def _run_and_test_execution(self, workers, multiprocess, filter_logs):
for execution_names in [None, [4, 'x', 'y', 'z']]:
with tempfile.TemporaryDirectory() as tmp_dir_name:
executor = EOExecutor(
self.workflow,
self.execution_args,
save_logs=True,
logs_folder=tmp_dir_name,
logs_filter=CustomLogFilter() if filter_logs else None,
execution_names=execution_names)
executor.run(workers=workers, multiprocess=multiprocess)
self.assertEqual(len(executor.execution_logs), 4)
for log in executor.execution_logs:
self.assertTrue(len(log.split()) >= 3)
log_filenames = sorted(os.listdir(executor.report_folder))
self.assertEqual(len(log_filenames), 4)
if execution_names:
for name, log_filename in zip(execution_names,
log_filenames):
self.assertTrue(
log_filename == 'eoexecution-{}.log'.format(name))
log_path = os.path.join(executor.report_folder,
log_filenames[0])
with open(log_path, 'r') as fp:
line_count = len(fp.readlines())
expected_line_count = 2 if filter_logs else 12
self.assertEqual(line_count, expected_line_count)
def _load_with_index(self):
"""
Split image to a number of EOPatches(lazy load data) with given splitter,
and index each EOPatch using two dimension list.
:param feature: Feature to be loaded
:type feature: (FeatureType, feature_name) or FeatureType
"""
add_data = ImportFromGeogenius(feature=self.feature,
geogenius_image=self.geogenius_image)
tile_rows, tile_columns = self._get_tile_rows_columns()
self.patch_index = [[0] * tile_columns for i in range(tile_rows)]
index_feature = IndexTask(patch_index=self.patch_index)
workflow = LinearWorkflow(add_data, index_feature)
execution_args = []
bbox_list = np.array(self.splitter.get_pixel_bbox_list())
for idx, bbox in enumerate(bbox_list):
row = idx % tile_rows
column = idx // tile_rows
execution_args.append({
add_data: {
'pixelbox': bbox
},
index_feature: {
"row": row,
"column": column
}
})
executor = EOExecutor(workflow, execution_args)
executor.run(workers=1, multiprocess=False)
return self.patch_index
def test_exceptions(workflow, execution_kwargs):
with pytest.raises(ValueError):
EOExecutor(workflow, {})
with pytest.raises(ValueError):
EOExecutor(workflow, execution_kwargs, execution_names={1, 2, 3, 4})
with pytest.raises(ValueError):
EOExecutor(workflow, execution_kwargs, execution_names=["a", "b"])
def test_read_logs(test_args, execution_names, workflow, execution_kwargs):
workers, multiprocess, filter_logs = test_args
with tempfile.TemporaryDirectory() as tmp_dir_name:
executor = EOExecutor(
workflow,
execution_kwargs,
save_logs=True,
logs_folder=tmp_dir_name,
logs_filter=CustomLogFilter() if filter_logs else None,
execution_names=execution_names,
)
executor.run(workers=workers, multiprocess=multiprocess)
execution_logs = executor.read_logs()
assert len(execution_logs) == 4
for log in execution_logs:
assert len(log.split()) >= 3
log_filenames = sorted(executor.filesystem.listdir(executor.report_folder))
assert len(log_filenames) == 4
if execution_names:
for name, log_filename in zip(execution_names, log_filenames):
assert log_filename == f"eoexecution-{name}.log"
log_path = os.path.join(executor.report_folder, log_filenames[0])
with executor.filesystem.open(log_path, "r") as fp:
line_count = len(fp.readlines())
expected_line_count = 2 if filter_logs else 12
assert line_count == expected_line_count
def test_execution_logs(self):
with tempfile.TemporaryDirectory() as tmp_dir_name:
executor = EOExecutor(self.workflow, self.execution_args, save_logs=True, logs_folder=tmp_dir_name)
executor.run()
self.assertEqual(len(executor.execution_logs), 4)
for log in executor.execution_logs:
self.assertTrue(len(log.split()) >= 3)
