def setup_fit(self, y):
'''
takes a data shape and returns a fit-primed object
'''
outputdir = None # nope
roifit = 0 # nope
roiwidth = y.shape[1] #need this to pretend its an image
b = McaAdvancedFitBatch.McaAdvancedFitBatch(
self.get_conf_path(), [y], outputdir, roifit, roiwidth,
fitfiles=0) # prime the beauty
b.pleaseBreak = 1
b.processList()
b.pleaseBreak = 0
return b
def setup_fit(self,y):
'''
takes a data shape and returns a fit-primed object
'''
outputdir=None # nope
roifit=0# nope
roiwidth=y.shape[1] #need this to pretend its an image
b = McaAdvancedFitBatch.McaAdvancedFitBatch(self.get_conf_path(),
[y],
outputdir,
roifit,
roiwidth,
fitfiles=0,
nosave=True,
quiet=True) # prime the beauty
b.pleaseBreak = 1
# temporary measure to stop the next line printing arrays to screen.
b.processList()
b.pleaseBreak = 0
return b
def testFitHdf5Stack(self):
import tempfile
from PyMca5.PyMcaIO import specfilewrapper as specfile
from PyMca5.PyMcaIO import ConfigDict
from PyMca5.PyMcaIO import HDF5Stack1D
from PyMca5.PyMcaPhysics.xrf import McaAdvancedFitBatch
spe = os.path.join(self.dataDir, "Steel.spe")
cfg = os.path.join(self.dataDir, "Steel.cfg")
sf = specfile.Specfile(spe)
self.assertTrue(len(sf) == 1, "File %s cannot be read" % spe)
self.assertTrue(sf[0].nbmca() == 1, "Spe file should contain MCA data")
y = counts = sf[0].mca(1)
x = channels = numpy.arange(y.size).astype(numpy.float)
sf = None
configuration = ConfigDict.ConfigDict()
configuration.read(cfg)
calibration = configuration["detector"]["zero"], \
configuration["detector"]["gain"], 0.0
initialTime = configuration["concentrations"]["time"]
# create the data
nRows = 5
nColumns = 10
nTimes = 3
data = numpy.zeros((nRows, nColumns, counts.size), dtype=numpy.float)
live_time = numpy.zeros((nRows * nColumns), dtype=numpy.float)
mcaIndex = 0
for i in range(nRows):
for j in range(nColumns):
data[i, j] = counts
live_time[i * nColumns + j] = initialTime * \
(1 + mcaIndex % nTimes)
mcaIndex += 1
self._h5File = os.path.join(tempfile.gettempdir(), "Steel.h5")
# write the stack to an HDF5 file
if os.path.exists(self._h5File):
os.remove(self._h5File)
h5 = h5py.File(self._h5File, "w")
h5["/entry/instrument/detector/calibration"] = calibration
h5["/entry/instrument/detector/channels"] = channels
h5["/entry/instrument/detector/data"] = data
h5["/entry/instrument/detector/live_time"] = live_time
# add nexus conventions
h5["/entry"].attrs["NX_class"] = u"NXentry"
h5["/entry/instrument"].attrs["NX_class"] = u"NXinstrument"
h5["/entry/instrument/detector/"].attrs["NX_class"] = u"NXdetector"
h5["/entry/instrument/detector/data"].attrs["interpretation"] = \
u"spectrum"
# case with softlink
h5["/entry/measurement/mca_soft/data"] = \
h5py.SoftLink("/entry/instrument/detector/data")
# case with info
h5["/entry/measurement/mca_with_info/data"] = \
h5["/entry/instrument/detector/data"]
h5["/entry/measurement/mca_with_info/info"] = \
h5["/entry/instrument/detector"]
h5.flush()
h5.close()
h5 = None
# check that the data can be read as a stack as
# single top level dataset (issue #226)
external = self._h5File + "external.h5"
if os.path.exists(external):
os.remove(external)
h5 = h5py.File(external, "w")
h5["/data_at_top"] = h5py.ExternalLink(
self._h5File, "/entry/measurement/mca_soft/data")
h5.flush()
h5.close()
