def finish(self):
self.axes.set_title(r"\begin{center}Distribution of Coincident Events (%d Foreground, %d Background Events, %d Injections Found in Coincidence, Logarithmic Density Contours)\end{center}" % (self.n_foreground, self.n_background, self.n_injections))
xcoords, ycoords = self.background_bins.centres()
# prepare the data
rate.filter_array(self.foreground_bins.array, rate.gaussian_window(8, 8))
rate.filter_array(self.background_bins.array, rate.gaussian_window(8, 8))
rate.filter_array(self.coinc_injection_bins.array, rate.gaussian_window(8, 8))
rate.filter_array(self.incomplete_coinc_injection_bins.array, rate.gaussian_window(8, 8))
self.foreground_bins.logregularize()
self.background_bins.logregularize()
self.coinc_injection_bins.logregularize()
self.incomplete_coinc_injection_bins.logregularize()
# plot background contours
max_density = math.log(self.background_bins.array.max())
self.axes.contour(xcoords, ycoords, numpy.transpose(numpy.log(self.background_bins.array)), [max_density - n for n in xrange(0, 10, 1)], cmap = matplotlib.cm.Greys)
# plot foreground (zero-lag) contours
max_density = math.log(self.foreground_bins.array.max())
self.axes.contour(xcoords, ycoords, numpy.transpose(numpy.log(self.foreground_bins.array)), [max_density - n for n in xrange(0, 10, 1)], cmap = matplotlib.cm.Reds)
#self.axes.plot(self.foreground_x, self.foreground_y, "r+")
# plot coincident injection contours
max_density = math.log(self.coinc_injection_bins.array.max())
self.axes.contour(xcoords, ycoords, numpy.transpose(numpy.log(self.coinc_injection_bins.array)), [max_density - n for n in xrange(0, 10, 1)], cmap = matplotlib.cm.Blues)
# plot incomplete coincident injection contours
max_density = math.log(self.incomplete_coinc_injection_bins.array.max())
self.axes.contour(xcoords, ycoords, numpy.transpose(numpy.log(self.incomplete_coinc_injection_bins.array)), [max_density - n for n in xrange(0, 10, 1)], cmap = matplotlib.cm.Greens)
# fix axes limits
self.axes.set_xlim([self.background_bins.bins.min[0], self.background_bins.bins.max[0]])
self.axes.set_ylim([self.background_bins.bins.min[1], self.background_bins.bins.max[1]])
def finish(self):
for key, pdf in self.densities.items():
if key.endswith("_snr2_chi2"):
rate.filter_array(pdf.array, rate.gaussian_window(11, 11, sigma = 20))
elif key.endswith("_dt") or key.endswith("_dA") or key.endswith("_df"):
rate.filter_array(pdf.array, rate.gaussian_window(11, sigma = 20))
elif key.startswith("instrumentgroup"):
# instrument group filter is a no-op
pass
else:
# shouldn't get here
raise Exception
pdf.normalize()
self.mkinterps()
def finish(self):
for key, pdf in self.densities.items():
if key.endswith("_snr2_chi2"):
rate.filter_array(pdf.array, rate.gaussian_window(11, 11, sigma = 20))
elif key.endswith("_dt") or key.endswith("_dA") or key.endswith("_df"):
rate.filter_array(pdf.array, rate.gaussian_window(11, sigma = 20))
elif key.startswith("instrumentgroup"):
# instrument group filter is a no-op
pass
else:
# shouldn't get here
raise Exception
pdf.normalize()
self.mkinterps()
def density_estimate(lnpdf, name, kernel=rate.gaussian_window(4.)):
"""
For internal use only.
"""
assert not numpy.isnan(lnpdf.array).any(
), "%s log likelihood ratio PDF contain NaNs" % name
rate.filter_array(lnpdf.array, kernel)
def finish(self, binning=None):
# compute the binning if needed, and set the injections
# into the numerator and denominator bins. also compute
# the smoothing window's parameters.
self._bin_events(binning)
# smooth the efficiency data.
print("Sum of numerator bins before smoothing = %g" %
self.efficiency.numerator.array.sum(),
file=sys.stderr)
print("Sum of denominator bins before smoothing = %g" %
self.efficiency.denominator.array.sum(),
file=sys.stderr)
rate.filter_binned_ratios(
self.efficiency,
rate.gaussian_window(self.window_size_x, self.window_size_y))
print("Sum of numerator bins after smoothing = %g" %
self.efficiency.numerator.array.sum(),
file=sys.stderr)
print("Sum of denominator bins after smoothing = %g" %
self.efficiency.denominator.array.sum(),
file=sys.stderr)
# regularize to prevent divide-by-zero errors
self.efficiency.regularize()
def finish(self):
livetime = rate.BinnedArray(self.counts.bins)
for offsets in self.tisi_rows:
self.seglists.offsets.update(offsets)
livetime[offsets[self.x_instrument],
offsets[self.y_instrument]] += float(
abs(self.seglists.intersection(self.seglists.keys())))
zvals = self.counts.at_centres() / livetime.at_centres()
rate.filter_array(zvals, rate.gaussian_window(3, 3))
xcoords, ycoords = self.counts.centres()
self.axes.contour(xcoords, ycoords, numpy.transpose(numpy.log(zvals)))
for offsets in self.tisi_rows:
if any(offsets):
# time slide vector is non-zero-lag
self.axes.plot((offsets[self.x_instrument], ),
(offsets[self.y_instrument], ), "k+")
else:
# time slide vector is zero-lag
self.axes.plot((offsets[self.x_instrument], ),
(offsets[self.y_instrument], ), "r+")
self.axes.set_xlim(
[self.counts.bins().min[0],
self.counts.bins().max[0]])
self.axes.set_ylim(
[self.counts.bins().min[1],
self.counts.bins().max[1]])
self.axes.set_title(
r"Coincident Event Rate vs. Instrument Time Offset (Logarithmic Rate Contours)"
)
def finish(self):
self.axes.set_title("Trigger Rate vs. Peak Frequency\n(%d Triggers)" % self.nevents)
# 21 bins per filter width
rate.filter_array(self.rate.array, rate.gaussian_window(21))
xvals = self.rate.centres()[0]
self.axes.plot(xvals, self.rate.at_centres(), "k")
self.axes.semilogy()
self.axes.set_xlim((min(xvals), max(xvals)))
def finish(self):
self.axes.set_title("Trigger Rate vs. Peak Frequency\n(%d Triggers)" % self.nevents)
# 21 bins per filter width
rate.filter_array(self.rate.array, rate.gaussian_window(21))
xvals = self.rate.centres()[0]
self.axes.plot(xvals, self.rate.at_centres(), "k")