def test_exceptions(self):
with self.assertRaises(ValueError):
EOExecutor(self.workflow, {})
with self.assertRaises(ValueError):
EOExecutor(self.workflow, self.execution_args, execution_names={1, 2, 3, 4})
with self.assertRaises(ValueError):
EOExecutor(self.workflow, self.execution_args, execution_names=['a', 'b'])
def test_execution_stats(self):
with tempfile.TemporaryDirectory() as tmp_dir_name:
executor = EOExecutor(self.workflow, self.execution_args, logs_folder=tmp_dir_name)
executor.run(workers=2)
self.assertEqual(len(executor.execution_stats), 4)
for stats in executor.execution_stats:
for time_stat in ['start_time', 'end_time']:
self.assertTrue(time_stat in stats and isinstance(stats[time_stat], datetime.datetime))
def test_execution_results(workflow, execution_kwargs):
with tempfile.TemporaryDirectory() as tmp_dir_name:
executor = EOExecutor(workflow, execution_kwargs, logs_folder=tmp_dir_name)
executor.run(workers=2)
assert len(executor.execution_results) == 4
for results in executor.execution_results:
for time_stat in [results.start_time, results.end_time]:
assert isinstance(time_stat, datetime.datetime)
def test_execution_results2(workflow, execution_kwargs):
executor = EOExecutor(workflow, execution_kwargs)
results = executor.run(workers=2, multiprocess=True)
assert isinstance(results, list)
for idx, workflow_results in enumerate(results):
assert isinstance(workflow_results, WorkflowResults)
if idx != 3:
assert workflow_results.outputs["output"] == 42
def test_execution_errors(self):
with tempfile.TemporaryDirectory() as tmp_dir_name:
executor = EOExecutor(self.workflow, self.execution_args, logs_folder=tmp_dir_name)
executor.run(workers=5)
for idx, stats in enumerate(executor.execution_stats):
if idx != 3:
self.assertFalse('error' in stats, 'Workflow {} should be executed without errors'.format(idx))
else:
self.assertTrue('error' in stats and stats['error'],
'This workflow should be executed with an error')
def test_mix_with_eoexecutor(workflow, execution_kwargs, simple_cluster):
rayexecutor = RayExecutor(workflow, execution_kwargs)
eoexecutor = EOExecutor(workflow, execution_kwargs)
for _ in range(10):
ray_results = rayexecutor.run()
eo_results = eoexecutor.run()
ray_outputs = [results.outputs for results in ray_results]
eo_outputs = [results.outputs for results in eo_results]
assert ray_outputs == eo_outputs
def test_execution_errors(self):
task = RaiserErrorTask()
workflow = EOWorkflow(dependencies=[
Dependency(task=task, inputs=[]),
])
execution_args = [
{'arg1': 1}
]
with tempfile.TemporaryDirectory() as tmpdirname:
executor = EOExecutor(workflow, execution_args, file_path=tmpdirname)
executor.run()
self.assertTrue('error' in executor.execution_stats[0])
def test_report_creation(self):
task = ExampleTask()
workflow = EOWorkflow(dependencies=[
Dependency(task=task, inputs=[]),
])
execution_args = [
{'arg1': 1}
]
with tempfile.TemporaryDirectory() as tmpdirname:
executor = EOExecutor(workflow, execution_args, file_path=tmpdirname)
executor.run()
self.assertIsNotNone(executor.make_report())
def save_patch(self,
save_folder,
feature=None,
overwrite_permission=OverwritePermission.OVERWRITE_PATCH,
compress_level=0):
"""
Save indexed EOPatches to a folder.
:param save_folder: folder to save eopatches
:type save_folder: str
:param feature: Feature to be exported
:type feature: (FeatureType, feature_name) or FeatureType
:param overwrite_permission: Permissions to overwrite exist EOPatch.
Permissions are in the following hierarchy:
- `ADD_ONLY` - Only new features can be added, anything that is already saved cannot be changed.
