Document all dataclass/ classes across API Reference and Architecture
- API-Reference: extend `from eruption_forecast.dataclass import (...)`
block to pull in StationData plus the four
ClassifierEnsembleSummary types; add a new
"ClassifierEnsembleSummary family" section (ProbabilityPick,
SeedSummary, EruptionWindow, ClassifierEnsembleSummary) with
builder / consumer pointers and None-vs-guaranteed invariants;
add a new StationData section with fields, derived nslc / nslct,
a runnable example, and the raised ValueError cases.
- Architecture: add SeedSummary to the classifier_ensemble_summary.py
tree comment (was missing).
460c976
Sync wiki from repo
- API-Reference.md: expanded (+133 lines)
- Architecture.md, Explanation-Workflow.md, Output-Structure.md, Visualization.md: updated
- figures/: add pipeline_overview{,_v1,_v2}.png
3c89b07
Sync wiki with feature alias utilities
- API-Reference: add "Feature alias utilities" section covering the writer/reader/backfill helpers, label formatters, and heatmap label_style
- Architecture: refresh utils/pathutils, utils/dataframe, utils/formatting function inventories
- Output-Structure: note alias/description columns on top_features CSVs and reference load_feature_aliases/update_top_features_csv
356257b
docs(feature-count-sweep): add experimental sweep page + surface at entry points
New page:
- Feature-Count-Sweep.md — full coverage of FeatureCountSweep and
sweep_feature_count with a prominent Experimental warning, Quick Start
snippet, forecast-vs-cv mode table, estimator_mode trade-off, fail-fast
behaviour on missing prediction-matrix features, EvaluationModel
prediction-reuse wiring (with build_label shortcut), 1-SE parsimony
rule, complete example, and full constructor / function reference.
Cross-links + surfaces:
- Home.md — new nav row (marked Experimental).
- Training-Workflow.md — Post-Hoc top_n_features Sweep sub-section with
a minimal runnable snippet and link to the deep-dive page.
- API-Reference.md — FeatureCountSweep (Experimental) section covering
constructor, .fit(...), sweep_feature_count(...), and persistence.
- Architecture.md — feature_count_sweep.py added to the features/
module listing.
- Output-Structure.md — sweep outputs nested under
training/features/{cv-slug}/sweep/{mode}/{classifier-name}/ and a
matching row in the What Lives Where cheat sheet.
Also captures accumulated smaller edits since the last wiki push
(evaluation, explanation, output-structure clarifications).
70e8b66
docs(usage,pipeline): surface the explain stage
- Usage.md: add explain() to Quick Start, Stage Cheat Sheet, and the
annotated example (mirroring main.py:100-107). Order the annotated
example as evaluate -> compare -> explain so .compare() stays with
the evaluation stage and explain() sits last.
- Pipeline-Walkthrough.md: update the Research Workflow intro/blurb,
add an explain box to the main.py stage-flow diagram, and rewrite
the "Optional: fm.explain(...)" per-stage note (it is no longer
optional and is called in main.py). Diagram flows
calculate -> train -> predict -> evaluate -> compare -> explain.
870bdd5
docs(prediction): document use_features_from modes
- Prediction-Workflow: add "Feature Scoping via use_features_from" section
covering the three modes ("all" / "files" / "training"), failure-mode
table, cache implications, and mode chooser.
- Configuration: add use_features_from, features_matrix_path,
label_features_csv, enable_segments_plot to the predict YAML block.
- API-Reference: extend fm.predict() signature with the four new kwargs
plus a compact mode table.
- Usage: add "Reuse features already selected during train()" variant.
ba053c9
docs(prediction): document load_features() shortcut
Adds a "Reuse a feature matrix from a prior run" section covering
PredictionModel.load_features() and the ForecastModel.predict()
features_matrix_path / label_features_csv shortcut. Mirrors the
existing TrainingModel.load_features() section.
