def test_nonexistent_location(self):
path = './folder/subfolder/new-eopatch/'
empty_eop = EOPatch()
for fs_loader in self.filesystem_loaders:
with fs_loader() as temp_fs:
with self.assertRaises(ResourceNotFound):
EOPatch.load(path, filesystem=temp_fs)
empty_eop.save(path, filesystem=temp_fs)
with TempFS() as temp_fs:
full_path = os.path.join(temp_fs.root_path, path)
with self.assertRaises(CreateFailed):
EOPatch.load(full_path)
load_task = LoadTask(full_path)
with self.assertRaises(CreateFailed):
load_task.execute()
empty_eop.save(full_path)
self.assertTrue(os.path.exists(full_path))
with TempFS() as temp_fs:
full_path = os.path.join(temp_fs.root_path, path)
save_task = SaveTask(full_path)
save_task.execute(empty_eop)
self.assertTrue(os.path.exists(full_path))
def test_nonexistent_location(fs_loader):
path = "./folder/subfolder/new-eopatch/"
empty_eop = EOPatch()
with fs_loader() as temp_fs:
with pytest.raises(ResourceNotFound):
EOPatch.load(path, filesystem=temp_fs)
empty_eop.save(path, filesystem=temp_fs)
with TempFS() as temp_fs:
full_path = os.path.join(temp_fs.root_path, path)
with pytest.raises(CreateFailed):
EOPatch.load(full_path)
load_task = LoadTask(full_path)
with pytest.raises(CreateFailed):
load_task.execute()
empty_eop.save(full_path)
assert os.path.exists(full_path)
with TempFS() as temp_fs:
full_path = os.path.join(temp_fs.root_path, path)
save_task = SaveTask(full_path)
save_task.execute(empty_eop)
assert os.path.exists(full_path)
def test_cleanup_different_compression(fs_loader, eopatch):
folder = "foo-folder"
patch_folder = "patch-folder"
with fs_loader() as temp_fs:
temp_fs.makedir(folder)
save_compressed_task = SaveTask(folder,
filesystem=temp_fs,
compress_level=9,
overwrite_permission=1)
save_noncompressed_task = SaveTask(folder,
filesystem=temp_fs,
compress_level=0,
overwrite_permission=1)
bbox_path = fs.path.join(folder, patch_folder, "bbox.geojson")
compressed_bbox_path = bbox_path + ".gz"
data_timeless_path = fs.path.join(folder, patch_folder,
"data_timeless", "mask.npy")
compressed_data_timeless_path = data_timeless_path + ".gz"
save_compressed_task(eopatch, eopatch_folder=patch_folder)
save_noncompressed_task(eopatch, eopatch_folder=patch_folder)
assert temp_fs.exists(bbox_path)
assert temp_fs.exists(data_timeless_path)
assert not temp_fs.exists(compressed_bbox_path)
assert not temp_fs.exists(compressed_data_timeless_path)
save_compressed_task(eopatch, eopatch_folder=patch_folder)
assert not temp_fs.exists(bbox_path)
assert not temp_fs.exists(data_timeless_path)
assert temp_fs.exists(compressed_bbox_path)
assert temp_fs.exists(compressed_data_timeless_path)
def get_tiffs_to_eopatches_workflow(config: TiffsToEopatchConfig,
delete_tiffs: bool = False) -> EOWorkflow:
""" Set up workflow to ingest tiff files into EOPatches """
# Set up credentials in sh config
sh_config = set_sh_config(config)
import_bands = [(ImportFromTiff(
(FeatureType.DATA, band),
folder=f's3://{config.bucket_name}/{config.tiffs_folder}',
config=sh_config), f'Import band {band}')
for band in config.band_names]
import_clp = (ImportFromTiff(
(FeatureType.DATA, config.clp_name),
folder=f's3://{config.bucket_name}/{config.tiffs_folder}',
config=sh_config), f'Import {config.clp_name}')
import_mask = (ImportFromTiff(
(FeatureType.MASK, config.mask_name),
folder=f's3://{config.bucket_name}/{config.tiffs_folder}',
config=sh_config), f'Import {config.mask_name}')
rearrange_bands = (RearrangeBands(), 'Swap time and band axis')
add_timestamps = (AddTimestampsUpdateTime(
f's3://{config.bucket_name}/{config.tiffs_folder}'), 'Load timestamps')
merge_bands = (MergeFeatureTask(
input_features={FeatureType.DATA: config.band_names},