- `OVERWRITE_FEATURES` - Overwrite only data for features which have to be saved. The remaining content of
saved EOPatch will stay unchanged.
- `OVERWRITE_PATCH` - Overwrite entire content of saved EOPatch and replace it with the new content.
:type overwrite_permission: OverwritePermission
:param compress_level: A level of data compression and can be specified with an integer from 0 (no compression)
to 9 (highest compression).
:type compress_level: int
"""
if not feature:
feature = self.feature
if not self._is_loaded():
self._load_with_index(feature=feature)
tile_rows, tile_columns = self._get_tile_rows_columns()
self._assure_folder_exist(save_folder)
save_task = SaveToDisk(save_folder,
features=[feature, FeatureType.BBOX],
overwrite_permission=overwrite_permission,
compress_level=compress_level)
workflow = LinearWorkflow(save_task)
execution_args = []
for row in range(tile_rows):
for column in range(tile_columns):
execution_args.append({
save_task: {
'eopatch_folder':
'patch_{row}_{column}'.format(row=row, column=column),
'eopatch':
self.patch_index[row][column]
}
})
executor = EOExecutor(workflow, execution_args)
executor.run(workers=1, multiprocess=False)
def test_execution_logs(self):
for execution_names in [None, [4, 'x', 'y', 'z']]:
with tempfile.TemporaryDirectory() as tmp_dir_name:
executor = EOExecutor(self.workflow, self.execution_args, save_logs=True, logs_folder=tmp_dir_name,
execution_names=execution_names)
executor.run()
self.assertEqual(len(executor.execution_logs), 4)
for log in executor.execution_logs:
self.assertTrue(len(log.split()) >= 3)
log_filenames = sorted(os.listdir(executor.report_folder))
self.assertEqual(len(log_filenames), 4)
if execution_names:
for name, log_filename in zip(execution_names, log_filenames):
self.assertTrue(log_filename == 'eoexecution-{}.log'.format(name))
def test_execution_stats(self):
task = ExampleTask()
workflow = EOWorkflow(dependencies=[
Dependency(task=task, inputs=[]),
])
execution_args = [
{'arg1': 1},
{'arg1': 2}
]
with tempfile.TemporaryDirectory() as tmpdirname:
executor = EOExecutor(workflow, execution_args, file_path=tmpdirname)
executor.run()
self.assertEqual(len(executor.execution_stats), 2)
def test_report_creation(self):
with tempfile.TemporaryDirectory() as tmp_dir_name:
executor = EOExecutor(self.workflow, self.execution_args, logs_folder=tmp_dir_name)
executor.run(workers=10)
executor.make_report()
self.assertTrue(os.path.exists(executor.get_report_filename()), 'Execution report was not created')
def test_execution_results(self):
for return_results in [True, False]:
executor = EOExecutor(self.workflow, self.execution_args)
results = executor.run(workers=2, multiprocess=True, return_results=return_results)
if return_results:
self.assertTrue(isinstance(results, list))
for idx, workflow_results in enumerate(results):
if idx == 3:
self.assertEqual(workflow_results, None)
else:
self.assertTrue(isinstance(workflow_results, WorkflowResults))
self.assertEqual(workflow_results[self.final_task], 42)
self.assertTrue(self.task not in workflow_results)
else:
self.assertEqual(results, None)
def execute_workflow(workflow, input_task, save_task, bbox_splitter, time_interval):
"""
Helper function for executing the EO-Learn workflow
"""
