def extract(file, directory, timestep=1.0, output="txt"):
print file
path = os.path.join(directory, file)
name = os.path.splitext(file)[0]
newdir = os.path.join(directory, name)
if output == "hdf5":
newdir = directory
splits = string.split(name, sep="_")
for i, s in enumerate(splits):
if s.lower() == "ramp":
start = float(splits[i + 1])
end = float(splits[i + 2])
step = float(splits[i + 3])
volts = np.arange(start, end + step, step)
times = np.arange(0.0, len(volts) * timestep, timestep)
print "Ramp:", times, volts
parse(path, times, timestep, volts, name, newdir, output=output)
return True
if os.path.splitext(file)[1] == ".mzML":
maxtime = mzMLimporter(path).get_max_time()
else:
maxtime = DataImporter(path).get_max_time()
times = np.arange(0, maxtime, timestep)
parse(path, times, timestep, None, name, newdir, output=output)
def parse_multiple(paths,
timestep,
newdir,
starttp,
endtp,
voltsarr=None,
outputname=None):
outfile = outputname + ".hdf5"
outpath = os.path.join(newdir, outfile)
hdf = h5py.File(outpath, "a")
try:
del hdf["ms_dataset"]
except:
pass
msdataset = hdf.require_group("ms_dataset")
if voltsarr is not None:
msdataset.attrs["v1name"] = "Collision Voltage"
else:
msdataset.attrs["v1name"] = "timestart"
msdataset.attrs["timestep"] = timestep
msdataset.attrs["v2name"] = "Original File"
config = hdf.require_group("config")
config.attrs["metamode"] = -1
num = 0
v = 0
print(starttp, endtp, timestep)
for path in paths:
if os.path.isfile(path):
if os.path.splitext(path)[1] == ".mzML":
d = mzMLimporter(path)
else:
d = DataImporter(path)
for t in np.arange(starttp, endtp, timestep):
data = d.get_data(time_range=(t, t + timestep))
if not ud.isempty(data):
group = msdataset.require_group(str(num))
replace_dataset(group, "raw_data", data=data)
# group=msdataset.require_group(str(v))
try:
if voltsarr[v] is not None:
temp = int(t / timestep)
group.attrs["Collision Voltage"] = voltsarr[v][
temp]
except:
pass
group.attrs["timestart"] = t
group.attrs["timeend"] = t + timestep
group.attrs["timemid"] = t + timestep * 0.5
splits = path.split(sep="\\")
group.attrs["Original File"] = splits[len(splits) - 1]
num += 1
pass
v += 1
else:
print("File not found: ", path)
msdataset.attrs["num"] = num
hdf.close()
return outpath
def auto_from_wizard(data, filename, mode):
# print data
eng = mudeng.MetaUniDec()
eng.data.new_file(filename)
for i, d in enumerate(data):
v1 = d[1]
v2 = d[2]
f=d[0]
try:
start = float(d[3])
except:
start = None
try:
stop = float(d[4])
except:
stop = None
path = d[5]
if start is None or stop is None:
eng.data.add_file(path=path)
else:
print start, stop
if os.path.splitext(path)[1] == ".mzML":
d = mzMLimporter(path)
else:
d = DataImporter(path)
if mode == 1:
data = d.get_data(scan_range=(start, stop))
elif mode == 0:
data = d.get_data(time_range=(start, stop))
eng.data.add_data(data, path)
eng.data.spectra[-1].var1 = v1
eng.data.spectra[-1].var2 = v2
eng.data.spectra[-1].name = f
eng.data.export_hdf5()
def extract_scans_multiple_files(files,
dirs,
startscan=1.0,
endscan=1.0,
outputname="Combined",
existing_path=None):
paths = []
names = []
startscan = int(float(startscan))
endscan = int(float(endscan))
newdir = 0
for f, d in zip(files, dirs):
path = os.path.join(d, f)
name = os.path.splitext(f)[0]
newdir = d
paths.append(path)
names.append(name)
outfile = outputname + ".hdf5"
if existing_path is None:
outpath = os.path.join(newdir, outfile)
else:
outpath = existing_path
hdf = h5py.File(outpath, "a")
try:
if existing_path is None:
del hdf["ms_dataset"]
except:
pass
msdataset = hdf.require_group("ms_dataset")
msdataset.attrs["v1name"] = "timemid"
msdataset.attrs["v2name"] = "Original File"
config = hdf.require_group("config")
config.attrs["metamode"] = -1
num = 0
for path in paths:
if os.path.isfile(path):
if os.path.splitext(path)[1] == ".mzML":
d = mzMLimporter(path)
else:
d = DataImporter(path)
data = d.get_data(scan_range=(startscan, endscan))
if not ud.isempty(data):
group = msdataset.require_group(str(num))
replace_dataset(group, "raw_data", data=data)
times = d.get_times_from_scans([startscan, endscan])
group.attrs["timestart"] = times[0]
group.attrs["timeend"] = times[2]
group.attrs["timemid"] = times[1]
group.attrs["scanstart"] = startscan
group.attrs["scanend"] = endscan
splits = path.split(sep="\\")
