feat(pipeline): statistical export, verified claims, and i18n restructuring - #20
Merged
Merged
Conversation
- materializes t-tests, chi-square, Bonferroni/BH corrections and bootstrap CIs as 4 CSVs in data/analysis/ - wired into run_pipeline as --step stats"
- float rounding in p * n / rank could land one ulp below the raw p-value, breaking the adjusted >= raw invariant - document Yates continuity correction on 2x2 tables and the pooled-SD Cohen's d convention alongside Welch's t-test
- p-value ranges, correction monotonicity, CI ordering, family membership, conditional-population flags - byte-identical determinism across two runs (fixed bootstrap seed) - scipy precision-loss warning silenced in this module only: expected on the near-constant synthetic sample, meaningful in production
- NB04: all 8 signals significant after both corrections (was 'most'); verified ranking with d values replaces hedged claim; effect sizes span small-to-large (was 'small-to-medium'); ghost gap quantified (4.8% vs 54.3%) and BQ5 definition divergence documented - NB05: Cramer's V peaks at 0.15 (was 'below 0.15'); numeric demographic d below 0.3 (was 'below 0.2', actual 0.28 and 0.21); behavioral range 0.5-0.9 (was '0.3-0.6'); ratio 2-4x (was '2-5x')
- bilingual scope narrows to business-facing documents (README, REPORT) - structural parity tests removed together with the mirrors" -- notebooks/it tests/test_notebooks_it.py
- relative links fixed in the moved files (language switcher, LICENSE, report and docs paths, figure paths)
- tests running main() without --step reached the real step 04, which opens the real DuckDB file: green locally only because db exists, red in CI - add --step stats selection test and stats error propagation test for symmetry with the other steps
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #20 +/- ##
==========================================
- Coverage 93.53% 90.97% -2.57%
==========================================
Files 9 10 +1
Lines 325 443 +118
==========================================
+ Hits 304 403 +99
- Misses 21 40 +19 ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
data/analysis/(t-tests, chi-square, Bonferroni and BH corrections, bootstrap CIs)_ITsuffixes toit/subfolders