def test_fred(x=2, y=2, z=50, ndv=-999):
print "Testing..."
data = numpy.load("/tmp/random_{x}_{y}_{z}.npy".format(x=x, y=y, z=z))
# print numpy.shape(data), data
# Calculate the percentiles stripping out no data values
p = numpy.empty((y, x), dtype=numpy.int16)
from itertools import product
for y, x in product(range(0, y), range(0, x)):
d = data[:, x, y]
# print "data", x, y, numpy.shape(d), d
# print "stripped data", numpy.shape(d[d != ndv]), d[d != ndv]
p[x, y] = numpy.percentile(d[d != ndv], 75, axis=0, interpolation="nearest")
# print "stripped percentiles", p[x, y]
print "percentiles\n", p
from datacube.api.utils import calculate_stack_statistic_percentile
print "calculated percentiles\n", calculate_stack_statistic_percentile(data, 75)
print data[:, 0, 0]
print numpy.apply_along_axis(do_percentile_1d, axis=0, arr=data)
def run(self):
_log.info("Calculating statistics for chunk")
filtile = []
ndv = get_dataset_type_ndv(self.dataset_type)
data_type = get_dataset_type_data_type(self.dataset_type)
tiles = self.get_tiles()
filtile = tiles
if self.tidal_workflow:
filtile = []
lines = self.load_filterfile()
cnt = 0
_log.info("\tlength of original tiles is %d", len(tiles))
for tile in tiles:
#import pdb; pdb.set_trace()
cnt = cnt + 1
dataset = tile.datasets[self.dataset_type]
tdate = str(tile.end_datetime.strftime("%Y-%m-%d"))
if tdate in lines:
filtile.append(tile)
_log.info("\tlength of new filtered tiles is %d", len(filtile))
stack = get_dataset_data_stack(filtile,
self.dataset_type,
self.band.name,
ndv=ndv,
x=self.x_offset,
y=self.y_offset,
x_size=self.x_chunk_size,
y_size=self.y_chunk_size,
mask_pqa_apply=self.mask_pqa_apply,
mask_pqa_mask=self.mask_pqa_mask)
if len(stack) == 0:
return
# TODO get statistics to be generated from command line argument
if Statistic.COUNT in self.statistics:
#log_mem("Before COUNT")
# COUNT
stack_stat = calculate_stack_statistic_count(stack=stack, ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.COUNT),
stack_stat)
del stack_stat
if Statistic.MIN in self.statistics:
log_mem("Before MIN")
# MIN
stack_stat = calculate_stack_statistic_min(stack=stack,
ndv=ndv,
dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MIN), stack_stat)
del stack_stat
if Statistic.MAX in self.statistics:
log_mem("Before MAX")
# MAX
stack_stat = calculate_stack_statistic_max(stack=stack,
ndv=ndv,
dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MAX), stack_stat)
del stack_stat
if Statistic.MEAN in self.statistics:
log_mem("Before MEAN")
# MEAN
stack_stat = calculate_stack_statistic_mean(stack=stack,
ndv=ndv,
dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MEAN), stack_stat)
del stack_stat
if Statistic.MEDIAN in self.statistics:
#log_mem("Before MEDIAN")
# MEAN
stack_stat = calculate_stack_statistic_median(stack=stack,
ndv=ndv,
dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MEDIAN),
stack_stat)
del stack_stat
if Statistic.VARIANCE in self.statistics:
log_mem("Before VARIANCE")
# VARIANCE
stack_stat = calculate_stack_statistic_variance(stack=stack,
ndv=ndv,
dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.VARIANCE),
stack_stat)
del stack_stat
if Statistic.STANDARD_DEVIATION in self.statistics:
#log_mem("Before STANDARD_DEVIATION")
# STANDARD_DEVIATION
stack_stat = calculate_stack_statistic_standard_deviation(
stack=stack, ndv=ndv, dtype=data_type)
numpy.save(
self.get_statistic_filename(Statistic.STANDARD_DEVIATION),
stack_stat)
del stack_stat
for percentile in PERCENTILE:
if percentile in self.statistics:
log_mem("Before {p}".format(p=percentile.name))
stack_stat = calculate_stack_statistic_percentile(
stack=stack,
percentile=PERCENTILE[percentile],
