def query_cells(xcells, ycells, satellites, min_date, max_date, dataset_types,
output_dir):
"""
Query the DB for each cell.
Currently the config file for this workflow requires the user to
specify a rectangular region. I have another workflow that takes a
vector file as input.
"""
base_out_fname = CONFIG.get('outputs', 'query_filename')
cell_queries = []
for ycell in ycells:
for xcell in xcells:
# create the output directory
cell_dir = '{}_{}'.format(int(xcell), int(ycell))
out_cell_dir = pjoin(output_dir, cell_dir)
if not exists(out_cell_dir):
os.makedirs(out_cell_dir)
tiles = list_tiles_as_list(x=[xcell], y=[ycell],
acq_min=min_date,
acq_max=max_date,
dataset_types=dataset_types,
satellites=satellites)
out_fname = pjoin(out_cell_dir, base_out_fname)
cell_queries.append(out_fname)
with open(out_fname, 'w') as outf:
pickle.dump(tiles, outf)
return cell_queries
def test_list_tiles_120_020_2005_ls578_no_ls8_pre_wrs_2(config=None):
dataset_types = [DatasetType.ARG25, DatasetType.PQ25, DatasetType.FC25]
tiles = list_tiles_as_list(x=[TEST_CELL_X], y=[TEST_CELL_Y],
acq_min=parse_date_min(TEST_YEAR_STR),
acq_max=parse_date_max(TEST_YEAR_STR),
satellites=[Satellite.LS5, Satellite.LS7, Satellite.LS8],
dataset_types=dataset_types,
exclude=[LS8_PRE_WRS_2_EXCLUSION],
config=config)
assert(tiles and len(list(tiles)) > 0)
for tile in tiles:
_log.info("Found tile xy = %s", tile.xy)
dataset = tile.datasets[DatasetType.ARG25]
assert dataset
_log.info("Found ARG25 dataset [%s]", dataset.path)
assert(tile.x == TEST_CELL_X and tile.y == TEST_CELL_Y and tile.xy == (TEST_CELL_X, TEST_CELL_Y)
and tile.end_datetime_year == TEST_YEAR
and (ds in tile.datasets for ds in dataset_types)
and (dataset.satellite != Satellite.LS8 or tile.end_datetime.date() >= LS8_PRE_WRS_2_ACQ_MAX))
def query_cells2(xcells, ycells, satellites, min_date, max_date, dataset_types,
output_dir):
"""
Query the DB for each cell.
Currently the config file for this workflow requires the user to
specify a rectangular region. I have another workflow that takes a
vector file as input.
"""
base_out_fname = CONFIG.get('outputs', 'query_filename')
cell_queries = []
for i in range(len(ycells)):
ycell = ycells[i]
xcell = xcells[i]
# create the output directory
#cell_dir = '{}_{}'.format(int(xcell), int(ycell))
cell_dir = str(xcell) + "_" + str(ycell).zfill(4)
out_cell_dir = pjoin(output_dir, cell_dir)
if not exists(out_cell_dir):
os.makedirs(out_cell_dir)
tiles = list_tiles_as_list(x=[xcell],
y=[ycell],
acq_min=min_date,
acq_max=max_date,
dataset_types=dataset_types,
satellites=satellites)
out_fname = pjoin(out_cell_dir, base_out_fname)
cell_queries.append(out_fname)
with open(out_fname, 'w') as outf:
pickle.dump(tiles, outf)
return cell_queries
def test_retrieve_data_ls5_mndwi(config=None):
filename = "LS5_TM_MNDWI_{x:03d}_{y:04d}_{date}.{x_offset:04d}_{y_offset:04d}.{x_size:04d}x{y_size:04d}.tif".format(x=CELL_X, y=CELL_Y, date=DATE, x_offset=X_OFFSET, y_offset=Y_OFFSET, x_size=X_SIZE, y_size=Y_SIZE)
tiles = list_tiles_as_list(x=[CELL_X], y=[CELL_Y],
acq_min=ACQ_LS5, acq_max=ACQ_LS5,
satellites=[Satellite.LS5],
dataset_types=[MNDWI_DATASET_TYPE],
config=config)
assert len(tiles) == 1
dataset = tiles[0].datasets[MNDWI_DATASET_TYPE]
data = get_dataset_data(dataset=dataset, x=X_OFFSET, y=Y_OFFSET, x_size=X_SIZE, y_size=Y_SIZE)
assert(data)
_log.info("data is [%s]\n%s", numpy.shape(data), data)
ndv = get_dataset_ndv(dataset)
assert(is_ndv(ndv, MNDWI_NDV))
data_type = get_dataset_datatype(dataset)
assert(data_type == MNDWI_DATA_TYPE)
metadata = generate_dataset_metadata(x=CELL_X, y=CELL_Y, acq_dt=ACQ_LS5,
dataset=dataset, bands=None,
mask_pqa_apply=False, mask_pqa_mask=None,
mask_wofs_apply=False, mask_wofs_mask=None)
raster_create_geotiff(filename, [data[b] for b in dataset.bands], CELL_GEO_TRANSFORM, CELL_PROJECTION, ndv, data_type,
dataset_metadata=metadata, band_ids=[b.name for b in dataset.bands])
assert filecmp.cmp(filename, get_test_data_path(filename))
def test_get_dataset_stack():
tiles = list_tiles_as_list(x=[120], y=[-20], satellites=[Satellite.LS5, Satellite.LS7],
acq_min=date(2014, 1, 1), acq_max=date(2014, 12, 31),
dataset_types=[DatasetType.ARG25, DatasetType.PQ25])
_log.info("\nFound %d tiles", len(tiles))
stack = get_dataset_data_stack(tiles, DatasetType.ARG25, Ls57Arg25Bands.BLUE.name, ndv=NDV,
mask_pqa_apply=True, mask_pqa_mask=[PqaMask.PQ_MASK_CLEAR])
_log.info("\nStack is %s", numpy.shape(stack))
def test_retrieve_data_ls5_arg_with_pqa_water_mask_dry(config=None):