output_feature=(FeatureType.DATA, config.data_name)),
'Merge band features')
remove_bands = (RemoveFeature(
features={FeatureType.DATA: config.band_names}), 'Remove bands')
rename_mask = (RenameFeature((FeatureType.MASK, config.mask_name,
config.is_data_mask)), 'Rename is data mask')
calculate_clm = (CloudMasking(), 'Get CLM mask from CLP')
save_task = (SaveTask(
path=f's3://{config.bucket_name}/{config.eopatches_folder}',
config=sh_config,
overwrite_permission=OverwritePermission.OVERWRITE_FEATURES),
'Save EOPatch')
filenames = [f'{band}.tif' for band in config.band_names] + \
[f'{config.mask_name}.tif', f'{config.clp_name}.tif', 'userdata.json']
delete_files = (DeleteFiles(path=config.tiffs_folder,
filenames=filenames), 'Delete batch files')
workflow = [
*import_bands, import_clp, import_mask, rearrange_bands,
add_timestamps, merge_bands, remove_bands, rename_mask, calculate_clm,
save_task
]
if delete_tiffs:
workflow.append(delete_files)
return LinearWorkflow(*workflow)
def predict_using_model(patch_dir, model_file, method, window_size):
''' Defines a workflow that will perform the prediction step on a given EOPatch.
For a given EOPatch, use the specified model to apply prediction step.
Parameters:
- patch_dir: the directory that contains the patch
- model_file; the path to the model file.
- method: The local noramalization method, one of 'min', 'median' or 'mean'. This should be the same as the one used to train the model.
- window_size: The window_size used in the local normalization step. Should be the same as that used to train the model.
Returns:
Nothing. Updates the EOPatch on disk.
'''
path = patch_dir
if (type(path) != str):
path = str(path)
save = SaveTask(path=path,
overwrite_permission=OverwritePermission.OVERWRITE_PATCH)
load_task = LoadTask(path=path)
local_norm = LocalNormalization()
detect_plastics = DetectPlastics(model_file=model_file)
workflow = LinearWorkflow(load_task, local_norm, detect_plastics, save)
workflow.execute(
{local_norm: {
'method': method,
'window_size': window_size
}})
def get_gsaa_to_eopatch_workflow(config: GsaaToEopatchConfig) -> EOWorkflow:
# set up AWS credentials
sh_config = set_sh_config(config)
# load patch
load_task = LoadTask(path=f's3://{config.bucket_name}/{config.eopatches_folder}', config=sh_config)
# add original vectors to patch
vec2vec = DB2Vector(database=config.database,
user=config.user, password=config.password,
host=config.host, port=config.port, crs=config.crs,
vector_output_feature=config.vector_feature)
# get extent mask from vector
vec2ras = VectorToRaster(config.vector_feature,
config.extent_feature,
values=1, raster_shape=(config.width, config.height),
no_data_value=config.no_data_value,
buffer=config.buffer_poly, write_to_existing=False)
# get boundary mask from extent mask
ras2bound = Extent2Boundary(config.extent_feature,
config.boundary_feature,
structure=disk(config.disk_radius))
# get distance from extent mask
ras2dist = Extent2Distance(config.extent_feature,
config.distance_feature,
normalize=True)
# save new features
save_task = SaveTask(path=f's3://{config.bucket_name}/{config.eopatches_folder}',
features=[config.vector_feature,
config.extent_feature,
config.boundary_feature,
config.distance_feature],
overwrite_permission=OverwritePermission.OVERWRITE_FEATURES, config=sh_config)
return LinearWorkflow(load_task, vec2vec, vec2ras, ras2bound, ras2dist, save_task)
def process_feature(feature, feature_index):
'''A function to download a given target pixel and it's surroundings as an EOPatch
Parameters:
feature (GeoSeries): A row from the GeoDataFrame produced by load_fetures_from_file
feature_index (int): The integer used in saving the EOPatch to disk.