ndv=ndv,
interpolation=self.interpolation)
numpy.save(self.get_statistic_filename(percentile), stack_stat)
del stack_stat
if Statistic.COUNT_OBSERVED in self.statistics:
#log_mem("Before OBSERVED COUNT")
# COUNT OBSERVED - note the copy=False is modifying the array so this is done last
stack_stat = calculate_stack_statistic_count_observed(stack=stack,
ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.COUNT_OBSERVED),
stack_stat)
del stack_stat
def run(self):
_log.info("Calculating statistics for chunk")
filtile = [ ]
ndv = get_dataset_type_ndv(self.dataset_type)
data_type = get_dataset_type_data_type(self.dataset_type)
tiles = self.get_tiles()
filtile = tiles
if self.tidal_workflow:
filtile = [ ]
lines = self.load_filterfile()
cnt=0
_log.info("\tlength of original tiles is %d", len(tiles))
for tile in tiles:
#import pdb; pdb.set_trace()
cnt=cnt+1
dataset = tile.datasets[self.dataset_type]
tdate= str(tile.end_datetime.strftime("%Y-%m-%d"))
if tdate in lines:
filtile.append(tile)
_log.info("\tlength of new filtered tiles is %d", len(filtile))
stack = get_dataset_data_stack(filtile, self.dataset_type, self.band.name, ndv=ndv,
x=self.x_offset, y=self.y_offset,
x_size=self.x_chunk_size, y_size=self.y_chunk_size,
mask_pqa_apply=self.mask_pqa_apply, mask_pqa_mask=self.mask_pqa_mask)
if len(stack) == 0:
return
# TODO get statistics to be generated from command line argument
if Statistic.COUNT in self.statistics:
#log_mem("Before COUNT")
# COUNT
stack_stat = calculate_stack_statistic_count(stack=stack, ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.COUNT), stack_stat)
del stack_stat
if Statistic.MIN in self.statistics:
log_mem("Before MIN")
# MIN
stack_stat = calculate_stack_statistic_min(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MIN), stack_stat)
del stack_stat
if Statistic.MAX in self.statistics:
log_mem("Before MAX")
# MAX
stack_stat = calculate_stack_statistic_max(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MAX), stack_stat)
del stack_stat
if Statistic.MEAN in self.statistics:
log_mem("Before MEAN")
# MEAN
stack_stat = calculate_stack_statistic_mean(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MEAN), stack_stat)
del stack_stat
if Statistic.MEDIAN in self.statistics:
#log_mem("Before MEDIAN")
# MEAN
stack_stat = calculate_stack_statistic_median(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MEDIAN), stack_stat)
del stack_stat
if Statistic.VARIANCE in self.statistics:
log_mem("Before VARIANCE")
# VARIANCE
stack_stat = calculate_stack_statistic_variance(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.VARIANCE), stack_stat)
del stack_stat
if Statistic.STANDARD_DEVIATION in self.statistics:
#log_mem("Before STANDARD_DEVIATION")
# STANDARD_DEVIATION
stack_stat = calculate_stack_statistic_standard_deviation(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.STANDARD_DEVIATION), stack_stat)
del stack_stat
for percentile in PERCENTILE:
if percentile in self.statistics:
log_mem("Before {p}".format(p=percentile.name))
stack_stat = calculate_stack_statistic_percentile(stack=stack, percentile=PERCENTILE[percentile],
ndv=ndv, interpolation=self.interpolation)
numpy.save(self.get_statistic_filename(percentile), stack_stat)
del stack_stat
if Statistic.COUNT_OBSERVED in self.statistics:
#log_mem("Before OBSERVED COUNT")
# COUNT OBSERVED - note the copy=False is modifying the array so this is done last
stack_stat = calculate_stack_statistic_count_observed(stack=stack, ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.COUNT_OBSERVED), stack_stat)
del stack_stat
def existing_nan_percentile(data):
print "existing nan percentile..."