filename = "LS5_TM_NBAR_WITH_PQA_WATER_DRY_{x:03d}_{y:04d}_{date}.{x_offset:04d}_{y_offset:04d}.{x_size:04d}x{y_size:04d}.tif".format(x=CELL_X, y=CELL_Y, date=DATE, x_offset=X_OFFSET, y_offset=Y_OFFSET, x_size=X_SIZE, y_size=Y_SIZE)
tiles = list_tiles_as_list(x=[CELL_X], y=[CELL_Y],
acq_min=ACQ_LS5, acq_max=ACQ_LS5,
satellites=[Satellite.LS5],
dataset_types=[ARG_DATASET_TYPE, PQ_DATASET_TYPE, WOFS_DATASET_TYPE],
config=config)
assert len(tiles) == 1
tile = tiles[0]
assert ARG_DATASET_TYPE in tile.datasets
dataset = tile.datasets[ARG_DATASET_TYPE]
assert PQ_DATASET_TYPE in tile.datasets
pqa = tile.datasets[PQ_DATASET_TYPE]
assert WOFS_DATASET_TYPE in tile.datasets
wofs = tile.datasets[WOFS_DATASET_TYPE]
mask = get_mask_pqa(pqa, x=X_OFFSET, y=Y_OFFSET, x_size=X_SIZE, y_size=Y_SIZE)
mask = get_mask_wofs(wofs, wofs_masks=[WofsMask.DRY, WofsMask.NO_DATA, WofsMask.SATURATION_CONTIGUITY,
WofsMask.SEA_WATER, WofsMask.TERRAIN_SHADOW, WofsMask.HIGH_SLOPE,
WofsMask.CLOUD_SHADOW, WofsMask.CLOUD],
x=X_OFFSET, y=Y_OFFSET, x_size=X_SIZE, y_size=Y_SIZE, mask=mask)
data = get_dataset_data_masked(dataset=dataset, x=X_OFFSET, y=Y_OFFSET, x_size=X_SIZE, y_size=Y_SIZE, mask=mask)
assert(data)
_log.info("data is [%s]\n%s", numpy.shape(data), data)
ndv = get_dataset_ndv(dataset)
assert(is_ndv(ndv, ARG_NDV))
data_type = get_dataset_datatype(dataset)
assert(data_type == ARG_DATA_TYPE)
metadata = generate_dataset_metadata(x=CELL_X, y=CELL_Y, acq_dt=ACQ_LS5,
dataset=dataset, bands=None,
mask_pqa_apply=False, mask_pqa_mask=None,
mask_wofs_apply=False, mask_wofs_mask=None)
raster_create_geotiff(filename, [data[b] for b in dataset.bands], CELL_GEO_TRANSFORM, CELL_PROJECTION, ndv, data_type,
dataset_metadata=metadata, band_ids=[b.name for b in dataset.bands])
assert filecmp.cmp(filename, get_test_data_path(filename))
def get_tiles(x, y, satellites, acq_min, acq_max, season, dataset_type, mask_pqa_apply):
acq_min, acq_max, criteria = build_season_date_criteria(acq_min, acq_max, season,
seasons=SEASONS, extend=True)
dataset_types = [dataset_type]
if mask_pqa_apply:
dataset_types.append(DatasetType.PQ25)
tiles = list_tiles_as_list(x=[x], y=[y], satellites=satellites,
acq_min=acq_min, acq_max=acq_max,
dataset_types=dataset_types, include=criteria)
return tiles
def get_tiles(self):
acq_min, acq_max, criteria = build_season_date_criteria(self.acq_min, self.acq_max, self.season,
seasons=SEASONS, extend=True)
_log.info("\tcriteria is %s", criteria)
dataset_types = [self.dataset_type]
if self.mask_pqa_apply:
dataset_types.append(DatasetType.PQ25)
tiles = list_tiles_as_list(x=[self.x], y=[self.y], satellites=self.satellites,
acq_min=acq_min, acq_max=acq_max,
dataset_types=dataset_types, include=criteria)
return tiles
def get_tiles(self):
acq_min, acq_max, criteria = build_season_date_criteria(self.acq_min, self.acq_max, self.season,
seasons=SEASONS, extend=True)
_log.info("\tcriteria is %s", criteria)
dataset_types = [self.dataset_type]
if self.mask_pqa_apply:
dataset_types.append(DatasetType.PQ25)
tiles = list_tiles_as_list(x=[self.x], y=[self.y], satellites=self.satellites,
acq_min=acq_min, acq_max=acq_max,
dataset_types=dataset_types, include=criteria)
return tiles
def query_cells(cell_list, satellites, min_date, max_date, dataset_types,
output_dir):
"""
"""
base_out_fname = CONFIG.get('outputs', 'query_filename')
for cell in cell_list:
x_cell = [int(cell[0])]
y_cell = [int(cell[1])]
tiles = list_tiles_as_list(x=x_cell, y=y_cell, acq_min=min_date,
acq_max=max_date,
dataset_types=dataset_types,
satellites=satellites)
out_dir = pjoin(output_dir, '{}_{}'.format(cell[0], cell[1]))
out_fname = pjoin(out_dir, base_out_fname)
with open(out_fname, 'w') as outf:
pickle.dump(tiles, outf)
def test_list_tiles_120_020_2005_ls578(config=None):
dataset_types = [DatasetType.ARG25, DatasetType.PQ25, DatasetType.FC25]
tiles = list_tiles_as_list(x=[TEST_CELL_X], y=[TEST_CELL_Y],
acq_min=parse_date_min(TEST_YEAR_STR), acq_max=parse_date_max(TEST_YEAR_STR),
satellites=[Satellite.LS5, Satellite.LS7, Satellite.LS8],
dataset_types=dataset_types,
config=config)
assert(tiles and len(list(tiles)) > 0)
for tile in tiles:
_log.info("Found tile xy = %s", tile.xy)
assert(tile.x == TEST_CELL_X and tile.y == TEST_CELL_Y and tile.xy == (TEST_CELL_X, TEST_CELL_Y)
and tile.end_datetime_year == TEST_YEAR
and ds in tile.datasets for ds in dataset_types)
def query_cells2(xcells, ycells, satellites, min_date, max_date, dataset_types,
output_dir):
"""
Query the DB for each cell.
Currently the config file for this workflow requires the user to
specify a rectangular region. I have another workflow that takes a
vector file as input.
