def losslessDecompress(f, group): paths = findDatasets(f, group, keyword="Events") paths.extend(findDatasets(f, group, keyword="Alignment")) paths.extend(findDatasets(f, "all", keyword="Signal", entry_point="Raw")) for path in paths: rewriteDataset(f, path) return "GZIP=1"
def deepLosslessCompress(f, group):
paths = findDatasets(f, group, "Events")
paths = [path for path in paths if "Basecall" in path]
# index event detection
if "UniqueGlobalKey/channel_id" in f:
sampleRate = f["UniqueGlobalKey/channel_id"].attrs["sampling_rate"]
for path in paths:
if f[path].parent.parent.attrs.__contains__("event_detection"):
# index back to event detection
dataset = f[path].value
start = np.array([int(round(sampleRate * i)) for i in dataset["start"]])
dataset = indexToZero(f, path, "start", dataColumn=start)
move = dataset["move"] # rewrite move dataset because it's int64 for max 2
# otherwise, event by event
dataset = drop_fields(dataset, ["mean", "stdv", "length", "move"])
dataset = append_fields(dataset, ["move"], [move], [getDtype(move)])
rewriteDataset(f, path, compression="gzip", compression_opts=9, dataset=dataset)
# rewrite eventdetection too - start is also way too big here
eventDetectionPath = findDatasets(f, "all", entry_point=f[path].parent.parent.attrs.get("event_detection"))[0]
if "picopore.start_index" not in f[eventDetectionPath].attrs.keys():
eventData = indexToZero(f, eventDetectionPath, "start")
rewriteDataset(f, eventDetectionPath, compression="gzip", compression_opts=9, dataset=eventData)
if __basegroup_name__ not in f:
f.create_group(__basegroup_name__)
for name, group in f.items():
if name != __basegroup_name__:
recursiveCollapseGroups(f, __basegroup_name__, name, group)
return losslessCompress(f, group)
def deepLosslessDecompress(f, group):
# rebuild group hierarchy
if __basegroup_name__ in f.keys():
uncollapseGroups(f, f[__basegroup_name__])
paths = findDatasets(f, group)
paths = [path for path in paths if "Basecall" in path]
sampleRate = f["UniqueGlobalKey/channel_id"].attrs["sampling_rate"]
for path in paths:
if f[path].parent.parent.attrs.__contains__("event_detection"):
# index back to event detection
dataset = f[path].value
if "mean" not in dataset.dtype.names:
eventDetectionPath = findDatasets(f, "all", entry_point=f[path].parent.parent.attrs.get("event_detection"))[0]
eventData = f[eventDetectionPath].value
try:
start = eventData["start"] + f[eventDetectionPath].attrs["picopore.start_index"]
del f[eventDetectionPath].attrs["picopore.start_index"]
eventData = drop_fields(eventData, ["start"])
eventData = append_fields(eventData, ["start"], [start], [getDtype(start)])
rewriteDataset(f, eventDetectionPath, compression="gzip", compression_opts=1, dataset=eventData)
except KeyError:
# must have been compressed without start indexing
pass
try:
start_index = f[path].attrs["picopore.start_index"]
del f[path].attrs["picopore.start_index"]
except KeyError:
# must have been compressed without start indexing
start_index=0
start = dataset["start"][0] + start_index
end = dataset["start"][-1] + start_index
# constrain to range in basecall
eventData = eventData[np.logical_and(eventData["start"] >= start, eventData["start"] <= end)]
# remove missing events
i=0
keepIndex = []
for time in dataset["start"]:
while eventData["start"][i] != time + start_index and i < eventData.shape[0]:
i += 1
keepIndex.append(i)
eventData = eventData[keepIndex]
dataset = drop_fields(dataset, "start")
start = [i/sampleRate for i in eventData["start"]]
length = [i/sampleRate for i in eventData["length"]]
dataset = append_fields(dataset, ["mean", "start", "stdv", "length"], [eventData["mean"], start, eventData["stdv"], length])
rewriteDataset(f, path, dataset=dataset)
return losslessDecompress(f, group)
