def plotDocUsageForProposal(docUsageByUID, savefilename=None, **kwargs):
''' Make trace plot of doc usage for each component.
'''
pylab.figure()
L = 0
maxVal = 0
for k, uid in enumerate(docUsageByUID):
ys = np.asarray(docUsageByUID[uid])
xs = np.arange(0, ys.size)
if k < 6: # only a few labels fit well on a legend
pylab.plot(xs, ys, label=uid)
else:
pylab.plot(xs, ys)
L = np.maximum(L, ys.size)
maxVal = np.maximum(maxVal, ys.max())
# Use big chunk of left-hand side of plot for legend display
xlims = np.asarray([-0.75*L, L-0.5])
pylab.xlim(xlims)
pylab.xticks(np.arange(1, L))
pylab.ylim([0, 1.1*maxVal])
pylab.xlabel('num proposal steps')
pylab.ylabel('num docs using each comp')
pylab.legend(loc='upper left', fontsize=12)
pylab.subplots_adjust(left=0.2)
if savefilename is not None:
pylab.savefig(savefilename, pad_inches=0)
pylab.close('all')
def plotELBOtermsForProposal(
curLdict, propLdictList,
xs=None,
ymin=-0.5,
ymax=0.5,
savefilename=None,
**kwargs):
''' Create trace plot of ELBO gain/loss relative to current model.
'''
pylab.figure()
L = len(propLdictList)
if xs is None:
xs = np.arange(0, L)
legendKeys = []
for key in curLdict:
if key.count('_') == 0:
legendKeys.append(key)
for key in legendKeys:
if key.count('total'):
linewidth= 4
alpha = 1
style = '-'
else:
linewidth = 3
alpha = 0.5
style = '--'
ys = np.asarray([propLdictList[i][key] for i in range(L)])
ys -= curLdict[key]
pylab.plot(xs, ys, style,
color=_getLineColorFromELBOKey(key),
linewidth=linewidth,
alpha=alpha,
label=key)
L = L + 1
xlims = np.asarray([-0.75*L, L-0.5])
pylab.xlim(xlims)
pylab.xticks(xs)
pylab.plot(xlims, np.zeros_like(xlims), 'k:')
pylab.xlabel('num proposal steps')
pylab.ylabel('L gain (prop - current)')
pylab.legend(loc='lower left', fontsize=12)
pylab.subplots_adjust(left=0.2)
if savefilename is not None:
pylab.savefig(savefilename, pad_inches=0)
pylab.close('all')
def plotJobs(jpaths, legNames, styles=None, fileSuffix='PredLik.mat',
xvar='laps', yvar='avgLikScore', loc='upper right',
minLap=0, showFinalPt=0,
prefix='predlik',
taskids=None, savefilename=None, tickfontsize=None,
xjitter=None, bbox_to_anchor=None, **kwargs):
''' Create line plots for provided jobs
'''
nLines = len(jpaths)
nLeg = len(legNames)
assert nLines <= nLeg
jitterByJob = np.linspace(-.5, .5, len(jpaths))
for lineID in range(nLines):
if styles is None:
curStyle = dict(colorID=lineID)
else:
curStyle = styles[lineID]
if xjitter is not None:
xjitter = jitterByJob[lineID]
plot_all_tasks_for_job(jpaths[lineID], legNames[lineID], minLap=minLap,
xvar=xvar, yvar=yvar, fileSuffix=fileSuffix,
showFinalPt=showFinalPt,
prefix=prefix,
taskids=taskids, xjitter=xjitter, **curStyle)
if loc is not None and len(jpaths) > 1:
pylab.legend(loc=loc, bbox_to_anchor=bbox_to_anchor)
if tickfontsize is not None:
pylab.tick_params(axis='both', which='major', labelsize=tickfontsize)
if savefilename is not None:
try:
pylab.show(block=False)
except TypeError:
pass # when using IPython notebook
pylab.savefig(savefilename, bbox_inches='tight', pad_inches=0)
else:
try:
pylab.show(block=True)
except TypeError:
pass # when using IPython notebook
def plotCompsFromSS(hmodel, SS, outfilepath=None, **kwargs):
''' Plot components defined by provided summary statistics.
Provided hmodel is just used for its hyperparameters, not current comps.
Post condition
--------------
Create matplotlib figure showing (subset of) SS.K components.