"""
base_out_fname = CONFIG.get('outputs', 'query_filename')
cell_queries = []
for i in range(len(ycells)):
ycell = ycells[i]
xcell = xcells[i]
# create the output directory
#cell_dir = '{}_{}'.format(int(xcell), int(ycell))
cell_dir = str(xcell) + "_" + str(ycell).zfill(4)
out_cell_dir = pjoin(output_dir, cell_dir)
if not exists(out_cell_dir):
os.makedirs(out_cell_dir)
tiles = list_tiles_as_list(x=[xcell],
y=[ycell],
acq_min=min_date,
acq_max=max_date,
dataset_types=dataset_types,
satellites=satellites)
fileTile = []
lines = load_filterfile(xcell, ycell)
cnt = 0
print "\tlength of original tiles is ", len(tiles)
for tile in tiles:
#import pdb; pdb.set_trace()
cnt = cnt + 1
dataset = tile.datasets[DatasetType.ARG25]
tdate = str(tile.end_datetime.strftime("%Y-%m-%d"))
if tdate in lines:
fileTile.append(tile)
out_fname = pjoin(out_cell_dir, base_out_fname)
cell_queries.append(out_fname)
with open(out_fname, 'w') as outf:
pickle.dump(fileTile, outf)
print "\tlength of new filtered tiles is %d", len(fileTile)
return cell_queries
def test_query():
workflow = Arg25BandStatisticsWorkflow()
workflow.x_min = workflow.x_max = TEST_X
workflow.y_min = workflow.y_max = TEST_Y
workflow.acq_min = parse_date_min("1985")
workflow.acq_max = parse_date_max("2014")
workflow.epoch = EpochParameter(5, 6)
workflow.seasons = Season
workflow.seasons = [Season.SUMMER]
workflow.satellites = [Satellite.LS5, Satellite.LS7]
workflow.mask_pqa_apply = True
workflow.mask_pqa_mask = [PqaMask.PQ_MASK_SATURATION, PqaMask.PQ_MASK_CONTIGUITY, PqaMask.PQ_MASK_CLOUD]
workflow.dataset_type = DatasetType.ARG25
workflow.bands = Ls57Arg25Bands
epochs = list(workflow.get_epochs())
print ""
print "epochs are", epochs
for season, epoch in product(workflow.seasons, epochs):
print season, epoch
from datacube.api.utils import build_season_date_criteria
acq_min, acq_max, criteria = build_season_date_criteria(epoch[0], epoch[1], season, seasons=SEASONS, extend=True)
print acq_min, acq_max, criteria
from datacube.api.query import list_tiles_as_list
tiles = list_tiles_as_list(x=[workflow.x_min], y=[workflow.y_min], satellites=workflow.satellites,
acq_min=acq_min, acq_max=acq_max,
dataset_types=[workflow.dataset_type], include=criteria)
print "Tiles found is ", len(tiles)
def query_cells(cell_list, satellites, min_date, max_date, dataset_types,
output_dir):
"""
"""
base_out_fname = CONFIG.get('outputs', 'query_filename')
for cell in cell_list:
x_cell = [int(cell[0])]
y_cell = [int(cell[1])]
tiles = list_tiles_as_list(x=x_cell,
y=y_cell,
acq_min=min_date,
acq_max=max_date,
dataset_types=dataset_types,
satellites=satellites)
out_dir = pjoin(output_dir, '{}_{}'.format(cell[0], cell[1]))
out_fname = pjoin(out_dir, base_out_fname)
with open(out_fname, 'w') as outf:
pickle.dump(tiles, outf)
def query_cells2(xcells, ycells, satellites, min_date, max_date, dataset_types,
output_dir):
"""
Query the DB for each cell.
Currently the config file for this workflow requires the user to
specify a rectangular region. I have another workflow that takes a
vector file as input.
"""
base_out_fname = CONFIG.get('outputs', 'query_filename')
cell_queries = []
for i in range(len(ycells)):
ycell = ycells[i]
xcell = xcells[i]
# create the output directory
#cell_dir = '{}_{}'.format(int(xcell), int(ycell))
cell_dir = str(xcell) + "_" + str(ycell).zfill(4)
out_cell_dir = pjoin(output_dir, cell_dir)
if not exists(out_cell_dir):
os.makedirs(out_cell_dir)
tiles = list_tiles_as_list(x=[xcell], y=[ycell],
acq_min=min_date,
acq_max=max_date,
dataset_types=dataset_types,
satellites=satellites)
fileTile = [ ]
lines = load_filterfile(xcell, ycell)
cnt=0
print "\tlength of original tiles is ", len(tiles)
for tile in tiles:
#import pdb; pdb.set_trace()
cnt=cnt+1
dataset = tile.datasets[DatasetType.ARG25]
tdate= str(tile.end_datetime.strftime("%Y-%m-%d"))
if tdate in lines:
fileTile.append(tile)
out_fname = pjoin(out_cell_dir, base_out_fname)
cell_queries.append(out_fname)
with open(out_fname, 'w') as outf:
pickle.dump(fileTile, outf)
print "\tlength of new filtered tiles is %d", len(fileTile)
return cell_queries
def go(self):
import numpy
from datacube.api.query import list_cells_as_list, list_tiles_as_list
from datacube.config import Config
x_min, x_max, y_max, y_min = self.extract_bounds_from_vector()
_log.debug("The bounds are [%s]", (x_min, x_max, y_min, y_max))
cells_vector = self.extract_cells_from_vector()
_log.debug("Intersecting cells_vector are [%d] [%s]", len(cells_vector), cells_vector)
config = Config()