from datacube.api.utils import calculate_stack_statistic_percentile
print "calculated percentiles\n", calculate_stack_statistic_percentile(data, [25, 50, 75])
def run(self):
_log.info("Calculating statistics for chunk")
ndv = get_dataset_type_ndv(self.dataset_type)
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_generator(x=[self.x], y=[self.y], satellites=self.satellites,
acq_min=acq_min, acq_max=acq_max,
dataset_types=dataset_types, include=criteria)
stack = get_dataset_data_stack(tiles, self.dataset_type, self.band.name, ndv=ndv,
x=self.x_offset, y=self.y_offset,
x_size=self.x_chunk_size, y_size=self.y_chunk_size,
mask_pqa_apply=self.mask_pqa_apply, mask_pqa_mask=self.mask_pqa_mask)
if len(stack) == 0:
return
# TODO get statistics to be generated from command line argument
if Statistic.COUNT in self.statistics:
log_mem("Before COUNT")
# COUNT
print "COUNT"
stack_stat = calculate_stack_statistic_count(stack=stack, ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.COUNT), stack_stat)
del stack_stat
if Statistic.MIN in self.statistics:
log_mem("Before MIN")
# MIN
print "MIN"
stack_stat = calculate_stack_statistic_min(stack=stack, ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.MIN), stack_stat)
del stack_stat
if Statistic.MAX in self.statistics:
log_mem("Before MAX")
# MAX
print "MAX"
stack_stat = calculate_stack_statistic_max(stack=stack, ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.MAX), stack_stat)
del stack_stat
if Statistic.MEAN in self.statistics:
log_mem("Before MEAN")
# MEAN
print "MEAN"
stack_stat = calculate_stack_statistic_mean(stack=stack, ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.MEAN), stack_stat)
del stack_stat
for percentile in [Statistic.PERCENTILE_25, Statistic.PERCENTILE_50, Statistic.PERCENTILE_75, Statistic.PERCENTILE_90, Statistic.PERCENTILE_95]:
if percentile in self.statistics:
log_mem("Before {p}".format(p=percentile.name))
print "Before {p}".format(p=percentile.name)
stack_stat = calculate_stack_statistic_percentile(stack=stack, percentile=PERCENTILE[percentile], ndv=ndv)
numpy.save(self.get_statistic_filename(percentile), stack_stat)
del stack_stat
if Statistic.COUNT_OBSERVED in self.statistics:
log_mem("Before OBSERVED COUNT")
# COUNT OBSERVED - note the copy=False is modifying the array so this is done last
print "COUNT OBSERVED"
stack_stat = calculate_stack_statistic_count_observed(stack=stack, ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.COUNT_OBSERVED), stack_stat)
del stack_stat
log_mem("DONE")
def run(self):
_log.info("Calculating statistics for chunk")
ndv = get_dataset_type_ndv(self.dataset_type)
data_type = get_dataset_type_data_type(self.dataset_type)
tiles = self.get_tiles()
stack = get_dataset_data_stack(tiles, self.dataset_type, self.band.name, ndv=ndv,
x=self.x_offset, y=self.y_offset,
x_size=self.x_chunk_size, y_size=self.y_chunk_size,
mask_pqa_apply=self.mask_pqa_apply, mask_pqa_mask=self.mask_pqa_mask)
if len(stack) == 0:
return
# TODO get statistics to be generated from command line argument
if Statistic.COUNT in self.statistics:
log_mem("Before COUNT")
# COUNT
stack_stat = calculate_stack_statistic_count(stack=stack, ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.COUNT), stack_stat)
del stack_stat
if Statistic.MIN in self.statistics:
log_mem("Before MIN")
# MIN
stack_stat = calculate_stack_statistic_min(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MIN), stack_stat)
del stack_stat
if Statistic.MAX in self.statistics:
log_mem("Before MAX")
# MAX
stack_stat = calculate_stack_statistic_max(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MAX), stack_stat)
del stack_stat
if Statistic.MEAN in self.statistics:
log_mem("Before MEAN")
# MEAN
stack_stat = calculate_stack_statistic_mean(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MEAN), stack_stat)