Returns:
Nothing
'''
save = SaveTask(path=f'{base_dir}/feature_{feature_index}/', overwrite_permission=OverwritePermission.OVERWRITE_PATCH)
train_test_workflow = LinearWorkflow(input_task,true_color,add_l2a,ndvi,ndwi,add_fdi,cloud_detection,water_detection,combine_mask,save )
feature_result = train_test_workflow.execute({
input_task: {
'bbox':BBox(bounds.iloc[feature_index],bbox_list[0].crs),
'time_interval': [feature.date_start, feature.date_end]
},
combine_mask:{
'use_water': False #(target.reduced_label != 'Timber')
},
add_fdi:{
'band_layer': USE_BANDS,
'band_names': band_names
}
})
patch = feature_result.eopatch()
return patch
def get_post_processing_workflow(config: PostProcessConfig) -> LinearWorkflow:
sh_config = set_sh_config(config)
load_task = LoadTask(path=f's3://{config.bucket_name}/{config.eopatches_folder}',
features=[config.feature_extent,
config.feature_boundary,
(FeatureType.MASK, 'CLM'),
(FeatureType.MASK, 'IS_DATA'),
FeatureType.TIMESTAMP,
FeatureType.META_INFO,
FeatureType.BBOX],
config=sh_config), 'Load EOPatch'
merge_extent_tasks = [(TemporalMerging(feature=config.feature_extent,
feature_merged=(FeatureType.DATA_TIMELESS,
f'{config.feature_extent[1]}_{month}'),
woy_start=woy_start, woy_end=woy_end,
percentile=config.percentile,
max_cloud_coverage=config.max_cloud_coverage), f'Merge EXTENT for {month}')
for month, (woy_start, woy_end) in config.time_intervals.items()]
merge_boundary_tasks = [(TemporalMerging(feature=config.feature_boundary,
feature_merged=(FeatureType.DATA_TIMELESS,
f'{config.feature_boundary[1]}_{month}'),
woy_start=woy_start, woy_end=woy_end,
percentile=config.percentile,
max_cloud_coverage=config.max_cloud_coverage),
f'Merge BOUNDARY for {month}')
for month, (woy_start, woy_end) in config.time_intervals.items()]
combine_tasks = [(CombineUpsample(
feature_extent=(FeatureType.DATA_TIMELESS, f'{config.feature_extent[1]}_{month}'),
feature_boundary=(FeatureType.DATA_TIMELESS, f'{config.feature_boundary[1]}_{month}'),
feature_output=(FeatureType.DATA_TIMELESS, f'PREDICTED_{config.model_version}_{month}'),
scale_factor=config.scale_factor, disk_size=config.disk_size), f'Combine masks for {month}')
for month in config.time_intervals]
save_task = SaveTask(path=f's3://{config.bucket_name}/{config.eopatches_folder}',
features=[(FeatureType.DATA_TIMELESS, f'{config.feature_extent[1]}_{month}')
for month in config.time_intervals] +
[(FeatureType.DATA_TIMELESS, f'{config.feature_boundary[1]}_{month}')
for month in config.time_intervals] +
[(FeatureType.DATA_TIMELESS, f'PREDICTED_{config.model_version}_{month}')
for month in config.time_intervals],
overwrite_permission=OverwritePermission.OVERWRITE_FEATURES,
config=sh_config), 'Save Task'
export_tasks = [(ExportToTiff(feature=(FeatureType.DATA_TIMELESS, f'PREDICTED_{config.model_version}_{month}'),
folder=f's3://{config.bucket_name}/{config.tiffs_folder}/{month}/',
image_dtype=np.float32), f'Export tiffs for {month}')
for month in config.time_intervals]
workflow = LinearWorkflow(load_task, *merge_extent_tasks, *merge_boundary_tasks,
*combine_tasks, save_task, *export_tasks)
return workflow
def get_and_process_patch(bounds, time_range, base_dir, index):
''' Defines a workflow that will download and process a specific EOPatch.
The pipline has the folowing steps
- Download data
- Calculate NDVI
- Calculate NDWI
- Calculate FDI
- Add cloud mask
- Add water mask
- Combine all masks
- Perform local noramalization
- Save the results.
Parameters:
- bounds: The bounding box of the EOPatch we wish to process
- time_range: An array of [start_time,end_time]. Any satelite pass in that range will be procesed.
- base_dir: the directory to save the patches to
- index: An index to label this patch
Returns:
The EOPatch for this region and time range.
