def createPyramidLevel(self, resolution=0, subdiv=(1, 2, 2), quiet=False):
""" Add a level in a multi-level pyramid.
Provided this function because TeraStitcher does
not have enough control over the sampling strategy for imaris files
"""
# find all of the imaris datasets under the specified resolution group
self._subdiv = subdiv
datasetnames = list()
resin = 'ResolutionLevel ' + str(resolution)
resout = 'ResolutionLevel ' + str(resolution + 1)
prf = '/DataSet/' + resin
self._file_object[prf].visit(datasetnames.append)
tt = [
type(self._file_object[prf + '/' + x]) == h5py._hl.dataset.Dataset
for x in datasetnames
]
res = list(compress(datasetnames, tt))
# Now we need to find the ones ending in '/Data'
tt = [x.endswith('/Data') for x in res]
res = list(compress(res, tt))
outpaths = ['/DataSet/' + resout + '/' + x for x in res]
inpaths = [prf + '/' + x for x in res]
pbar = ProgressBar()
for idx in range(len(inpaths)):
if not quiet:
print(inpaths[idx])
pbar.register()
self._subdivide(self._file_object, inpaths[idx], outpaths[idx])
if not quiet:
pbar.unregister()
def show_progress(arr, msg: str = None, nthreads: int = 1):
from dask.diagnostics import ProgressBar
if msg is not None:
logger.info(msg)
pbar = ProgressBar()
pbar.register()
res = controlled_compute(arr, nthreads)
pbar.unregister()
return res
def main():
paths = list(Path(args.dir).rglob("*.txt"))
pbar = ProgressBar()
pbar.register()
a_bag = db.from_sequence(paths, npartitions=mp.cpu_count())
a_bag = a_bag.map(lambda a_path: parse_path(a_path))
frame_data = a_bag.compute()
pbar.unregister()
frame = pd.DataFrame(frame_data)
frame.to_pickle(args.out)
def test_register(capsys):
try:
p = ProgressBar()
p.register()
assert Callback.active
get_threaded(dsk, "e")
check_bar_completed(capsys)
p.unregister()
assert not Callback.active
finally:
Callback.active.clear()
def test_register(capsys):
try:
p = ProgressBar()
p.register()
assert _globals['callbacks']
get(dsk, 'e')
check_bar_completed(capsys)
p.unregister()
assert not _globals['callbacks']
finally:
_globals['callbacks'].clear()
def test_register(capsys):
try:
p = ProgressBar()
p.register()
assert Callback.active
get_threaded(dsk, 'e')
check_bar_completed(capsys)
p.unregister()
assert not Callback.active
finally:
Callback.active.clear()
def test_register(capsys):
try:
p = ProgressBar()
p.register()
assert _globals['callbacks']
get_threaded(dsk, 'e')
check_bar_completed(capsys)
p.unregister()
assert not _globals['callbacks']
finally:
_globals['callbacks'].clear()
def test_register(capsys):
try:
p = ProgressBar()
p.register()
assert _globals['callbacks']
get(dsk, 'e')
out, err = capsys.readouterr()
bar, percent, time = [i.strip() for i in out.split('\r')[-1].split('|')]
assert bar == "[########################################]"
assert percent == "100% Completed"
p.unregister()
assert not _globals['callbacks']
finally:
_globals['callbacks'].clear()
def show_progress(arr, msg: str = None, nthreads: int = 1):
"""
Performs computation with Dask and shows progress bar.
Args:
arr:
msg: message to log, default None
nthreads: number of threads to use for computation, default 1
Returns:
Result of computation.
"""
from dask.diagnostics import ProgressBar
if msg is not None:
logger.info(msg)
pbar = ProgressBar()
pbar.register()
res = controlled_compute(arr, nthreads)
pbar.unregister()
return res
def Movie(
da,
odir,
varname=None,
framedim="time",
moviename="movie",
clim=None,
cmap=None,
bgcolor=np.array([1, 1, 1]) * 0.3,
framewidth=1280,
frameheight=720,
dpi=100,
lon=None,
lat=None,
dask=True,
delete=True,
ffmpeg=True,
plot_style="simple",
norm=mpl.colors.Normalize(),
progbar=False,
):
# Set defaults:
if not ffmpeg and delete:
raise RuntimeError("raw picture deletion makes only \
sense if ffmpeg conversion is enabled")
if not isinstance(da, xr.DataArray):
raise RuntimeError("input has to be an xarray DataStructure, instead\
is " + str(type(da)))
if not os.path.exists(odir):
os.makedirs(odir)
# Infer defaults from data
if clim is None:
print("clim will be inferred from data, this can take very long...")
