def run(plot=True):
## Initialize peak extraction
# Create peak extraction object
ppe = PDFPeakExtraction()
# Load the PDF from a file
ppe.loadpdf("data/Ag_nyquist_qmax30.gr")
## Set up extraction parameters.
# For convenience we add all parameters to a dictionary before passing them
# to the extraction object.
#
# The "rng" (range) parameter defines the region over which peaks will be
# extracted and fit. For the well isolated nearest-neighbor silver peak,
# which occurs near 2.9 angstroms, it is sufficient to perform extraction
# between 2 and 3.5 angstroms.
#
# The "baseline" parameter lets us define the PDF baseline, which is
# linear for a crystal. If a linear baseline is specified without
# numerical parameters diffpy.srmise attempts to estimate them from the
# data, and this is usually sufficient when peaks do not overlap much.
kwds = {}
kwds["rng"] = [2.0, 3.5]
kwds["baseline"] = Polynomial(degree=1)
# Apply peak extraction parameters.
ppe.setvars(**kwds)
## Perform peak extraction
ppe.extract()
## Save output
# The write() method saves a file which preserves all aspects of peak
# extraction and its results, by convention using the .srmise extension,
# and which can later be read by diffpy.srmise.
#
# The writepwa() method saves a file intended as a human-readable summary.
# In particular, it reports the position, width (as full-width at
# half-maximum), and area of of extracted peaks. The reported values
# are for Gaussians in the radial distribution function (RDF) corresponding
# to this PDF.
ppe.write("output/extract_single_peak.srmise")
ppe.writepwa("output/extract_single_peak.pwa")
## Plot results.
# Display plot of extracted peak. It is also possible to plot an existing
# .srmise file from the command line using
# srmise output/Ag_singlepeak.srmise --no-extract --plot
# For additional plotting options, run "srmiseplot --help".
if plot:
makeplot(ppe)
plt.show()
def run(plot=True):
## Initialize peak extraction
# Create peak extraction object
ppe = PDFPeakExtraction()
# Load the PDF from a file
ppe.loadpdf("data/TiO2_fine_qmax26.gr")
###### Set up extraction parameters.
# In this section we'll examine the major extraction parameters in detail.
# diffpy.srmise strives to provide reasonable default values for these
# parameters. For normal use setting the range, baseline, and uncertainty
# should be sufficient.
kwds = {}
## Range
# Range defaults to the entire PDF if not specified.
kwds["rng"] = [1.5, 10.]
## dg
# diffpy.srmise selects model complexity based primarily on the uncertainty
# of the PDF. Note that very small uncertainties (<1%) can make peak
# extraction excessively slow. In general, the smaller the uncertainty the
# more complex the model. PDFs which report no uncertainty, or report
# unreliable values must be assigned one. By default, a PDF which does not
# report uncertainties uses 5% the maximum minus minimum values. Common
# causes of unreliable uncertainties include oversampling (uncertainties in
# nearby data are strongly correlated, as for this PDF) and/or
# integrated diffraction patterns obtained by a method that also introduces
# correlation to the 1D diffraction pattern. Consequently, the assumption
# of both least-squares fitting and the Akaike Information Criterion that
# the data are at least approximately independently distributed is not
# valid. In this case results obtained by diffpy.srmise may be useful,
# especially when they can be intrepreted in light of prior knowledge, but
# strong statistical conclusions cannot be drawn. For additional
# discussion of this subtle yet important issue see:
# [1] Egami and Billinge. (2012). Underneath the Bragg Peaks: Structural
# Analysis of Complex Materials (2nd ed.). Oxford: Pergamon Press.
# [2] Granlund, et al. (2015) Acta Crystallographica A, 71(4), 392-409.
# doi:10.1107/S2053273315005276
# [3] Yang, et al. (2014). Journal of Applied Crystallography, 47(4),
# 1273-1283. doi:10.1107/S1600576714010516
kwds["dg"] = 0.35 # Play with this value!
