Akiba So
fc468464b2
Context: Build a spatial risk assessment system correlating air quality data with children's respiratory disease incidence across Wuhan. Approach: FastAPI backend serving PostGIS spatial queries, React frontend with Deck.gl maps, and a PyTorch SpatialTemporalGCN pipeline for multi-day (1d/3d/7d) risk prediction. Changes: - backend/ — FastAPI API with auth (JWT), alerts, risk analysis, geocoded case data, grid statistics, and report endpoints - frontend/ — React dashboard with interactive risk maps, alert monitoring, district comparison charts, and timeline player - models/ — SpatialTemporalGCN model with trained weights and ONNX export for inference - scripts/ — ETL pipeline for weather + medical data, grid generation, feature engineering, training, and daily inference - deploy/ — Docker Compose configs for backend, frontend, and MLflow - docs/ — API docs, deployment guide, user guide, and code review Impact: Enables spatial risk visualization, alert monitoring, and ML-driven health risk forecasting for environmental health teams.
73 lines
2.4 KiB
Python
73 lines
2.4 KiB
Python
#!/usr/bin/env python3
|
|
"""Resample DEM and population density to 100m grid."""
|
|
|
|
import pandas as pd
|
|
import rasterio
|
|
from rasterio.warp import transform
|
|
|
|
|
|
def resample_dem(dem_path: str, grid_parquet: str, output_path: str):
|
|
import numpy as np
|
|
df = pd.read_parquet(grid_parquet)
|
|
|
|
with rasterio.open(dem_path) as src:
|
|
elevations = []
|
|
for lon, lat in zip(df['center_lon'], df['center_lat']):
|
|
py, px = src.index(lon, lat)
|
|
if 0 <= py < src.height and 0 <= px < src.width:
|
|
elevations.append(src.read(1)[py, px])
|
|
else:
|
|
elevations.append(np.nan)
|
|
|
|
result = pd.DataFrame({'grid_id': df['grid_id'], 'elevation_m': elevations})
|
|
result.to_parquet(output_path, index=False)
|
|
print(f"DEM saved: {output_path}")
|
|
|
|
|
|
def resample_population(pop_dir: str, grid_parquet: str, output_path: str):
|
|
import numpy as np
|
|
import glob
|
|
df = pd.read_parquet(grid_parquet)
|
|
|
|
tif_files = glob.glob(f"{pop_dir}/*.tif")
|
|
if not tif_files:
|
|
print(f"No TIF files found in {pop_dir}")
|
|
return
|
|
|
|
populations = []
|
|
for lon, lat in zip(df['center_lon'], df['center_lat']):
|
|
val = 0
|
|
for tif_file in tif_files:
|
|
try:
|
|
with rasterio.open(tif_file) as src:
|
|
py, px = src.index(lon, lat)
|
|
if 0 <= py < src.height and 0 <= px < src.width:
|
|
val += src.read(1)[py, px]
|
|
except:
|
|
pass
|
|
populations.append(val)
|
|
|
|
result = pd.DataFrame({'grid_id': df['grid_id'], 'population_density': populations})
|
|
result.to_parquet(output_path, index=False)
|
|
print(f"Population saved: {output_path}")
|
|
|
|
|
|
def main():
|
|
import argparse
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--dem', default='Datas/DEM/CJJJD_DEM.TIF')
|
|
parser.add_argument('--pop-dir', default='Datas/landscan-hd-china-v1-assets')
|
|
parser.add_argument('--grid-parquet', default='processed/grid_100m_index.parquet')
|
|
parser.add_argument('--output-dem', default='processed/grid_dem.parquet')
|
|
parser.add_argument('--output-pop', default='processed/grid_population.parquet')
|
|
args = parser.parse_args()
|
|
|
|
print("Resampling DEM...")
|
|
resample_dem(args.dem, args.grid_parquet, args.output_dem)
|
|
|
|
print("Resampling population density...")
|
|
resample_population(args.pop_dir, args.grid_parquet, args.output_pop)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main() |