bbox_list = np.array(bbox_splitter.get_bbox_list())
total_patches = len(bbox_splitter.bbox_list)
# Define additional parameters of the workflow
execution_args = [
{
input_task: {'bbox':bbox_list[idx], 'time_interval':time_interval},
save_task: {'eopatch_folder': 'eopatch_{}'.format(idx)}
} for idx in range(total_patches)
]
executor = EOExecutor(workflow, execution_args, save_logs=True)
executor.run(workers=5, multiprocess=True)
return total_patches
def test_keyboard_interrupt():
exception_node = EONode(KeyboardExceptionTask())
workflow = EOWorkflow([exception_node])
execution_kwargs = []
for _ in range(10):
execution_kwargs.append({exception_node: {"arg1": 1}})
run_kwargs = [{"workers": 1}, {"workers": 3, "multiprocess": True}, {"workers": 3, "multiprocess": False}]
for kwarg in run_kwargs:
with pytest.raises(KeyboardInterrupt):
EOExecutor(workflow, execution_kwargs).run(**kwarg)
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_report_creation(save_logs, include_logs):
with tempfile.TemporaryDirectory() as tmp_dir_name:
executor = EOExecutor(
WORKFLOW,
EXECUTION_KWARGS,
logs_folder=tmp_dir_name,
save_logs=save_logs,
execution_names=["ex 1", 2, 0.4, None],
)
executor.run(workers=10)
executor.make_report(include_logs=include_logs)
assert os.path.exists(
executor.get_report_path()), "Execution report was not created"
def test_execution_errors(multiprocess, workflow, execution_kwargs):
with tempfile.TemporaryDirectory() as tmp_dir_name:
executor = EOExecutor(workflow, execution_kwargs, logs_folder=tmp_dir_name)
executor.run(workers=5, multiprocess=multiprocess)
for idx, results in enumerate(executor.execution_results):
if idx == 3:
assert results.workflow_failed()
else:
assert not results.workflow_failed()
assert executor.get_successful_executions() == [0, 1, 2]
assert executor.get_failed_executions() == [3]
def test_keyboardInterrupt(self):
exeption_task = KeyboardExceptionTask()
workflow = LinearWorkflow(exeption_task)
execution_args = []
for _ in range(10):
execution_args.append({exeption_task: {'arg1': 1}})
run_args = [{
'workers': 1
}, {
'workers': 3,
'multiprocess': True
}, {
'workers': 3,
'multiprocess': False
}]
for arg in run_args:
self.assertRaises(KeyboardInterrupt,
EOExecutor(workflow, execution_args).run, **arg)
def test_execution_errors(self):
for multiprocess in [True, False]:
with tempfile.TemporaryDirectory() as tmp_dir_name:
executor = EOExecutor(self.workflow, self.execution_args, logs_folder=tmp_dir_name)
executor.run(workers=5, multiprocess=multiprocess)
for idx, stats in enumerate(executor.execution_stats):
if idx != 3:
self.assertFalse('error' in stats, 'Workflow {} should be executed without errors'.format(idx))
else:
self.assertTrue('error' in stats and stats['error'],
'This workflow should be executed with an error')
self.assertEqual(executor.get_successful_executions(), [0, 1, 2])
self.assertEqual(executor.get_failed_executions(), [3])
for i in range(len(patchIDs)):
execution_args.append({
load: {
'eopatch_folder': 'eopatch_{}'.format(i)
},
export_tiff: {
'filename':
'{}/prediction_eopatch_{}.tiff'.format(tiff_location, i)
},
save: {
'eopatch_folder': 'eopatch_{}'.format(i)
}
})
# run the executor on 2 cores
executor = EOExecutor(workflow, execution_args)
executor.run(workers=2)
