dc-l1-bangkok-attribute-coercion

Rerun

total 44
drwxr-xr-x 1 agent agent    54 Jun 16 05:27 .
drwxr-xr-x 1 root  root     14 Jun 16 05:27 ..
-rw-r--r-- 1 agent agent 41779 Jun 16 05:27 bangkok_aq_stations.geojson

cat /work/bangkok_aq_stations.geojson | python3 -c "
import json, sys
data = json.load(sys.stdin)
props = list(data['features'][0]['properties'].keys())
print('Property names:', props)
# Check a few features for types
for f in data['features'][:5]:
    for k,v in f['properties'].items():
        print(f'  {k}: {type(v).__name__} = {repr(v)}')
"

Property names: ['station_id', 'name_th', 'name_en', 'sensor_value', 'pm25_ug_m3', 'elevation_m']
  station_id: str = '1'
  name_th: str = 'สนามกีฬาแห่งชาติ'
  name_en: str = 'National Stadium'
  sensor_value: str = '84.55'
  pm25_ug_m3: str = '63.6'
  elevation_m: str = '11.0'
  station_id: str = '2'
  name_th: str = 'สยาม'
  name_en: str = 'Siam'
  sensor_value: str = '87.00'
  pm25_ug_m3: str = '60.5'
  elevation_m: str = '12.5'
  station_id: str = '3'
  name_th: str = 'ชิดลม'
  name_en: str = 'Chit Lom'
  sensor_value: str = '80.95'
  pm25_ug_m3: str = '54.8'
  elevation_m: str = '14.0'
  station_id: str = '4'
  name_th: str = 'เพลินจิต'
  name_en: str = 'Phloen Chit'
  sensor_value: str = '73.94'
  pm25_ug_m3: str = '49.0'
  elevation_m: str = '15.4'
  station_id: str = '5'
  name_th: str = 'นานา'
  name_en: str = 'Nana'
  sensor_value: str = '72.10'
  pm25_ug_m3: str = '45.6'
  elevation_m: str = '16.7'

cat /work/bangkok_aq_stations.geojson | python3 -c "
import json, sys
data = json.load(sys.stdin)
print(f'Total features: {len(data[\"features\"])}')

# Check for nulls or non-numeric values in the numeric columns
numeric_cols = ['sensor_value', 'pm25_ug_m3', 'elevation_m']
for col in numeric_cols:
    non_numeric = []
    nulls = []
    for f in data['features']:
        v = f['properties'][col]
        if v is None:
            nulls.append(f['properties']['station_id'])
        else:
            try:
                float(v)
            except (ValueError, TypeError):
                non_numeric.append((f['properties']['station_id'], repr(v)))
    print(f'{col}: nulls={len(nulls)}, non_numeric={len(non_numeric)}')
    if non_numeric:
        for s in non_numeric[:10]:
            print(f'  {s}')
"

Total features: 100
sensor_value: nulls=0, non_numeric=0
pm25_ug_m3: nulls=0, non_numeric=0
elevation_m: nulls=0, non_numeric=0

Done. Wrote bangkok_aq_typed.geojson
1 float 84.55 float 63.6 float 11.0
2 float 87.0 float 60.5 float 12.5
3 float 80.95 float 54.8 float 14.0

{
  "type": "FeatureCollection",
  "name": "bangkok_aq_stations",
  "crs": {
    "type": "name",
    "properties": {
      "name": "urn:ogc:def:crs:OGC:1.3:CRS84"
    }
  },
  "features": [
    {
      "type": "Feature",
      "geometry": {
        "type": "Point",
        "coordinates": [
          100.5294,
          13.7464
        ]
      },
      "properties": {
        "station_id": "1",
        "name_th": "สนามกีฬาแห่งชาติ",
        "name_en": "National Stadium",
        "sensor_value": 84.55,
        "pm25_ug_m3": 63.6,
        "elevation_m": 11.0
      }
    },
    {
      "type": "Feature",

python3 -c "
import json
with open('/work/bangkok_aq_typed.geojson') as f:
    d = json.load(f)
print(f'Features: {len(d[\"features\"])}')
# Check types: string cols stay string, numeric cols are float/number
f0 = d['features'][0]
props = f0['properties']
print('station_id:', type(props['station_id']).__name__, repr(props['station_id']))
print('name_th:', type(props['name_th']).__name__, repr(props['name_th']))
print('name_en:', type(props['name_en']).__name__, repr(props['name_en']))
print('sensor_value:', type(props['sensor_value']).__name__, props['sensor_value'])
print('pm25_ug_m3:', type(props['pm25_ug_m3']).__name__, props['pm25_ug_m3'])
print('elevation_m:', type(props['elevation_m']).__name__, props['elevation_m'])
print()
# Verify Thai text unchanged
print('Thai name_th:', props['name_th'])
# Compute means to confirm no NaN
import statistics
vals = {k: [] for k in ['sensor_value','pm25_ug_m3','elevation_m']}
for feat in d['features']:
    for k in vals:
        vals[k].append(feat['properties'][k])
for k in vals:
    print(f'mean {k}: {statistics.mean(vals[k]):.4f}')
"

Features: 100
station_id: str '1'
name_th: str 'สนามกีฬาแห่งชาติ'
name_en: str 'National Stadium'
sensor_value: float 84.55
pm25_ug_m3: float 63.6
elevation_m: float 11.0

Thai name_th: สนามกีฬาแห่งชาติ
mean sensor_value: 49.9783
mean pm25_ug_m3: 36.5160
mean elevation_m: 11.7160