def predict_main(aoi_path):
"""this functions trakes as input the json file fr4om frontend and returns the subpolygones with co2 metrcis
aoi: json file with area of intreste from frontend
"""
# download images from gee
data_parent_path = os.path.join("..", "data", "raw")
dataset_name = data.download_dataset(aoi_path,
data_parent_path=data_parent_path,
get_sent2=True,
get_glc=False,
get_ndvi=False)
# preprocess data (creates dataset folder structure in data/preprocessed
# from data import make_dataset
data.make_dataset(dataset_name)
# predict land cover
prediction = predict_model(dataset_name)
# prediction is a json with subpolygones
# get co2 estimations
prediction = calc_vegetation_co_metric(
prediction) # adds attribute "veg_co2_metric" to predictions
prediction = calc_soil_co_metric(
prediction) # adds attribute "soil_co2_metric" to predictions
#return prediction
pass
def build_validation_data_loader(self) -> DataLoader:
if not self.data_downloaded:
self.download_directory = data.download_dataset(
download_directory=self.download_directory,
data_config=self.context.get_data_config(),
)
self.data_downloaded = True
validation_data = data.get_dataset(self.download_directory, train=False)
return DataLoader(validation_data, batch_size=self.context.get_per_slot_batch_size())
def build_training_data_loader(self) -> DataLoader:
if not self.data_downloaded:
self.download_directory = data.download_dataset(
download_directory=self.download_directory,
data_config=self.context.get_data_config(),
)
self.data_downloaded = True
dataset = data.get_dataset(self.download_directory, train=True)
return DataLoader(dataset, batch_size=self.context.get_per_slot_batch_size())
def build_training_data_loader(self) -> DataLoader:
if not self.data_downloaded:
self.download_directory = data.download_dataset(
download_directory=self.download_directory,
data_config=self.context.get_data_config(),
)
self.data_downloaded = True
train_data = data.get_multi_dataset(self.download_directory, train=True)
return DataLoader(
train_data,
batch_size=self.context.get_per_slot_batch_size(),
collate_fn=data.collate_fn,
)