_log.debug(config.to_str())
x_list = range(x_min, x_max + 1)
y_list = range(y_min, y_max + 1)
_log.debug("x = [%s] y=[%s]", x_list, y_list)
cells_db = list()
for cell in list_cells_as_list(x=x_list, y=y_list, acq_min=self.acq_min, acq_max=self.acq_max,
satellites=[satellite for satellite in self.satellites],
dataset_types=[self.dataset_type]):
cells_db.append((cell.x, cell.y))
_log.debug("Cells from DB are [%d] [%s]", len(cells_db), cells_db)
cells = intersection(cells_vector, cells_db)
_log.debug("Combined cells are [%d] [%s]", len(cells), cells)
for (x, y) in cells:
_log.info("Processing cell [%3d/%4d]", x, y)
tiles = list_tiles_as_list(x=x_list, y=y_list, acq_min=self.acq_min, acq_max=self.acq_max,
satellites=[satellite for satellite in self.satellites],
dataset_types=[self.dataset_type])
_log.info("There are [%d] tiles", len(tiles))
if self.list_only:
for tile in tiles:
_log.info("Would process [%s]", tile.datasets[self.dataset_type].path)
continue
# Calculate the mask for the cell
mask_aoi = self.get_mask_aoi_cell(x, y)
pixel_count = 4000 * 4000
pixel_count_aoi = (mask_aoi == False).sum()
_log.debug("mask_aoi is [%s]\n[%s]", numpy.shape(mask_aoi), mask_aoi)
metadata = None
with self.get_output_file() as csv_file:
csv_writer = csv.writer(csv_file)
import operator
header = reduce(operator.add, [["DATE", "INSTRUMENT", "# PIXELS", "# PIXELS IN AOI"]] + [
["%s - # DATA PIXELS" % band_name,
"%s - # DATA PIXELS AFTER PQA" % band_name,
"%s - # DATA PIXELS AFTER PQA WOFS" % band_name,
"%s - # DATA PIXELS AFTER PQA WOFS AOI" % band_name,
"%s - MIN" % band_name, "%s - MAX" % band_name, "%s - MEAN" % band_name] for band_name in self.bands])
csv_writer.writerow(header)
for tile in tiles:
_log.info("Processing tile [%s]", tile.datasets[self.dataset_type].path)
if self.list_only:
continue
if not metadata:
metadata = get_dataset_metadata(tile.datasets[self.dataset_type])
# Apply PQA if specified
pqa = None
mask_pqa = None
if self.mask_pqa_apply and DatasetType.PQ25 in tile.datasets:
pqa = tile.datasets[DatasetType.PQ25]
mask_pqa = get_mask_pqa(pqa, self.mask_pqa_mask)
_log.debug("mask_pqa is [%s]\n[%s]", numpy.shape(mask_pqa), mask_pqa)
# Apply WOFS if specified
wofs = None
mask_wofs = None
if self.mask_wofs_apply and DatasetType.WATER in tile.datasets:
wofs = tile.datasets[DatasetType.WATER]
mask_wofs = get_mask_wofs(wofs, self.mask_wofs_mask)
_log.debug("mask_wofs is [%s]\n[%s]", numpy.shape(mask_wofs), mask_wofs)
dataset = tile.datasets[self.dataset_type]
bands = []
dataset_band_names = [b.name for b in dataset.bands]
for b in self.bands:
if b in dataset_band_names:
bands.append(dataset.bands[b])
data = get_dataset_data(tile.datasets[self.dataset_type], bands=bands)
_log.debug("data is [%s]\n[%s]", numpy.shape(data), data)
pixel_count_data = dict()
pixel_count_data_pqa = dict()
pixel_count_data_pqa_wofs = dict()
pixel_count_data_pqa_wofs_aoi = dict()
mmin = dict()
mmax = dict()
mmean = dict()
for band_name in self.bands:
# Add "zeroed" entries for non-present bands - should only be if outputs for those bands have been explicitly requested
if band_name not in dataset_band_names:
pixel_count_data[band_name] = 0
pixel_count_data_pqa[band_name] = 0
pixel_count_data_pqa_wofs[band_name] = 0
pixel_count_data_pqa_wofs_aoi[band_name] = 0
mmin[band_name] = numpy.ma.masked
mmax[band_name] = numpy.ma.masked
mmean[band_name] = numpy.ma.masked
continue
band = dataset.bands[band_name]
data[band] = numpy.ma.masked_equal(data[band], NDV)
_log.debug("masked data is [%s] [%d]\n[%s]", numpy.shape(data), numpy.ma.count(data), data)
pixel_count_data[band_name] = numpy.ma.count(data[band])
if pqa:
data[band].mask = numpy.ma.mask_or(data[band].mask, mask_pqa)
_log.debug("PQA masked data is [%s] [%d]\n[%s]", numpy.shape(data[band]), numpy.ma.count(data[band]), data[band])
pixel_count_data_pqa[band_name] = numpy.ma.count(data[band])
if wofs:
data[band].mask = numpy.ma.mask_or(data[band].mask, mask_wofs)
_log.debug("WOFS masked data is [%s] [%d]\n[%s]", numpy.shape(data[band]), numpy.ma.count(data[band]), data[band])
pixel_count_data_pqa_wofs[band_name] = numpy.ma.count(data[band])
data[band].mask = numpy.ma.mask_or(data[band].mask, mask_aoi)
_log.debug("AOI masked data is [%s] [%d]\n[%s]", numpy.shape(data[band]), numpy.ma.count(data[band]), data[band])
pixel_count_data_pqa_wofs_aoi[band_name] = numpy.ma.count(data[band])
mmin[band_name] = numpy.ma.min(data[band])
mmax[band_name] = numpy.ma.max(data[band])
mmean[band_name] = numpy.ma.mean(data[band])
