OpenEO randomforest training

randomforest_training.py

import shapely
from shapely.geometry import Polygon, MultiPolygon
import openeo
from openeo.rest.job import JobResults
from openeo.rest.mlmodel import MlModel
from openeo.rest.job import BatchJob

feature_collection = {"type": "FeatureCollection", "features": [
    {
        "type": "Feature",
        "properties": {"id": "b3dw-wd23", "target": 0},
        "geometry": {"type": "Point", "coordinates": [3.4, 51.1]}
    },
    {
        "type": "Feature",
        "properties": {"id": "r8dh-3jkd", "target": 1},
        "geometry": {"type": "Point", "coordinates": [3.6, 51.2]}
    }
    ]
}

connection = openeo.connect("https://openeo.dataspace.copernicus.eu/").authenticate_oidc()
cube = connection.load_collection(
    "SENTINEL2_L2A",
    temporal_extent=["2020-12-30", "2022-01-01"],
    spatial_extent={
        'west': 3.39,
        'east': 3.61,
        'south': 51.09,
        'north': 51.21
    },
    bands=["B02", "B03", "B04"]
)
cube = cube.reduce_dimension(dimension="t", reducer="mean")
predictors = cube.aggregate_spatial(feature_collection, reducer="mean")
# predictors.download("predictors2.json")
# cube.download("cube.nc")
# exit()
model = predictors.fit_class_random_forest(
    target=feature_collection
)
model = model.save_ml_model()
training_job = model.create_job(title="randomforest_training_job")
print(training_job)
results : JobResults = training_job.start_and_wait().get_results()
print(results)
links = results.get_metadata()['links']
ml_model_metadata_url = [link for link in links if 'ml_model_metadata.json' in link['href']][0]['href']
print(ml_model_metadata_url)

# c = openeo.connect("https://openeo.dataspace.copernicus.eu/").authenticate_oidc()
# job: BatchJob = c.job("j-24050486ed974fdc80e73eff53974d89")
# results : JobResults = job.get_results()
# links = results.get_metadata()['links']
# ml_model_metadata_url = [link for link in links if 'ml_model_metadata.json' in link['href']][0]['href']
# print(ml_model_metadata_url)