self.axes.semilogy()
self.axes.set_xlim((min(xvals), max(xvals)))
def finish(self):
self.axes.set_title("Trigger Peak Time - Injection Peak Time\n(%d Found Injections)" % self.found)
# 21 bins per filter width
filter = rate.gaussian_window(21)
rate.filter_array(self.offsets.array, filter)
rate.filter_array(self.coinc_offsets.array, filter)
self.axes.plot(self.offsets.centres()[0], self.offsets.at_centres(), "k")
self.axes.plot(self.coinc_offsets.centres()[0], self.coinc_offsets.at_centres(), "r")
self.axes.legend(["%s residuals" % self.instrument, "SNR-weighted mean of residuals in all instruments"], loc = "lower right")
def finish(self):
for instrument, data in sorted(self.data.items()):
fig, axes = SnglBurstUtils.make_burst_plot(r"$t_{\mathrm{recovered}} - t_{\mathrm{injected}}$ (s)", "Triggers per Unit Offset")
axes.semilogy()
axes.set_title("Trigger Peak Time - Injection Peak Time in %s\n(%d Found Injections)" % (instrument, data.found))
# 21 bins per filter width
rate.filter_array(data.offsets.array, rate.gaussian_window(21))
axes.plot(data.offsets.centres()[0], data.offsets.at_centres(), "k")
#axes.legend(["%s residuals" % instrument, "SNR-weighted mean of residuals in all instruments"], loc = "lower right")
yield fig
def finish(self):
self.axes.set_title("Time Between Triggers\n(%d Triggers)" % self.nevents)
rate.filter_array(self.bins.array, rate.gaussian_window(21))
xvals = self.bins.centres()[0]
yvals = self.bins.at_centres()
self.axes.plot(xvals, yvals, "k")
self.axes.set_xlim((0, xvals[-1]))
self.axes.set_ylim((1, 10.0**(int(math.log10(yvals.max())) + 1)))
def finish(self):
self.axes.set_title("Time Between Triggers\n(%d Triggers)" % self.nevents)
rate.filter_array(self.bins.array, rate.gaussian_window(21))
xvals = self.bins.centres()[0]
yvals = self.bins.at_centres()
self.axes.plot(xvals, yvals, "k")
self.axes.set_xlim((0, xvals[-1]))
self.axes.set_ylim((1, 10.0**(int(math.log10(yvals.max())) + 1)))
def finish(self):
self.axes.set_title("Trigger Peak Frequency / Injection Centre Frequency\n(%d Found Injections)" % self.found)
# 21 bins per filter width
filter = rate.gaussian_window(21)
rate.filter_array(self.offsets.array, filter)
rate.filter_array(self.coinc_offsets.array, filter)
self.axes.plot(10**self.offsets.centres()[0], self.offsets.at_centres(), "k")
self.axes.plot(10**self.coinc_offsets.centres()[0], self.coinc_offsets.at_centres(), "r")
self.axes.legend(["%s triggers" % self.instrument, "SNR-weighted mean of all matching triggers"], loc = "lower right")
ymin, ymax = self.axes.get_ylim()
if ymax / ymin > 1e6:
ymin = ymax / 1e6
self.axes.set_ylim((ymin, ymax))
def create_efficiency_plot(axes, all_injections, found_injections, detection_threshold, cal_uncertainty):
filter_width = 16.7
# formats
axes.semilogx()
axes.set_position([0.10, 0.150, 0.86, 0.77])
# set desired yticks
axes.set_yticks((0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0))
axes.set_yticklabels((r"\(0\)", r"\(0.1\)", r"\(0.2\)", r"\(0.3\)", r"\(0.4\)", r"\(0.5\)", r"\(0.6\)", r"\(0.7\)", r"\(0.8\)", r"\(0.9\)", r"\(1.0\)"))
axes.xaxis.grid(True, which = "major,minor")
axes.yaxis.grid(True, which = "major,minor")
# put made and found injections in the denominators and
# numerators of the efficiency bins
bins = rate.NDBins((rate.LogarithmicBins(min(sim.amplitude for sim in all_injections), max(sim.amplitude for sim in all_injections), 400),))
efficiency_num = rate.BinnedArray(bins)
efficiency_den = rate.BinnedArray(bins)
for sim in found_injections:
efficiency_num[sim.amplitude,] += 1
for sim in all_injections:
efficiency_den[sim.amplitude,] += 1
# generate and plot trend curves. adjust window function
# normalization so that denominator array correctly
# represents the number of injections contributing to each
# bin: make w(0) = 1.0. note that this factor has no
# effect on the efficiency because it is common to the
# numerator and denominator arrays. we do this for the
# purpose of computing the Poisson error bars, which
# requires us to know the counts for the bins
windowfunc = rate.gaussian_window(filter_width)
windowfunc /= windowfunc[len(windowfunc) / 2 + 1]
rate.filter_array(efficiency_num.array, windowfunc)
rate.filter_array(efficiency_den.array, windowfunc)
# regularize: adjust unused bins so that the efficiency is
# 0, not NaN
assert (efficiency_num.array <= efficiency_den.array).all()
efficiency_den.array[(efficiency_num.array == 0) & (efficiency_den.array == 0)] = 1
line1, A50, A50_err = render_data_from_bins(file("string_efficiency.dat", "w"), axes, efficiency_num, efficiency_den, cal_uncertainty, filter_width, colour = "k", linestyle = "-", erroralpha = 0.2)
# add a legend to the axes
axes.legend((line1,), (r"\noindent Injections recovered with $\log \Lambda > %.2f$" % detection_threshold,), loc = "lower right")
# adjust limits
axes.set_xlim([3e-22, 3e-19])
axes.set_ylim([0.0, 1.0])
def finish(self, binning = None): # compute the binning if needed, and set the injections # into the numerator and denominator bins. also compute # the smoothing window's parameters. self._bin_events(binning) # smooth the efficiency data. print >>sys.stderr, "Sum of numerator bins before smoothing = %g" % self.efficiency.numerator.array.sum() print >>sys.stderr, "Sum of denominator bins before smoothing = %g" % self.efficiency.denominator.array.sum() rate.filter_binned_ratios(self.efficiency, rate.gaussian_window(self.window_size_x, self.window_size_y)) print >>sys.stderr, "Sum of numerator bins after smoothing = %g" % self.efficiency.numerator.array.sum() print >>sys.stderr, "Sum of denominator bins after smoothing = %g" % self.efficiency.denominator.array.sum() # regularize to prevent divide-by-zero errors self.efficiency.regularize()
def finish(self):
self.axes.set_title(
