name-all-lakes-by-area-quiz/get_data.py

import requests
import json
import zipfile
import tempfile
import os
import subprocess
import io

with tempfile.TemporaryDirectory() as tmpdir:
    print(f"Fetching lake data", flush=True)
    res = requests.get(f"https://resources.gisdata.mn.gov/pub/gdrs/data/pub/us_mn_state_dnr/water_dnr_hydrography/shp_water_dnr_hydrography.zip")
    print("extracting zip file", flush=True)
    zipfile.ZipFile(io.BytesIO(res.content)).extractall(tmpdir)
    shapefile_name = os.path.join(tmpdir, f"dnr_hydro_features_all.shp")
    geojson_file_name = os.path.join(tmpdir, "out.geojson")
    print("converting to geojson", flush=True)
    subprocess.run(f"ogr2ogr -f GeoJSON {geojson_file_name} {shapefile_name}", shell=True)
    print("loading json", flush=True)
    with open(geojson_file_name) as f:
        data = json.load(f)

print("processing", flush=True)
lakes_by_name = {} # {"Marion": {"centers": [[lon, lat], ...], "area": area_in_acres}, ...}

for feature in data['features']:
    if feature['properties']['sub_flag'] == 'Y':
        continue
    name = feature['properties']['map_label'] # or pw_basin_n or pw_parent_ or...??
    if not name: # many lakes with null name
        continue
    if name == "Unnamed":
        continue
    if name not in lakes_by_name:
        lakes_by_name[name] = {"centers": [], "area": 0}
    lakes_by_name[name]["centers"].append([feature['properties']['INSIDE_X'], feature['properties']['INSIDE_Y']])
    lakes_by_name[name]["area"] += feature['properties']['acres']

lakes = []
for name, lake in lakes_by_name.items():
    lake["name"] = name
    lakes.append(lake)

lakes.sort(key=lambda lake: lake['area'], reverse=True)

with open(f"lakes.json", 'w') as f:
    f.write(json.dumps(lakes))