'''
if 'xlabels' not in kwargs:
xlabels = uidsAndCounts2strlist(SS)
kwargs['xlabels'] = xlabels
tmpModel = hmodel.copy()
tmpModel.obsModel.update_global_params(SS)
plotCompsFromHModel(tmpModel, **kwargs)
if outfilepath is not None:
pylab.savefig(outfilepath)
pylab.close('all')
print('Wrote: %s' % (outfilepath))
def plotManyPanelsByPVar(jpathPattern='/tmp/',
pvar=None,
pvals=None,
W=5,
H=4,
savefilename=None,
doShowNow=False,
**kwargs):
''' Create line plots for jobs matching pattern and provided kwargs
'''
if pvar is None:
jpathList = [jpathPattern]
pvar = None
pvals = [None]
else:
prefixfilepath = os.path.sep.join(jpathPattern.split(os.path.sep)[:-1])
PPListMap = makePPListMapFromJPattern(jpathPattern)
if pvals is None:
pvals = PPListMap[pvar]
else:
pvals = [p for p in pvals if p in PPListMap[pvar]]
jpathList = makeListOfJPatternsWithSpecificVals(
PPListMap,
prefixfilepath=prefixfilepath,
key=pvar,
vals=pvals,
**kwargs)
nrows = 1
ncols = len(pvals)
pylab.subplots(nrows=nrows, ncols=ncols, figsize=(ncols * W, nrows * H))
axH = None
for panelID, panel_jobPattern in enumerate(jpathList):
axH = pylab.subplot(nrows, ncols, panelID + 1, sharey=axH, sharex=axH)
# Only show legend on first plot
if panelID > 0 and 'loc' in kwargs:
kwargs['loc'] = None
kwargs['doShowNow'] = False
plotMultipleLinesByLVar(panel_jobPattern, **kwargs)
if pvar is not None:
pylab.title('%s=%s' % (pvar, pvals[panelID]))
pylab.subplots_adjust(bottom=0.15, wspace=0.5)
if savefilename is not None:
try:
pylab.show(block=False)
except TypeError:
pass # when using IPython notebook
pylab.savefig(savefilename, bbox_inches='tight', pad_inches=0)
elif doShowNow:
try:
pylab.show(block=True)
except TypeError:
pass # when using IPython notebook
Info = dict(
nrows=nrows,
ncols=ncols,
)
return Info
def plotMultipleLinesByLVar(jpathPattern,
lvar=None,
lvals=None,
ColorMap=DefaultColorList,
loc=None,
bbox_to_anchor=None,
savefilename=None,
tickfontsize=None,
doShowNow=False,
**kwargs):
''' Create line plots for provided jobs.
'''
prefixfilepath = os.path.sep.join(jpathPattern.split(os.path.sep)[:-1])
PPListMap = makePPListMapFromJPattern(jpathPattern)
if lvals is None:
lvals = PPListMap[lvar]
elif not isinstance(lvals, list):
lvals = [lvals]
# Make sure all lval values are street legal (aka exist on disk)
lvals = [ll for ll in lvals if ll == '.best' or ll in PPListMap[lvar]]
# Do ranking in advance for each relevant job
'''if lvals[0] == '.best':
xvar = kwargs['xvar']
if 'xvals' in kwargs:
xvals = kwargs['xvals']
else:
xvals = PPListMap[xvar]
for xval in xvals:
keyValDict = dict()
keyValDict[xvar] = xval
jpatternForXVal = makeJPatternWithSpecificVals(
PPListMap,
prefixfilepath=prefixfilepath, **keyValDict)
TaskRanker.markBestAmongJobPatternOnDisk(jpatternForXVal)
'''
# Create list of jobs with corresponding pattern
jpathList = makeListOfJPatternsWithSpecificVals(
PPListMap,
prefixfilepath=prefixfilepath,
key=lvar,
vals=lvals,
**kwargs)
for lineID, line_jobPattern in enumerate(jpathList):
line_label = '%s=%s' % (lvar, lvals[lineID])
if isinstance(ColorMap, dict):
for label in [line_label, line_jobPattern]:
try:
line_color = ColorMap[label]
except KeyError:
line_color = DefaultColorList[lineID]
else:
# Access next elt in ColorMap list
line_color = ColorMap[lineID]
plotSingleLineAcrossJobsByXVar(line_jobPattern,
label=line_label,
color=line_color,
lineID=lineID,
lvar=lvar,
**kwargs)
if loc is not None and len(jpathList) > 1:
pylab.legend(loc=loc, bbox_to_anchor=bbox_to_anchor)
if tickfontsize is not None:
pylab.tick_params(axis='both', which='major', labelsize=tickfontsize)
if savefilename is not None:
try:
pylab.show(block=False)
except TypeError:
pass # when using IPython notebook
pylab.savefig(savefilename, bbox_inches='tight', pad_inches=0)
elif doShowNow:
try:
pylab.show(block=True)
except TypeError:
pass # when using IPython notebook
def makePlot(muVals=[(0.01,0), (0.1,0), (1,0), (10,0)], doCorrection=1):
pylab.figure()
xgrid = np.linspace(-8, 8, 2000)
pylab.hold('on')
pylab.plot(xgrid, np.zeros_like(xgrid), ':', alpha=0.2)
for mu1, mu2 in muVals:
ygrid = calcBregDiv_Gauss1D(xgrid, mu1, mu2, doCorrection=doCorrection)
print ygrid.min()
pylab.plot(xgrid, ygrid, label='mu1=% 6.2f mu2=% 6.2f' % (mu1, mu2))
pylab.legend(loc='lower right')
pylab.xlim([xgrid.min(), xgrid.max()])
pylab.ylim([xgrid.min(), xgrid.max()])
pylab.xlabel('x')
if doCorrection:
pylab.ylabel('D(x, \mu) + correction')
else:
pylab.ylabel('D(x, \mu)')
if __name__ == "__main__":
for doC in [1]:
makePlot(muVals=[(0.01,0), (0.1,0), (1,0), (10,0)], doCorrection=doC)
pylab.savefig('BregDivGauss1D_fixedMean_doC=%d.eps' % (doC),
pad_inches=0, bbox_inches='tight')
makePlot(muVals=[(4+1,-2), (1,0), (4+1,2), (16+1,4)], doCorrection=doC)
pylab.savefig('BregDivGauss1D_fixedVar_doC=%d.eps' % (doC),
pad_inches=0, bbox_inches='tight')
makePlot(muVals=[(10,0), (4+1,2), (25+0.01,5)], doCorrection=doC)
pylab.savefig('BregDivGauss1D_general_doC=%d.eps' % (doC),
pad_inches=0, bbox_inches='tight')
pylab.show(block=True)
def plotJobs(jpaths,
legNames,
styles=None,
density=2,
xvar='laps',
yvar='evidence',
loc='upper right',
xmin=None,
xmax=None,
taskids=None,
savefilename=None,
tickfontsize=None,
bbox_to_anchor=None,
**kwargs):
''' Create line plots for provided jobs.