# Convert the mean to an int...taking into account masking....
if not numpy.ma.is_masked(mmean[band_name]):
mmean[band_name] = mmean[band_name].astype(numpy.int16)
pixel_count_data_pqa_wofs_aoi_all_bands = reduce(operator.add, pixel_count_data_pqa_wofs_aoi.itervalues())
if pixel_count_data_pqa_wofs_aoi_all_bands == 0 and not self.output_no_data:
_log.info("Skipping dataset with no non-masked data values in ANY band")
continue
row = reduce(
operator.add,
[[tile.end_datetime,
self.decode_satellite_as_instrument(tile.datasets[self.dataset_type].satellite),
pixel_count, pixel_count_aoi]] +
[[pixel_count_data[band_name], pixel_count_data_pqa[band_name],
pixel_count_data_pqa_wofs[band_name], pixel_count_data_pqa_wofs_aoi[band_name],
mmin[band_name], mmax[band_name], mmean[band_name]] for band_name in self.bands])
csv_writer.writerow(row)
def run(self):
_log.info("Creating stack for band [%s]", self.band.name)
data_type = get_dataset_type_datatype(self.dataset_type)
ndv = get_dataset_type_ndv(self.dataset_type)
metadata = None
driver = None
raster = None
acq_min, acq_max, criteria = build_season_date_criteria(self.acq_min, self.acq_max, self.season,
seasons=SEASONS, extend=True)
_log.info("\tacq %s to %s criteria is %s", acq_min, acq_max, criteria)
dataset_types = [self.dataset_type]
if self.mask_pqa_apply:
dataset_types.append(DatasetType.PQ25)
tiles = list_tiles_as_list(x=[self.x], y=[self.y], satellites=self.satellites,
acq_min=acq_min, acq_max=acq_max,
dataset_types=dataset_types, include=criteria)
for index, tile in enumerate(tiles, start=1):
dataset = tile.datasets[self.dataset_type]
assert dataset
# band = dataset.bands[self.band]
# assert band
band = self.band
pqa = (self.mask_pqa_apply and DatasetType.PQ25 in tile.datasets) and tile.datasets[DatasetType.PQ25] or None
if self.dataset_type not in tile.datasets:
_log.debug("No [%s] dataset present for [%s] - skipping", self.dataset_type.name, tile.end_datetime)
continue
filename = self.output().path
if not metadata:
metadata = get_dataset_metadata(dataset)
assert metadata
if not driver:
if self.output_format == OutputFormat.GEOTIFF:
driver = gdal.GetDriverByName("GTiff")
elif self.output_format == OutputFormat.ENVI:
driver = gdal.GetDriverByName("ENVI")
assert driver
if not raster:
if self.output_format == OutputFormat.GEOTIFF:
raster = driver.Create(filename, metadata.shape[0], metadata.shape[1], len(tiles), data_type, options=["BIGTIFF=YES", "INTERLEAVE=BAND"])
elif self.output_format == OutputFormat.ENVI:
raster = driver.Create(filename, metadata.shape[0], metadata.shape[1], len(tiles), data_type, options=["INTERLEAVE=BSQ"])
assert raster
# NOTE: could do this without the metadata!!
raster.SetGeoTransform(metadata.transform)
raster.SetProjection(metadata.projection)
raster.SetMetadata(self.generate_raster_metadata())
mask = None
if pqa:
mask = get_mask_pqa(pqa, self.mask_pqa_mask, mask=mask)
_log.info("Stacking [%s] band data from [%s] with PQA [%s] and PQA mask [%s] to [%s]",
band.name, dataset.path,
pqa and pqa.path or "", pqa and self.mask_pqa_mask or "",
filename)
data = get_dataset_data_masked(dataset, mask=mask, ndv=ndv)
_log.debug("data is [%s]", data)
stack_band = raster.GetRasterBand(index)
stack_band.SetDescription(os.path.basename(dataset.path))
stack_band.SetNoDataValue(ndv)
stack_band.WriteArray(data[band])
stack_band.ComputeStatistics(True)
stack_band.SetMetadata({"ACQ_DATE": format_date(tile.end_datetime), "SATELLITE": dataset.satellite.name})
stack_band.FlushCache()
del stack_band
if raster:
raster.FlushCache()
del raster
raster = None
if __name__ == '__main__':
logging.basicConfig(level=logging.INFO,
format='%(asctime)s %(levelname)s %(message)s')
config = Config()
satellites = [Satellite(i) for i in ['LS5', 'LS7', 'LS8']]
min_date = date(1995, 01, 01)
max_date = date(2015, 12, 31)
ds_type = DatasetType.ARG25
x_cell = [146]
y_cell = [-34]
tiles = list_tiles_as_list(x=x_cell,
y=y_cell,
acq_min=min_date,
acq_max=max_date,
satellites=satellites,
datasets=ds_type,
database=config.get_db_database(),
user=config.get_db_username(),
password=config.get_db_password(),
host=config.get_db_host(),
port=config.get_db_port())
#bs_workflow(tiles, outdir='/g/data/v10/testing_ground/jps547/percentiles')
#bs_workflow(tiles, outdir='/g/data/v10/testing_ground/jps547/percentiles/pct_95', percentile=95)
tidal_workflow(tiles,
outdir='/g/data2/v10/ARG25-tidal-analysis/test',
percentile=10)
def run(self):
_log.info("Creating stack for band [%s]", self.band.name)
data_type = get_dataset_type_datatype(self.dataset_type)
ndv = get_dataset_type_ndv(self.dataset_type)
metadata = None
driver = None
raster = None
acq_min, acq_max, criteria = build_season_date_criteria(
self.acq_min,
self.acq_max,
self.season,
seasons=SEASONS,
extend=True)
_log.info("\tacq %s to %s criteria is %s", acq_min, acq_max, criteria)
dataset_types = [self.dataset_type]
if self.mask_pqa_apply:
dataset_types.append(DatasetType.PQ25)
tiles = list_tiles_as_list(x=[self.x],
y=[self.y],
satellites=self.satellites,
acq_min=acq_min,
acq_max=acq_max,
dataset_types=dataset_types,
include=criteria)
for index, tile in enumerate(tiles, start=1):
dataset = tile.datasets[self.dataset_type]
assert dataset
# band = dataset.bands[self.band]
# assert band
band = self.band
pqa = (self.mask_pqa_apply and DatasetType.PQ25 in tile.datasets
) and tile.datasets[DatasetType.PQ25] or None
if self.dataset_type not in tile.datasets:
_log.debug("No [%s] dataset present for [%s] - skipping",
self.dataset_type.name, tile.end_datetime)
continue
filename = self.output().path
if not metadata:
metadata = get_dataset_metadata(dataset)
assert metadata
if not driver:
if self.output_format == OutputFormat.GEOTIFF:
driver = gdal.GetDriverByName("GTiff")
elif self.output_format == OutputFormat.ENVI:
driver = gdal.GetDriverByName("ENVI")
assert driver
if not raster:
if self.output_format == OutputFormat.GEOTIFF:
raster = driver.Create(
filename,
metadata.shape[0],
metadata.shape[1],
len(tiles),
data_type,
options=["BIGTIFF=YES", "INTERLEAVE=BAND"])
elif self.output_format == OutputFormat.ENVI:
raster = driver.Create(filename,
metadata.shape[0],
metadata.shape[1],
len(tiles),
data_type,
options=["INTERLEAVE=BSQ"])