"Trigger Peak Time - Injection Peak Time\n(%d Found Injections)" %
self.found)
# 21 bins per filter width
filter = rate.gaussian_window(21)
rate.filter_array(self.offsets.array, filter)
rate.filter_array(self.coinc_offsets.array, filter)
self.axes.plot(self.offsets.centres()[0], self.offsets.at_centres(),
"k")
self.axes.plot(self.coinc_offsets.centres()[0],
self.coinc_offsets.at_centres(), "r")
self.axes.legend([
"%s residuals" % self.instrument,
"SNR-weighted mean of residuals in all instruments"
],
loc="lower right")
def finish(self): livetime = rate.BinnedArray(self.counts.bins) for offsets in self.tisi_rows: self.seglists.offsets.update(offsets) livetime[offsets[self.x_instrument], offsets[self.y_instrument]] += float(abs(self.seglists.intersection(self.seglists.keys()))) zvals = self.counts.at_centres() / livetime.at_centres() rate.filter_array(zvals, rate.gaussian_window(3, 3)) xcoords, ycoords = self.counts.centres() self.axes.contour(xcoords, ycoords, numpy.transpose(numpy.log(zvals))) for offsets in self.tisi_rows: if any(offsets): # time slide vector is non-zero-lag self.axes.plot((offsets[self.x_instrument],), (offsets[self.y_instrument],), "k+") else: # time slide vector is zero-lag self.axes.plot((offsets[self.x_instrument],), (offsets[self.y_instrument],), "r+") self.axes.set_xlim([self.counts.bins().min[0], self.counts.bins().max[0]]) self.axes.set_ylim([self.counts.bins().min[1], self.counts.bins().max[1]]) self.axes.set_title(r"Coincident Event Rate vs. Instrument Time Offset (Logarithmic Rate Contours)")
def rate_posterior_from_samples(samples):
"""
Construct and return a BinnedArray containing a histogram of a
sequence of samples. If limits is None (default) then the limits
of the binning will be determined automatically from the sequence,
otherwise limits is expected to be a tuple or other two-element
sequence providing the (low, high) limits, and in that case the
sequence can be a generator.
"""
nbins = int(math.sqrt(len(samples)) / 40.)
assert nbins >= 1, "too few samples to construct histogram"
lo = samples.min() * (1. - nbins / len(samples))
hi = samples.max() * (1. + nbins / len(samples))
ln_pdf = rate.BinnedLnPDF(
rate.NDBins((rate.LogarithmicBins(lo, hi, nbins), )))
count = ln_pdf.count # avoid attribute look-up in loop
for sample in samples:
count[sample, ] += 1.
rate.filter_array(ln_pdf.array, rate.gaussian_window(5), use_fft=False)
ln_pdf.normalize()
return ln_pdf
def finish(self):
self.axes.set_title(
"Trigger Peak Frequency / Injection Centre Frequency\n(%d Found Injections)"
% self.found)
# 21 bins per filter width
filter = rate.gaussian_window(21)
rate.filter_array(self.offsets.array, filter)
rate.filter_array(self.coinc_offsets.array, filter)
self.axes.plot(10**self.offsets.centres()[0],
self.offsets.at_centres(), "k")
self.axes.plot(10**self.coinc_offsets.centres()[0],
self.coinc_offsets.at_centres(), "r")
self.axes.legend([
"%s triggers" % self.instrument,
"SNR-weighted mean of all matching triggers"
],
loc="lower right")
ymin, ymax = self.axes.get_ylim()
if ymax / ymin > 1e6:
ymin = ymax / 1e6
self.axes.set_ylim((ymin, ymax))
def finish(self):
for key, pdf in self.densities.items():
rate.filter_array(pdf.array, rate.gaussian_window(11, 5))
pdf.normalize()
self.mkinterps()
def finish(self):
self.axes.set_title(
r"\begin{center}Distribution of Coincident Events (%d Foreground, %d Background Events, %d Injections Found in Coincidence, Logarithmic Density Contours)\end{center}"
% (self.n_foreground, self.n_background, self.n_injections))
xcoords, ycoords = self.background_bins.centres()
# prepare the data
rate.filter_array(self.foreground_bins.array,
rate.gaussian_window(8, 8))
rate.filter_array(self.background_bins.array,
rate.gaussian_window(8, 8))
rate.filter_array(self.coinc_injection_bins.array,
rate.gaussian_window(8, 8))
rate.filter_array(self.incomplete_coinc_injection_bins.array,
rate.gaussian_window(8, 8))
self.foreground_bins.logregularize()
self.background_bins.logregularize()
self.coinc_injection_bins.logregularize()
self.incomplete_coinc_injection_bins.logregularize()
# plot background contours
max_density = math.log(self.background_bins.array.max())
self.axes.contour(xcoords,
ycoords,
numpy.transpose(numpy.log(
self.background_bins.array)),
[max_density - n for n in xrange(0, 10, 1)],
cmap=matplotlib.cm.Greys)
# plot foreground (zero-lag) contours
max_density = math.log(self.foreground_bins.array.max())
self.axes.contour(xcoords,
ycoords,
numpy.transpose(numpy.log(
self.foreground_bins.array)),
[max_density - n for n in xrange(0, 10, 1)],
cmap=matplotlib.cm.Reds)
#self.axes.plot(self.foreground_x, self.foreground_y, "r+")
# plot coincident injection contours
max_density = math.log(self.coinc_injection_bins.array.max())
self.axes.contour(xcoords,
ycoords,
numpy.transpose(
numpy.log(self.coinc_injection_bins.array)),
[max_density - n for n in xrange(0, 10, 1)],
cmap=matplotlib.cm.Blues)
# plot incomplete coincident injection contours
max_density = math.log(
self.incomplete_coinc_injection_bins.array.max())
self.axes.contour(xcoords,
ycoords,
numpy.transpose(
numpy.log(
self.incomplete_coinc_injection_bins.array)),
[max_density - n for n in xrange(0, 10, 1)],
cmap=matplotlib.cm.Greens)
# fix axes limits
self.axes.set_xlim([
self.background_bins.bins.min[0], self.background_bins.bins.max[0]
])
self.axes.set_ylim([
self.background_bins.bins.min[1], self.background_bins.bins.max[1]
])
def finish(self, threshold):
# bin the injections
self._bin_events()
# use the same binning for the found injection density as
# was constructed for the efficiency
self.found_density = rate.BinnedArray(self.efficiency.denominator.bins)
# construct the amplitude weighting function
amplitude_weight = rate.BinnedArray(rate.NDBins((rate.LinearBins(threshold - 100, threshold + 100, 10001),)))
