def test_get_line_cache_name(cachedir, cachefile, n_images, n_row, n_bands):
cfg = dict(cache_line_dir=cachedir)
assert cachefile == cache.get_line_cache_name(cfg,
n_images, n_row, n_bands)
def test_get_line_cache_name(self):
name = cache.get_line_cache_name(self.config, self.n_images,
self.n_row, self.n_bands)
self.assertEqual(name, self.test_file)
def test_get_line_cache_name(self):
name = cache.get_line_cache_name(
self.config, self.n_images, self.n_row, self.n_bands)
self.assertEqual(name, self.test_file)
def read_line(line, images, image_IDs, dataset_config,
ncol, nband, dtype,
read_cache=False, write_cache=False, validate_cache=False):
""" Reads in dataset from cache or images if required
Args:
line (int): line to read in from images
images (list): list of image filenames to read from
image_IDs (iterable): list image identifying strings
dataset_config (dict): dictionary of dataset configuration options
ncol (int): number of columns
nband (int): number of bands
dtype (type): NumPy datatype
read_cache (bool, optional): try to read from cache directory
(default: False)
write_cache (bool, optional): try to to write to cache directory
(default: False)
validate_cache (bool, optional): validate that cache data come from same
images specified in `images` (default: False)
Returns:
Y (np.ndarray): 3D array of image data (nband, n_image, n_cols)
"""
start_time = time.time()
read_from_disk = True
cache_filename = get_line_cache_name(
dataset_config, len(images), line, nband)
Y_shape = (nband, len(images), ncol)
if read_cache:
Y = read_cache_file(cache_filename,
image_IDs if validate_cache else None)
if Y is not None and Y.shape == Y_shape:
logger.debug('Read in Y from cache file')
read_from_disk = False
elif Y is not None and Y.shape != Y_shape:
logger.warning(
'Data from cache file does not meet size requested '
'({y} versus {r})'.format(y=Y.shape, r=Y_shape))
if read_from_disk:
# Read in Y
if dataset_config['use_bip_reader']:
# Use BIP reader
logger.debug('Reading in data from disk using BIP reader')
Y = read_row_BIP(images, line, (ncol, nband), dtype)
else:
# Read in data just using GDAL
logger.debug('Reading in data from disk using GDAL')
Y = read_row_GDAL(images, line)
logger.debug('Took {s}s to read in the data'.format(
s=round(time.time() - start_time, 2)))
if write_cache and read_from_disk:
logger.debug('Writing Y data to cache file {f}'.format(
f=cache_filename))
write_cache_file(cache_filename, Y, image_IDs)
return Y
def read_line(line,
images,
image_IDs,
dataset_config,
ncol,
nband,
dtype,
read_cache=False,
write_cache=False,
validate_cache=False):
""" Reads in dataset from cache or images if required
Args:
line (int): line to read in from images
images (list): list of image filenames to read from
image_IDs (iterable): list image identifying strings
dataset_config (dict): dictionary of dataset configuration options
ncol (int): number of columns
nband (int): number of bands
dtype (type): NumPy datatype
read_cache (bool, optional): try to read from cache directory
(default: False)
write_cache (bool, optional): try to to write to cache directory
(default: False)
validate_cache (bool, optional): validate that cache data come from same
images specified in `images` (default: False)
Returns:
Y (np.ndarray): 3D array of image data (nband, n_image, n_cols)
"""
start_time = time.time()
read_from_disk = True
cache_filename = get_line_cache_name(dataset_config, len(images), line,
nband)
Y_shape = (nband, len(images), ncol)
if read_cache:
Y = read_cache_file(cache_filename,
image_IDs if validate_cache else None)
if Y is not None and Y.shape == Y_shape:
logger.debug('Read in Y from cache file')
read_from_disk = False
elif Y is not None and Y.shape != Y_shape:
logger.warning('Data from cache file does not meet size requested '
'({y} versus {r})'.format(y=Y.shape, r=Y_shape))
if read_from_disk:
# Read in Y
if dataset_config['use_bip_reader']:
# Use BIP reader
logger.debug('Reading in data from disk using BIP reader')
Y = read_row_BIP(images, line, (ncol, nband), dtype)
else:
# Read in data just using GDAL
logger.debug('Reading in data from disk using GDAL')
Y = read_row_GDAL(images, line)
logger.debug('Took {s}s to read in the data'.format(
s=round(time.time() - start_time, 2)))
if write_cache and read_from_disk:
logger.debug(
'Writing Y data to cache file {f}'.format(f=cache_filename))
