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 test_get_tasks(self):
in_task = InputTask()
inc_task = Inc()
pow_task = Pow()
task_names = ['InputTask', 'Inc', 'Pow']
workflow_tasks = [in_task, inc_task, pow_task]
eow = LinearWorkflow(*workflow_tasks)
returned_tasks = eow.get_tasks()
# check if tasks are present
for task_name in task_names:
self.assertIn(task_name, returned_tasks.keys())
# check if tasks still work
arguments_dict = {
in_task: {'val': 2},
inc_task: {'d': 2},
pow_task: {'n': 3}
}
res_workflow = eow.execute(arguments_dict)
res_workflow_value = [res_workflow[key] for key in res_workflow.keys()][0]
for idx, task in enumerate(workflow_tasks):
if idx == 0:
res_tasks_value = task.execute(**arguments_dict[task])
else:
res_tasks_value = task.execute(res_tasks_value, **arguments_dict[task])
self.assertEqual(res_workflow_value, res_tasks_value)
def test_get_tasks(self):
in_task = InputTask()
inc_task = Inc()
task_names = ['InputTask', 'Inc', 'Inc_1', 'Inc_2']
eow = LinearWorkflow(in_task, inc_task, inc_task, inc_task)
returned_tasks = eow.get_tasks()
# check if tasks are present
self.assertEqual(sorted(task_names), sorted(returned_tasks))
# check if tasks still work
arguments_dict = {in_task: {'val': 2}, inc_task: {'d': 2}}
res_workflow = eow.execute(arguments_dict)
res_workflow_value = list(res_workflow.values())
res_tasks_values = []
for idx, task in enumerate(returned_tasks.values()):
res_tasks_values = [
task.execute(*res_tasks_values, **arguments_dict.get(task, {}))
]
self.assertEqual(res_workflow_value, res_tasks_values)
def test_linear_workflow(self):
in_task = InputTask()
in_task_name = 'My input task'
inc_task = Inc()
pow_task = Pow()
eow = LinearWorkflow((in_task, in_task_name), inc_task, inc_task,
pow_task)
res = eow.execute({
in_task: {
'val': 2
},
inc_task: {
'd': 2
}, # Note that this will assign value only to one instance of Inc task
pow_task: {
'n': 3
}
})
self.assertEqual(res[pow_task], (2 + 2 + 1)**3)
task_map = eow.get_tasks()
self.assertTrue(
in_task_name in task_map,
"A task with name '{}' should be amongst tasks".format(
in_task_name))
self.assertEqual(
task_map[in_task_name], in_task,
"A task with name '{}' should map into {}".format(
in_task_name, in_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 test_linear_workflow(self):
in_task = InputTask()
inc_task = Inc()
pow_task = Pow()
eow = LinearWorkflow((in_task, 'task name'), inc_task, inc_task, pow_task)
res = eow.execute({
in_task: {'val': 2},
inc_task: {'d': 2}, # Note that this will assign value only to one instance of Inc task
pow_task: {'n': 3}
})
self.assertEqual(res[pow_task], (2 + 2 + 1) ** 3)
def test_linear_workflow(self):
in_task = InputTask()
inc_task = Inc()
pow_task = Pow()
eow = LinearWorkflow(in_task, inc_task, pow_task)
res = eow.execute({
in_task: {'val': 2},
inc_task: {'d': 2},
pow_task: {'n': 3}
})
self.assertEqual(res[pow_task], (2+2)**3)
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 get_elevation(self, bounds):
INSTANCE_ID = '4aaea2ec-3a2c-4e1c-8a51-851e220d0273'
roi = BBox(bbox=bounds, crs=CRS.WGS84)
layer = 'MAPZEN_DEM'
time_interval = ('2019-01-01', '2019-06-01')
add_dem = DEMWCSInput(layer=layer, instance_id=INSTANCE_ID)
