Skip to content

28/statistical hypothesis testing - #31

Merged
Krisenberg merged 12 commits into
mainfrom
28/statistical-hypothesis-testing
Nov 7, 2026
Merged

Krisenberg merged 12 commits into
mainfrom
28/statistical-hypothesis-testing

Conversation

@Krisenberg

Copy link
Copy Markdown
Owner

No description provided.

…h args to SASRecTrainingPipeline.train() method to let the caller explicitly specify where to save best-performing model checkpoint and where corresponding ImpactConfig YAML snapshot
…DCG@k metrics to allow collecting raw, unaggregated metrics (for statistical testing), make the functions computing aggregated metrics (means) simple wrappers over per-sample computations
…eval pipeline to calculate both batch-level metric sums (unnormalized) and raw per-sample metric values for statistical testing
…onPipeline to allow the caller specify whether only aggregated metrics should be computed or, optionally, aggregated metrics + raw per-sample metrics (for statistical testing)
…ain entrypoint to let the caller optionally save raw metrics (for statistical testing) specifying where
…pothesis testing implementations (e.g. built-in Wilcoxon test)
…r IMPACT evaluation using Wilcoxon signed-rank test; add scipy-stubs library to resolve typing issues
…point, tables_data.py for pure table data computation and tables_render_latex.py for rendering the computed data into LaTeX tables
…tput LaTeX code for the data funnel stats table (positioning and number format)
@Krisenberg Krisenberg self-assigned this Nov 7, 2026
@Krisenberg Krisenberg added the enhancement New feature or request label Nov 7, 2026
@Krisenberg
Krisenberg merged commit 6b245e0 into main Nov 7, 2026
0 of 3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant