def processing_task(task_id=None, geo_chunk_id=None, time_chunk_id=None, geographic_chunk=None, time_chunk=None, **parameters): """Process a parameter set and save the results to disk. Uses the geographic and time chunk id to identify output products. **params is updated with time and geographic ranges then used to load data. the task model holds the iterative property that signifies whether the algorithm is iterative or if all data needs to be loaded at once. Args: task_id, geo_chunk_id, time_chunk_id: identification for the main task and what chunk this is processing geographic_chunk: range of latitude and longitude to load - dict with keys latitude, longitude time_chunk: list of acquisition dates parameters: all required kwargs to load data. Returns: path to the output product, metadata dict, and a dict containing the geo/time ids """ chunk_id = "_".join([str(geo_chunk_id), str(time_chunk_id)]) task = CustomMosaicToolTask.objects.get(pk=task_id) logger.info("Starting chunk: " + chunk_id) if not os.path.exists(task.get_temp_path()): return None iteration_data = None metadata = {} def _get_datetime_range_containing(*time_ranges): return (min(time_ranges) - timedelta(microseconds=1), max(time_ranges) + timedelta(microseconds=1)) times = list( map(_get_datetime_range_containing, time_chunk) if task.get_iterative() else [_get_datetime_range_containing(time_chunk[0], time_chunk[-1])]) dc = DataAccessApi(config=task.config_path) updated_params = parameters updated_params.update(geographic_chunk) #updated_params.update({'products': parameters['']}) iteration_data = None base_index = (task.get_chunk_size()['time'] if task.get_chunk_size()['time'] is not None else 1) * time_chunk_id for time_index, time in enumerate(times): updated_params.update({'time': time}) data = dc.get_stacked_datasets_by_extent(**updated_params) if data is None or 'time' not in data: logger.info("Invalid chunk.") continue clear_mask = create_cfmask_clean_mask(data.cf_mask) if 'cf_mask' in data else create_bit_mask(data.pixel_qa, [1, 2]) add_timestamp_data_to_xr(data) metadata = task.metadata_from_dataset(metadata, data, clear_mask, updated_params) iteration_data = task.get_processing_method()(data, clean_mask=clear_mask, intermediate_product=iteration_data) if task.animated_product.animation_id != "none": path = os.path.join(task.get_temp_path(), "animation_{}_{}.nc".format(str(geo_chunk_id), str(base_index + time_index))) if task.animated_product.animation_id == "scene": #need to clear out all the metadata.. clear_attrs(data) #can't reindex on time - weird? data.isel(time=0).drop('time').to_netcdf(path) elif task.animated_product.animation_id == "cumulative": iteration_data.to_netcdf(path) task.scenes_processed = F('scenes_processed') + 1 task.save() path = os.path.join(task.get_temp_path(), chunk_id + ".nc") if iteration_data is None: return None iteration_data.to_netcdf(path) dc.close() logger.info("Done with chunk: " + chunk_id) return path, metadata, {'geo_chunk_id': geo_chunk_id, 'time_chunk_id': time_chunk_id}
def processing_task(task_id=None, geo_chunk_id=None, time_chunk_id=None, geographic_chunk=None, time_chunk=None, **parameters): """Process a parameter set and save the results to disk. Uses the geographic and time chunk id to identify output products. **params is updated with time and geographic ranges then used to load data. the task model holds the iterative property that signifies whether the algorithm is iterative or if all data needs to be loaded at once. Args: task_id, geo_chunk_id, time_chunk_id: identification for the main task and what chunk this is processing geographic_chunk: range of latitude and longitude to load - dict with keys latitude, longitude time_chunk: list of acquisition dates parameters: all required kwargs to load data. Returns: path to the output product, metadata dict, and a dict containing the geo/time ids """ chunk_id = "_".join([str(geo_chunk_id), str(time_chunk_id)]) task = TsmTask.objects.get(pk=task_id) logger.info("Starting chunk: " + chunk_id) if not os.path.exists(task.get_temp_path()): return None metadata = {} def _get_datetime_range_containing(*time_ranges): return (min(time_ranges) - timedelta(microseconds=1), max(time_ranges) + timedelta(microseconds=1)) times = list( map(_get_datetime_range_containing, time_chunk) if task.get_iterative( ) else [_get_datetime_range_containing(time_chunk[0], time_chunk[-1])]) dc = DataAccessApi(config=task.config_path) updated_params = parameters updated_params.update(geographic_chunk) #updated_params.update({'products': parameters['']}) water_analysis = None tsm_analysis = None combined_data = None base_index = (task.get_chunk_size()['time'] if task.get_chunk_size() ['time'] is not None else 1) * time_chunk_id for time_index, time in enumerate(times): updated_params.update({'time': time}) data = dc.get_stacked_datasets_by_extent(**updated_params) if data is None or 'time' not in data: logger.info("Invalid chunk.") continue clear_mask = create_cfmask_clean_mask( data.cf_mask) if 'cf_mask' in data else create_bit_mask( data.pixel_qa, [1, 2]) wofs_data = task.get_processing_method()(data, clean_mask=clear_mask, enforce_float64=True) water_analysis = perform_timeseries_analysis( wofs_data, 'wofs', intermediate_product=water_analysis) clear_mask[(data.swir2.values > 100) | (wofs_data.wofs.values == 0)] = False tsm_data = tsm(data, clean_mask=clear_mask, no_data=-9999) tsm_analysis = perform_timeseries_analysis( tsm_data, 'tsm', intermediate_product=tsm_analysis, no_data=-9999) combined_data = tsm_analysis combined_data['wofs'] = water_analysis.total_data combined_data['wofs_total_clean'] = water_analysis.total_clean metadata = task.metadata_from_dataset(metadata, tsm_data, clear_mask, updated_params) if task.animated_product.animation_id != "none": path = os.path.join( task.get_temp_path(), "animation_{}_{}.nc".format(str(geo_chunk_id), str(base_index + time_index))) animated_data = tsm_data.isel( time=0, drop=True ) if task.animated_product.animation_id == "scene" else combined_data animated_data.to_netcdf(path) task.scenes_processed = F('scenes_processed') + 1 task.save() if combined_data is None: return None path = os.path.join(task.get_temp_path(), chunk_id + ".nc") combined_data.to_netcdf(path) dc.close() logger.info("Done with chunk: " + chunk_id) return path, metadata, { 'geo_chunk_id': geo_chunk_id, 'time_chunk_id': time_chunk_id }