del stack_stat
if Statistic.VARIANCE in self.statistics:
log_mem("Before VARIANCE")
# VARIANCE
stack_stat = calculate_stack_statistic_variance(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.VARIANCE), stack_stat)
del stack_stat
if Statistic.STANDARD_DEVIATION in self.statistics:
log_mem("Before STANDARD_DEVIATION")
# STANDARD_DEVIATION
stack_stat = calculate_stack_statistic_standard_deviation(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.STANDARD_DEVIATION), stack_stat)
del stack_stat
for percentile in PERCENTILE:
if percentile in self.statistics:
log_mem("Before {p}".format(p=percentile.name))
stack_stat = calculate_stack_statistic_percentile(stack=stack, percentile=PERCENTILE[percentile],
ndv=ndv, interpolation=self.interpolation)
numpy.save(self.get_statistic_filename(percentile), stack_stat)
del stack_stat
if Statistic.COUNT_OBSERVED in self.statistics:
log_mem("Before OBSERVED COUNT")
# COUNT OBSERVED - note the copy=False is modifying the array so this is done last
stack_stat = calculate_stack_statistic_count_observed(stack=stack, ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.COUNT_OBSERVED), stack_stat)
del stack_stat
log_mem("DONE")
def run(self):
_log.info("Calculating statistics for chunk")
ndv = get_dataset_type_ndv(self.dataset_type)
data_type = get_dataset_type_data_type(self.dataset_type)
tiles = self.get_tiles()
stack = get_dataset_data_stack(tiles, self.dataset_type, self.band.name, ndv=ndv,
x=self.x_offset, y=self.y_offset,
x_size=self.x_chunk_size, y_size=self.y_chunk_size,
mask_pqa_apply=self.mask_pqa_apply, mask_pqa_mask=self.mask_pqa_mask)
if len(stack) == 0:
return
# TODO get statistics to be generated from command line argument
if Statistic.COUNT in self.statistics:
log_mem("Before COUNT")
# COUNT
stack_stat = calculate_stack_statistic_count(stack=stack, ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.COUNT), stack_stat)
del stack_stat
if Statistic.MIN in self.statistics:
log_mem("Before MIN")
# MIN
stack_stat = calculate_stack_statistic_min(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MIN), stack_stat)
del stack_stat
if Statistic.MAX in self.statistics:
log_mem("Before MAX")
# MAX
stack_stat = calculate_stack_statistic_max(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MAX), stack_stat)
del stack_stat
if Statistic.MEAN in self.statistics:
log_mem("Before MEAN")
# MEAN
stack_stat = calculate_stack_statistic_mean(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.MEAN), stack_stat)
del stack_stat
if Statistic.VARIANCE in self.statistics:
log_mem("Before VARIANCE")
# VARIANCE
stack_stat = calculate_stack_statistic_variance(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.VARIANCE), stack_stat)
del stack_stat
if Statistic.STANDARD_DEVIATION in self.statistics:
log_mem("Before STANDARD_DEVIATION")
# STANDARD_DEVIATION
stack_stat = calculate_stack_statistic_standard_deviation(stack=stack, ndv=ndv, dtype=data_type)
numpy.save(self.get_statistic_filename(Statistic.STANDARD_DEVIATION), stack_stat)
del stack_stat
for percentile in PERCENTILE:
if percentile in self.statistics:
log_mem("Before {p}".format(p=percentile.name))
stack_stat = calculate_stack_statistic_percentile(stack=stack, percentile=PERCENTILE[percentile],
ndv=ndv, interpolation=self.interpolation)
numpy.save(self.get_statistic_filename(percentile), stack_stat)
del stack_stat
if Statistic.COUNT_OBSERVED in self.statistics:
log_mem("Before OBSERVED COUNT")
# COUNT OBSERVED - note the copy=False is modifying the array so this is done last
stack_stat = calculate_stack_statistic_count_observed(stack=stack, ndv=ndv)
numpy.save(self.get_statistic_filename(Statistic.COUNT_OBSERVED), stack_stat)
del stack_stat
log_mem("DONE")