35c5624
Sync wiki from eruption-forecast/wiki
e5f04a6
Update Training-Workflow.md
1fdcc85
Sync wiki from eruption-forecast/wiki
Adds Explanation-Workflow page and refreshes existing pages.
ea0e128
Full rewrite of all 13 wiki pages against current src/ surface
Realigned with the post-ft/metrics-ensemble model/ refactor: dropped
references to removed ModelTrainer/ModelPredictor/ModelEvaluator/
MultiModelEvaluator and the old extract_features → train → forecast API;
documented the current TrainingModel/PredictionModel/EvaluationModel +
MetricsEnsemble stack, the BaseModel + CacheModel mixin pattern, and the
scenarios.py workflow.
Deleted 5 superseded pages (Installation, Quick-Start, Classifiers-and-CV,
Evaluation-and-Forecasting, Training-Workflows). Created 5 new pages
(Getting-Started, Usage, Training-Workflow, Prediction-Workflow,
Evaluation-Workflow). Rewrote 8 in place (Home, Data-Sources,
Pipeline-Walkthrough, Visualization, Configuration, Output-Structure,
Architecture, API-Reference). Final count 13 pages; no dead old links.
bf6bedb
Fix stale references: ClassifierEnsembler typo and merged_model_ filenames
8d4e9e7
Update docs: SeedEnsemble filename, ClassifierEnsembler.pkl, ModelPredictor fix
ab00982
Remove docs/ reference; wiki/ is now the single source of truth
603f47a
Update wiki: sync all pages from local wiki/ directory (2026-04-26)
b33c1bb
Update Architecture: fix ShannonEntropy typo, remove predict()/predict_best(), add resampled cache, update utils tables, update threshold default to 0.7
4195030
Update wiki: API-Reference, Architecture, Pipeline-Walkthrough, Visualization
3d744e7
docs: sync wiki pages from local repository
f8c65cf
Add GPU acceleration documentation for XGBoost
Document use_gpu and gpu_id parameters in ModelTrainer, parallelism
restrictions when GPU is active, and GPU-capable classifier annotations
for xgb and voting across Training-Workflows, Classifiers-and-CV,
and API-Reference pages.
3da888e
docs: add Research Workflow (workflow.py) diagram to Architecture
71c589d
docs: add Research Workflow (workflow.py) diagram to Architecture
66dd7d4
docs: sync remaining wiki pages with local changes
- Classifiers-and-CV: fix output path (model-only → evaluations)
- Home: add data_container.py and sources/ to package layout tree
- Pipeline-Walkthrough: fix model-only → predictions output paths;
add 'Merge Seed Models' section with SeedEnsemble diagram + example
- Quick-Start: fix train() output path (model-only → predictions)
- Training-Workflows: add 'Merging Seed Models' section with
merge_models() / merge_classifier_models() diagram and examples
c020970
docs: sync Architecture wiki with docs/architecture.md
- Add Pipeline Overview ASCII diagram (was missing from wiki)
- Add per-component narrative sections (Tremor, Label, Features, Model)
with code examples for CalculateTremor (SDS + FDSN workflows)
- Add Data Source Adapters section
- Add Configuration Dataclasses section
- Preserve full model class relationship diagrams (Training + Evaluation
phases, SeedEnsemble, ClassifierEnsemble, scope summary table)
- Add seed_ensemble.py and classifier_ensemble.py to package layout tree
9a39264
docs: update SHAP sections to reflect beeswarm refactor
- Replace all 'mean |SHAP| bar chart' references with 'beeswarm showing
feature contributions across seeds'
- Update plot_aggregate_shap_summary examples: return is shap.Explanation
not pd.DataFrame
- Add aggregate_shap_summary.png + .pkl to output structure tree
- Sync API-Reference and Evaluation-and-Forecasting tables accordingly
b0e7f8f
Destroyed Home Test (markdown)
b22b3a7
Add wiki pages (13 pages)
1da4e5b