h5 = None
stack = HDF5Stack1D.HDF5Stack1D([external], {"y": "/data_at_top"})
# check that the data can be read as a stack through a external link
external = self._h5File + "external.h5"
if os.path.exists(external):
os.remove(external)
h5 = h5py.File(external, "w")
h5["/data_at_top"] = h5py.ExternalLink(
self._h5File, "/entry/measurement/mca_soft/data")
h5["/entry/data"] = h5py.ExternalLink(
self._h5File, "/entry/measurement/mca_soft/data")
h5.flush()
h5.close()
h5 = None
fileList = [external]
for selection in [
{
"y": "/data_at_top"
}, # dataset at top level
{
"y": "/data"
}, # GOOD: selection inside /entry
{
"y": "/entry/data"
}
]: # WRONG: complete path
stack = HDF5Stack1D.HDF5Stack1D(fileList, selection)
info = stack.info
for key in ["McaCalib", "McaLiveTime"]:
self.assertTrue(
key in info,
"Key <%s> not present but it should be there")
readCalib = info["McaCalib"]
readLiveTime = info["McaLiveTime"]
self.assertTrue(abs(readCalib[0] - calibration[0]) < 1.0e-10,
"Calibration zero. Expected %f got %f" % \
(calibration[0], readCalib[0]))
self.assertTrue(abs(readCalib[1] - calibration[1]) < 1.0e-10,
"Calibration gain. Expected %f got %f" % \
(calibration[1], readCalib[0]))
self.assertTrue(abs(readCalib[2] - calibration[2]) < 1.0e-10,
"Calibration 2nd order. Expected %f got %f" % \
(calibration[2], readCalib[2]))
self.assertTrue(live_time.size == readLiveTime.size,
"Incorrect size of live time data")
self.assertTrue(numpy.allclose(live_time, readLiveTime),
"Incorrect live time read")
self.assertTrue(numpy.allclose(stack.x, channels),
"Incorrect channels read")
self.assertTrue(numpy.allclose(stack.data, data),
"Incorrect data read")
# check that the data can be read as a stack
fileList = [self._h5File]
for selection in [{
"y": "/measurement/mca_with_info/data"
}, {
"y": "/measurement/mca_soft/data"
}, {
"y": "/instrument/detector/data"
}]:
stack = HDF5Stack1D.HDF5Stack1D(fileList, selection)
info = stack.info
for key in ["McaCalib", "McaLiveTime"]:
self.assertTrue(
key in info,
"Key <%s> not present but it should be there")
readCalib = info["McaCalib"]
readLiveTime = info["McaLiveTime"]
self.assertTrue(abs(readCalib[0] - calibration[0]) < 1.0e-10,
"Calibration zero. Expected %f got %f" % \
(calibration[0], readCalib[0]))
self.assertTrue(abs(readCalib[1] - calibration[1]) < 1.0e-10,
"Calibration gain. Expected %f got %f" % \
(calibration[1], readCalib[0]))
self.assertTrue(abs(readCalib[2] - calibration[2]) < 1.0e-10,
"Calibration 2nd order. Expected %f got %f" % \
(calibration[2], readCalib[2]))
self.assertTrue(live_time.size == readLiveTime.size,
"Incorrect size of live time data")
self.assertTrue(numpy.allclose(live_time, readLiveTime),
"Incorrect live time read")
self.assertTrue(numpy.allclose(stack.x, channels),
"Incorrect channels read")
self.assertTrue(numpy.allclose(stack.data, data),
"Incorrect data read")
# perform the batch fit
self._outputDir = os.path.join(tempfile.gettempdir(), "SteelTestDir")
if not os.path.exists(self._outputDir):
os.mkdir(self._outputDir)
cfgFile = os.path.join(tempfile.gettempdir(), "SteelNew.cfg")
if os.path.exists(cfgFile):
try:
os.remove(cfgFile)
except:
print("Cannot remove file %s" % cfgFile)
# we need to make sure we use fundamental parameters and
# the time read from the file
configuration["concentrations"]["usematrix"] = 0
configuration["concentrations"]["useautotime"] = 1
if not os.path.exists(cfgFile):
configuration.write(cfgFile)
os.chmod(cfgFile, 0o777)
batch = McaAdvancedFitBatch.McaAdvancedFitBatch(
cfgFile,
filelist=[self._h5File],
outputdir=self._outputDir,
concentrations=True,
selection=selection,
quiet=True)
batch.processList()
# recover the results
imageFile = os.path.join(self._outputDir, "IMAGES", "Steel.dat")
self.assertTrue(os.path.isfile(imageFile),
"Batch fit result file <%s> not present" % imageFile)
sf = specfile.Specfile(imageFile)
labels = sf[0].alllabels()
scanData = sf[0].data()
sf = None
self.assertTrue(
scanData.shape[-1] == (nRows * nColumns),
"Expected %d values got %d" %
(nRows * nColumns, scanData.shape[-1]))
referenceResult = {}
for point in range(scanData.shape[-1]):
for label in labels:
idx = labels.index(label)
if label in ["Point", "row", "column"]:
continue
elif point == 0:
referenceResult[label] = scanData[idx, point]
elif label.endswith("-mass-fraction"):
#print("label = ", label)
#print("reference = ", referenceResult[label])
#print("current = ", scanData[idx, point])
reference = referenceResult[label]
current = scanData[idx, point]
#print("ratio = ", current / reference)
#print("time ratio = ", readLiveTime[point] / readLiveTime[0])
if point % nTimes:
if abs(reference) > 1.0e-10:
self.assertTrue(
reference != current,
"Incorrect concentration for point %d" % point)
corrected = current * \
(readLiveTime[point] / readLiveTime[0])
if abs(reference) > 1.0e-10:
delta = \
100 * abs((reference - corrected) / reference)
self.assertTrue(
delta < 0.01,
"Incorrect concentration(t) for point %d" %
point)
else:
self.assertTrue(
abs(reference - corrected) < 1.0e-5,
"Incorrect concentration(t) for point %d" %
point)
else:
self.assertTrue(
reference == current,
"Incorrect concentration for point %d" % point)
elif label not in ["Point", "row", "column"]:
reference = referenceResult[label]
current = scanData[idx, point]
self.assertTrue(reference == current,
"Incorrect value for point %d" % point)
# Batch fitting went well
# Test the fast XRF
from PyMca5.PyMcaPhysics.xrf import FastXRFLinearFit
ffit = FastXRFLinearFit.FastXRFLinearFit()
configuration["concentrations"]["usematrix"] = 0
configuration["concentrations"]["useautotime"] = 1
configuration['fit']['stripalgorithm'] = 1
outputDict = ffit.fitMultipleSpectra(y=stack,
weight=0,
configuration=configuration,
concentrations=True,
refit=0)
names = outputDict["names"]
parameters = outputDict["parameters"]
uncertainties = outputDict["uncertainties"]
concentrations = outputDict["concentrations"]
cCounter = 0
for i in range(len(names)):
name = names[i]
if name.startswith("C(") and name.endswith(")"):
# it is a concentrations parameter
# verify that concentrations took into account the time
reference = concentrations[cCounter][0, 0]
cTime = configuration['concentrations']['time']
values = concentrations[cCounter][:]
values.shape = -1
for point in range(live_time.size):
current = values[point]
if DEBUG:
print(name, point, reference, current, point % nTimes)
if (point % nTimes) and (abs(reference) > 1.0e-10):
self.assertTrue(
reference != current,
"Incorrect concentration for point %d" % point)
corrected = current * live_time[point] / cTime
if abs(reference) > 1.0e-10:
delta = 100 * abs((reference - corrected) / reference)
self.assertTrue(
delta < 0.01,
"Incorrect concentration(t) for point %d" % point)
else:
self.assertTrue(
abs(reference - corrected) < 1.0e-5,
"Incorrect concentration(t) for point %d" % point)
cCounter += 1
else:
if DEBUG:
print(name, parameters[i][0, 0])
delta = (parameters[i] - parameters[i][0, 0])
self.assertTrue(delta.max() == 0,
"Different fit value for parameter %s delta %f" % \
(name, delta.max()))
self.assertTrue(delta.min() == 0,
"Different fit value for parameter %s delta %f" % \
(name, delta.min()))
delta = (uncertainties[i] - uncertainties[i][0, 0])
self.assertTrue(delta.max() == 0,
"Different sigma value for parameter %s delta %f" % \
(name, delta.max()))
self.assertTrue(delta.min() == 0,
"Different sigma value for parameter %s delta %f" % \
(name, delta.min()))
outputDict = ffit.fitMultipleSpectra(y=stack,
weight=0,
configuration=configuration,
concentrations=True,
refit=1)
names = outputDict["names"]
parameters = outputDict["parameters"]
uncertainties = outputDict["uncertainties"]
concentrations = outputDict["concentrations"]
cCounter = 0
for i in range(len(names)):
name = names[i]
if name.startswith("C(") and name.endswith(")"):
# it is a concentrations parameter
# verify that concentrations took into account the time
reference = concentrations[cCounter][0, 0]
cTime = configuration['concentrations']['time']
values = concentrations[cCounter][:]
values.shape = -1
for point in range(live_time.size):
current = values[point]
if DEBUG:
print(name, point, reference, current, point % nTimes)
if (point % nTimes) and (abs(reference) > 1.0e-10):
self.assertTrue(
reference != current,
"Incorrect concentration for point %d" % point)
corrected = current * live_time[point] / cTime
if abs(reference) > 1.0e-10:
delta = 100 * abs((reference - corrected) / reference)
self.assertTrue(
delta < 0.01,
"Incorrect concentration(t) for point %d" % point)
else:
self.assertTrue(
abs(reference - corrected) < 1.0e-5,
"Incorrect concentration(t) for point %d" % point)
cCounter += 1
else:
if DEBUG:
print(name, parameters[i][0, 0])
delta = (parameters[i] - parameters[i][0, 0])
self.assertTrue(delta.max() == 0,
"Different fit value for parameter %s delta %f" % \
(name, delta.max()))
self.assertTrue(delta.min() == 0,
"Different fit value for parameter %s delta %f" % \
(name, delta.min()))
delta = (uncertainties[i] - uncertainties[i][0, 0])
self.assertTrue(delta.max() == 0,
"Different sigma value for parameter %s delta %f" % \
(name, delta.max()))
self.assertTrue(delta.min() == 0,
"Different sigma value for parameter %s delta %f" % \
(name, delta.min()))
def testFitHdf5Stack(self):
import tempfile
from PyMca5.PyMcaIO import specfilewrapper as specfile
from PyMca5.PyMcaIO import ConfigDict
from PyMca5.PyMcaIO import HDF5Stack1D
from PyMca5.PyMcaPhysics.xrf import McaAdvancedFitBatch
from PyMca5.PyMcaPhysics.xrf import LegacyMcaAdvancedFitBatch
spe = os.path.join(self.dataDir, "Steel.spe")
cfg = os.path.join(self.dataDir, "Steel.cfg")
sf = specfile.Specfile(spe)
self.assertTrue(len(sf) == 1, "File %s cannot be read" % spe)
self.assertTrue(sf[0].nbmca() == 1, "Spe file should contain MCA data")
y = counts = sf[0].mca(1)
x = channels = numpy.arange(y.size).astype(numpy.float)
sf = None
configuration = ConfigDict.ConfigDict()
configuration.read(cfg)
calibration = configuration["detector"]["zero"], \
configuration["detector"]["gain"], 0.0
initialTime = configuration["concentrations"]["time"]
# create the data
nRows = 5
nColumns = 10
nTimes = 3
data = numpy.zeros((nRows, nColumns, counts.size), dtype=numpy.float)
live_time = numpy.zeros((nRows * nColumns), dtype=numpy.float)
mcaIndex = 0
for i in range(nRows):
for j in range(nColumns):
data[i, j] = counts
live_time[i * nColumns + j] = initialTime * \
(1 + mcaIndex % nTimes)
mcaIndex += 1
self._h5File = os.path.join(tempfile.gettempdir(), "Steel.h5")
# write the stack to an HDF5 file
if os.path.exists(self._h5File):
os.remove(self._h5File)
h5 = h5py.File(self._h5File, "w")
h5["/entry/instrument/detector/calibration"] = calibration
h5["/entry/instrument/detector/channels"] = channels
h5["/entry/instrument/detector/data"] = data
h5["/entry/instrument/detector/live_time"] = live_time
# add nexus conventions
h5["/entry"].attrs["NX_class"] = u"NXentry"
h5["/entry/instrument"].attrs["NX_class"] = u"NXinstrument"
h5["/entry/instrument/detector/"].attrs["NX_class"] = u"NXdetector"
h5["/entry/instrument/detector/data"].attrs["interpretation"] = \
u"spectrum"
# case with softlink
h5["/entry/measurement/mca_soft/data"] = \
h5py.SoftLink("/entry/instrument/detector/data")
# case with info
h5["/entry/measurement/mca_with_info/data"] = \
h5["/entry/instrument/detector/data"]
h5["/entry/measurement/mca_with_info/info"] = \
h5["/entry/instrument/detector"]
h5.flush()
h5.close()
h5 = None
# check that the data can be read as a stack as
# single top level dataset (issue #226)
external = self._h5File + "external.h5"
if os.path.exists(external):
os.remove(external)
h5 = h5py.File(external, "w")
h5["/data_at_top"] = h5py.ExternalLink(
self._h5File, "/entry/measurement/mca_soft/data")
h5.flush()
h5.close()
h5 = None
stack = HDF5Stack1D.HDF5Stack1D([external], {"y": "/data_at_top"})
# check that the data can be read as a stack through a external link
external = self._h5File + "external.h5"
if os.path.exists(external):
os.remove(external)
h5 = h5py.File(external, "w")
h5["/data_at_top"] = h5py.ExternalLink(
self._h5File, "/entry/measurement/mca_soft/data")
h5["/entry/data"] = h5py.ExternalLink(
self._h5File, "/entry/measurement/mca_soft/data")
h5.flush()
h5.close()
h5 = None
fileList = [external]
for selection in [
{
"y": "/data_at_top"
}, # dataset at top level
{
"y": "/data"
}, # GOOD: selection inside /entry
{
"y": "/entry/data"
}
]: # WRONG: complete path
stack = HDF5Stack1D.HDF5Stack1D(fileList, selection)
info = stack.info
for key in ["McaCalib", "McaLiveTime"]:
self.assertTrue(
key in info,
"Key <%s> not present but it should be there")
readCalib = info["McaCalib"]
readLiveTime = info["McaLiveTime"]
self.assertTrue(abs(readCalib[0] - calibration[0]) < 1.0e-10,
"Calibration zero. Expected %f got %f" % \
(calibration[0], readCalib[0]))
self.assertTrue(abs(readCalib[1] - calibration[1]) < 1.0e-10,
"Calibration gain. Expected %f got %f" % \
(calibration[1], readCalib[0]))
self.assertTrue(abs(readCalib[2] - calibration[2]) < 1.0e-10,
"Calibration 2nd order. Expected %f got %f" % \
(calibration[2], readCalib[2]))
self.assertTrue(live_time.size == readLiveTime.size,
"Incorrect size of live time data")
self.assertTrue(numpy.allclose(live_time, readLiveTime),
"Incorrect live time read")
self.assertTrue(numpy.allclose(stack.x, channels),
"Incorrect channels read")
self.assertTrue(numpy.allclose(stack.data, data),
"Incorrect data read")
# check that the data can be read as a stack
fileList = [self._h5File]
for selection in [{
"y": "/measurement/mca_with_info/data"
}, {
"y": "/measurement/mca_soft/data"
}, {
"y": "/instrument/detector/data"
}]:
stack = HDF5Stack1D.HDF5Stack1D(fileList, selection)
info = stack.info
for key in ["McaCalib", "McaLiveTime"]:
self.assertTrue(
key in info,
"Key <%s> not present but it should be there")
readCalib = info["McaCalib"]
readLiveTime = info["McaLiveTime"]
self.assertTrue(abs(readCalib[0] - calibration[0]) < 1.0e-10,
"Calibration zero. Expected %f got %f" % \
(calibration[0], readCalib[0]))
self.assertTrue(abs(readCalib[1] - calibration[1]) < 1.0e-10,
"Calibration gain. Expected %f got %f" % \
(calibration[1], readCalib[0]))
self.assertTrue(abs(readCalib[2] - calibration[2]) < 1.0e-10,
"Calibration 2nd order. Expected %f got %f" % \
(calibration[2], readCalib[2]))
self.assertTrue(live_time.size == readLiveTime.size,
"Incorrect size of live time data")
self.assertTrue(numpy.allclose(live_time, readLiveTime),
"Incorrect live time read")
self.assertTrue(numpy.allclose(stack.x, channels),
"Incorrect channels read")
self.assertTrue(numpy.allclose(stack.data, data),
"Incorrect data read")
# TODO: this is done in PyMcaBatchTest on multiple input formats
# so not needed here
return
# perform the batch fit
self._outputDir = os.path.join(tempfile.gettempdir(), "SteelTestDir")
if not os.path.exists(self._outputDir):
os.mkdir(self._outputDir)
cfgFile = os.path.join(tempfile.gettempdir(), "SteelNew.cfg")
if os.path.exists(cfgFile):
try:
os.remove(cfgFile)
except:
print("Cannot remove file %s" % cfgFile)
# we need to make sure we use fundamental parameters and
# the time read from the file
configuration["concentrations"]["usematrix"] = 0
configuration["concentrations"]["useautotime"] = 1
if not os.path.exists(cfgFile):
configuration.write(cfgFile)
os.chmod(cfgFile, 0o777)
# Test batch fitting (legacy)
batch = LegacyMcaAdvancedFitBatch.McaAdvancedFitBatch(
cfgFile,
filelist=[self._h5File],
outputdir=self._outputDir,
concentrations=True,
selection=selection,
quiet=True)
batch.processList()
imageFile = os.path.join(self._outputDir, "IMAGES", "Steel.dat")
self._verifyBatchFitResult(imageFile,
nRows,
nColumns,
live_time,
nTimes,
legacy=True)
# Test batch fitting
batch = McaAdvancedFitBatch.McaAdvancedFitBatch(
cfgFile,
filelist=[self._h5File],
outputdir=self._outputDir,
concentrations=True,
selection=selection,
quiet=True)
batch.outbuffer.extensions = ['.dat']
batch.processList()
imageFile = batch.outbuffer.filename('.dat')
self._verifyBatchFitResult(imageFile, nRows, nColumns, live_time,
nTimes)
# Batch fitting went well
# Test the fast XRF
configuration["concentrations"]["usematrix"] = 0
configuration["concentrations"]["useautotime"] = 1
configuration['fit']['stripalgorithm'] = 1
self._verifyFastFit(stack, configuration, live_time, nTimes)
def PerformBatchFitOld(
filelist,
outdir,
outname,
cfg,
energy,
mlines=None,
quant=None,
fast=False,
addhigh=0,
):
"""Fit XRF spectra in batch with one primary beam energy.
Least-square fitting. If you intend a linear fit, modify the configuration:
- Get current energy calibration with "Load From Fit"
- Enable: Perform a Linear Fit
- Disable: Stripping
- Strip iterations = 0
Fast linear least squares:
- Use SNIP instead of STRIP
Args:
filelist(list(str)): spectra to fit
outdir(str): directory for results
outname(str): output radix
cfg(str or ConfigDict): configuration file to use
energy(num): primary beam energy
mlines(Optional(dict)): elements (keys) which M line group must be replaced by some M subgroups (values)
fast(Optional(bool)): fast fitting (linear)
quant(Optional(dict)):
addhigh(Optional(int))
Returns:
files(list(str)): files produced by pymca
labels(list(str)): corresponding HDF5 labels
"""
outdir = localfs.Path(outdir).mkdir()
if instance.isstring(cfg):
cfg = ConfigDict.ConfigDict(filelist=cfg)
with outdir.temp(name=outname + ".cfg", force=True) as cfgfile:
AdaptPyMcaConfig(
cfg, energy, mlines=mlines, quant=quant, fast=fast, addhigh=addhigh
)
cfg.write(cfgfile.path)
buncertainties = False
bconcentrations = bool(quant)
if fast:
# Prepare fit
fastFit = FastXRFLinearFit.FastXRFLinearFit()
fastFit.setFitConfiguration(cfg)
dataStack = EDFStack.EDFStack(filelist, dtype=np.float32)
# Fit
result = fastFit.fitMultipleSpectra(
y=dataStack, refit=1, concentrations=bconcentrations
)
# Save result and keep filenames + labels
names = result["names"]
if bconcentrations:
names = names[: -len(result["concentrations"])]
parse = re.compile("^(?P<Z>.+)[_ -](?P<line>.+)$")
def filename(x):
return outdir["{}_{}.edf".format(outname, x)].path
labels = []
files = []
j = 0
for i, name in enumerate(names):
m = parse.match(name)
if not m:
continue
m = m.groupdict()
Z, line = m["Z"], m["line"]
# Peak area
label = "{}_{}".format(Z, line)
f = filename(label)
edf.saveedf(
f, result["parameters"][i], {"Title": label}, overwrite=True
)
labels.append(label)
files.append(f)
# Error on peak area
if buncertainties:
label = "s{}_{}".format(Z, line)
f = filename(label)
edf.saveedf(
f, result["uncertainties"][i], {"Title": label}, overwrite=True
)
labels.append(label)
files.append(f)
# Mass fraction
if bconcentrations and Z.lower() != "scatter":
label = "w{}_{}".format(Z, line)
f = filename(label)
edf.saveedf(
f, result["concentrations"][j], {"Title": label}, overwrite=True
)
labels.append(label)
files.append(f)
j += 1
else:
b = McaAdvancedFitBatch.McaAdvancedFitBatch(
cfgfile.path,
filelist=filelist,
outputdir=outdir.path,
fitfiles=0,
concentrations=bconcentrations,
)
b.processList()
filemask = os.path.join(outdir.path, "IMAGES", "*.dat")
def basename(x):
return os.path.splitext(os.path.basename(x))[0]
nbase = len(basename(glob.glob(filemask)[0])) + 1
filemask = os.path.join(outdir.path, "IMAGES", "*.edf")
labels = []
files = []
for name in sorted(glob.glob(filemask)):
label = basename(name)[nbase:]
if label.endswith("mass_fraction"):
label = "w" + label[:-14]
if label == "chisq":
label = "calc_chisq"
labels.append(label)
files.append(name)
return files, labels
def PerformBatchFitNew(
filelist,
outdir,
outname,
cfg,
energy,
mlines=None,
quant=None,
fast=False,
addhigh=0,
):
"""Fit XRF spectra in batch with one primary beam energy.
Least-square fitting. If you intend a linear fit, modify the configuration:
- Get current energy calibration with "Load From Fit"
- Enable: Perform a Linear Fit
- Disable: Stripping
- Strip iterations = 0
Fast linear least squares:
- Use SNIP instead of STRIP
Args:
filelist(list(str)): spectra to fit
outdir(str): directory for results
outname(str): output radix
cfg(str or ConfigDict): configuration file to use
energy(num): primary beam energy
mlines(Optional(dict)): elements (keys) which M line group must be replaced by some M subgroups (values)
fast(Optional(bool)): fast fitting (linear)
quant(Optional(dict)):
addhigh(Optional(int))
Returns:
files(list(str)): files produced by pymca
labels(list(str)): corresponding HDF5 labels
"""
# Adapt cfg in memory
if instance.isstring(cfg):
cfg = ConfigDict.ConfigDict(filelist=cfg)
AdaptPyMcaConfig(
cfg, energy, mlines=mlines, quant=quant, fast=fast, addhigh=addhigh
)
buncertainties = False
bconcentrations = bool(quant)
# Save cfg in temporary file
outdir = localfs.Path(outdir).mkdir()
with outdir.temp(name=outname + ".cfg", force=True) as cfgfile:
cfg.write(cfgfile.path)
kwargs = {
"outputDir": outdir.path,
"fileEntry": outname,
"h5": False,
"edf": True,
"multipage": False,
"saveFOM": True,
}
outbuffer = OutputBuffer(**kwargs)
if fast:
batch = FastXRFLinearFit.FastXRFLinearFit()
stack = FastXRFLinearFit.prepareDataStack(filelist)
kwargs = {
"y": stack,
"configuration": cfg,
"concentrations": bconcentrations,
"refit": 1,
"weight": None, # None -> from cfg file
"outbuffer": outbuffer,
}
else:
kwargs = {
"filelist": filelist,
"concentrations": bconcentrations,
"fitfiles": 0,
"fitconcfile": 0,
"outbuffer": outbuffer,
}
batch = McaAdvancedFitBatch.McaAdvancedFitBatch(cfgfile.path, **kwargs)
with outbuffer.saveContext():
if fast:
batch.fitMultipleSpectra(**kwargs)
else:
batch.processList()
# List of files and labels
files, labels = [], []
groups = ["parameters", "massfractions"]
if buncertainties:
groups.append("uncertainties")
for group in groups:
for label in outbuffer.labels(group, labeltype="filename"):
filename = outbuffer.filename(".edf", suffix="_" + label)
labels.append(label)
files.append(filename)
if "chisq" in outbuffer:
labels.append("calc_chisq")
files.append(outbuffer.filename(".edf", suffix="_chisq"))
return files, labels
def PerformBatchFitHDF5(
filelist,
cfg,
outuri,
energy=None,
mlines=None,
quant=None,
fast=False,
addhigh=0,
**kw
):
"""Fit XRF spectra in batch with one primary beam energy.
Least-square fitting. If you intend a linear fit, modify the configuration:
- Get current energy calibration with "Load From Fit"
- Enable: Perform a Linear Fit
- Disable: Stripping
- Strip iterations = 0
Fast linear least squares:
- Use SNIP instead of STRIP
Args:
filelist(list(str)): spectra to fit
cfg(str or ConfigDict): configuration file to use
outuri(h5fs.Path): directory for results
energy(num): primary beam energy
mlines(Optional(dict)): elements (keys) which M line group must be replaced by some M subgroups (values)
fast(Optional(bool)): fast fitting (linear)
quant(Optional(dict)):
addhigh(Optional(int)):
"""
if instance.isstring(cfg):
cfg = ConfigDict.ConfigDict(filelist=cfg)
AdaptPyMcaConfig(
cfg, energy, mlines=mlines, quant=quant, fast=fast, addhigh=addhigh
)
# outputDir/outputRoot.h5::/fileEntry/fileProcess
kw["h5"] = True
kw["edf"] = False
kw["outputDir"] = outuri.device.parent.path
kw["outputRoot"] = os.path.splitext(outuri.device.name)[0]
kw["fileEntry"] = outuri.parent.path
kw["fileProcess"] = outuri.name
outbuffer = OutputBuffer(**kw)
if fast:
batch = FastXRFLinearFit.FastXRFLinearFit()
stack = FastXRFLinearFit.prepareDataStack(filelist)
kwargs = {
"y": stack,
"configuration": cfg,
"concentrations": bool(quant),
"refit": 1,
"outbuffer": outbuffer,
}
with outbuffer.saveContext():
batch.fitMultipleSpectra(**kwargs)
else:
split_results = list(zip(*(filename.split("::") for filename in filelist)))
if len(split_results) == 1:
selection = None
else:
filelist, path_in_file = split_results
if len(set(path_in_file)) != 1:
raise ValueError(path_in_file, "HDF5 group must be the same for all")
filelist = list(filelist)
selection = {"y": path_in_file[0]}
kwargs = {
"filelist": filelist,
"selection": selection,
"concentrations": bool(quant),
"fitfiles": 0,
"fitconcfile": 0,
"outbuffer": outbuffer,
}
with tempPyMcaConfigFile(cfg) as cfgfilename:
batch = McaAdvancedFitBatch.McaAdvancedFitBatch(cfgfilename, **kwargs)
with outbuffer.saveContext():
batch.processList()