assert raster
# NOTE: could do this without the metadata!!
raster.SetGeoTransform(metadata.transform)
raster.SetProjection(metadata.projection)
raster.SetMetadata(self.generate_raster_metadata())
mask = None
if pqa:
mask = get_mask_pqa(pqa, self.mask_pqa_mask, mask=mask)
_log.info(
"Stacking [%s] band data from [%s] with PQA [%s] and PQA mask [%s] to [%s]",
band.name, dataset.path, pqa and pqa.path or "",
pqa and self.mask_pqa_mask or "", filename)
data = get_dataset_data_masked(dataset, mask=mask, ndv=ndv)
_log.debug("data is [%s]", data)
stack_band = raster.GetRasterBand(index)
stack_band.SetDescription(os.path.basename(dataset.path))
stack_band.SetNoDataValue(ndv)
stack_band.WriteArray(data[band])
stack_band.ComputeStatistics(True)
stack_band.SetMetadata({
"ACQ_DATE": format_date(tile.end_datetime),
"SATELLITE": dataset.satellite.name
})
stack_band.FlushCache()
del stack_band
if raster:
raster.FlushCache()
del raster
raster = None
# Close the output files
nbar_outds.close()
all_outds.close()
if __name__ == '__main__':
logging.basicConfig(level=logging.INFO, format='%(asctime)s %(levelname)s %(message)s')
config = Config()
#satellites = [Satellite(i) for i in ['LS5', 'LS7', 'LS8']]
satellites = [Satellite(i) for i in ['LS5', 'LS7']]
min_date = date(1987, 01, 01)
max_date = date(2015, 12, 31)
ds_type = DatasetType.ARG25
x_cell = [146]
y_cell = [-34]
tiles = list_tiles_as_list(x=x_cell, y=y_cell, acq_min=min_date,
acq_max=max_date,
satellites=satellites,
datasets=ds_type,
database=config.get_db_database(),
user=config.get_db_username(),
password=config.get_db_password(),
host=config.get_db_host(),
port=config.get_db_port())
#bs_workflow(tiles, outdir='/g/data/v10/testing_ground/jps547/percentiles')
#bs_workflow(tiles, outdir='/g/data/v10/testing_ground/jps547/percentiles/pct_95', percentile=95)
bs_workflow(tiles, outdir='/g/data/v10/testing_ground/jps547/percentiles/test', percentile=95)
def run(self):
self.parse_arguments()
config = Config()
_log.debug(config.to_str())
path = self.get_output_filename(self.dataset_type)
_log.info("Output file is [%s]", path)
if os.path.exists(path):
if self.overwrite:
_log.info("Removing existing output file [%s]", path)
os.remove(path)
else:
_log.error("Output file [%s] exists", path)
raise Exception("Output file [%s] already exists" % path)
# TODO
bands = get_bands(self.dataset_type, self.satellites[0])
# TODO once WOFS is in the cube
tiles = list_tiles_as_list(x=[self.x], y=[self.y], acq_min=self.acq_min, acq_max=self.acq_max,
satellites=[satellite for satellite in self.satellites],
dataset_types=[self.dataset_type],
database=config.get_db_database(),
user=config.get_db_username(),
password=config.get_db_password(),
host=config.get_db_host(), port=config.get_db_port())
raster = None
metadata = None
# TODO - PQ is UNIT16 (others are INT16) and so -999 NDV doesn't work
ndv = self.dataset_type == DatasetType.PQ25 and UINT16_MAX or NDV
_log.debug("Current MAX RSS usage is [%d] MB", resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1024)
import itertools
for x, y in itertools.product(range(0, 4000, self.chunk_size_x), range(0, 4000, self.chunk_size_y)):
_log.info("About to read data chunk ({xmin:4d},{ymin:4d}) to ({xmax:4d},{ymax:4d})".format(xmin=x, ymin=y, xmax=x+self.chunk_size_x-1, ymax=y+self.chunk_size_y-1))
_log.debug("Current MAX RSS usage is [%d] MB", resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1024)
stack = dict()
for tile in tiles:
if self.list_only:
_log.info("Would summarise dataset [%s]", tile.datasets[self.dataset_type].path)
continue
pqa = None
_log.debug("Reading dataset [%s]", tile.datasets[self.dataset_type].path)
if not metadata:
metadata = get_dataset_metadata(tile.datasets[self.dataset_type])
# Apply PQA if specified
if self.apply_pqa_filter:
data = get_dataset_data_with_pq(tile.datasets[self.dataset_type], tile.datasets[DatasetType.PQ25], bands=bands, x=x, y=y, x_size=self.chunk_size_x, y_size=self.chunk_size_y, pq_masks=self.pqa_mask, ndv=ndv)
else:
data = get_dataset_data(tile.datasets[self.dataset_type], bands=bands, x=x, y=y, x_size=self.chunk_size_x, y_size=self.chunk_size_y)
for band in bands:
if band in stack:
stack[band].append(data[band])
else:
stack[band] = [data[band]]
_log.debug("data[%s] has shape [%s] and MB [%s]", band.name, numpy.shape(data[band]), data[band].nbytes/1000/1000)
_log.debug("stack[%s] has [%s] elements", band.name, len(stack[band]))
# Apply summary method
_log.info("Finished reading {count} datasets for chunk ({xmin:4d},{ymin:4d}) to ({xmax:4d},{ymax:4d}) - about to summarise them".format(count=len(tiles), xmin=x, ymin=y, xmax=x+self.chunk_size_x-1, ymax=y+self.chunk_size_y-1))
_log.debug("Current MAX RSS usage is [%d] MB", resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1024)
masked_stack = dict()
for band in bands:
masked_stack[band] = numpy.ma.masked_equal(stack[band], ndv)
_log.debug("masked_stack[%s] is %s", band.name, masked_stack[band])
_log.debug("masked stack[%s] has shape [%s] and MB [%s]", band.name, numpy.shape(masked_stack[band]), masked_stack[band].nbytes/1000/1000)
_log.debug("Current MAX RSS usage is [%d] MB", resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1024)
if self.summary_method == TimeSeriesSummaryMethod.MIN:
masked_summary = numpy.min(masked_stack[band], axis=0)
elif self.summary_method == TimeSeriesSummaryMethod.MAX:
masked_summary = numpy.max(masked_stack[band], axis=0)
elif self.summary_method == TimeSeriesSummaryMethod.MEAN:
masked_summary = numpy.mean(masked_stack[band], axis=0)
elif self.summary_method == TimeSeriesSummaryMethod.MEDIAN:
masked_summary = numpy.median(masked_stack[band], axis=0)
# aka 50th percentile
elif self.summary_method == TimeSeriesSummaryMethod.MEDIAN_NON_INTERPOLATED:
masked_sorted = numpy.ma.sort(masked_stack[band], axis=0)
masked_percentile_index = numpy.ma.floor(numpy.ma.count(masked_sorted, axis=0) * 0.95).astype(numpy.int16)
masked_summary = numpy.ma.choose(masked_percentile_index, masked_sorted)
elif self.summary_method == TimeSeriesSummaryMethod.COUNT:
# TODO Need to artificially create masked array here since it is being expected/filled below!!!
masked_summary = numpy.ma.masked_equal(masked_stack[band].count(axis=0), ndv)
elif self.summary_method == TimeSeriesSummaryMethod.SUM:
masked_summary = numpy.sum(masked_stack[band], axis=0)
elif self.summary_method == TimeSeriesSummaryMethod.STANDARD_DEVIATION:
masked_summary = numpy.std(masked_stack[band], axis=0)
elif self.summary_method == TimeSeriesSummaryMethod.VARIANCE:
masked_summary = numpy.var(masked_stack[band], axis=0)
# currently 95th percentile
elif self.summary_method == TimeSeriesSummaryMethod.PERCENTILE:
masked_sorted = numpy.ma.sort(masked_stack[band], axis=0)
masked_percentile_index = numpy.ma.floor(numpy.ma.count(masked_sorted, axis=0) * 0.95).astype(numpy.int16)
masked_summary = numpy.ma.choose(masked_percentile_index, masked_sorted)
elif self.summary_method == TimeSeriesSummaryMethod.YOUNGEST_PIXEL:
# TODO the fact that this is band at a time might be problematic. We really should be considering
# all bands at once (that is what the landsat_mosaic logic did). If PQA is being applied then
# it's probably all good but if not then we might get odd results....
masked_summary = empty_array(shape=(self.chunk_size_x, self.chunk_size_x), dtype=numpy.int16, ndv=ndv)
# Note the reversed as the stack is created oldest first
for d in reversed(stack[band]):
masked_summary = numpy.where(masked_summary == ndv, d, masked_summary)
# If the summary doesn't contain an no data values then we can stop
if not numpy.any(masked_summary == ndv):
break
# TODO Need to artificially create masked array here since it is being expected/filled below!!!
masked_summary = numpy.ma.masked_equal(masked_summary, ndv)
elif self.summary_method == TimeSeriesSummaryMethod.OLDEST_PIXEL:
# TODO the fact that this is band at a time might be problematic. We really should be considering
# all bands at once (that is what the landsat_mosaic logic did). If PQA is being applied then
# it's probably all good but if not then we might get odd results....
masked_summary = empty_array(shape=(self.chunk_size_x, self.chunk_size_x), dtype=numpy.int16, ndv=ndv)
# Note the NOT reversed as the stack is created oldest first
for d in stack[band]:
masked_summary = numpy.where(masked_summary == ndv, d, masked_summary)
# If the summary doesn't contain an no data values then we can stop
if not numpy.any(masked_summary == ndv):
break
# TODO Need to artificially create masked array here since it is being expected/filled below!!!
masked_summary = numpy.ma.masked_equal(masked_summary, ndv)
masked_stack[band] = None
_log.debug("NONE-ing masked stack[%s]", band.name)
_log.debug("Current MAX RSS usage is [%d] MB", resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1024)
_log.debug("masked summary is [%s]", masked_summary)
_log.debug("Current MAX RSS usage is [%d] MB", resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1024)
# Create the output file
if not os.path.exists(path):
_log.info("Creating raster [%s]", path)
driver = gdal.GetDriverByName("GTiff")
assert driver
raster = driver.Create(path, metadata.shape[0], metadata.shape[1], len(bands), gdal.GDT_Int16)
assert raster
raster.SetGeoTransform(metadata.transform)
raster.SetProjection(metadata.projection)
for b in bands:
raster.GetRasterBand(b.value).SetNoDataValue(ndv)
_log.info("Writing band [%s] data to raster [%s]", band.name, path)
_log.debug("Current MAX RSS usage is [%d] MB", resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1024)
raster.GetRasterBand(band.value).WriteArray(masked_summary.filled(ndv), xoff=x, yoff=y)
raster.GetRasterBand(band.value).ComputeStatistics(True)
raster.FlushCache()
masked_summary = None
_log.debug("NONE-ing the masked summary")
_log.debug("Current MAX RSS usage is [%d] MB", resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1024)
stack = None
_log.debug("Just NONE-ed the stack")
_log.debug("Current MAX RSS usage is [%d] MB", resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1024)
raster = None
_log.debug("Just NONE'd the raster")
_log.debug("Current MAX RSS usage is [%d] MB", resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1024)
_log.info("Memory usage was [%d MB]", resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1024)
_log.info("CPU time used [%s]", timedelta(seconds=int(resource.getrusage(resource.RUSAGE_SELF).ru_utime)))
def go(self):
import numpy
from datacube.api.query import list_cells_as_list, list_tiles_as_list
from datacube.config import Config
# Verify that all the requested satellites have the same band combinations
dataset_bands = get_bands(self.dataset_type, self.satellites[0])
_log.info("dataset bands is [%s]", " ".join([b.name for b in dataset_bands]))
for satellite in self.satellites:
if dataset_bands != get_bands(self.dataset_type, satellite):
_log.error("Satellites [%s] have differing bands", " ".join([satellite.name for satellite in self.satellites]))
raise Exception("Satellites with different band combinations selected")
bands = []
dataset_bands_list = list(dataset_bands)
if not self.bands:
bands = dataset_bands_list