input_task = S2L1CWCSInput(layer=layer,
resx='30m',
resy='30m',
instance_id=INSTANCE_ID)
workflow = LinearWorkflow(input_task, add_dem)
result = workflow.execute(
{input_task: {
'bbox': roi,
'time_interval': time_interval
}})
eopatch = list(result.values())[0]
return eopatch
count_val_sh, save)
for idx, bbox in enumerate(bbox_list[patchIDs]):
# define additional parameters of the workflow
extra_param = {
add_data: {
'bbox': bbox,
'time_interval': time_interval
},
save: {
'eopatch_folder': 'eopatch_{}'.format(idx)
}
}
workflow.execute(extra_param)
print('Download finished')
#%% Check the IS_VALID npy array
#isvalid = np.load('./eopatches_large/eopatch_0/mask/IS_VALID.npy')
#print(np.sum(isvalid))
#print(np.size(isvalid) - np.count_nonzero(isvalid))
#%% See the structure of a selected EOPatch
EOPatch.load('./eopatches_large/eopatch_3/')
#%% Section 5
ValidDataCoveragePredicate(cloud_coverage_threshold))
water_detection = WaterDetector()
# Define the EOWorkflow
workflow = LinearWorkflow(download_task, calculate_ndwi,
add_nominal_water, add_valid_mask,
add_coverage, remove_cloudy_scenes,
water_detection)
# Run the workflow
time_interval = [input_json["startDate"], input_json["endDate"]]
result = workflow.execute({
download_task: {
'bbox': dam_bbox,
'time_interval': time_interval
},
})
eopatch = list(result.values())[-1]
output = []
for i in range(len(eopatch.scalar['WATER_LEVEL'])):
numpyData = {
"measurement_date":
eopatch.timestamp[i].strftime('%d/%m/%Y'),
"bbox":
eopatch.bbox.geometry.bounds,
"crs":
eopatch.bbox.crs.epsg,
eopatch.add_feature(FeatureType.SCALAR, 'WATER_LEVEL',
water_levels[..., np.newaxis])
return eopatch
water_det = WaterDetector()
workflow = LinearWorkflow(input_task, add_ndwi, cloud_det, add_nominal_water,
add_valmask, add_coverage, remove_cloudy_scenes,
water_det)
time_interval = ['2015-01-01', '2018-08-31']
result = workflow.execute({
input_task: {
'bbox': dam_bbox,
'time_interval': time_interval
},
})
patch = list(result.values())[-1]
from skimage.filters import sobel
from skimage.morphology import disk
from skimage.morphology import erosion, dilation, opening, closing, white_tophat
def plot_rgb_w_water(eopatch, idx):
ratio = np.abs(eopatch.bbox.max_x -
eopatch.bbox.min_x) / np.abs(eopatch.bbox.max_y -
eopatch.bbox.min_y)
fig, ax = plt.subplots(figsize=(ratio * 10, 10))
# ---------------------------------------------------------------------------------------------------------- #
# eo-learn request
input_task = SentinelHubInputTask(
data_collection=DataCollection.SENTINEL2_L1C,
additional_data=[(FeatureType.DATA, 'CLP'),
(FeatureType.MASK, 'dataMask')],
time_difference=datetime.timedelta(seconds=1),
resolution=60,
config=config)
timelapse = LinearWorkflow(input_task)
try:
result = timelapse.execute(
{input_task: {
'bbox': full_bbox,
'time_interval': time_interval
}})
except:
continue
# parse cloud images and register useful blocks
blocks_per_timestamp = {}
l = result.eopatch()
for i in range(len(l.data['CLP'])):
print('Parsing image {} of {}.'.format(i + 1, len(l.data['CLP'])))
sys.stdout.flush()
# get cloud mask and mask of valid pixels
cloud_mask = np.asarray(l.data['CLP'][i], dtype=np.float32) / 255.0
mask = np.asarray(l.mask['dataMask'][i], dtype=np.int32)