group.attrs["Original File"] = splits[len(splits) - 1]
num += 1
else:
print("File not found: ", path)
msdataset.attrs["num"] = num
hdf.close()
return outpath
def parse(path, times, timestep, volts, outputheader, directory, output="txt"):
if os.path.isfile(path):
if output == "hdf5":
outfile = outputheader + ".hdf5"
outpath = os.path.join(directory, outfile)
hdf = h5py.File(outpath, "a")
try:
del hdf["ms_dataset"]
except:
pass
msdataset = hdf.require_group("ms_dataset")
if volts is not None:
msdataset.attrs["v1name"] = "Collision Voltage"
else:
msdataset.attrs["v1name"] = "timestart"
msdataset.attrs["timestep"] = timestep
config = hdf.require_group("config")
config.attrs["metamode"] = -1
num = 0
if os.path.splitext(path)[1] == ".mzML":
d = mzMLimporter(path)
else:
d = DataImporter(path)
for v, time in enumerate(times):
data = d.get_data(time_range=(time, time + timestep))
if not ud.isempty(data):
if output == "txt":
if volts is not None:
outfile = outputheader + "_" + str(int(
volts[v])) + ".txt"
else:
outfile = outputheader + "_" + str(v) + ".txt"
if not os.path.isdir(directory):
os.mkdir(directory)
outpath = os.path.join(directory, outfile)
np.savetxt(outpath, data)
print("Saved:", outpath)
elif output == "hdf5":
group = msdataset.require_group(str(v))
replace_dataset(group, "raw_data", data=data)
# group=msdataset.require_group(str(v))
if volts is not None:
group.attrs["Collision Voltage"] = volts[v]
group.attrs["timestart"] = time
group.attrs["timeend"] = time + timestep
group.attrs["timemid"] = time + timestep * 0.5
num += 1
pass
if output == "hdf5":
msdataset.attrs["num"] = num
hdf.close()
else:
print("File not found:", path)
return outpath
def extract(file, directory, timestep=1.0, output="txt"):
print(file)
path = os.path.join(directory, file)
name = os.path.splitext(file)[0]
newdir = os.path.join(directory, name)
if output == "hdf5":
newdir = directory
#name=ud.smartdecode(name)
splits = name.split(sep="_")
try:
for i, s in enumerate(splits):
if s.lower() == "ramp":
start = float(splits[i + 1])
end = float(splits[i + 2])
step = float(splits[i + 3])
volts = np.arange(start, end + step, step)
times = np.arange(0.0, len(volts) * timestep, timestep)
print("Ramp:", times, volts)
parse(path,
times,
timestep,
volts,
name,
newdir,
output=output)
return True
except:
print("Error parsing ramp keyword. Ignoring.")
if os.path.splitext(file)[1] == ".mzML":
maxtime = mzMLimporter(path).get_max_time()
else:
maxtime = DataImporter(path).get_max_time()
times = np.arange(0, maxtime, timestep)
outpath = parse(path, times, timestep, None, name, newdir, output=output)
return outpath
def extract_scans(file, directory, scanbins=1, output="txt"):
print file
scanbins = int(float(scanbins))
path = os.path.join(directory, file)
if os.path.isfile(path):
if os.path.splitext(path)[1] == ".mzML":
d = mzMLimporter(path)
else:
d = DataImporter(path)
name = os.path.splitext(file)[0]
newdir = os.path.join(directory, name)
if output == "hdf5":
newdir = directory
if os.path.splitext(file)[1] == ".mzML":
maxtime = d.get_max_time()
maxscans = d.get_max_scans()
else:
maxtime = d.get_max_time()
maxscans = d.get_max_scans()
print maxscans
scans = np.arange(0, maxscans, scanbins)
if output == "hdf5":
outfile = name + ".hdf5"
outpath = os.path.join(newdir, outfile)
hdf = h5py.File(outpath, "a")
try:
del hdf["ms_dataset"]
except:
pass
msdataset = hdf.require_group("ms_dataset")
msdataset.attrs["v1name"] = "timemid"
config = hdf.require_group("config")
config.attrs["metamode"] = -1
num = 0
for v, scan in enumerate(scans):
data = d.get_data(scan_range=(scan, scan + scanbins))
if not ud.isempty(data):
if output == "txt":
outfile = name + "_" + str(v) + ".txt"
if not os.path.isdir(newdir):
os.mkdir(newdir)
outpath = os.path.join(newdir, outfile)
np.savetxt(outpath, data)
print "Saved:", outpath
elif output == "hdf5":
group = msdataset.require_group(str(v))
replace_dataset(group, "raw_data", data=data)
times = d.get_times_from_scans([scan, scan + scanbins])
group.attrs["timestart"] = times[0]
group.attrs["timeend"] = times[2]
group.attrs["timemid"] = times[1]
group.attrs["scanstart"] = scan
group.attrs["scanend"] = scan + scanbins
num += 1
pass
if output == "hdf5":
msdataset.attrs["num"] = num
hdf.close()
print outpath
else:
print "File not found:", path