# gaussian window's width is the number of bins
# corresponding to 10 units of amplitude, which is computed
# by dividing 10 by the "volume" of the bin corresponding
# to threshold. index is the index of the element in
# amplitude_weight corresponding to the threshold.
index, = amplitude_weight.bins[threshold,]
window = rate.gaussian_window(10.0 / amplitude_weight.bins.volumes()[index])
window /= 10 * window[(len(window) - 1) / 2]
# set the window data into the BinnedArray object. the
# Gaussian peaks on the middle element of the window, which
# we want to place at index in the amplitude_weight array.
lo = index - (len(window) - 1) / 2
hi = lo + len(window)
if lo < 0 or hi > len(amplitude_weight.array):
raise ValueError("amplitude weighting window too large")
amplitude_weight.array[lo:hi] = window
# store the recovered injections in the found density bins
# weighted by amplitude
for x, y, z in self.recovered_xyz:
try:
weight = amplitude_weight[z,]
except IndexError:
# beyond the edge of the window
weight = 0.0
self.found_density[x, y] += weight
# the efficiency is only valid up to the highest energy
# that has been injected. this creates problems later on
# so, instead, for each frequency, identify the highest
# energy that has been measured and copy the values for
# that bin's numerator and denominator into the bins for
# all higher energies. do the same for the counts in the
# found injection density bins.
#
# numpy.indices() returns two arrays array, the first of
# which has each element set equal to its x index, the
# second has each element set equal to its y index, we keep
# the latter. meanwhile numpy.roll() cyclically permutes
# the efficiency bins down one along the y (energy) axis.
# from this, the conditional finds bins where the
# efficiency is greater than 0.9 but <= 0.9 in the bin
# immediately above it in energy. we select the elements
# from the y index array where the conditional is true, and
# then use numpy.max() along the y direction to return the
# highest such y index for each x index, which is a 1-D
# array. finally, enumerate() is used to iterate over x
# index and corresponding y index, and if the y index is
# not negative (was found) the value from that x-y bin is
# copied to all higher bins.
n = self.efficiency.numerator.array
d = self.efficiency.denominator.array
f = self.found_density.array
bady = -1
for x, y in enumerate(numpy.max(numpy.where((d > 0) & (numpy.roll(d, -1, axis = 1) <= 0), numpy.indices(d.shape)[1], bady), axis = 1)):
if y != bady:
n[x, y + 1:] = n[x, y]
d[x, y + 1:] = d[x, y]
f[x, y + 1:] = f[x, y]
# now do the same for the bins at energies below those that
# have been measured.
bady = d.shape[1]
for x, y in enumerate(numpy.min(numpy.where((d > 0) & (numpy.roll(d, 1, axis = 1) <= 0), numpy.indices(d.shape)[1], bady), axis = 1)):
if y != bady:
n[x, 0:y] = n[x, y]
d[x, 0:y] = d[x, y]
f[x, 0:y] = f[x, y]
diagnostic_plot(self.efficiency.numerator.array, self.efficiency.denominator.bins, r"Efficiency Numerator (Before Averaging)", self.amplitude_lbl, "lalapps_excesspowerfinal_efficiency_numerator_before.png")
diagnostic_plot(self.efficiency.denominator.array, self.efficiency.denominator.bins, r"Efficiency Denominator (Before Averaging)", self.amplitude_lbl, "lalapps_excesspowerfinal_efficiency_denominator_before.png")
diagnostic_plot(self.found_density.array, self.efficiency.denominator.bins, r"Injections Lost / Unit of Threshold (Before Averaging)", self.amplitude_lbl, "lalapps_excesspowerfinal_found_density_before.png")
# smooth the efficiency bins and the found injection
# density bins using the same 2D window.
window = rate.gaussian_window(self.window_size_x, self.window_size_y)
window /= window[tuple((numpy.array(window.shape, dtype = "double") - 1) / 2)]
rate.filter_binned_ratios(self.efficiency, window)
rate.filter_array(self.found_density.array, window)
diagnostic_plot(self.efficiency.numerator.array, self.efficiency.denominator.bins, r"Efficiency Numerator (After Averaging)", self.amplitude_lbl, "lalapps_excesspowerfinal_efficiency_numerator_after.png")
diagnostic_plot(self.efficiency.denominator.array, self.efficiency.denominator.bins, r"Efficiency Denominator (After Averaging)", self.amplitude_lbl, "lalapps_excesspowerfinal_efficiency_denominator_after.png")
diagnostic_plot(self.found_density.array, self.efficiency.denominator.bins, r"Injections Lost / Unit of Threshold (After Averaging)", self.amplitude_lbl, "lalapps_excesspowerfinal_found_density_after.png")