'''
nLines = len(jpaths)
if nLines == 0:
raise ValueError('Empty job list. Nothing to plot.')
nLeg = len(legNames)
for lineID in range(nLines):
if styles is None:
curStyle = dict(colorID=lineID)
else:
curStyle = styles[lineID]
task_kwargs = dict(**kwargs)
task_kwargs.update(curStyle)
plot_all_tasks_for_job(jpaths[lineID],
legNames[lineID],
xvar=xvar,
yvar=yvar,
taskids=taskids,
density=density,
**task_kwargs)
# Y-axis limit determination
# If we have "enough" data about the run beyond two full passes of dataset,
# we zoom in on the region of data beyond lap 2
if xvar == 'laps' and yvar == 'evidence':
xmax = 0
ymin = np.inf
ymin2 = np.inf
ymax = -np.inf
allRunsHaveXBeyond1 = True
for line in pylab.gca().get_lines():
xd = line.get_xdata()
yd = line.get_ydata()
if xd.size < 3:
allRunsHaveXBeyond1 = False
continue
posLap1 = np.searchsorted(xd, 1.0)
posLap2 = np.searchsorted(xd, 2.0)
if posLap1 < xd.size:
ymin = np.minimum(ymin, yd[posLap1])
ymax = np.maximum(ymax, yd[posLap1:].max())
if posLap2 < xd.size:
ymin2 = np.minimum(ymin2, yd[posLap2])
xmax = np.maximum(xmax, xd.max())
if xd.max() <= 1:
allRunsHaveXBeyond1 = False
if allRunsHaveXBeyond1 and xmax > 1.5:
# If all relevant curves extend beyond x=1, only show that part
xmin = 1.0 - 1e-5
else:
xmin = 0
if allRunsHaveXBeyond1 and ymin2 < ymax:
range1 = ymax - ymin
range2 = ymax - ymin2
if 10 * range2 < range1:
# Y values jump from lap1 to lap2 is enormous,
# so let's just show y values from lap2 onward...
ymin = ymin2
if (not np.allclose(ymax, ymin)) and allRunsHaveXBeyond1:
pylab.ylim([ymin, ymax + 0.1 * (ymax - ymin)])
pylab.xlim([xmin, xmax + .05 * (xmax - xmin)])
if loc is not None and len(jpaths) > 1:
pylab.legend(loc=loc, bbox_to_anchor=bbox_to_anchor)
if tickfontsize is not None:
pylab.tick_params(axis='both', which='major', labelsize=tickfontsize)
if savefilename is not None:
try:
pylab.show(block=False)
except TypeError:
pass # when using IPython notebook
pylab.savefig(savefilename, bbox_inches='tight', pad_inches=0)
else:
try:
pylab.show(block=True)
except TypeError:
pass # when using IPython notebook
pylab.xlim([-0.1, xgrid.max()])
pylab.ylim([-0.1, xgrid.max()])
pylab.xlabel('x')
pylab.ylabel('D(x, \mu)')
pylab.title('B=%s nu=%s' % (str(B), str(nu)))
if __name__ == "__main__":
'''
Data = StarCovarK5.get_data()
hmodel = makeModelForData(Data)
Mu = FSG.calcClusterMean_ZeroMeanGauss(Data.X, hmodel)
Div = FSG.calcBregDiv_ZeroMeanGauss(Data.X, Mu)
initSS, Info = FSG.initSSByBregDiv_ZeroMeanGauss(
Dslice=Data, curModel=hmodel, K=7,
b_initHardCluster=1)
'''
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--nu', type=str, default='3')
parser.add_argument('--B', type=str, default='1e-10')
args = parser.parse_args()
for B in args.B.split(','):
for nu in args.nu.split(','):
B = float(B)
nu = float(nu)
makePlot(justMahalTerm=0, nu=nu, B=B)
savefilename = 'BregDiv_B=%s_nu=%s.eps' % (str(B), str(nu))
pylab.savefig(savefilename, bbox_inches='tight', pad_inches=0)
pylab.show(block=True)