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 plotExampleBarsDocs(Data, docIDsToPlot=None, figID=None,
vmax=None, nDocToPlot=16, doShowNow=False,
seed=0, randstate=np.random.RandomState(0),
xlabels=None,
W=1, H=1,
**kwargs):
kwargs['vmin'] = 0
kwargs['interpolation'] = 'nearest'
if vmax is not None:
kwargs['vmax'] = vmax
if seed is not None:
randstate = np.random.RandomState(seed)
V = Data.vocab_size
sqrtV = int(np.sqrt(V))
assert np.allclose(sqrtV * sqrtV, V)
if docIDsToPlot is not None:
nDocToPlot = len(docIDsToPlot)
else:
size = np.minimum(Data.nDoc, nDocToPlot)
docIDsToPlot = randstate.choice(Data.nDoc, size=size, replace=False)
ncols = 5
nrows = int(np.ceil(nDocToPlot / float(ncols)))
if vmax is None:
DocWordArr = Data.getDocTypeCountMatrix()
vmax = int(np.max(np.percentile(DocWordArr, 98, axis=0)))
if figID is None:
figH, ha = pylab.subplots(nrows=nrows, ncols=ncols,
figsize=(ncols * W, nrows * H))
for plotPos, docID in enumerate(docIDsToPlot):
start = Data.doc_range[docID]
stop = Data.doc_range[docID + 1]
wIDs = Data.word_id[start:stop]
wCts = Data.word_count[start:stop]
docWordHist = np.zeros(V)
docWordHist[wIDs] = wCts
squareIm = np.reshape(docWordHist, (sqrtV, sqrtV))
pylab.subplot(nrows, ncols, plotPos + 1)
pylab.imshow(squareIm, **kwargs)
pylab.axis('image')
pylab.xticks([])
pylab.yticks([])
if xlabels is not None:
pylab.xlabel(xlabels[plotPos])
# Disable empty plots!
for kdel in xrange(plotPos + 2, nrows * ncols + 1):
aH = pylab.subplot(nrows, ncols, kdel)
aH.axis('off')
# Fix margins between subplots
pylab.subplots_adjust(wspace=0.04, hspace=0.04, left=0.01, right=0.99,
top=0.99, bottom=0.01)
if doShowNow:
pylab.show()
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 showTopicsAsSquareImages(topics,
activeCompIDs=None,
compsToHighlight=None,
compListToPlot=None,
xlabels=[],
Kmax=50,
ncols=5,
W=1, H=1, figH=None,
**kwargs):
global imshowArgs
local_imshowArgs = dict(**imshowArgs)
for key in local_imshowArgs:
if key in kwargs:
local_imshowArgs[key] = kwargs[key]
if len(xlabels) > 0:
H = 1.5 * H
K, V = topics.shape
sqrtV = int(np.sqrt(V))
assert np.allclose(sqrtV, np.sqrt(V))
if compListToPlot is None:
compListToPlot = np.arange(0, K)
if activeCompIDs is None:
activeCompIDs = np.arange(0, K)
compsToHighlight = np.asarray(compsToHighlight)
if compsToHighlight.ndim == 0:
compsToHighlight = np.asarray([compsToHighlight])
# Create Figure
Kplot = np.minimum(len(compListToPlot), Kmax)
#ncols = 5 # int(np.ceil(Kplot / float(nrows)))
nrows = int(np.ceil(Kplot / float(ncols)))
if figH is None:
# Make a new figure
figH, ha = pylab.subplots(nrows=nrows, ncols=ncols,
figsize=(ncols * W, nrows * H))
else:
# Use existing figure
# TODO: Find a way to make this call actually change the figsize
figH, ha = pylab.subplots(nrows=nrows, ncols=ncols,
figsize=(ncols * W, nrows * H),
num=figH.number)
for plotID, compID in enumerate(compListToPlot):
if plotID >= Kmax:
print 'DISPLAY LIMIT EXCEEDED. Showing %d/%d components' \
% (plotID, len(activeCompIDs))
break
if compID not in activeCompIDs:
aH = pylab.subplot(nrows, ncols, plotID + 1)
aH.axis('off')
continue
kk = np.flatnonzero(compID == activeCompIDs)[0]
topicIm = np.reshape(topics[kk, :], (sqrtV, sqrtV))
ax = pylab.subplot(nrows, ncols, plotID + 1)
pylab.imshow(topicIm, **local_imshowArgs)
pylab.xticks([])
pylab.yticks([])
# Draw colored border around highlighted topics
if compID in compsToHighlight:
[i.set_color('green') for i in ax.spines.itervalues()]
[i.set_linewidth(3) for i in ax.spines.itervalues()]
if xlabels is not None:
if len(xlabels) > 0:
pylab.xlabel(xlabels[plotID], fontsize=11)
# Disable empty plots!
for kdel in xrange(plotID + 2, nrows * ncols + 1):
aH = pylab.subplot(nrows, ncols, kdel)
aH.axis('off')
# Fix margins between subplots
pylab.subplots_adjust(
wspace=0.1,
hspace=0.1 * nrows,
left=0.001, right=0.999,
bottom=0.1, top=0.999)
return figH
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