'''
save = SaveTask(path=f'{base_dir}/feature_{index}/',
overwrite_permission=OverwritePermission.OVERWRITE_PATCH)
add_fdi = CalcFDI()
water_detection = WaterDetector()
combine_mask = CombineMask()
local_norm = LocalNormalization()
fetch_workflow = LinearWorkflow(input_task, true_color, add_l2a,
ndvi_task(), ndwi_task(), add_fdi,
cloud_classifier_task(), water_detection,
combine_mask, local_norm, save)
feature_result = fetch_workflow.execute({
input_task: {
'bbox': BBox(bounds, CRS.WGS84),
'time_interval': time_range
},
combine_mask: {
'use_water': False
},
local_norm: {
'method': 'min',
'window_size': 10,
}
})
patch = feature_result.eopatch()
return patch
def test_save_and_load_tasks(eopatch, fs_loader):
folder = "foo-folder"
patch_folder = "patch-folder"
with fs_loader() as temp_fs:
temp_fs.makedir(folder)
save_task = SaveTask(folder, filesystem=temp_fs, compress_level=9)
load_task = LoadTask(folder, filesystem=temp_fs, lazy_loading=False)
saved_eop = save_task(eopatch, eopatch_folder=patch_folder)
bbox_path = fs.path.join(folder, patch_folder, "bbox.geojson.gz")
assert temp_fs.exists(bbox_path)
assert saved_eop == eopatch
eop = load_task(eopatch_folder=patch_folder)
assert eop == eopatch
def download_patches(path, shp, bbox_list, indexes):
add_data = S2L1CWCSInput(
layer='BANDS-S2-L1C',
feature=(FeatureType.DATA, 'BANDS'), # save under name 'BANDS'
resx='10m', # resolution x
resy='10m', # resolution y
maxcc=0.8, # maximum allowed cloud cover of original ESA tiles
)
path_out = path + '/Slovenia/'
if not os.path.isdir(path_out):
os.makedirs(path_out)
save = SaveTask(path_out,
overwrite_permission=OverwritePermission.OVERWRITE_PATCH)
workflow = LinearWorkflow(add_data, save)
time_interval = ['2017-01-01',
'2017-12-31'] # time interval for the SH request
execution_args = []
for idx, bbox in zip(indexes, bbox_list[indexes]):
execution_args.append({
add_data: {
'bbox': bbox,
'time_interval': time_interval
},
save: {
'eopatch_folder': 'eopatch_{}'.format(idx)
}
})
start_time = time.time()
executor = EOExecutor(workflow, execution_args, save_logs=True)
executor.run(workers=1, multiprocess=False)
file = open('timing.txt', 'a')
running = str(
dt.datetime.now()) + ' Running time: {}\n'.format(time.time() -
start_time)
print(running)
file.write(running)
file.close()
def test_save_and_load_tasks(self):
folder = 'foo-folder'
patch_folder = 'patch-folder'
for fs_loader in self.filesystem_loaders:
with fs_loader() as temp_fs:
temp_fs.makedir(folder)
save_task = SaveTask(folder,
filesystem=temp_fs,
compress_level=9)
load_task = LoadTask(folder,
filesystem=temp_fs,
lazy_loading=False)
saved_eop = save_task(self.eopatch,
eopatch_folder=patch_folder)
bbox_path = fs.path.join(folder, patch_folder, 'bbox.pkl.gz')
self.assertTrue(temp_fs.exists(bbox_path))
self.assertEqual(saved_eop, self.eopatch)
eop = load_task(eopatch_folder=patch_folder)
self.assertEqual(eop, self.eopatch)
resx='10m',
resy='10m',
maxcc=0.2)
# task to get ground-truth from Geopedia
geopedia_data = AddGeopediaFeature(
(FeatureType.MASK_TIMELESS, 'TREE_COVER'),
layer='ttl2275',
theme='QP',
raster_value=raster_value)
# task to compute median values
get_median_pixel = MedianPixel(
(FeatureType.DATA, 'TRUE-COLOR-S2-L2A'),
feature_out=(FeatureType.DATA_TIMELESS, 'MEDIAN_PIXEL'))
# task to save to disk
save = SaveTask(op.join(output_path, 'eopatch'),
overwrite_permission=OverwritePermission.OVERWRITE_PATCH,
compress_level=2)
# initialize workflow
workflow = LinearWorkflow(input_task, geopedia_data, get_median_pixel,
save)
