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

feat(nimbus): ingest DAU and its new statistic #12066

Merged
merged 6 commits into from
Feb 14, 2025
Merged

feat(nimbus): ingest DAU and its new statistic #12066

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
5dfe443
feat(nimbus): ingest DAU and its new statistic
mikewilli Jan 17, 2025
2a8556f
formatting
mikewilli Jan 21, 2025
6541cc9
Merge branch 'main' into 12065-dau-default-guardrail-ingest
mikewilli Jan 21, 2025
1a50b79
Merge branch 'main' into 12065-dau-default-guardrail-ingest
mikewilli Jan 22, 2025
b8edd86
Merge branch 'main' into 12065-dau-default-guardrail-ingest
mikewilli Feb 14, 2025
b06ba85
add tests for dau impact stat ingest
mikewilli Feb 14, 2025
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
3 changes: 2 additions & 1 deletion experimenter/experimenter/jetstream/client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,6 +106,7 @@ def get_results_metrics_map(
Metric.SEARCH: {Statistic.MEAN},
Metric.DAYS_OF_USE: {Statistic.MEAN},
Metric.USER_COUNT: {Statistic.COUNT, Statistic.PERCENT},
Metric.DAILY_ACTIVE_USERS: {Statistic.PER_CLIENT_DAU_IMPACT},
}
primary_metrics_set: set[str] = set()
primary_outcome_metrics: list[OutcomeMetric] = list(
Expand Down Expand Up @@ -159,7 +160,7 @@ def get_other_metrics_names_and_map(
other_metrics_map = {}

# This is an ordered list of priorities of stats to graph
priority_stats = [Statistic.MEAN, Statistic.BINOMIAL]
priority_stats = [Statistic.MEAN, Statistic.BINOMIAL, Statistic.PER_CLIENT_DAU_IMPACT]
other_data = [
data_point for data_point in data if data_point.metric not in results_metrics_map
]
Expand Down
5 changes: 4 additions & 1 deletion experimenter/experimenter/jetstream/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@ class Metric(StrEnum):
SEARCH = "search_count"
DAYS_OF_USE = "days_of_use"
USER_COUNT = "identity"
DAILY_ACTIVE_USERS = "client_level_daily_active_users_v2"


class Statistic(StrEnum):
Expand All @@ -44,6 +45,8 @@ class Statistic(StrEnum):
MEAN = "mean"
COUNT = "count"
POPULATION_RATIO = "population_ratio"
PER_CLIENT_DAU_IMPACT = "per_client_dau_impact"
LINEAR_MODEL_MEAN = "mean_lm"


class Segment(StrEnum):
Expand Down Expand Up @@ -294,7 +297,7 @@ def __init__(
pairwise_comparison_data.all.append(data_point)

def append_conversion_count(self, primary_metrics_set):
for branch_name in self.__fields__:
for branch_name in self.model_fields:
branch = getattr(self, branch_name)
branch_data = branch.branch_data
for primary_metric in primary_metrics_set:
Expand Down
6 changes: 3 additions & 3 deletions experimenter/experimenter/jetstream/tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ def fetch_experiment_data(experiment_id):
if experiment is not None and hasattr(experiment, "slug"):
failure_message += f"{experiment.slug} "
failure_message += f"failed: {e}"
logger.info(failure_message)
logger.error(failure_message)
raise e


Expand Down Expand Up @@ -60,15 +60,15 @@ def fetch_jetstream_data():
fetch_experiment_data.delay(experiment.id)
metrics.incr("fetch_jetstream_data.completed")
else:
metrics.incr("fetch_jetstream_data.skipped")
logger.info(
f"Skipping cache refresh for old experiment {experiment.name}"
f" ({experiment.slug})"
)
metrics.incr("fetch_jetstream_data.skipped")

except Exception as e:
metrics.incr("fetch_jetstream_data.failed")
logger.info(f"Fetching Jetstream data failed: {e}")
logger.error(f"Fetching Jetstream data failed: {e}")
raise e


