datagen.py

def worker(ndocs):
    global fake
    result = []

    for _ in range(ndocs):
        uuid = str(uuid4())
        coords = fake.local_latlng(country_code="US", coords_only=True)
        lat = round(float(coords[0]) + random.uniform(-1, 1), 5)  # faker local_latlng generates duplicates.  this is a workaround
        lng = round(float(coords[1]) + random.uniform(-1, 1), 5)
        point_lnglat = f'{lng} {lat}'
        point_wkt = Point(lng, lat).wkt
        dob = fake.date_of_birth(minimum_age=10, maximum_age=90).year
        result.append({"uuid": uuid, "point_lnglat": point_lnglat, "point_wkt": point_wkt, "dob": dob})
    return result