## baseline
# As a crystal PDF, a linear baseline crossing the origin is appropriate.
# Here we define the linear baseline B(r) = -.5*r + 0, and explicitly set
# the y-intercept as a fixed parameter which will not be fit. For
# crystal PDFs the theoretical value of the slope is -4*pi*rho0, where
# rho0 is the number density. Nevertheless, imperfect normalization of the
# PDF means the experimental baseline is proportional to that value.
blfunc = Polynomial(degree=1)
slope = -.65 # Play with this value!
y_intercept = 0.
kwds["baseline"] = blfunc.actualize([slope, y_intercept],
free=[True, False])
## pf
# The pf (peakfunction) parameter allows setting the shape of peaks to be
# extracted. Termination effects are added automatically to the peak
# function during extraction. In the harmonic approximation of atomic
# interactions peaks in the PDF are well approximated by a Gaussian/r.
# (Note, however, that the values used for peak parameters -- namely
# position, width, and area -- are for the Gaussian itself). diffpy.srmise
# uses width-limited peaks to reduce the likelihood of extracting
# unphysically wide peaks in regions of high overlap. The parameter
# indicates the max fwhm permitted. By default, diffpy.srmise uses a
# maximum width of 0.7, which is generally reasonable if the r-axis of the
# PDF is given in angstroms. Models where many peaks reach the maximum
# width, and models that are very sensitive to the choice in maximum width,
# are strong signs that diffpy.srmise is having difficulty finding peaks
# which are sufficiently constrained by the data.
pf = GaussianOverR(0.7)
kwds["pf"] = [pf] # Despite the list, only one entry is currently supported.
## qmax
# PDFs typically report the value of qmax (i.e. the maximum momentum
# transfer q in the measurement), but it can be specified explicitly also.
# If the PDF does not report qmax, diffpy.srmise attempts to estimate it
# directly from the data. This estimate can also be used by setting qmax
# to "automatic". An infinite qmax can be specified by setting qmax to 0,
# In that case the Nyquist rate is 0 (infinite resolution), and
# diffpy.srmise does not consider Nyquist sampling or termination effects.
kwds["qmax"] = 26.0
## nyquist
# This parameter governs whether diffpy.srmise attempts to find a model
# on a Nyquist-sampled grid with dr=pi/qmax, which is a grid where data
# uncertainties are least correlated without loss of information. By
# default this parameter is True whenever qmax > 0, and generally it
# should not need to be changed. Setting it to False allows extracted
# models retain more complexity because the data appear to have more
# statistically independent points than they truly do. For a detailed
# discussion of Nyquist sampling and the PDF see:
# [4] Farrow et al. (2011). Physical Review B, 84(13), 134105.
# doi:10.1103/PhysRevB.84.134105
kwds["nyquist"] = True
## supersample
# This parameter dictates the data be oversampled by at least this factor
# (relative to the Nyquist rate) during the early stages of peak
# extraction. If the input PDF is even more finely sampled, that level of
# sampling is used instead. The default value of 4.0 is ad hoc, but has
# been empirically sufficient. Increasing this value may help the peak-
# finding and clustering process, but reduces speed.
kwds["supersample"] = 4.0
## cres
# The cres (clustering resolution) parameter governs the sensitivity of the
# clustering method used by diffpy.srmise. In short, when the data are
# being clustered, data which are further than the clustering resolution
# from any other cluster (measured along the r-axis) are considered to be a
# new cluster rather than a member of an existing one. The default value
# is the Nyquist sampling interval pi/qmax, and on most data it should not
# greatly impact model complexity. In some cases making it smaller may
# help the peak-finding process. Here it is roughly half the Nyquist
# interval.
kwds["cres"] = 0.05
# Apply peak extraction parameters.
ppe.setvars(**kwds)
## initial_peaks
# Initial peaks are peaks which are kept fixed during the early stages of
# peak extraction, effectively condition results upon their values. Since
# initial peaks are sometimes dependent on other SrMise parameters (e.g.
# the peak function used) it is good practice to set them after other
# parameters. Although the "initial_peaks" parameter can be set as with
# the parameters above, SrMise provides helper functions to do so more
# easily. There are two basic ways to quickly specify initial peaks:
# 1) Supplying the approximate position of the peak, and letting
# diffpy.srmise estimate the peak parameters.
# 2) Explicit specification of peak parameters.
## Initial peaks from approximate positions.
# This routine estimates peak parameters by finding the peak-like cluster
# containing the specified point. It does not search for occluded peaks,
# so works best on well-separated peaks. It does, however, take any
# existing initial peaks into account during estimation.
positions = [2.0, 4.5]
for p in positions:
ppe.estimate_peak(p) # adds to initial_peaks
## Initial peaks from explicit parameters.
# Adding initial peaks explicitly is similar to defining a baseline.
# Namely, choosing a peak function and then actualizing it with given
# parameters. For this example peaks are created from the same GaussianOverR
# used during extraction, but one could use a different peak function from
# diffpy.srmise.peaks if desired. The peak parameters are given in terms
# terms of position, width (fwhm), and area, and it is important to specify
# that format is being used so they are correctly changed into the
# internal parameterization. Here two peaks are added in a region of
# overlap, and the width parameter is fixed at a reasonable value to aid
# convergence in this region.
pars = [[6.2, 0.25, 2.6],[6.45, 0.25, 2.7],[7.15, 0.25, 5]]
peaks = []
for p in pars:
peaks.append(pf.actualize(p, free=[True, False, True], in_format="pwa"))
ppe.add_peaks(peaks) # adds to initial_peaks
## Initial peaks and pruning
# While initial peaks condition what other peaks can be extracted, by
# default they can also be pruned if a simpler model appears better. To
# prevent this, they can be set as non-removable.
for ip in ppe.initial_peaks:
ip.removable = False
## Plot initial parameters
if plot:
makeplot(ppe)
plt.title("Initial Peaks")
###### Perform peak extraction
ppe.extract()
## Save output
# The write() method saves a file which preserves all aspects of peak
# extraction and its results, by convention using the .srmise extension,
# and which can later be read by diffpy.srmise.
#
# The writepwa() method saves a file intended as a human-readable summary.
# In particular, it reports the position, width (as full-width
# half-maximum), and area of of extracted peaks. The reported values
# are for Gaussians in the radial distribution function (RDF) corresponding
# to this PDF.
ppe.write("output/parameter_summary.srmise")
ppe.writepwa("output/parameter_summary.pwa")
## Plot results.
# Display plot of extracted peak. It is also possible to plot an existing
# .srmise file from the command line using
# srmise output/TiO2_parameterdetail.srmise --no-extract --plot
if plot:
plt.figure()
makeplot(ppe)
plt.show()
def run(plot=True):
## Initialize peak extraction
# Create peak extraction object
ppe = PDFPeakExtraction()
# Load the PDF from a file
ppe.loadpdf("data/Ag_nyquist_qmax30.gr")
# Obtain baseline from a saved diffpy.srmise trial. This is not the
# initial baseline estimate from the previous example, but the baseline
# after both it and the extracted peaks have been fit to the data.
ppebl = PDFPeakExtraction()
ppebl.read("output/extract_single_peak.srmise")
baseline = ppebl.extracted.baseline
## Set up extraction parameters.
# Peaks are extracted between 2 and 10 angstroms, using the baseline
# from the isolated peak example.
kwds = {}
kwds["rng"] = [2.0, 10.]
kwds["baseline"] = baseline
# Apply peak extraction parameters.
ppe.setvars(**kwds)
## Perform peak extraction, and retain object containing a copy of the
# model and the full covariance matrix.
cov = ppe.extract()
print "\n======= Accessing SrMise Results ========"
## Accessing results of extraction
#
# Model parameters are organized using a nested structure, with a list
# of peaks each of which is a list of parameters, similar to the the
# following schematic.
# Peak
# Position
# Width
# Area
# Peak
# Position
# Width
# Area*
# ...
# Baseline
# Slope
# Intercept
# By convention, the baseline is the final "peak." The ModelCovariance
# object returned by extract() can return information about any peak by
# using the appropriate tuple of indices (i,j). That is, (i,j) denotes
# the jth parameter of the ith peak. For example, the starred parameter
# above is the area (index = 2) of the next nearest neighbor (index = 1)
# peak. Thus, this parameter can be referenced as (1,2). Several examples
# are presented below.
print "\n------ Parameter values and uncertainties ------"
# ModelCovariance.get() returns a (value, uncertainty) tuple for a given
# parameter. These are the results for the nearest-neighbor peak.
p0 = cov.get((0,0))
w0 = cov.get((0,1))
a0 = cov.get((0,2))
print "Nearest-neighbor peak: "
print " position = %f +/- %f" %p0
print " width = %f +/- %f" %w0
print " area = %f +/- %f" %a0
print " Covariance(width, area) = ", cov.getcovariance((0,1),(0,2))
# Baseline parameters. By convention, baseline is final element in cov.
(slope, intercept) = cov.model[-1]
print "\nThe linear baseline B(r)=%f*r + %f" \
% tuple(par for par in cov.model[-1])
print "\n ------ Uncertainties from a Saved File --------"
# A .srmise file does not save the full covariance matrix, so it must be
# recalculated when loading from these files. For example, here is the
# nearest-neighbor peak in the file which we used to define the initial
# baseline.
cov2 = ModelCovariance()
ppebl.extracted.fit(fitbaseline=True, cov=cov2, cov_format="default_output")
p0_saved = cov2.get((0,0))
w0_saved = cov2.get((0,1))
a0_saved = cov2.get((0,2))
print "Nearest-neighbor peak:"
print " position = %f +/- %f" %p0_saved
print " width == %f +/- %f" %w0_saved
print " area = = %f +/- %f" %a0_saved
print " Covariance(width, area) = ", cov2.getcovariance((0,1),(0,2))
print "\n ---------- Alternate Parameterizations ---------"
## Different Parameterizations
# Peaks and baselines may have equivalent parameterizations that are useful
# in different situations. For example, the types defined by the
# GaussianOverR peak function are:
# "internal" - Used in diffpy.srmise calculations, explicitly enforces a
# maximum peak width
# "pwa" - The position, width (full-width at half-maximum), area.
# "mu_sigma_area" - The position, width (the distribution standard
# deviation sigma), area.
# "default_output" - Defines default format to use in most user-facing
# scenarios. Maps to the "pwa" parameterization.
# "default_input" - Defines default format to use when specifying peak
# parameters. Maps to the "internal" parameterization.
# All diffpy.srmise peak and baseline functions are required to have the
# "internal", "default_output", and "default_input" formats. In many
# cases, such as polynomial baselines, all of these are equivalent.
#
# Suppose you want to know peak widths in terms of the standard deviation
# sigma of the Gaussian distribution. It is then appropriate to convert
# all peaks to the "mu_sigma_area" format. Valid options for the "parts"
# keyword are "peaks", "baseline", or a sequence of indices (e.g. [1,2,3]
# would transform the second, third, and fourth peaks). If the keyword
# is omitted, the transformation is attempted for all parts of the fit.
cov.transform(in_format="pwa", out_format="mu_sigma_area", parts="peaks")
print "Width (sigma) of nearest-neighbor peak: %f +/- %f" %cov.get((0,1))
print "\n ------------ Highly Correlated Parameters ------------"
# Highly-correlated parameters can indicate difficulties constraining the
# fit. This function lists all pairs of parameters with an absolute value
# of correlation which exceeds a given threshold.
print "|Correlation| > 0.9:"
print "par1 par2 corr(par1, par2)"
print "\n".join(str(c) for c in cov.correlationwarning(.9))
print "\n-------- Estimate coordination shell occupancy ---------"
# Estimate the scale factor and its uncertainty from first peak's intensity.
# G_normalized = scale * G_observed
# dscale = scale * dG_observed/G_observed
scale = 12./a0[0]
dscale = scale * a0[1]/a0[0]
print "Estimate scale factor assuming nearest-neighbor intensity = 12"
print "Scale factor is %f +/- %f" %(scale, dscale)
# Reference for number of atoms in coordination shells for FCC.
# http://chem-faculty.lsu.edu/watkins/MERLOT/cubic_neighbors/cubic_near_neighbors.html
ideal_intensity = [12, 6, 24, 12, 24, 8, 48, 6, 36, 24, 24, 24]
# Calculated the scaled intensities and uncertainties.
intensity = []
for i in range(0, len(cov.model)-1):
(area, darea) = cov.get((i,2))
area *= scale
darea = area*np.sqrt((dscale/scale)**2 + (darea/area)**2)
intensity.append((ideal_intensity[i], area, darea))
print "\nIntensity"
print "Ideal: Estimated"
for i in intensity:
print "%i: %f +/- %f" %i
print "\nTotal intensity"
# It is possible to iterate over peaks directly without using indices.
# In addition, peak parameters can be accessed using string keys. For the
# Gaussian over r all of "position", "width", and "area" are valid.
total_observed_intensity = 0
total_ideal_intensity = 0
for peak, ii in zip(cov.model[:-1], ideal_intensity):
total_observed_intensity += scale*peak["area"]
total_ideal_intensity += ii
print "Ideal: Observed (using estimated scale factor)"
print "%i: %f" %(total_ideal_intensity, total_observed_intensity)
## Save output
ppe.write("output/query_results.srmise")
ppe.writepwa("output/query_results.pwa")
## Evaluating a model.
# Although the ModelCovariance object is useful, the model used for fitting
# can be directly accessed through PDFPeakExtraction as well, albeit
# without uncertainties. This is particularly helpful when evaluating a
# model since the parameters stay in the "internal" format used for
# calculations. For example, here we plot the data and every second peak
# on an arbitrary grid. Unlike with ModelCovariance, the baseline and
# peaks are kept separate.
if plot:
plt.figure()
grid = np.arange(2, 10, .01)
bl = ppe.extracted.baseline
everysecondpeak = ppe.extracted.model[::2]
plt.plot(ppe.x, ppe.y, 'o')
for peak in everysecondpeak:
plt.plot(grid, bl.value(grid) + peak.value(grid))
plt.xlim(2, 10)
plt.show()
class PeakStability:
"""Utility to test robustness of peaks.
results: [error scalar, model, bl, dr]
ppe: a PDFPeakExtraction instance """
def __init__(self):
self.results = []
self.ppe = None
self.current = None
def setppe(self, ppe):
self.ppe = ppe
def load(self, filename):
try:
import cPickle as pickle
except:
import pickle
in_s = open(filename, 'rb')
try:
(self.results, ppestr) = pickle.load(in_s)
self.ppe = PDFPeakExtraction()
self.ppe.readstr(ppestr)
# Ugly kluge for the baseline, since FromSequence
# can't pickle.
for r in self.results:
bl = self.ppe.baseline
kwds = r[2]
if r[2] is not None:
kwds = r[2]
if hasattr(bl, "estimate_parameters"):
r[2] = bl.actualize(default_input="internal", **kwds)
else:
r[2] = bl.owner().actualize(in_format="internal",
**kwds)
finally:
in_s.close()
self.setcurrent(0)
def save(self, filename):
try:
import cPickle as pickle
except:
import pickle
out_s = open(filename, 'wb')
try:
# Write to the stream
outstr = self.ppe.writestr()
# ugly kluge to let FromSequence pickle
# (it stores xyrepr() in metadict)
results2 = []
for r in self.results:
if r[2] is None:
bldict = None
else:
bldict = {
"pars": r[2].pars,
"free": r[2].free,
"removable": r[2].removable,
"static_owner": r[2].static_owner
}
results2.append([r[0], r[1], bldict, r[3]])
pickle.dump([results2, outstr], out_s)
finally:
out_s.close()
def plotseries(self, style='o', **kwds):
plt.figure()
plt.ioff()
for e, r, bl, dr in self.results:
peakpos = [p["position"] for p in r]
es = [e] * len(peakpos)
plt.plot(peakpos, es, style, **kwds)
plt.ion()
plt.draw()
def plot(self, **kwds):
"""Plot the current model. Keywords passed to pyplot.plot()"""
plt.clf()
plt.plot(*self.ppe.extracted.plottable(), **kwds)
q = self.ppe.extracted.quality()
plt.suptitle(
"[%i/%i]\n"
"Uncertainty: %6.3f. Peaks: %i.\n"
"Quality: %6.3f. Chi-square: %6.3f" %
(self.current + 1, len(self.results), self.ppe.effective_dy[0],
len(self.ppe.extracted.model), q.stat, q.chisq))
def setcurrent(self, idx):
"""Make the idxth model the active one."""
self.current = idx
if idx is not None:
result = self.results[idx]
self.ppe.setvars(quiet=True,
effective_dy=result[0] * np.ones(len(self.ppe.x)))
(r, y, dr, dy) = self.ppe.resampledata(result[3])
self.ppe.extracted = ModelCluster(result[1], result[2], r, y, dy,
None, self.ppe.error_method,
self.ppe.pf)
else:
self.ppe.clearcalc()
def animate(self, results=None, step=False, **kwds):
"""Show animation of extracted peaks from first to last.
Parameters:
step - Require keypress to show next plot
results - The indices of results to show
Keywords passed to pyplot.plot()"""
if results is None:
results = range(len(self.results))
oldcurrent = self.current
self.setcurrent(0)
plt.ion()
plt.plot(*self.ppe.extracted.plottable())
a = plt.axis()
for i in results:
self.setcurrent(i)
plt.ioff()
self.plot(**kwds)
plt.ion()
plt.draw()
if step:
raw_input()
self.setcurrent(oldcurrent)
def run(self, err, savecovs=False):
"""err is sequence of uncertainties to run at.
