ratio_non_existing_metrics(self):
{"branch": ["treatment"] * 10 + ["control"] * 10, "ad_ratio": np.nan}
)
error_str = (
"None of [Index(['non_existing', 'non_existing'], dtype='object')] are in the [columns]"
"None of [Index(['non_existing', 'non_existing'], dtype='str')] are in the [columns]"
)
with pytest.raises(Exception, match=re.escape(error_str)):
stat.transform(test_data, "ad_ratio", "control", None, AnalysisBasis.ENROLLMENTS, "all")
Expand Down
Loading
Loading