# compute the uncertainties in the efficiency and its
# derivative by assuming these to be the binomial counting
# fluctuations in the numerators.
p = self.efficiency.ratio()
self.defficiency = numpy.sqrt(p * (1 - p) / self.efficiency.denominator.array)
p = self.found_density.array / self.efficiency.denominator.array
self.dfound_density = numpy.sqrt(p * (1 - p) / self.efficiency.denominator.array)
fig = figure.Figure()
canvas = FigureCanvas(fig)
fig.set_size_inches(width, height)
fig.gca().set_position([
border[0] / width, border[1] / height,
(width - border[0] - border[2]) / width,
(height - border[1] - border[3]) / height
])
return fig
fig = newfig(options.segment)
axes = fig.gca()
rate.filter_array(trigger_rate.array,
rate.gaussian_window(bins_per_filterwidth))
axes.plot(trigger_rate.centres()[0], trigger_rate.at_centres())
axes.set_xlim(list(options.segment))
axes.grid(True)
for seg in ~seglist & segments.segmentlist([options.segment]):
axes.axvspan(seg[0], seg[1], facecolor="k", alpha=0.2)
axes.set_title(
"%s Excess Power Trigger Rate vs. Time\n(%d Triggers, %g s Moving Average)"
% (options.instrument, num_triggers, options.window))
ticks = make_xticks(options.segment)
axes.set_xticks(ticks[0])
def finish(self): for key, pdf in self.densities.items(): rate.filter_array(pdf.array, rate.gaussian_window(11, 5)) pdf.normalize() self.mkinterps()
def finish(self):
fig, axes = SnglBurstUtils.make_burst_plot(r"Injection Amplitude (\(\mathrm{s}^{-\frac{1}{3}}\))", "Detection Efficiency", width = 108.0)
axes.set_title(r"Detection Efficiency vs.\ Amplitude")
axes.semilogx()
axes.set_position([0.10, 0.150, 0.86, 0.77])
# set desired yticks
axes.set_yticks((0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0))
axes.set_yticklabels((r"\(0\)", r"\(0.1\)", r"\(0.2\)", r"\(0.3\)", r"\(0.4\)", r"\(0.5\)", r"\(0.6\)", r"\(0.7\)", r"\(0.8\)", r"\(0.9\)", r"\(1.0\)"))
axes.xaxis.grid(True, which = "major,minor")
axes.yaxis.grid(True, which = "major,minor")
# put made and found injections in the denominators and
# numerators of the efficiency bins
bins = rate.NDBins((rate.LogarithmicBins(min(sim.amplitude for sim in self.all), max(sim.amplitude for sim in self.all), 400),))
efficiency_num = rate.BinnedArray(bins)
efficiency_den = rate.BinnedArray(bins)
for sim in self.found:
efficiency_num[sim.amplitude,] += 1
for sim in self.all:
efficiency_den[sim.amplitude,] += 1
# generate and plot trend curves. adjust window function
# normalization so that denominator array correctly
# represents the number of injections contributing to each
# bin: make w(0) = 1.0. note that this factor has no
# effect on the efficiency because it is common to the
# numerator and denominator arrays. we do this for the
# purpose of computing the Poisson error bars, which
# requires us to know the counts for the bins
windowfunc = rate.gaussian_window(self.filter_width)
windowfunc /= windowfunc[len(windowfunc) / 2 + 1]
rate.filter_array(efficiency_num.array, windowfunc)
rate.filter_array(efficiency_den.array, windowfunc)
# regularize: adjust unused bins so that the efficiency is
# 0, not NaN
assert (efficiency_num.array <= efficiency_den.array).all()
efficiency_den.array[(efficiency_num.array == 0) & (efficiency_den.array == 0)] = 1
line1, A50, A50_err = render_data_from_bins(file("string_efficiency.dat", "w"), axes, efficiency_num, efficiency_den, self.cal_uncertainty, self.filter_width, colour = "k", linestyle = "-", erroralpha = 0.2)
print("Pipeline's 50%% efficiency point for all detections = %g +/- %g%%\n" % (A50, A50_err * 100), file=sys.stderr)
# add a legend to the axes
axes.legend((line1,), (r"\noindent Injections recovered with $\log \Lambda > %.2f$" % self.detection_threshold,), loc = "lower right")
# adjust limits
axes.set_xlim([3e-22, 3e-19])
axes.set_ylim([0.0, 1.0])
#
# dump some information about the highest-amplitude missed
# and quietest-amplitude found injections
#
self.loudest_missed.sort(reverse = True)
self.quietest_found.sort(reverse = True)
f = file("string_loud_missed_injections.txt", "w")
print("Highest Amplitude Missed Injections", file=f)
print("===================================", file=f)
for amplitude, sim, offsetvector, filename, ln_likelihood_ratio in self.loudest_missed:
print(file=f)
print("%s in %s:" % (str(sim.simulation_id), filename), file=f)
if ln_likelihood_ratio is None:
print("Not recovered", file=f)
else:
print("Recovered with \\log \\Lambda = %.16g, detection threshold was %.16g" % (ln_likelihood_ratio, self.detection_threshold), file=f)
for instrument in self.seglists:
print("In %s:" % instrument, file=f)
print("\tInjected amplitude:\t%.16g" % SimBurstUtils.string_amplitude_in_instrument(sim, instrument, offsetvector), file=f)
print("\tTime of injection:\t%s s" % sim.time_at_instrument(instrument, offsetvector), file=f)
print("Amplitude in waveframe:\t%.16g" % sim.amplitude, file=f)
t = sim.get_time_geocent()
print("Time at geocentre:\t%s s" % t, file=f)
print("Segments within 60 seconds:\t%s" % segmentsUtils.segmentlistdict_to_short_string(self.seglists & segments.segmentlistdict((instrument, segments.segmentlist([segments.segment(t-offsetvector[instrument]-60, t-offsetvector[instrument]+60)])) for instrument in self.seglists)), file=f)
print("Vetoes within 60 seconds:\t%s" % segmentsUtils.segmentlistdict_to_short_string(self.vetoseglists & segments.segmentlistdict((instrument, segments.segmentlist([segments.segment(t-offsetvector[instrument]-60, t-offsetvector[instrument]+60)])) for instrument in self.vetoseglists)), file=f)