If savecovs is True, return the covariance matrix for each final fit."""
self.results = []
covs = []
for i, e in enumerate(err):
print "---- Running for uncertainty %s (%i/%i) ----" % (e, i,
len(err))
self.ppe.clearcalc()
self.ppe.setvars(effective_dy=e)
if savecovs:
covs.append(self.ppe.extract())
else:
self.ppe.extract()
dr = (self.ppe.extracted.r_cluster[-1] -
self.ppe.extracted.r_cluster[0]) / (
len(self.ppe.extracted.r_cluster) - 1)
self.results.append(
[e, self.ppe.extracted.model, self.ppe.extracted.baseline, dr])
for e, r, bl, dr in self.results:
print "---- Results for uncertainty %s ----" % e
print r
return covs
def run(plot=True):
## Initialize peak extraction
# Create peak extraction object
ppe = PDFPeakExtraction()
# Load the PDF from a file
ppe.loadpdf("data/TiO2_fine_qmax26.gr")
###### Set up extraction parameters.
# In this section we'll examine the major extraction parameters in detail.
# diffpy.srmise strives to provide reasonable default values for these
# parameters. For normal use setting the range, baseline, and uncertainty
# should be sufficient.
kwds = {}
## Range
# Range defaults to the entire PDF if not specified.
kwds["rng"] = [1.5, 10.]
## dg
# diffpy.srmise selects model complexity based primarily on the uncertainty
# of the PDF. Note that very small uncertainties (<1%) can make peak
# extraction excessively slow. In general, the smaller the uncertainty the
# more complex the model. PDFs which report no uncertainty, or report
# unreliable values must be assigned one. By default, a PDF which does not
# report uncertainties uses 5% the maximum minus minimum values. Common
# causes of unreliable uncertainties include oversampling (uncertainties in
# nearby data are strongly correlated, as for this PDF) and/or
# integrated diffraction patterns obtained by a method that also introduces
# correlation to the 1D diffraction pattern. Consequently, the assumption
# of both least-squares fitting and the Akaike Information Criterion that
# the data are at least approximately independently distributed is not
# valid. In this case results obtained by diffpy.srmise may be useful,
# especially when they can be intrepreted in light of prior knowledge, but
# strong statistical conclusions cannot be drawn. For additional
# discussion of this subtle yet important issue see:
# [1] Egami and Billinge. (2012). Underneath the Bragg Peaks: Structural
# Analysis of Complex Materials (2nd ed.). Oxford: Pergamon Press.
# [2] Granlund, et al. (2015) Acta Crystallographica A, 71(4), 392-409.
# doi:10.1107/S2053273315005276
# [3] Yang, et al. (2014). Journal of Applied Crystallography, 47(4),
# 1273-1283. doi:10.1107/S1600576714010516
kwds["dg"] = 0.35 # Play with this value!
## baseline
# As a crystal PDF, a linear baseline crossing the origin is appropriate.
# Here we define the linear baseline B(r) = -.5*r + 0, and explicitly set
# the y-intercept as a fixed parameter which will not be fit. For
# crystal PDFs the theoretical value of the slope is -4*pi*rho0, where
# rho0 is the number density. Nevertheless, imperfect normalization of the
# PDF means the experimental baseline is proportional to that value.
blfunc = Polynomial(degree=1)
slope = -.65 # Play with this value!
y_intercept = 0.
kwds["baseline"] = blfunc.actualize([slope, y_intercept],
free=[True, False])
## pf
# The pf (peakfunction) parameter allows setting the shape of peaks to be
# extracted. Termination effects are added automatically to the peak
# function during extraction. In the harmonic approximation of atomic
# interactions peaks in the PDF are well approximated by a Gaussian/r.
# (Note, however, that the values used for peak parameters -- namely
# position, width, and area -- are for the Gaussian itself). diffpy.srmise
# uses width-limited peaks to reduce the likelihood of extracting
# unphysically wide peaks in regions of high overlap. The parameter
# indicates the max fwhm permitted. By default, diffpy.srmise uses a
# maximum width of 0.7, which is generally reasonable if the r-axis of the
# PDF is given in angstroms. Models where many peaks reach the maximum
# width, and models that are very sensitive to the choice in maximum width,
# are strong signs that diffpy.srmise is having difficulty finding peaks
# which are sufficiently constrained by the data.
pf = GaussianOverR(0.7)
kwds["pf"] = [pf
] # Despite the list, only one entry is currently supported.