# uncomment below save the logs in the current directory and produce a report!
#executor = EOExecutor(workflow, execution_args, save_logs=True)
#executor.run(workers = 2)
#executor.make_report()
#%%Plot: Frequency of classes
fig = plt.figure(figsize=(15, 8))
label_ids, label_counts = np.unique(labels_train, return_counts=True)
plt.bar(range(len(label_ids)), label_counts)
plt.xticks(range(len(label_ids)), [class_names[i] for i in label_ids],
workflow = LinearWorkflow(add_data, save)
# Execute the workflow
# define additional parameters of the workflow
execution_args = []
for idx, bbox in enumerate(bbox_list[patchIDs]):
execution_args.append({
add_data: {
'bbox': bbox
},
save: {
'eopatch_folder': 'eopatch_{}'.format(idx)
}
})
executor = EOExecutor(workflow, execution_args, save_logs=True)
executor.run(workers=5, multiprocess=False)
# should install graphviz
# executor.make_report()
# Load GeogeniusEOPatch
eopatch = GeogeniusEOPatch.load(path=os.path.join(path_out,
'eopatch_{}'.format(0)),
lazy_loading=True)
print(eopatch)
# Print data
print(eopatch.get_feature(FeatureType.DATA, 'BANDS'))
# Convert all patches to tiff
tiff_out = get_current_folder("tiff")
def download_data(path_save,
coords_top,
coords_bot,
patch_n,
s_date,
e_date,
debug=False):
# before moving onto actual tasks, check setup
check_sentinel_cfg()
[lat_left_top, lon_left_top] = coords_top
[lat_right_bot, lon_right_bot] = coords_bot
# TASK FOR BAND DATA
# add a request for B(B02), G(B03), R(B04), NIR (B08), SWIR1(B11), SWIR2(B12)
# from default layer 'ALL_BANDS' at 10m resolution
# Here we also do a simple filter of cloudy scenes. A detailed cloud cover
# detection is performed in the next step
custom_script = "return [B02, B03, B04, B08, B11, B12];"
add_data = S2L1CWCSInput(
layer="BANDS-S2-L1C",
feature=(FeatureType.DATA, "BANDS"), # save under name 'BANDS'
# custom url for 6 specific bands
custom_url_params={CustomUrlParam.EVALSCRIPT: custom_script},
resx="10m", # resolution x
resy="10m", # resolution y
maxcc=0.1, # maximum allowed cloud cover of original ESA tiles
)
# TASK FOR CLOUD INFO
# cloud detection is performed at 80m resolution
# and the resulting cloud probability map and mask
# are scaled to EOPatch's resolution
cloud_classifier = get_s2_pixel_cloud_detector(average_over=2,
dilation_size=1,
all_bands=False)
add_clm = AddCloudMaskTask(
cloud_classifier,
"BANDS-S2CLOUDLESS",
cm_size_y="80m",
cm_size_x="80m",
cmask_feature="CLM", # cloud mask name
cprobs_feature="CLP", # cloud prob. map name
)
# TASKS FOR CALCULATING NEW FEATURES
# NDVI: (B08 - B04)/(B08 + B04)
# NDWI: (B03 - B08)/(B03 + B08)
# NORM: sqrt(B02^2 + B03^2 + B04^2 + B08^2 + B11^2 + B12^2)
ndvi = NormalizedDifferenceIndex("NDVI", "BANDS/3", "BANDS/2")
ndwi = NormalizedDifferenceIndex("NDWI", "BANDS/1", "BANDS/3")
norm = EuclideanNorm("NORM", "BANDS")
# TASK FOR VALID MASK
# validate pixels using SentinelHub's cloud detection mask and region of acquisition
add_sh_valmask = AddValidDataMaskTask(
SentinelHubValidData(),
"IS_VALID" # name of output mask
)
# TASK FOR COUNTING VALID PIXELS
# count number of valid observations per pixel using valid data mask
count_val_sh = CountValid(
"IS_VALID",
"VALID_COUNT" # name of existing mask # name of output scalar
)
# TASK FOR SAVING TO OUTPUT (if needed)
path_save = Path(path_save)
path_save.mkdir(exist_ok=True)
# if not os.path.isdir(path_save):
# os.makedirs(path_save)
save = SaveToDisk(path_save,
overwrite_permission=OverwritePermission.OVERWRITE_PATCH)
# Define the workflow
workflow = LinearWorkflow(add_data, add_clm, ndvi, ndwi, norm,
add_sh_valmask, count_val_sh, save)
# Execute the workflow
# time interval for the SH request
# TODO: need to check if specified time interval is valid
time_interval = [s_date, e_date]
# define additional parameters of the workflow
execution_args = []
path_EOPatch = path_save / f"eopatch_{patch_n}"
execution_args.append({
add_data: {
"bbox":
BBox(
((lon_left_top, lat_left_top), (lon_right_bot, lat_right_bot)),
crs=CRS.WGS84,
),
"time_interval":
time_interval,
},
save: {
"eopatch_folder": path_EOPatch.stem
},
})
executor = EOExecutor(workflow, execution_args, save_logs=True)
if debug:
print("Downloading Satellite data ...")