# use a function to run this workflow on a single bbox
def execute_workflow(index):
bbox = bbox_splitter.bbox_list[index]
info = bbox_splitter.info_list[index]
patch_name = 'eopatch_{0}_row-{1}_col-{2}'.format(
index, info['index_x'], info['index_y'])
results = workflow.execute({
(FeatureType.DATA, 'BANDS'), (FeatureType.DATA, 'NDVI'),
[band_names.index('B08'),
band_names.index('B04')])
ndwi = NormalizedDifferenceIndexTask(
(FeatureType.DATA, 'BANDS'), (FeatureType.DATA, 'NDWI'),
[band_names.index('B03'),
band_names.index('B08')])
ndbi = NormalizedDifferenceIndexTask(
(FeatureType.DATA, 'BANDS'), (FeatureType.DATA, 'NDBI'),
[band_names.index('B11'),
band_names.index('B08')])
#SaveTask
save = SaveTask(SAVE_PATH,
overwrite_permission=OverwritePermission.OVERWRITE_PATCH)
#Workflow
workflow = LinearWorkflow(
add_data,
ndvi,
ndwi,
ndbi,
save,
)
time_interval = {
'18/19': ['2018-11-01', '2019-05-01'],
'19/20': ['2019-11-01', '2020-05-01'],
}
gradient[..., np.newaxis])
return eopatch
if __name__ == '__main__':
# path = 'E:/Data/PerceptiveSentinel'
path = '/home/beno/Documents/test/Slovenia/'
size_small = (337, 333)
size_big = (505, 500)
load = LoadTask(path, lazy_loading=True)
save_path_location = path
if not os.path.isdir(save_path_location):
os.makedirs(save_path_location)
save = SaveTask(save_path_location,
overwrite_permission=OverwritePermission.OVERWRITE_PATCH)
dem = SentinelHubDemTask((FeatureType.DATA_TIMELESS, 'DEM'), size=size_big)
grad = AddGradientTask((FeatureType.DATA_TIMELESS, 'DEM'),
(FeatureType.DATA_TIMELESS, 'INCLINATION'))
workflow = LinearWorkflow(load, dem, grad, save)
no_patches = 1061
execution_args = []
for i in range(no_patches):
i = i + 2
execution_args.append({
load: {
'eopatch_folder': 'eopatch_{}'.format(i)
def run_prediction_on_eopatch(
eopatch_name: str,
config: PredictionConfig,
model: ResUnetA = None,
normalisation_factors: pd.DataFrame = None) -> dict:
""" Run prediction workflow on one eopatch. Model and dataframe can be provided to avoid loading them every time """
sh_config = set_sh_config(config)
filesystem = prepare_filesystem(config)
if normalisation_factors is None:
normalisation_factors = load_metadata(filesystem, config)
if model is None:
model = load_model(filesystem, config)
load_task = LoadTask(
path=f's3://{config.bucket_name}/{config.eopatches_folder}',
features=[
config.feature_bands, config.reference_distance,
config.reference_extent, config.reference_boundary,
FeatureType.TIMESTAMP, FeatureType.META_INFO, FeatureType.BBOX
],
config=sh_config)
save_task = SaveTask(
path=f's3://{config.bucket_name}/{config.eopatches_folder}',
features=[
config.feature_extent, config.feature_boundary,
config.feature_distance, FeatureType.META_INFO
],
overwrite_permission=OverwritePermission.OVERWRITE_FEATURES,
config=sh_config)
try:
eop = load_task.execute(eopatch_folder=eopatch_name)
eop = prediction_fn(eop,
normalisation_factors=normalisation_factors,
normalise=config.normalise,
model=model,
model_name=config.model_name,
extent_feature=config.feature_extent,
boundary_feature=config.feature_boundary,
distance_feature=config.feature_distance,
suffix=config.model_version,
batch_size=config.batch_size,
n_classes=config.n_classes,
bands_feature=config.feature_bands,
reference_boundary=config.reference_boundary,
reference_distance=config.reference_distance,
reference_extent=config.reference_extent)
_ = save_task.execute(eop, eopatch_folder=eopatch_name)
del eop
return dict(name=eopatch_name, status='Success')
except Exception as exc:
return dict(name=eopatch_name, status=exc)
