You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Sven Geboers
d2310edfc4
feat(right-wing): LLM-based policy extremity scoring
Implements U4: extremity_scorer.py uses ai_provider.chat_completion_json_parallel
with a JSON schema enforcing integer 1-5 + Dutch explanation.
Design:
- Batch size 10, max_workers 5 for parallel API calls
- Prompt asks for concrete policy + radicalism score in Dutch
- Stores results in table (motion_id, score, explanation, error)
- Updates with yearly averages
- Default sample=50 for validation; --sample -1 scores all motions
Sample validation (50 motions): scores distributed 1→2, 2→34, 3→7, 4→7,
yearly averages ~2.0-2.5 (mild-to-moderate radicalism).
|
1 month ago |
| .. |
|
right_wing
|
feat(right-wing): LLM-based policy extremity scoring
|
1 month ago |
|
tabs
|
feat: agent-native refactor, SVD consistency fixes, UX cleanup, mobile support
|
2 months ago |
|
__init__.py
|
feat(pipeline): add orchestrator CLI, analysis modules, and ActorFractie ingestion
|
3 months ago |
|
axis_classifier.py
|
refactor: remove Stemgedrag cohesie section and fallback axis message
|
3 months ago |
|
clustering.py
|
refactor: make duckdb imports optional in analysis modules
|
2 months ago |
|
config.py
|
infra: fix CI, config, docker-compose, README, and pre-commit
|
2 months ago |
|
explorer_data.py
|
feat: agent-native refactor, SVD consistency fixes, UX cleanup, mobile support
|
2 months ago |
|
political_axis.py
|
Use aligned PCA scores for all SVD components 1-10
|
2 months ago |
|
projections.py
|
refactor: extract data loading and trajectory logic from explorer.py
|
3 months ago |
|
svd_labels.py
|
fix: resolve SVD axis label alignment and score mismatch in tijdtraject view
|
2 months ago |
|
trajectory.py
|
refactor: make duckdb imports optional in analysis modules
|
2 months ago |
|
visualize.py
|
feat: complete parliamentary embedding pipeline with full historical coverage
|
3 months ago |
