mirror of
https://github.com/hanzoai/insights.git
synced 2026-10-30 16:15:31 +00:00
zeekay
1b367e2b62
The tree was a debranded snapshot of upstream taken around 2026-02-20, and upstream has moved about five months since. This replaces it with upstream master, mechanically re-derived: bin/debrand does the rename, and the pipeline and squashed migrations are restored from the shipped tree. Not a merge. The previous import replaced the tree wholesale in a single commit, so there is no shared content history to merge against. Reproducing the rename on the new tree is what actually converges. What survives: .hanzo/workflows, the Dockerfiles and bin/docker* entrypoints, compose files, LLM.md, and insights/migrations. The squashed initial migration is load-bearing — the live database records it by name, so upstream's ~918 individual migrations cannot come back. Nine products are dropped as unreferenced. Twenty-one more that we do not run are kept anyway because the core app still imports them; unpicking those is a refactor and does not belong in a rebase. This base does not build yet, and the reasons are not in the rename: upstream now wants Python 3.13.13 against our 3.12.12 and Django 5.2 against our 4.2, and the dependency manifests still name upstream packages that we republish under our own names. Those are decisions, not renames.
51 lines
1.8 KiB
Python
51 lines
1.8 KiB
Python
"""
|
|
Analysis-health signals for experiments. Pure functions — no I/O.
|
|
|
|
Currently evaluates one signal: asymmetric `$multiple`-exclusion bias on uneven
|
|
splits. Designed to grow (SRM, low exposures, variant drift, ...) as additional
|
|
pure evaluators when needed.
|
|
"""
|
|
|
|
from insights.schema import BiasRisk, MultipleVariantHandling
|
|
|
|
from products.experiments.backend.variant_distribution import is_evenly_distributed
|
|
|
|
MULTIPLE_VARIANT_KEY = "$multiple"
|
|
|
|
# `$multiple` share above this triggers the warning. Below this, the asymmetric-
|
|
# exclusion effect on arm means is too small to matter in practice.
|
|
MULTIPLE_VARIANT_BIAS_THRESHOLD = 0.1 # on the 0-100 scale (0.1 = 0.1%)
|
|
|
|
|
|
def evaluate_bias_risk(
|
|
flag_variants: list[dict] | None,
|
|
multiple_variant_handling: MultipleVariantHandling,
|
|
total_exposures: dict[str, int],
|
|
) -> BiasRisk | None:
|
|
"""
|
|
Empirically observed multi-variant exclusion bias risk: uneven split + EXCLUDE
|
|
handling + observed `$multiple` share above the threshold.
|
|
Returns a `BiasRisk` only when all three conditions hold; `None` otherwise.
|
|
"""
|
|
if multiple_variant_handling != MultipleVariantHandling.EXCLUDE:
|
|
return None
|
|
|
|
variants = flag_variants or []
|
|
if not variants:
|
|
return None
|
|
|
|
rollout_percentages = [variant.get("rollout_percentage", 0) for variant in variants]
|
|
if is_evenly_distributed(rollout_percentages):
|
|
return None
|
|
|
|
total_observed = sum(total_exposures.values())
|
|
if total_observed <= 0:
|
|
return None
|
|
|
|
multiple_observed = total_exposures.get(MULTIPLE_VARIANT_KEY, 0)
|
|
multiple_variant_percentage = (multiple_observed / total_observed) * 100
|
|
if multiple_variant_percentage <= MULTIPLE_VARIANT_BIAS_THRESHOLD:
|
|
return None
|
|
|
|
return BiasRisk(multiple_variant_percentage=multiple_variant_percentage)
|