write_cache_file(cache_filename, Y, image_IDs)
return Y
def test_get_line_cache_name(cachedir, cachefile, n_images, n_row, n_bands):
cfg = dict(cache_line_dir=cachedir)
assert cachefile == cache.get_line_cache_name(cfg, n_images, n_row,
n_bands)
def main(args):
# Parse and validate configuration file
dataset_config, yatsm_config = config_parser.parse_config_file(
args['config_file'])
if not os.path.isdir(dataset_config['cache_line_dir']):
os.makedirs(dataset_config['cache_line_dir'])
dates, images = utils.csvfile_to_dataset(
dataset_config['input_file'],
date_format=dataset_config['date_format']
)
image_IDs = utils.get_image_IDs(images)
nrow, ncol, nband, dtype = reader.get_image_attribute(images[0])
# Determine lines to work on
job_lines = utils.calculate_lines(args['job_number'],
args['total_jobs'],
nrow,
interlaced=args['interlace'])
logger.debug('Responsible for lines: {l}'.format(l=job_lines))
# Determine file reader
if dataset_config['use_bip_reader']:
logger.debug('Reading in data from disk using BIP reader')
image_reader = reader.read_row_BIP
image_reader_kwargs = {'size': (ncol, nband),
'dtype': dtype}
else:
logger.debug('Reading in data from disk using GDAL')
image_reader = reader.read_row_GDAL
image_reader_kwargs = {}
# Attempt to update cache files
previous_cache = None
if args['update_pattern']:
previous_cache = fnmatch.filter(
os.listdir(dataset_config['cache_line_dir']),
args['update_pattern'])
if not previous_cache:
logger.warning('Could not find cache files to update with pattern'
'{p}'.format(p=args['update_pattern']))
else:
logger.debug('Found {n} previously cached files to update'.format(
n=len(previous_cache)))
for job_line in job_lines:
cache_filename = cache.get_line_cache_name(
dataset_config, len(images), job_line, nband)
logger.debug('Caching line {l} to {f}'.format(
l=job_line, f=cache_filename))
start_time = time.time()
# Find matching cache file
update = False
if previous_cache:
pattern = cache.get_line_cache_pattern(
job_line, nband, regex=False)
potential = fnmatch.filter(previous_cache, pattern)
if not potential:
logger.info('Found zero previous cache files for '
'line {l}'.format(l=job_line))
elif len(potential) > 1:
logger.info('Found more than one previous cache file for '
'line {l}. Keeping first'.format(l=job_line))
update = os.path.join(dataset_config['cache_line_dir'],
potential[0])
else:
update = os.path.join(dataset_config['cache_line_dir'],
potential[0])
logger.info('Updating from cache file {f}'.format(f=update))
if update:
cache.update_cache_file(
images, image_IDs,
update, cache_filename,
job_line, image_reader, image_reader_kwargs
)
else:
if dataset_config['use_bip_reader']:
# Use BIP reader
logger.debug('Reading in data from disk using BIP reader')
Y = reader.read_row_BIP(images, job_line, (ncol, nband), dtype)
else:
# Read in data just using GDAL
logger.debug('Reading in data from disk using GDAL')
Y = reader.read_row_GDAL(images, job_line)
cache.write_cache_file(cache_filename, Y, image_IDs)
logger.debug('Took {s}s to cache the data'.format(
s=round(time.time() - start_time, 2)))
def main(args):
# Parse and validate configuration file
dataset_config, yatsm_config = config_parser.parse_config_file(
args['config_file'])
if not os.path.isdir(dataset_config['cache_line_dir']):
os.makedirs(dataset_config['cache_line_dir'])
dates, images = utils.csvfile_to_dataset(
dataset_config['input_file'],
date_format=dataset_config['date_format'])
image_IDs = utils.get_image_IDs(images)
nrow, ncol, nband, dtype = reader.get_image_attribute(images[0])
# Determine lines to work on
job_lines = utils.calculate_lines(args['job_number'],
args['total_jobs'],
nrow,
interlaced=args['interlace'])
logger.debug('Responsible for lines: {l}'.format(l=job_lines))
# Determine file reader
if dataset_config['use_bip_reader']:
logger.debug('Reading in data from disk using BIP reader')
image_reader = reader.read_row_BIP
image_reader_kwargs = {'size': (ncol, nband), 'dtype': dtype}
else:
logger.debug('Reading in data from disk using GDAL')
image_reader = reader.read_row_GDAL
image_reader_kwargs = {}
# Attempt to update cache files
previous_cache = None
if args['update_pattern']:
previous_cache = fnmatch.filter(
os.listdir(dataset_config['cache_line_dir']),
args['update_pattern'])
if not previous_cache:
logger.warning('Could not find cache files to update with pattern'
'{p}'.format(p=args['update_pattern']))
else:
logger.debug('Found {n} previously cached files to update'.format(
n=len(previous_cache)))
for job_line in job_lines:
cache_filename = cache.get_line_cache_name(dataset_config, len(images),
job_line, nband)
logger.debug('Caching line {l} to {f}'.format(l=job_line,
f=cache_filename))
start_time = time.time()
# Find matching cache file
update = False
if previous_cache:
pattern = cache.get_line_cache_pattern(job_line,
nband,
regex=False)
potential = fnmatch.filter(previous_cache, pattern)
if not potential:
logger.info('Found zero previous cache files for '
'line {l}'.format(l=job_line))
elif len(potential) > 1:
logger.info('Found more than one previous cache file for '
'line {l}. Keeping first'.format(l=job_line))
update = os.path.join(dataset_config['cache_line_dir'],
potential[0])
else:
update = os.path.join(dataset_config['cache_line_dir'],
potential[0])
logger.info('Updating from cache file {f}'.format(f=update))
if update:
cache.update_cache_file(images, image_IDs, update, cache_filename,
job_line, image_reader,
image_reader_kwargs)
else:
if dataset_config['use_bip_reader']:
# Use BIP reader
logger.debug('Reading in data from disk using BIP reader')
Y = reader.read_row_BIP(images, job_line, (ncol, nband), dtype)
else:
# Read in data just using GDAL
logger.debug('Reading in data from disk using GDAL')
Y = reader.read_row_GDAL(images, job_line)
cache.write_cache_file(cache_filename, Y, image_IDs)
logger.debug('Took {s}s to cache the data'.format(
s=round(time.time() - start_time, 2)))
def cache(ctx, config, job_number, total_jobs, update_pattern, interlace):
cfg = parse_config_file(config)
if not os.path.isdir(cfg['dataset']['cache_line_dir']):
os.makedirs(cfg['dataset']['cache_line_dir'])
df = csvfile_to_dataframe(cfg['dataset']['input_file'],
cfg['dataset']['date_format'])
df['image_IDs'] = get_image_IDs(df['filename'])
nrow, ncol, nband, dtype = reader.get_image_attribute(df['filename'][0])
# Determine lines to work on
job_lines = distribute_jobs(job_number, total_jobs, nrow,
interlaced=interlace)
logger.debug('Responsible for lines: {l}'.format(l=job_lines))
# Determine file reader
if cfg['dataset']['use_bip_reader']:
logger.debug('Reading in data from disk using BIP reader')
image_reader = reader.read_row_BIP
image_reader_kwargs = {'size': (ncol, nband),
'dtype': dtype}
else:
logger.debug('Reading in data from disk using GDAL')
image_reader = reader.read_row_GDAL
image_reader_kwargs = {}
# Attempt to update cache files
previous_cache = None
if update_pattern:
previous_cache = fnmatch.filter(
os.listdir(cfg['dataset']['cache_line_dir']), update_pattern)
if not previous_cache:
logger.warning('Could not find cache files to update with pattern '
'%s' % update_pattern)
else:
logger.debug('Found %s previously cached files to update' %
len(previous_cache))
for job_line in job_lines:
cache_filename = get_line_cache_name(cfg['dataset'], len(df),
job_line, nband)
logger.debug('Caching line {l} to {f}'.format(
l=job_line, f=cache_filename))
start_time = time.time()
# Find matching cache file
update = False
if previous_cache:
pattern = get_line_cache_pattern(job_line, nband, regex=False)
potential = fnmatch.filter(previous_cache, pattern)
if not potential:
logger.info('Found zero previous cache files for '
'line {l}'.format(l=job_line))
elif len(potential) > 1:
logger.info('Found more than one previous cache file for '
'line {l}. Keeping first'.format(l=job_line))
update = os.path.join(cfg['dataset']['cache_line_dir'],
potential[0])
else:
update = os.path.join(cfg['dataset']['cache_line_dir'],
potential[0])
logger.info('Updating from cache file {f}'.format(f=update))
if update:
update_cache_file(df['filename'], df['image_IDs'],
update, cache_filename,
job_line, image_reader, image_reader_kwargs)
else:
if cfg['dataset']['use_bip_reader']:
# Use BIP reader
logger.debug('Reading in data from disk using BIP reader')
Y = reader.read_row_BIP(df['filename'], job_line,
(ncol, nband), dtype)
else:
# Read in data just using GDAL
logger.debug('Reading in data from disk using GDAL')
Y = reader.read_row_GDAL(df['filename'], job_line)
write_cache_file(cache_filename, Y, df['image_IDs'])
logger.debug('Took {s}s to cache the data'.format(
s=round(time.time() - start_time, 2)))