clim = [da.min(), da.max()]
if cmap is None:
cmap = plt.cm.viridis
if plot_style in ["map"]:
if None in [lon, lat]:
raise RuntimeError("map plotting requires lon and lat")
else:
lons = np.array(da[lon].data)
lats = np.array(da[lat].data)
if len(lons.shape) != 2:
lons, lats = np.meshgrid(lons, lats)
time = np.array(da["time"].data)
else:
lons = None
lats = None
time = None
# Annnd here we go
print("+++ Execute plot function +++")
if dask:
data = da.data
frame_axis = da.get_axis_num(framedim)
drop_axis = [da.get_axis_num(a) for a in da.dims if not a == framedim]
chunks = list(data.shape)
chunks[frame_axis] = 1
data = data.rechunk(chunks)
if progbar:
pbar = ProgressBar()
pbar.register()
data.map_blocks(
FramePrint,
chunks=[1],
drop_axis=drop_axis,
dtype=np.float64,
dask=dask,
frame_axis=frame_axis,
odir=odir,
cmap=cmap,
clim=clim,
framewidth=framewidth,
frameheight=frameheight,
bgcolor=bgcolor,
plot_style=plot_style,
lons=lons,
lats=lats,
time=time,
norm=norm,
dpi=dpi,
).compute(get=get)
if progbar:
pbar.unregister()
# The .compute(get=get) line is some dask 'magic': it parallelizes the
# print function with processes and not threads,which is a lot faster
# for custom functions apparently!
else:
# do it with a simple for loop...can this really be quicker?
print("This is slow! Do it in dask!")
for ii in range(0, len(da.time)):
start_time = time.time()
da_slice = da[{framedim: ii}]
# fig,ax,h = FramePrint(da_slice,
FramePrint(
da_slice,
frame=ii,
odir=odir,
cmap=cmap,
clim=clim,
framewidth=framewidth,
frameheight=dpi,
bgcolor=bgcolor,
plot_style=plot_style,
lons=lons,
lats=lats,
norm=norm,
dpi=dpi,
)
if ii % 100 == 0:
remaining_time = (len(da.time) - ii) * (time.time() -
start_time) / 60
print("FRAME---%04d---" % ii)
print("Estimated time left : %d minutes" % remaining_time)
query = ('ffmpeg -y -i "frame_%05d.png" -c:v libx264 -preset veryslow \
-crf 6 -pix_fmt yuv420p \
-framerate 10 \
"' + moviename + '.mp4"')
with cd(odir):
if ffmpeg:
print("+++ Convert frames to video +++")
excode = os.system(query)
if excode == 0 and delete:
os.system("rm *.png")
X, Y = self.make_dataset(table=self.t, var='SB', additional=['L_MAX', 'LAYER', 'SOL_Z'])
X, Y = self.duplicate_dataset(X, Y)
self.SB = continuous.model('SB', X, Y, x, logger=logger, load_save=True)
del X, Y
X, Y = self.make_dataset(table=self.t, var='CS', additional=['L_MAX', 'LAYER', 'SOL_Z', 'SOL_SAND'])
X, Y = self.duplicate_dataset(X, Y)
x = self.modify_dataset(x, series=self.SOL_Z.Y_mod, name='SOL_SAND')
self.CS = continuous.model('CS', X, Y, x, logger=logger, load_save=True)
del X, Y
X, Y = self.make_dataset(table=self.t, var='FS', additional=['L_MAX', 'LAYER', 'SOL_Z', 'SOL_SAND'])
X, Y = self.duplicate_dataset(X, Y)
self.FS = continuous.model('FS', X, Y, x, logger=logger, load_save=True)
del X, Y, x
self.write_results()
if __name__ == '__main__':
from dask.diagnostics import ProgressBar
from dask import config
from multiprocessing import freeze_support
freeze_support()
pbar = ProgressBar()
pbar.register()
config.set(scheduler='processes')
main(r"C:\Users\putzr\Documents\GitHub\sleepy\model\training.txt",
r"C:\Users\putzr\Documents\GitHub\sleepy\model\modelling.txt").run()
pbar.unregister()
def get(*args, **kwargs):
pbar = ProgressBar()
pbar.register()
out = client.get(*args, **kwargs)
pbar.unregister()
return out