executor.run(workers=2, multiprocess=False)
if executor.get_failed_executions():
raise RuntimeError("EOExecutor failed in finishing tasks!")
if debug:
executor.make_report()
if debug:
print("Satellite data is downloaded")
return path_EOPatch
ndwi,
ndbi,
save,
)
time_interval = {
'18/19': ['2018-11-01', '2019-05-01'],
'19/20': ['2019-11-01', '2020-05-01'],
}
downloaded = os.listdir(SAVE_PATH)
downloaded = list(map(lambda x: int(x.split('_')[1]), downloaded))
execution_args = []
for id, row in gdf.loc[~gdf.index.isin(downloaded), :].iterrows():
bbox = row.geometry.bounds
bbox = BBox(bbox, CRS('32720'))
execution_args.append({
add_data: {
'bbox': bbox,
'time_interval': time_interval[row.Campania]
},
save: {
'eopatch_folder': f'eopatch_{id}'
}
})
executor = EOExecutor(workflow, execution_args)
executor.run(workers=None, multiprocess=True)
executor.make_report()
def load_LPIS(country, year, path, no_patches):
patch_location = path + '/{}/'.format(country)
load = LoadFromDisk(patch_location)
save_path_location = patch_location
if not os.path.isdir(save_path_location):
os.makedirs(save_path_location)
save = SaveToDisk(save_path_location,
overwrite_permission=OverwritePermission.OVERWRITE_PATCH)
# workflow_data = get_create_and_add_lpis_workflow(country, year, save_path_location)
name_of_feature = 'LPIS_{}'.format(year)
groups_to_number, crops_to_number = create_mapping(country)
layer_id = GEOPEDIA_LPIS_LAYERS[f'{country}_LPIS_{year}']
ftr_name = f'LPIS_{year}'
year_filter = (
GEOPEDIA_LPIS_YEAR_NAME[country],
year) if GEOPEDIA_LPIS_YEAR_NAME[country] is not None else None
add_lpis = AddGeopediaVectorFeature(
(FeatureType.VECTOR_TIMELESS, ftr_name),
layer=layer_id,
year_filter=year_filter,
drop_duplicates=True)
area_ratio = AddAreaRatio(
(FeatureType.VECTOR_TIMELESS, ftr_name),
(FeatureType.SCALAR_TIMELESS, 'FIELD_AREA_RATIO'))
fixlpis = FixLPIS(feature=name_of_feature, country=country)
rasterize = VectorToRaster(vector_input=(FeatureType.VECTOR_TIMELESS,
name_of_feature),
raster_feature=(FeatureType.MASK_TIMELESS,
name_of_feature),
values=None,
values_column='GROUP',
raster_shape=(FeatureType.DATA, 'BANDS'),
raster_dtype=np.int16,
no_data_value=np.nan)
add_group = AddGroup(crops_to_number, name_of_feature)
remove_dtf = RemoveFeature(FeatureType.VECTOR_TIMELESS, name_of_feature)
exclude = WorkflowExclude(area_ratio, fixlpis, add_group, rasterize,
remove_dtf)
workflow = LinearWorkflow(load, add_lpis, exclude, save)
execution_args = []
for i in range(no_patches):
execution_args.append({
load: {
'eopatch_folder': 'eopatch_{}'.format(i)
},
save: {
'eopatch_folder': 'eopatch_{}'.format(i)
}
})
##### here you choose how many processes/threads you will run, workers=none is max of processors
executor = EOExecutor(workflow,
execution_args,
save_logs=True,
logs_folder='ExecutionLogs')
# executor.run(workers=None, multiprocess=True)
executor.run()
