def merge(self, d1, qmax=-1, qmin=-1, fix_scale=-1):
"""
combine the data in self and d1
scale d1 intensity to match self
self and d1 should have the same qgrid
if qmax or qmin <0
simply keep the WAXS data that is beyond qmax for the SAXS data
this is useful for utilizing WAXS to normalize intensity but keep SAXS data only
"""
print("merging data: %s and %s ..." % (self.label, d1.label))
if not (d1.qgrid == self.qgrid).all():
print("merging data sets should have the same qgrid.")
exit()
# this gives the overlapping region
idx = (self.data > 0) & (d1.data > 0)
if len(self.qgrid[idx]) > 0:
qmin0 = min(d1.qgrid[idx])
qmax0 = max(self.qgrid[idx])
# merge SAXS/WAXS based on intensity in the overlapping region
if qmax0 < qmax:
qmax = qmax0
if qmin0 > qmin:
qmin = qmin0
idx = (self.qgrid > qmin) & (self.qgrid < qmax)
# save the raw data in case needed, e.g. for ploting
self.overlaps.append({'q_overlap': self.qgrid[idx],
'raw_data1': self.data[idx],
'raw_data2': d1.data[idx]})
else:
# no overlap
# simply stack WAXS data to the high q end of SAXS data
qmin = qmax = max(self.qgrid[self.data > 0])
# idx = np.asarray([],dtype=int)
if len(self.qgrid[idx]) < 2:
print("data sets are not overlapping in the given q range.")
if fix_scale < 0:
fix_scale = 1
print("forcing fix_scale=1.")
elif len(self.qgrid[idx]) < 10:
print("too few overlapping points: %d" % len(self.qgrid[idx]))
if fix_scale > 0:
# For a given experimental configuration, the intensity normlization
# factor between the SAXS and WAXS should be well-defined. This factor
# can be determined using scattering data with siginificant intensity
# in the overlapping q-range and applied to all data collected in the
# same configuration.
sc = fix_scale
else:
# idx = idx[1:-1]
sc = np.linalg.lstsq(np.asmatrix(self.data[idx]).T, np.asmatrix(d1.data[idx]).T)[0]
sc = np.trace(sc)
d1.data /= sc
d1.err /= sc
if len(self.qgrid[idx]) > 0:
self.overlaps[-1]['raw_data2'] /= sc
self.label = common_name(self.label, d1.label)
print("set2 scaled by 1/%f" % sc)
print("merged set re-named %s." % self.label)
if len(self.qgrid[idx]) > 0:
self.data[idx] = (self.data[idx] + d1.data[idx]) / 2
# this won't work well if the merging data are mis-matched before bkg subtraction
# but match well after bkg subtraction
# self.err[idx] = (self.err[idx]+d1.err[idx])/2+np.fabs(self.data[idx]-d1.data[idx])
self.err[idx] = (self.err[idx] + d1.err[idx]) / 2
self.data[self.qgrid >= qmax] = d1.data[self.qgrid >= qmax]
self.err[self.qgrid >= qmax] = d1.err[self.qgrid >= qmax]
self.comments += "# merged with the following set by matching intensity within (%.4f, %.4f)," % (qmin, qmax)
self.comments += " scaled by %f\n" % sc
self.comments += d1.comments.replace("# ", "## ")
def avg(self, dsets, plot_data=False, ax=None):
"""
dset is a collection of Data1d
ax is the Axes to plot the data in
TODO: should calculate something like the cross-correlation between sets
to evaluate the consistency between them
"""
print("averaging data with %s:" % self.label, end=' ')
n = 1
if plot_data:
if ax is None:
plt.figure()
plt.subplots_adjust(bottom=0.15)
ax = plt.gca()
ax.set_xlabel("$q (\AA^{-1})$", fontsize='x-large')
ax.set_ylabel("$I$", fontsize='x-large')
ax.set_xscale('log')
ax.set_yscale('log')
idx = (self.data > 0)
ax.errorbar(self.qgrid[idx], self.data[idx], self.err[idx], label=self.label)
for ov in self.overlaps:
ax.plot(ov['q_overlap'], ov['raw_data1'], "v")
ax.plot(ov['q_overlap'], ov['raw_data2'], "^")
for d1 in dsets:
print("%s " % d1.label, end=' ')
if not (self.qgrid == d1.qgrid).all():
print("\n1D sets cannot be averaged: qgrid mismatch")
exit()
self.trans += d1.trans
self.data += d1.data
self.err += d1.err
self.comments += "# averaged with \n%s" % d1.comments.replace("# ", "## ")
if plot_data:
idx = (d1.data > 0) # Remove Zeros on plot
ax.errorbar(d1.qgrid[idx], d1.data[idx] * VOFFSET ** n, d1.err[idx] * VOFFSET ** n, label=d1.label)
for ov in d1.overlaps:
ax.plot(ov['q_overlap'], ov['raw_data1'] * VOFFSET ** n, "v")
ax.plot(ov['q_overlap'], ov['raw_data2'] * VOFFSET ** n, "^")
n += 1
self.label = common_name(self.label, d1.label)
self.trans /= n
self.data /= n
self.err /= np.sqrt(n)
print("\naveraged set re-named to %s." % self.label)
if plot_data:
# plot the averaged data over each individual curve
for i in range(n):
if i == 0:
idx = (self.data > 0) # Remove Zeros on plot
handles, labels = ax.get_legend_handles_labels()
lbl = "averaged" if "averaged" not in labels else ""
ax.plot(self.qgrid[idx], self.data[idx] * VOFFSET ** i, color="gray", lw=2, ls="--", label=lbl)
else:
idx = (self.data > 0) # Remove Zeros on plot
ax.plot(self.qgrid[idx], self.data[idx] * VOFFSET ** i, color="gray", lw=2, ls="--")
leg = ax.legend(loc='upper right', frameon=False)
for t in leg.get_texts():
t.set_fontsize('small')