Expand Down
23 changes: 23 additions & 0 deletions experimenter/experimenter/jetstream/tests/constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -411,6 +411,13 @@ def get_test_data(cls, primary_outcomes):
VARIANT_DATA_DEFAULT_METRIC_ROW_RATIO.statistic = Statistic.POPULATION_RATIO
VARIANT_DATA_DEFAULT_METRIC_ROW_RATIO.branch = "variant"

VARIANT_DATA_DEFAULT_METRIC_ROW_DAU_IMPACT = DATA_IDENTITY_ROW.copy()
VARIANT_DATA_DEFAULT_METRIC_ROW_DAU_IMPACT.metric = "some_dau_impact"
VARIANT_DATA_DEFAULT_METRIC_ROW_DAU_IMPACT.statistic = (
Statistic.PER_CLIENT_DAU_IMPACT
)
VARIANT_DATA_DEFAULT_METRIC_ROW_DAU_IMPACT.branch = "variant"

VARIANT_DATA_DEFAULT_METRIC_ROW_BINOMIAL = DATA_IDENTITY_ROW.copy()
VARIANT_DATA_DEFAULT_METRIC_ROW_BINOMIAL.metric = "another_count"
VARIANT_DATA_DEFAULT_METRIC_ROW_BINOMIAL.statistic = Statistic.BINOMIAL
Expand Down Expand Up @@ -482,6 +489,16 @@ def get_test_data(cls, primary_outcomes):
AnalysisBasis.EXPOSURES
)

EXPOSURES_VARIANT_DATA_DEFAULT_METRIC_ROW_DAU_IMPACT = DATA_IDENTITY_ROW.copy()
EXPOSURES_VARIANT_DATA_DEFAULT_METRIC_ROW_DAU_IMPACT.metric = "some_dau_impact"
EXPOSURES_VARIANT_DATA_DEFAULT_METRIC_ROW_DAU_IMPACT.statistic = (
Statistic.PER_CLIENT_DAU_IMPACT
)
EXPOSURES_VARIANT_DATA_DEFAULT_METRIC_ROW_DAU_IMPACT.branch = "variant"
EXPOSURES_VARIANT_DATA_DEFAULT_METRIC_ROW_DAU_IMPACT.analysis_basis = (
AnalysisBasis.EXPOSURES
)

