def run(logger, args, extra_argv=None):
try:
os.makedirs(args.out_dir)
except OSError as e:
if e.errno != errno.EEXIST:
sys.exit('Cannot create output dir: %s' % e)
tag, ext = os.path.splitext(os.path.basename(args.in_fn))
out_fn = os.path.join(args.out_dir, '%s_features%s' % (tag, ext))
logger.info('writing to %s', out_fn)
with open(out_fn, 'w') as fout:
writer = AvroFileWriter(fout, out_schema)
with open(args.in_fn) as fin:
reader = AvroFileReader(fin)
for r in reader:
p = BioImgPlane(r)
pixels = p.get_xy()
logger.info('processing %r', [p.z, p.c, p.t])
kw = {
'long': args.long,
'w': args.width,
'h': args.height,
'dx': args.delta_x,
'dy': args.delta_y,
'ox': args.offset_x,
'oy': args.offset_y,
}
for fv in calc_features(pixels, p.name, **kw):
out_rec = to_avro(fv)
for name in 'img_path', 'series', 'z', 'c', 't':
out_rec[name] = getattr(p, name)
writer.write(out_rec)
writer.close()
return 0
def map(self, ctx):
p = BioImgPlane(ctx.value)
pixels = p.get_xy()
# TODO: support tiling
out_rec = to_avro(calc_features(pixels, p.name))
for name in 'img_path', 'series', 'z', 'c', 't':
out_rec[name] = getattr(p, name)
ctx.emit(None, out_rec)
def map(self, ctx):
p = BioImgPlane(ctx.value)
pixels = p.get_xy()
bn = '%s-z%04d-c%04d-t%04d.npy' % (p.name, p.z, p.c, p.t)
fn = hdfs.path.join(self.out_dir, p.name, bn)
with hdfs.open(fn, 'w') as fo:
np.save(fo, pixels)
ctx.emit(fn, '%s\t%s' % (p.dimension_order, pixels.shape))
def map(self, ctx):
p = BioImgPlane(ctx.value)
pixels = p.get_xy()
bn = '%s-z%04d-c%04d-t%04d.npy' % (p.name, p.z, p.c, p.t)
fn = hdfs.path.join(self.out_dir, p.name, bn)
with hdfs.open(fn, 'w') as fo:
np.save(fo, pixels)
ctx.emit(fn, '%s\t%s' % (p.dimension_order, pixels.shape))
def map(self, ctx):
p = BioImgPlane(ctx.value)
pixels = p.get_xy()
# TODO: support tiling
out_rec = to_avro(calc_features(pixels, p.name))
for name in 'img_path', 'series', 'z', 'c', 't':
out_rec[name] = getattr(p, name)
ctx.emit(None, out_rec)
def run(logger, args, extra_argv=None):
try:
os.makedirs(args.out_dir)
except OSError as e:
if e.errno != errno.EEXIST:
sys.exit('Cannot create output dir: %s' % e)
tag, ext = os.path.splitext(os.path.basename(args.in_fn))
out_fn = os.path.join(args.out_dir, '%s_features%s' % (tag, ext))
logger.info('writing to %s', out_fn)
zsubset, csubset, tsubset = get_subsets(args)
with open(out_fn, 'w') as fout:
writer = AvroFileWriter(fout, out_schema)
with open(args.in_fn) as fin:
reader = AvroFileReader(fin)
for r in reader:
p = BioImgPlane(r)
if zsubset and p.z not in zsubset:
continue
if csubset and p.c not in csubset:
continue
if tsubset and p.t not in tsubset:
continue
pixels = p.get_xy()
logger.info('processing %r', [p.z, p.c, p.t])
kw = {
'long': args.long,
'w': args.width,
'h': args.height,
'dx': args.delta_x,
'dy': args.delta_y,
'ox': args.offset_x,
'oy': args.offset_y,
}
for fv in calc_features(pixels, p.name, **kw):
out_rec = to_avro(fv)
for name in 'img_path', 'series', 'z', 'c', 't':
out_rec[name] = getattr(p, name)
writer.write(out_rec)
writer.close()
return 0
def map(self, ctx):
p = BioImgPlane(ctx.value)
if len(self.img_set) >= SET_SIZE:
self.__process_current_set(ctx)
self.img_set = []
self.img_set.append(p)
def iterplanes(avro_file):
with open(avro_file, 'rb') as f:
reader = AvroFileReader(f)
for r in reader:
yield BioImgPlane(r)