Function to select data from gee and save it in a netCDF file

select_data.py

from satellitetools import gee
import geopandas as gpd
import os


def select_data(geofile, outdir, start, end, qi_threshold):
    
    # read in the input file containing coordinates
    df = gpd.read_file(geofile)

    request = gee.S2RequestParams(start, end)

    # filter area of interest from the coordinates in the input file
    area = gee.AOI(df[df.columns[0]].iloc[0], df[df.columns[1]].iloc[0])

    # calcuate qi attribute for the AOI
    gee.ee_get_s2_quality_info(area, request)

    # get the final data
    gee.ee_get_s2_data(area, request, qi_threshold=qi_threshold)

    # convert dataframe to an xarray dataset, used later for converting to netCDF
    gee.s2_data_to_xarray(area, request)
    
    # if specified output directory does not exist, create it.
    if not os.path.exists(outdir):
        os.makedirs(outdir, exist_ok=True)

    # saving the netCDF file
    area.data.to_netcdf(os.path.join(outdir, area.name + "_test.nc"))