## qmax
# PDFs typically report the value of qmax (i.e. the maximum momentum
# transfer q in the measurement), but it can be specified explicitly also.
# If the PDF does not report qmax, diffpy.srmise attempts to estimate it
# directly from the data. This estimate can also be used by setting qmax
# to "automatic". An infinite qmax can be specified by setting qmax to 0,
# In that case the Nyquist rate is 0 (infinite resolution), and
# diffpy.srmise does not consider Nyquist sampling or termination effects.
kwds["qmax"] = 26.0
## nyquist
# This parameter governs whether diffpy.srmise attempts to find a model
# on a Nyquist-sampled grid with dr=pi/qmax, which is a grid where data
# uncertainties are least correlated without loss of information. By
# default this parameter is True whenever qmax > 0, and generally it
# should not need to be changed. Setting it to False allows extracted
# models retain more complexity because the data appear to have more
# statistically independent points than they truly do. For a detailed
# discussion of Nyquist sampling and the PDF see:
# [4] Farrow et al. (2011). Physical Review B, 84(13), 134105.
# doi:10.1103/PhysRevB.84.134105
kwds["nyquist"] = True
## supersample
# This parameter dictates the data be oversampled by at least this factor
# (relative to the Nyquist rate) during the early stages of peak
# extraction. If the input PDF is even more finely sampled, that level of
# sampling is used instead. The default value of 4.0 is ad hoc, but has
# been empirically sufficient. Increasing this value may help the peak-
# finding and clustering process, but reduces speed.
kwds["supersample"] = 4.0
## cres
# The cres (clustering resolution) parameter governs the sensitivity of the
# clustering method used by diffpy.srmise. In short, when the data are
# being clustered, data which are further than the clustering resolution
# from any other cluster (measured along the r-axis) are considered to be a
# new cluster rather than a member of an existing one. The default value
# is the Nyquist sampling interval pi/qmax, and on most data it should not
# greatly impact model complexity. In some cases making it smaller may
# help the peak-finding process. Here it is roughly half the Nyquist
# interval.
kwds["cres"] = 0.05
# Apply peak extraction parameters.
ppe.setvars(**kwds)
## initial_peaks
# Initial peaks are peaks which are kept fixed during the early stages of
# peak extraction, effectively condition results upon their values. Since
# initial peaks are sometimes dependent on other SrMise parameters (e.g.
# the peak function used) it is good practice to set them after other
# parameters. Although the "initial_peaks" parameter can be set as with
# the parameters above, SrMise provides helper functions to do so more
# easily. There are two basic ways to quickly specify initial peaks:
# 1) Supplying the approximate position of the peak, and letting
# diffpy.srmise estimate the peak parameters.
# 2) Explicit specification of peak parameters.
## Initial peaks from approximate positions.
# This routine estimates peak parameters by finding the peak-like cluster
# containing the specified point. It does not search for occluded peaks,
# so works best on well-separated peaks. It does, however, take any
# existing initial peaks into account during estimation.
positions = [2.0, 4.5]
for p in positions:
ppe.estimate_peak(p) # adds to initial_peaks
## Initial peaks from explicit parameters.
# Adding initial peaks explicitly is similar to defining a baseline.
# Namely, choosing a peak function and then actualizing it with given
# parameters. For this example peaks are created from the same GaussianOverR
# used during extraction, but one could use a different peak function from
# diffpy.srmise.peaks if desired. The peak parameters are given in terms
# terms of position, width (fwhm), and area, and it is important to specify
# that format is being used so they are correctly changed into the
# internal parameterization. Here two peaks are added in a region of
# overlap, and the width parameter is fixed at a reasonable value to aid
# convergence in this region.
pars = [[6.2, 0.25, 2.6], [6.45, 0.25, 2.7], [7.15, 0.25, 5]]
peaks = []
for p in pars:
peaks.append(pf.actualize(p, free=[True, False, True],
in_format="pwa"))
ppe.add_peaks(peaks) # adds to initial_peaks
## Initial peaks and pruning
# While initial peaks condition what other peaks can be extracted, by
# default they can also be pruned if a simpler model appears better. To
# prevent this, they can be set as non-removable.
for ip in ppe.initial_peaks:
ip.removable = False
## Plot initial parameters
if plot:
makeplot(ppe)
plt.title("Initial Peaks")
###### Perform peak extraction
ppe.extract()
## Save output
# The write() method saves a file which preserves all aspects of peak
# extraction and its results, by convention using the .srmise extension,
# and which can later be read by diffpy.srmise.
#
# The writepwa() method saves a file intended as a human-readable summary.
# In particular, it reports the position, width (as full-width
# half-maximum), and area of of extracted peaks. The reported values
# are for Gaussians in the radial distribution function (RDF) corresponding
# to this PDF.
ppe.write("output/parameter_summary.srmise")
ppe.writepwa("output/parameter_summary.pwa")
## Plot results.
# Display plot of extracted peak. It is also possible to plot an existing
# .srmise file from the command line using
# srmise output/TiO2_parameterdetail.srmise --no-extract --plot
if plot:
plt.figure()
makeplot(ppe)
plt.show()
class PeakStability:
"""Utility to test robustness of peaks.