f = file("string_quiet_found_injections.txt", "w")
print("Lowest Amplitude Found Injections", file=f)
print("=================================", file=f)
for inv_amplitude, sim, offsetvector, filename, ln_likelihood_ratio in self.quietest_found:
print(file=f)
print("%s in %s:" % (str(sim.simulation_id), filename), file=f)
if ln_likelihood_ratio is None:
print("Not recovered", file=f)
else:
print("Recovered with \\log \\Lambda = %.16g, detection threshold was %.16g" % (ln_likelihood_ratio, self.detection_threshold), file=f)
for instrument in self.seglists:
print("In %s:" % instrument, file=f)
print("\tInjected amplitude:\t%.16g" % SimBurstUtils.string_amplitude_in_instrument(sim, instrument, offsetvector), file=f)
print("\tTime of injection:\t%s s" % sim.time_at_instrument(instrument, offsetvector), file=f)
print("Amplitude in waveframe:\t%.16g" % sim.amplitude, file=f)
t = sim.get_time_geocent()
print("Time at geocentre:\t%s s" % t, file=f)
print("Segments within 60 seconds:\t%s" % segmentsUtils.segmentlistdict_to_short_string(self.seglists & segments.segmentlistdict((instrument, segments.segmentlist([segments.segment(t-offsetvector[instrument]-60, t-offsetvector[instrument]+60)])) for instrument in self.seglists)), file=f)
print("Vetoes within 60 seconds:\t%s" % segmentsUtils.segmentlistdict_to_short_string(self.vetoseglists & segments.segmentlistdict((instrument, segments.segmentlist([segments.segment(t-offsetvector[instrument]-60, t-offsetvector[instrument]+60)])) for instrument in self.vetoseglists)), file=f)
#
# done
#
return fig,
def finish(self, threshold):
# bin the injections
self._bin_events()
# use the same binning for the found injection density as
# was constructed for the efficiency
self.found_density = rate.BinnedArray(self.efficiency.denominator.bins)
# construct the amplitude weighting function
amplitude_weight = rate.BinnedArray(rate.NDBins((rate.LinearBins(threshold - 100, threshold + 100, 10001),)))
# gaussian window's width is the number of bins
# corresponding to 10 units of amplitude, which is computed
# by dividing 10 by the "volume" of the bin corresponding
# to threshold. index is the index of the element in
# amplitude_weight corresponding to the threshold.
index, = amplitude_weight.bins[threshold,]
window = rate.gaussian_window(10.0 / amplitude_weight.bins.volumes()[index])
window /= 10 * window[(len(window) - 1) / 2]
# set the window data into the BinnedArray object. the
# Gaussian peaks on the middle element of the window, which
# we want to place at index in the amplitude_weight array.
lo = index - (len(window) - 1) / 2
hi = lo + len(window)
if lo < 0 or hi > len(amplitude_weight.array):
raise ValueError("amplitude weighting window too large")
amplitude_weight.array[lo:hi] = window
# store the recovered injections in the found density bins
# weighted by amplitude
for x, y, z in self.recovered_xyz:
try:
weight = amplitude_weight[z,]
except IndexError:
# beyond the edge of the window
weight = 0.0
self.found_density[x, y] += weight
# the efficiency is only valid up to the highest energy
# that has been injected. this creates problems later on
# so, instead, for each frequency, identify the highest
# energy that has been measured and copy the values for
# that bin's numerator and denominator into the bins for
# all higher energies. do the same for the counts in the
# found injection density bins.
#
# numpy.indices() returns two arrays array, the first of
# which has each element set equal to its x index, the
# second has each element set equal to its y index, we keep
# the latter. meanwhile numpy.roll() cyclically permutes
# the efficiency bins down one along the y (energy) axis.
# from this, the conditional finds bins where the
# efficiency is greater than 0.9 but <= 0.9 in the bin
# immediately above it in energy. we select the elements
# from the y index array where the conditional is true, and
# then use numpy.max() along the y direction to return the
# highest such y index for each x index, which is a 1-D
# array. finally, enumerate() is used to iterate over x
# index and corresponding y index, and if the y index is
# not negative (was found) the value from that x-y bin is
# copied to all higher bins.
n = self.efficiency.numerator.array
d = self.efficiency.denominator.array
f = self.found_density.array
bady = -1
for x, y in enumerate(numpy.max(numpy.where((d > 0) & (numpy.roll(d, -1, axis = 1) <= 0), numpy.indices(d.shape)[1], bady), axis = 1)):
if y != bady:
n[x, y + 1:] = n[x, y]
d[x, y + 1:] = d[x, y]
f[x, y + 1:] = f[x, y]
# now do the same for the bins at energies below those that
# have been measured.
bady = d.shape[1]
for x, y in enumerate(numpy.min(numpy.where((d > 0) & (numpy.roll(d, 1, axis = 1) <= 0), numpy.indices(d.shape)[1], bady), axis = 1)):
if y != bady:
n[x, 0:y] = n[x, y]
d[x, 0:y] = d[x, y]
f[x, 0:y] = f[x, y]
diagnostic_plot(self.efficiency.numerator.array, self.efficiency.denominator.bins, r"Efficiency Numerator (Before Averaging)", self.amplitude_lbl, "lalapps_excesspowerfinal_efficiency_numerator_before.png")
diagnostic_plot(self.efficiency.denominator.array, self.efficiency.denominator.bins, r"Efficiency Denominator (Before Averaging)", self.amplitude_lbl, "lalapps_excesspowerfinal_efficiency_denominator_before.png")
diagnostic_plot(self.found_density.array, self.efficiency.denominator.bins, r"Injections Lost / Unit of Threshold (Before Averaging)", self.amplitude_lbl, "lalapps_excesspowerfinal_found_density_before.png")
