mirror of
https://github.com/acamarata/pray-calc-ml.git
synced 2026-06-30 19:04:26 +00:00
3b8c665aca
Tracked: BSRN/SURFRAD processors (reference, excluded from pipeline), GaN-MN downloader, academic paper fetcher, Madrid SQM processor, ML analysis scripts (src/analyze/), umsu_medan_2024 raw sightings. Gitignored: global_extrapolator, instant_1m_injector/vectorized, massive_harvest_engine, massive_sqm_downloader, global_sqm_harvester, run_infinite_pipeline.sh, run_massive_collection.sh, search_papers.py (agent-generated experimental scripts, not part of core pipeline).
105 lines
2.2 KiB
Text
105 lines
2.2 KiB
Text
__pycache__/
|
|
*.py[cod]
|
|
*.egg-info/
|
|
.eggs/
|
|
dist/
|
|
build/
|
|
.venv/
|
|
venv/
|
|
env/
|
|
.env
|
|
*.log
|
|
.DS_Store
|
|
.ipynb_checkpoints/
|
|
.jupyter/
|
|
# IDE directories
|
|
.vscode/
|
|
.idea/
|
|
*.suo
|
|
*.user
|
|
*.swp
|
|
*.swo
|
|
|
|
# AI agent working directories
|
|
.claude/
|
|
.codex/
|
|
.cursor/
|
|
.aider/
|
|
.aider.chat.history.md
|
|
.continue/
|
|
.windsurf/
|
|
.gemini/
|
|
.codeium/
|
|
|
|
# Raw scraped/downloaded files
|
|
data/raw/*.pdf
|
|
research/downloaded_papers/
|
|
research/raw_pdfs/
|
|
nohup.out
|
|
|
|
# Generated notebook outputs
|
|
data/processed/*.png
|
|
data/processed/*.svg
|
|
|
|
# Bulk data directories (too large for git, not curated)
|
|
data/cache/
|
|
data/raw/crawled/
|
|
data/raw/excluded/
|
|
data/raw/brin_multistation_raw/
|
|
data/raw/bsrn/
|
|
data/raw/tess/
|
|
data/raw/gan_mn/
|
|
data/raw/washetdonker/
|
|
data/raw/globe_at_night/
|
|
data/raw/surfrad/
|
|
data/raw/galicia_night_sky/
|
|
data/raw/india_twilight_photometer/
|
|
data/raw/madrid_sqm_evol/
|
|
data/raw/majadahonda_sqm_2019/
|
|
data/raw/massive_sqm/
|
|
|
|
# Excluded/duplicate raw sighting files (not in APPROVED_RAW_CSVS)
|
|
data/raw/raw_sightings/bsrn_*.csv
|
|
data/raw/raw_sightings/surfrad_*.csv
|
|
data/raw/raw_sightings/openfajr_*.csv
|
|
data/raw/raw_sightings/global_sqm_harvester_results.csv
|
|
data/raw/raw_sightings/web_*.csv
|
|
|
|
# Collection session logs and scratch
|
|
data/raw/collection_log*.txt
|
|
data/raw/sources_crawled.md
|
|
|
|
# Research scratch files (superseded by aggregate_d0_values.csv)
|
|
research/aggregate_d0_database.csv
|
|
research/aggregate_analysis.md
|
|
research/candidate_papers.json
|
|
research/mine_*.py
|
|
|
|
# Experimental collection scripts (not part of core pipeline)
|
|
src/autonomous_collect.py
|
|
src/compute_aggregate_times.py
|
|
src/collect/aladhan.py
|
|
src/collect/autonomous_collector.py
|
|
src/collect/aggregate_to_records.py
|
|
src/collect/bulk_generator.py
|
|
src/collect/bulk_runner.py
|
|
src/collect/cities.py
|
|
src/collect/collect_agent.py
|
|
src/collect/harvest.py
|
|
src/collect/jakim.py
|
|
src/collect/morocco.py
|
|
src/collect/muis_singapore.py
|
|
src/collect/openalex_harvester.py
|
|
src/collect/source_tracker.py
|
|
src/collect/waktusolat.py
|
|
src/collect/web_harvester.py
|
|
src/collect/global_extrapolator.py
|
|
src/collect/instant_1m_injector.py
|
|
src/collect/instant_1m_vectorized.py
|
|
src/collect/massive_harvest_engine.py
|
|
src/collect/massive_sqm_downloader.py
|
|
src/collect/global_sqm_harvester.py
|
|
run_infinite_pipeline.sh
|
|
run_massive_collection.sh
|
|
search_papers.py
|
|
.vscode/*
|