results: [error scalar, model, bl, dr]
ppe: a PDFPeakExtraction instance """
def __init__(self):
self.results = []
self.ppe = None
self.current = None
def setppe(self, ppe):
self.ppe = ppe
def load(self, filename):
try:
import cPickle as pickle
except:
import pickle
in_s = open(filename, 'rb')
try:
(self.results, ppestr) = pickle.load(in_s)
self.ppe = PDFPeakExtraction()
self.ppe.readstr(ppestr)
# Ugly kluge for the baseline, since FromSequence
# can't pickle.
for r in self.results:
bl = self.ppe.baseline
kwds = r[2]
if r[2] is not None:
kwds = r[2]
if hasattr(bl, "estimate_parameters"):
r[2] = bl.actualize(default_input="internal", **kwds)
else:
r[2] = bl.owner().actualize(in_format="internal", **kwds)
finally:
in_s.close()
self.setcurrent(0)
def save(self, filename):
try:
import cPickle as pickle
except:
import pickle
out_s = open(filename, 'wb')
try:
# Write to the stream
outstr = self.ppe.writestr()
# ugly kluge to let FromSequence pickle
# (it stores xyrepr() in metadict)
results2 = []
for r in self.results:
if r[2] is None:
bldict = None
else:
bldict = {"pars":r[2].pars, "free":r[2].free, "removable":r[2].removable, "static_owner":r[2].static_owner}
results2.append([r[0], r[1], bldict, r[3]])
pickle.dump([results2, outstr], out_s)
finally:
out_s.close()
def plotseries(self, style='o', **kwds):
plt.figure()
plt.ioff()
for e, r, bl, dr in self.results:
peakpos = [p["position"] for p in r]
es = [e]*len(peakpos)
plt.plot(peakpos, es, style, **kwds)
plt.ion()
plt.draw()
def plot(self, **kwds):
"""Plot the current model. Keywords passed to pyplot.plot()"""
plt.clf()
plt.plot(*self.ppe.extracted.plottable(), **kwds)
q = self.ppe.extracted.quality()
plt.suptitle("[%i/%i]\n"
"Uncertainty: %6.3f. Peaks: %i.\n"
"Quality: %6.3f. Chi-square: %6.3f"
%(self.current+1, len(self.results), self.ppe.effective_dy[0], len(self.ppe.extracted.model), q.stat, q.chisq))
def setcurrent(self, idx):
"""Make the idxth model the active one."""
self.current = idx
if idx is not None:
result = self.results[idx]
self.ppe.setvars(quiet=True, effective_dy=result[0]*np.ones(len(self.ppe.x)))
(r, y, dr, dy) = self.ppe.resampledata(result[3])
self.ppe.extracted = ModelCluster(result[1], result[2], r, y, dy, None, self.ppe.error_method, self.ppe.pf)
else:
self.ppe.clearcalc()
def animate(self, results=None, step=False, **kwds):
"""Show animation of extracted peaks from first to last.
Parameters:
step - Require keypress to show next plot
results - The indices of results to show
Keywords passed to pyplot.plot()"""
if results is None:
results = range(len(self.results))
oldcurrent = self.current
self.setcurrent(0)
plt.ion()
plt.plot(*self.ppe.extracted.plottable())
a = plt.axis()
for i in results:
self.setcurrent(i)
plt.ioff()
self.plot(**kwds)
plt.ion()
plt.draw()
if step:
raw_input()
self.setcurrent(oldcurrent)
def run(self, err, savecovs=False):
"""err is sequence of uncertainties to run at.
If savecovs is True, return the covariance matrix for each final fit."""
self.results = []
covs = []
for i, e in enumerate(err):
print "---- Running for uncertainty %s (%i/%i) ----" %(e, i, len(err))
self.ppe.clearcalc()
self.ppe.setvars(effective_dy=e)
if savecovs:
covs.append(self.ppe.extract())
else:
self.ppe.extract()
dr = (self.ppe.extracted.r_cluster[-1]-self.ppe.extracted.r_cluster[0])/(len(self.ppe.extracted.r_cluster)-1)
self.results.append([e, self.ppe.extracted.model, self.ppe.extracted.baseline, dr])
for e, r, bl, dr in self.results:
print "---- Results for uncertainty %s ----" %e
print r
return covs