filter data using h3 indices

h3_filter.py

park = (con
        .read_geo("/vsicurl/https://huggingface.co/datasets/cboettig/biodiversity/resolve/main/data/NPS.gdb")
        .filter(_.UNIT_NAME == "Yosemite National Park")
        .select(_.SHAPE)
        .mutate(SHAPE = _.SHAPE.convert('EPSG:3857', 'EPSG:4326'))
        .mutate(lng = _.SHAPE.centroid().x(), lat = _.SHAPE.centroid().y())
        .mutate(h1 = h3_latlng_to_cell(_.lat, _.lng, 1) )
        .mutate(neighbors = h3_grid_disk(_.h1, 1))
        #.mutate(cells = h3_polygon_wkt_to_cells_string(_.SHAPE.as_text(),1))
       )

park = park.execute()
h1_neighbors = [format(i, 'X') for i in park.neighbors[0]]

aoi = con.create_table("aoi", {'h1': h1_neighbors}, overwrite=True)
aoi.execute()


gbif = con.read_parquet("s3://cboettig/gbif/2024-10-01/**")
gbif.join(aoi, "h1").count().execute()