# smooth the efficiency bins and the found injection
# density bins using the same 2D window.
window = rate.gaussian_window(self.window_size_x, self.window_size_y)
window /= window[tuple((numpy.array(window.shape, dtype = "double") - 1) / 2)]
rate.filter_binned_ratios(self.efficiency, window)
rate.filter_array(self.found_density.array, window)
diagnostic_plot(self.efficiency.numerator.array, self.efficiency.denominator.bins, r"Efficiency Numerator (After Averaging)", self.amplitude_lbl, "lalapps_excesspowerfinal_efficiency_numerator_after.png")
diagnostic_plot(self.efficiency.denominator.array, self.efficiency.denominator.bins, r"Efficiency Denominator (After Averaging)", self.amplitude_lbl, "lalapps_excesspowerfinal_efficiency_denominator_after.png")
diagnostic_plot(self.found_density.array, self.efficiency.denominator.bins, r"Injections Lost / Unit of Threshold (After Averaging)", self.amplitude_lbl, "lalapps_excesspowerfinal_found_density_after.png")
# compute the uncertainties in the efficiency and its
# derivative by assuming these to be the binomial counting
# fluctuations in the numerators.
p = self.efficiency.ratio()
self.defficiency = numpy.sqrt(p * (1 - p) / self.efficiency.denominator.array)
p = self.found_density.array / self.efficiency.denominator.array
self.dfound_density = numpy.sqrt(p * (1 - p) / self.efficiency.denominator.array)
def finish(self):
snrsq_kernel_width_at_64 = 16.,
chisq_kernel_width = 0.02,
sigma = 10.
for key, lnpdf in self.densities.items():
if key.endswith("_snr2_chi2"):
numsamples = max(lnpdf.array.sum() / 10. + 1., 1e3)
snrsq_bins, chisq_bins = lnpdf.bins
snrsq_per_bin_at_64 = (snrsq_bins.upper() -
snrsq_bins.lower())[snrsq_bins[64.]]
chisq_per_bin_at_0_02 = (chisq_bins.upper() -
chisq_bins.lower())[chisq_bins[0.02]]
# apply Silverman's rule so that the width scales
# with numsamples**(-1./6.) for a 2D PDF
snrsq_kernel_bins = snrsq_kernel_width_at_64 / snrsq_per_bin_at_64 / numsamples**(
1. / 6.)
chisq_kernel_bins = chisq_kernel_width / chisq_per_bin_at_0_02 / numsamples**(
1. / 6.)
# check the size of the kernel. We don't ever let
# it get smaller than the 2.5 times the bin size
if snrsq_kernel_bins < 2.5:
snrsq_kernel_bins = 2.5
warnings.warn("Replacing snrsq kernel bins with 2.5")
if chisq_kernel_bins < 2.5:
chisq_kernel_bins = 2.5
warnings.warn("Replacing chisq kernel bins with 2.5")
# convolve bin count with density estimation kernel
rate.filter_array(
lnpdf.array,
rate.gaussian_window(snrsq_kernel_bins,
chisq_kernel_bins,
sigma=sigma))
# zero everything below the SNR cutoff. need to do the slicing
# ourselves to avoid zero-ing the at-threshold bin
lnpdf.array[:lnpdf.bins[0][self.snr_threshold], :] = 0.
elif key.endswith("_snr2_duration"):
# FIXME the duration filter kernel is left as a guess
rate.filter_array(
lnpdf.array,
rate.gaussian_window(snrsq_kernel_bins, 11, sigma=sigma))
# zero everything below the SNR cutoff. need to do the slicing
# ourselves to avoid zero-ing the at-threshold bin
lnpdf.array[:lnpdf.bins[0][self.snr_threshold], :] = 0.
else:
# shouldn't get here
raise Exception
lnpdf.normalize()
self.mkinterps()
#
# never allow PDFs that have had the density estimation
# transform applied to be written to disk: on-disk files
# must only ever provide raw counts. also don't allow
# density estimation to be applied twice
#
def to_xml(*args, **kwargs):
raise NotImplementedError(
"writing .finish()'ed LnLRDensity object to disk is forbidden")
self.to_xml = to_xml
def finish(*args, **kwargs):
raise NotImplementedError(
".finish()ing a .finish()ed LnLRDensity object is forbidden")
self.finish = finish
weeks = float(abs(segment)) / 86400.0 / 7.0 # FIXME: leep seconds?
border = (0.5, 0.75, 0.125, 0.625) # inches
width = max(10.0, weeks * 3.0 + border[0] + border[2]) # inches
height = 8.0 # inches
fig = figure.Figure()
canvas = FigureCanvas(fig)
fig.set_size_inches(width, height)
fig.gca().set_position([border[0] / width, border[1] / height, (width - border[0] - border[2]) / width, (height - border[1] - border[3]) / height])
return fig
fig = newfig(options.segment)
axes = fig.gca()
rate.filter_array(trigger_rate.array, rate.gaussian_window(bins_per_filterwidth))
axes.plot(trigger_rate.centres()[0], trigger_rate.at_centres())
axes.set_xlim(list(options.segment))
axes.grid(True)
for seg in ~seglist & segments.segmentlist([options.segment]):
axes.axvspan(seg[0], seg[1], facecolor = "k", alpha = 0.2)
axes.set_title("%s Excess Power Trigger Rate vs. Time\n(%d Triggers, %g s Moving Average)" % (options.instrument, num_triggers, options.window))
def SNRPDF(instruments,
horizon_distances,
snr_cutoff,
n_samples=200000,
bins=rate.ATanLogarithmicBins(3.6, 1e3, 150)):
"""
Precomputed SNR PDF for each detector
Returns a BinnedArray containing
P(snr_{inst1}, snr_{inst2}, ... | signal seen in exactly
{inst1, inst2, ...} in a network of instruments
with a given set of horizon distances)
i.e., the joint probability density of observing a set of
SNRs conditional on them being the result of signal that
has been recovered in a given subset of the instruments in
a network of instruments with a given set of horizon
distances.
The axes of the PDF correspond to the instruments in
alphabetical order. The binning used for all axes is set
with the bins parameter.
The n_samples parameter sets the number of iterations for
the internal Monte Carlo sampling loop.