else:
for b in self.bands:
bands.append(dataset_bands_list[b - 1])
_log.info("Using bands [%s]", " ".join(band.name for band in bands))
x_min, x_max, y_max, y_min = self.extract_bounds_from_vector()
_log.debug("The bounds are [%s]", (x_min, x_max, y_min, y_max))
cells_vector = self.extract_cells_from_vector()
_log.debug("Intersecting cells_vector are [%d] [%s]", len(cells_vector), cells_vector)
config = Config(os.path.expanduser("~/.datacube/config"))
_log.debug(config.to_str())
x_list = range(x_min, x_max + 1)
y_list = range(y_min, y_max + 1)
_log.debug("x = [%s] y=[%s]", x_list, y_list)
cells_db = list()
for cell in list_cells_as_list(x=x_list, y=y_list, acq_min=self.acq_min, acq_max=self.acq_max,
satellites=[satellite for satellite in self.satellites],
dataset_types=[self.dataset_type]):
cells_db.append((cell.x, cell.y))
_log.debug("Cells from DB are [%d] [%s]", len(cells_db), cells_db)
cells = intersection(cells_vector, cells_db)
_log.debug("Combined cells are [%d] [%s]", len(cells), cells)
for (x, y) in cells:
_log.info("Processing cell [%3d/%4d]", x, y)
tiles = list_tiles_as_list(x=x_list, y=y_list, acq_min=self.acq_min, acq_max=self.acq_max,
satellites=[satellite for satellite in self.satellites],
dataset_types=[self.dataset_type])
_log.info("There are [%d] tiles", len(tiles))
if self.list_only:
for tile in tiles:
_log.info("Would process [%s]", tile.datasets[self.dataset_type].path)
continue
# Calculate the mask for the cell
mask_aoi = self.get_mask_aoi_cell(x, y)
pixel_count = 4000 * 4000
pixel_count_aoi = (mask_aoi == False).sum()
_log.debug("mask_aoi is [%s]\n[%s]", numpy.shape(mask_aoi), mask_aoi)
metadata = None
with self.get_output_file() as csv_file:
csv_writer = csv.writer(csv_file)
import operator
header = reduce(operator.add, [["DATE", "INSTRUMENT", "# PIXELS", "# PIXELS IN AOI"]] + [
["%s - # DATA PIXELS" % b.name,
"%s - # DATA PIXELS AFTER PQA" % b.name,
"%s - # DATA PIXELS AFTER PQA WOFS" % b.name,
"%s - # DATA PIXELS AFTER PQA WOFS AOI" % b.name,
"%s - MIN" % b.name, "%s - MAX" % b.name, "%s - MEAN" % b.name] for b in bands])
csv_writer.writerow(header)
for tile in tiles:
_log.info("Processing tile [%s]", tile.datasets[self.dataset_type].path)
if self.list_only:
continue
if not metadata:
metadata = get_dataset_metadata(tile.datasets[self.dataset_type])
# Apply PQA if specified
pqa = None
mask_pqa = None
if self.mask_pqa_apply and DatasetType.PQ25 in tile.datasets:
pqa = tile.datasets[DatasetType.PQ25]
mask_pqa = get_mask_pqa(pqa, self.mask_pqa_mask)
_log.debug("mask_pqa is [%s]\n[%s]", numpy.shape(mask_pqa), mask_pqa)
# Apply WOFS if specified
wofs = None
mask_wofs = None
if self.mask_wofs_apply and DatasetType.WATER in tile.datasets:
wofs = tile.datasets[DatasetType.WATER]
mask_wofs = get_mask_wofs(wofs, self.mask_wofs_mask)
_log.debug("mask_wofs is [%s]\n[%s]", numpy.shape(mask_wofs), mask_wofs)
data = get_dataset_data(tile.datasets[self.dataset_type], bands=bands)
_log.debug("data is [%s]\n[%s]", numpy.shape(data), data)
pixel_count_data = dict()
pixel_count_data_pqa = dict()
pixel_count_data_pqa_wofs = dict()
pixel_count_data_pqa_wofs_aoi = dict()
mmin = dict()
mmax = dict()
mmean = dict()
for band in bands:
data[band] = numpy.ma.masked_equal(data[band], NDV)
_log.debug("masked data is [%s] [%d]\n[%s]", numpy.shape(data), numpy.ma.count(data), data)
pixel_count_data[band] = numpy.ma.count(data[band])
if pqa:
data[band].mask = numpy.ma.mask_or(data[band].mask, mask_pqa)
_log.debug("PQA masked data is [%s] [%d]\n[%s]", numpy.shape(data[band]), numpy.ma.count(data[band]), data[band])
pixel_count_data_pqa[band] = numpy.ma.count(data[band])
if wofs:
data[band].mask = numpy.ma.mask_or(data[band].mask, mask_wofs)
_log.debug("WOFS masked data is [%s] [%d]\n[%s]", numpy.shape(data[band]), numpy.ma.count(data[band]), data[band])
pixel_count_data_pqa_wofs[band] = numpy.ma.count(data[band])
data[band].mask = numpy.ma.mask_or(data[band].mask, mask_aoi)
_log.debug("AOI masked data is [%s] [%d]\n[%s]", numpy.shape(data[band]), numpy.ma.count(data[band]), data[band])
pixel_count_data_pqa_wofs_aoi[band] = numpy.ma.count(data[band])
mmin[band] = numpy.ma.min(data[band])
mmax[band] = numpy.ma.max(data[band])
mmean[band] = numpy.ma.mean(data[band])
# Convert the mean to an int...which is actually trickier than you would expect due to masking....
if numpy.ma.count(mmean[band]) != 0:
mmean[band] = mmean[band].astype(numpy.int16)
# Should we output if no data values found?
pixel_count_data_pqa_wofs_aoi_all_bands = reduce(operator.add, pixel_count_data_pqa_wofs_aoi.itervalues())
if pixel_count_data_pqa_wofs_aoi_all_bands == 0 and not self.output_no_data:
_log.info("Skipping dataset with no non-masked data values in ANY band")
continue
row = reduce(
operator.add,
[[tile.end_datetime,
self.decode_satellite_as_instrument(tile.datasets[self.dataset_type].satellite),
pixel_count, pixel_count_aoi]] +
[[pixel_count_data[band], pixel_count_data_pqa[band],
pixel_count_data_pqa_wofs[band], pixel_count_data_pqa_wofs_aoi[band],
mmin[band], mmax[band], mmean[band]] for band in bands])
csv_writer.writerow(row)
