def plotDataAsSquareImages(Data,
unitIDsToPlot=None,
figID=None,
nPlots=16,
doShowNow=False,
seed=0,
randstate=np.random.RandomState(0),
**kwargs):
if seed is not None:
randstate = np.random.RandomState(seed)
if figID is None:
pylab.figure()
V = Data.dim
assert isPerfectSquare(V)
sqrtV = int(np.sqrt(V))
if unitIDsToPlot is not None:
nPlots = len(unitIDsToPlot)
else:
size = np.minimum(Data.nObs, nPlots)
unitIDsToPlot = randstate.choice(Data.nObs, size=size, replace=False)
nRows = np.floor(np.sqrt(nPlots))
nCols = np.ceil(nPlots / nRows)
for plotPos, unitID in enumerate(unitIDsToPlot):
squareIm = np.reshape(Data.X[unitID], (sqrtV, sqrtV))
pylab.subplot(nRows, nCols, plotPos + 1)
pylab.imshow(squareIm, **imshowArgs)
pylab.axis('image')
pylab.xticks([])
pylab.yticks([])
pylab.tight_layout()
if doShowNow:
pylab.show()
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 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)')
def makePlot(muVals=[0.01, 0.1, 1, 10], B=1e-10, nu=2, justMahalTerm=0):
pylab.figure()
xgrid = np.linspace(0, 8, 2000)
pylab.hold('on')
for mu in muVals:
ygrid = calcBregDiv_ZeroMean(xgrid,
mu,
B=B,
nu=nu,
justMahalTerm=justMahalTerm)
pylab.plot(xgrid, ygrid, linewidth=2, label='\mu=%6.2f' % (mu))
pylab.legend(loc='upper right')
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)))
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 plotBarsFromHModel(
hmodel,
Data=None,
doShowNow=False,
figH=None,
doSquare=1,
xlabels=[],
compsToHighlight=None,
compListToPlot=None,
activeCompIDs=None,
Kmax=50,
width=6,
height=3,
vmax=None,
block=0, # unused
jobname='', # unused
**kwargs):
if vmax is not None:
kwargs['vmax'] = vmax
if hasattr(hmodel.obsModel, 'Post'):
lam = hmodel.obsModel.Post.lam
topics = lam / lam.sum(axis=1)[:, np.newaxis]
else:
topics = hmodel.obsModel.EstParams.phi.copy()
# Determine intensity scale for topic-word image
global imshowArgs
if vmax is not None:
imshowArgs['vmax'] = vmax
else:
imshowArgs['vmax'] = 1.5 * np.percentile(topics, 95)
if doSquare:
figH = showTopicsAsSquareImages(topics,
activeCompIDs=activeCompIDs,
compsToHighlight=compsToHighlight,
compListToPlot=compListToPlot,
Kmax=Kmax,
figH=figH,
xlabels=xlabels,
**kwargs)
else:
if figH is None:
figH = pylab.figure(figsize=(width, height))
else:
pylab.axes(figH)
showAllTopicsInSingleImage(topics, compsToHighlight, **kwargs)
if doShowNow:
pylab.show()
return figH
def plotCompsAsRowsInSingleImage(phi,
compsToHighlight,
width=6,
height=3,
**kwargs):
figH = pylab.figure(figsize=(width, height))
K, D = phi.shape
aspectR = D / float(K)
pylab.imshow(phi, aspect=aspectR, **imshowArgs)
if compsToHighlight is not None:
ks = np.asarray(compsToHighlight)
if ks.ndim == 0:
ks = np.asarray([ks])
pylab.yticks(ks, ['**** %d' % (k) for k in ks])
return figH