"""
if n_samples < 1:
raise ValueError("n_samples=%d must be >= 1" % n_samples)
# get instrument names
instruments = sorted(instruments)
if len(instruments) < 1:
raise ValueError(instruments)
# get the horizon distances in the same order
DH_times_8 = 8. * numpy.array(
[horizon_distances[inst] for inst in instruments])
# get detector responses in the same order
resps = [
lalsimulation.DetectorPrefixToLALDetector(str(inst)).response
for inst in instruments
]
# get horizon distances and responses of remaining
# instruments (order doesn't matter as long as they're in
# the same order)
DH_times_8_other = 8. * numpy.array([
dist
for inst, dist in horizon_distances.items() if inst not in instruments
])
resps_other = tuple(
lalsimulation.DetectorPrefixToLALDetector(str(inst)).response
for inst in horizon_distances if inst not in instruments)
# initialize the PDF array, and pre-construct the sequence of
# snr, d(snr) tuples. since the last SNR bin probably has
# infinite size, we remove it from the sequence
# (meaning the PDF will be left 0 in that bin)
pdf = rate.BinnedArray(rate.NDBins([bins] * len(instruments)))
snr_sequence = rate.ATanLogarithmicBins(3.6, 1e3, 500)
snr_snrlo_snrhi_sequence = numpy.array(
zip(snr_sequence.centres(), snr_sequence.lower(),
snr_sequence.upper())[:-1])
# compute the SNR at which to begin iterations over bins
assert type(snr_cutoff) is float
snr_min = snr_cutoff - 3.0
assert snr_min > 0.0
# we select random uniformly-distributed right assensions
# so there's no point in also choosing random GMSTs and any
# vlaue is as good as any other
gmst = 0.0
# run the sample the requested # of iterations. save some
# symbols to avoid doing module attribute look-ups in the
# loop
acos = math.acos
random_uniform = random.uniform
twopi = 2. * math.pi
pi_2 = math.pi / 2.
xlal_am_resp = lal.ComputeDetAMResponse
# FIXME: scipy.stats.rice.rvs broken on reference OS.
# switch to it when we can rely on a new-enough scipy
#rice_rvs = stats.rice.rvs # broken on reference OS
# the .reshape is needed in the event that x is a 1x1
# array: numpy returns a scalar from sqrt(), but we must
# have something that we can iterate over
rice_rvs = lambda x: numpy.sqrt(stats.ncx2.rvs(2., x**2.)).reshape(x.shape)
for i in xrange(n_samples):
# select random sky location and source orbital
# plane inclination
# the signal is linearly polaraized, and h_cross = 0
# is assumed, so we need only F+ (its absolute value).
ra = random_uniform(0., twopi)
dec = pi_2 - acos(random_uniform(-1., 1.))
psi = random_uniform(0., twopi)
fplus = tuple(
abs(xlal_am_resp(resp, ra, dec, psi, gmst)[0]) for resp in resps)
# 1/8 ratio of inverse SNR to distance for each instrument
# (1/8 because horizon distance is defined for an SNR of 8,
# and we've omitted that factor for performance)
snr_times_D = DH_times_8 * fplus
# snr * D in instrument whose SNR grows fastest
# with decreasing D
max_snr_times_D = snr_times_D.max()
# snr_times_D.min() / snr_min = the furthest a
# source can be and still be above snr_min in all
# instruments involved. max_snr_times_D / that
# distance = the SNR that distance corresponds to
# in the instrument whose SNR grows fastest with
# decreasing distance --- the SNR the source has in
# the most sensitive instrument when visible to all
# instruments in the combo
try:
start_index = snr_sequence[max_snr_times_D /
(snr_times_D.min() / snr_min)]
except ZeroDivisionError:
# one of the instruments that must be able
# to see the event is blind to it
continue
# min_D_other is minimum distance at which source
# becomes visible in an instrument that isn't
# involved. max_snr_times_D / min_D_other gives
# the SNR in the most sensitive instrument at which
# the source becomes visible to one of the
# instruments not allowed to participate
if len(DH_times_8_other):
min_D_other = (DH_times_8_other * fplus).min() / snr_cutoff
try:
end_index = snr_sequence[max_snr_times_D / min_D_other] + 1
except ZeroDivisionError:
# all instruments that must not see
# it are blind to it
end_index = None
else:
# there are no other instruments
end_index = None
# if start_index >= end_index then in order for the
# source to be close enough to be visible in all
# the instruments that must see it it is already
# visible to one or more instruments that must not.
# don't need to check for this, the for loop that
# comes next will simply not have any iterations.
# iterate over the nominal SNRs (= noise-free SNR
# in the most sensitive instrument) at which we
# will add weight to the PDF. from the SNR in
# most sensitive instrument, the distance to the
# source is:
#
# D = max_snr_times_D / snr
#
# and the (noise-free) SNRs in all instruments are:
#
# snr_times_D / D
#
# scipy's Rice-distributed RV code is used to
# add the effect of background noise, converting
# the noise-free SNRs into simulated observed SNRs
#
# number of sources b/w Dlo and Dhi:
#
# d count \propto D^2 |dD|
# count \propto Dhi^3 - Dlo**3
D_Dhi_Dlo_sequence = max_snr_times_D / snr_snrlo_snrhi_sequence[
start_index:end_index]
for snr, weight in zip(
rice_rvs(snr_times_D /
numpy.reshape(D_Dhi_Dlo_sequence[:, 0],
(len(D_Dhi_Dlo_sequence), 1))),
D_Dhi_Dlo_sequence[:, 1]**3. - D_Dhi_Dlo_sequence[:, 2]**3.):
pdf[tuple(snr)] += weight
# check for divide-by-zeros that weren't caught. also
# finds nans if they are there
assert numpy.isfinite(pdf.array).all()
# convolve samples with gaussian kernel
rate.filter_array(pdf.array,
rate.gaussian_window(*(1.875, ) * len(pdf.array.shape)))
# protect against round-off in FFT convolution leading to
# negative valuesin the PDF
numpy.clip(pdf.array, 0., PosInf, pdf.array)
# zero counts in bins that are below the trigger threshold.
# have to convert SNRs to indexes ourselves and adjust so
# that we don't zero the bin in which the SNR threshold
# falls
range_all = slice(None, None)
range_low = slice(None, pdf.bins[0][snr_cutoff])
for i in xrange(len(instruments)):
slices = [range_all] * len(instruments)
slices[i] = range_low
# convert bin counts to normalized PDF
pdf.to_pdf()
# one last sanity check
assert numpy.isfinite(pdf.array).all()
# done
return pdf
