loboprajwal/pfz-advisory-india

# 1. Clone / enter project
cd pfz_project

# 2. Python environment
python3 -m venv venv
source venv/bin/activate          # Windows: venv\Scripts\activate
pip install -r requirements.txt

# 3. Copy your existing files
cp /path/to/ecofish_golden.db  data/raw/cmfri/
cp /path/to/marine_species_range_shift.ipynb  notebooks/

# 4. Set environment variables
cp config/.env.example config/.env
# Edit config/.env with your API keys (see API_KEYS.md)

# 5. Run the full pipeline (first time ~2-4 hours, fetches all data)
python scripts/run_pipeline.py --species-all --year-start 2005 --year-end 2025

# 6. Start the API
uvicorn api.main:app --reload --port 8000

# 7. Start the frontend (new terminal)
cd frontend
npm install
npm run dev
# Open http://localhost:5173

pfz_project/
├── README.md
├── requirements.txt
├── config/
│   ├── .env.example
│   ├── settings.py           # All config loaded here
│   └── species_config.py     # 15 target species definitions
├── pipeline/
│   ├── 01_fetch_occurrences.py   # OBIS + GBIF + iNaturalist
│   ├── 02_fetch_satellite.py     # Bio-Oracle + CMEMS SST/Chl/SSH
│   ├── 03_build_feature_grid.py  # 0.1° grid feature matrix
│   ├── 04_train_models.py        # XGBoost per species
│   ├── 05_run_inference.py       # Daily PFZ raster generation
│   └── 06_export_tiles.py        # GeoJSON + MBTiles output
├── api/
│   ├── main.py               # FastAPI app
│   └── routers/
│       ├── pfz.py            # /api/pfz/daily, /api/pfz/nodes
│       ├── species.py        # /api/species/{name}/map
│       └── catch.py          # /api/catch/history
├── frontend/
│   ├── package.json
│   └── src/
│       ├── App.jsx           # Root with Leaflet map
│       ├── components/
│       │   ├── PfzMap.jsx        # Main Leaflet map
│       │   ├── SpeciesPanel.jsx  # Left sidebar
│       │   ├── NodeMarkers.jsx   # 1223 coastal nodes
│       │   └── AdvisoryCard.jsx  # Node popup
│       └── utils/
│           └── api.js        # Fetch helpers
├── data/
│   ├── raw/
│   │   ├── occurrences/      # CSV per species from OBIS/GBIF
│   │   ├── satellite/        # NetCDF/CSV from Bio-Oracle
│   │   └── cmfri/            # ecofish_golden.db lives here
│   ├── processed/            # Merged feature matrices
│   ├── models/               # Trained XGBoost .pkl files
│   └── tiles/                # GeoJSON + MBTiles outputs
├── notebooks/
│   ├── marine_species_range_shift.ipynb   # YOUR EXISTING FILE
│   └── 02_model_training_eda.ipynb
└── scripts/
    ├── run_pipeline.py       # Orchestrator
    └── seed_incois_nodes.py  # Download 1223 node coords