EXPOSURES_VARIANT_DATA_DEFAULT_METRIC_ROW_BINOMIAL = DATA_IDENTITY_ROW.copy()
EXPOSURES_VARIANT_DATA_DEFAULT_METRIC_ROW_BINOMIAL.metric = "another_count"
EXPOSURES_VARIANT_DATA_DEFAULT_METRIC_ROW_BINOMIAL.statistic = Statistic.BINOMIAL
Expand Down Expand Up @@ -514,6 +531,7 @@ def get_test_data(cls, primary_outcomes):
VARIANT_DATA_ROW.dict(exclude_none=True),
VARIANT_DATA_DEFAULT_METRIC_ROW_MEAN.dict(exclude_none=True),
VARIANT_DATA_DEFAULT_METRIC_ROW_RATIO.dict(exclude_none=True),
VARIANT_DATA_DEFAULT_METRIC_ROW_DAU_IMPACT.dict(exclude_none=True),
VARIANT_DATA_DEFAULT_METRIC_ROW_BINOMIAL.dict(exclude_none=True),
VARIANT_POSITIVE_SIGNIFICANCE_DATA_ROW.dict(exclude_none=True),
VARIANT_NEGATIVE_SIGNIFICANCE_DATA_ROW.dict(exclude_none=True),
Expand All @@ -526,6 +544,7 @@ def get_test_data(cls, primary_outcomes):
EXPOSURES_VARIANT_DATA_ROW.dict(exclude_none=True),
EXPOSURES_VARIANT_DATA_DEFAULT_METRIC_ROW_MEAN.dict(exclude_none=True),
EXPOSURES_VARIANT_DATA_DEFAULT_METRIC_ROW_RATIO.dict(exclude_none=True),
EXPOSURES_VARIANT_DATA_DEFAULT_METRIC_ROW_DAU_IMPACT.dict(exclude_none=True),
EXPOSURES_VARIANT_DATA_DEFAULT_METRIC_ROW_BINOMIAL.dict(exclude_none=True),
EXPOSURES_VARIANT_POSITIVE_SIGNIFICANCE_DATA_ROW.dict(exclude_none=True),
EXPOSURES_VARIANT_NEGATIVE_SIGNIFICANCE_DATA_ROW.dict(exclude_none=True),
Expand Down Expand Up @@ -598,6 +617,7 @@ def get_test_data(cls, primary_outcomes):
"identity": ABSOLUTE_METRIC_DATA_A.dict(exclude_none=True),
"some_count": EMPTY_METRIC_DATA.dict(exclude_none=True),
"some_ratio": EMPTY_METRIC_DATA.dict(exclude_none=True),
"some_dau_impact": EMPTY_METRIC_DATA.dict(exclude_none=True),
"another_count": EMPTY_METRIC_DATA.dict(exclude_none=True),
"retained": DIFFERENCE_METRIC_DATA_WEEKLY_NEUTRAL_VARIANT.dict(
exclude_none=True
Expand All @@ -621,6 +641,7 @@ def get_test_data(cls, primary_outcomes):
"identity": ABSOLUTE_METRIC_DATA_A.dict(exclude_none=True),
"some_count": ABSOLUTE_METRIC_DATA_A.dict(exclude_none=True),
"some_ratio": EMPTY_METRIC_DATA.dict(exclude_none=True),
"some_dau_impact": ABSOLUTE_METRIC_DATA_A.dict(exclude_none=True),
"another_count": ABSOLUTE_METRIC_DATA_A.dict(exclude_none=True),
"retained": DIFFERENCE_METRIC_DATA_WEEKLY_NEGATIVE_CONTROL.dict(
exclude_none=True
Expand All @@ -645,6 +666,7 @@ def get_test_data(cls, primary_outcomes):
),
"some_count": EMPTY_METRIC_DATA.dict(exclude_none=True),
"some_ratio": EMPTY_METRIC_DATA.dict(exclude_none=True),
"some_dau_impact": EMPTY_METRIC_DATA.dict(exclude_none=True),
"another_count": EMPTY_METRIC_DATA.dict(exclude_none=True),
"default_browser_action": EMPTY_METRIC_DATA.dict(
exclude_none=True
Expand Down Expand Up @@ -673,6 +695,7 @@ def get_test_data(cls, primary_outcomes):
),
"some_count": ABSOLUTE_METRIC_DATA_F.dict(exclude_none=True),
"some_ratio": EMPTY_METRIC_DATA.dict(exclude_none=True),
"some_dau_impact": ABSOLUTE_METRIC_DATA_F.dict(exclude_none=True),
"another_count": ABSOLUTE_METRIC_DATA_F.dict(exclude_none=True),
"retained": DIFFERENCE_METRIC_DATA_OVERALL_NEGATIVE_CONTROL.dict(
exclude_none=True
Expand Down
2 changes: 2 additions & 0 deletions experimenter/experimenter/jetstream/tests/test_tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -448,6 +448,7 @@ def test_valid_results_data_parsed_and_stored(self, lifecycle):
Group.OTHER.value: {
"some_count": "Some Count",
"another_count": "Another Count",
"some_dau_impact": "Some Dau Impact",
},
},
"metadata": {
Expand Down Expand Up @@ -1048,6 +1049,7 @@ def test_results_data_with_zeros_parsed_and_stored(
Group.OTHER.value: {
"some_count": "Some Count",
"another_count": "Another Count",
"some_dau_impact": "Some Dau Impact",
},
},
"metadata": {},
Expand Down