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 showAllTopicsInSingleImage(topics, compsToHighlight, **imshowArgs):
K, V = topics.shape
aspectR = V / float(K)
pylab.imshow(topics, 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])
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 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
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 plotCovMatFromHModel(hmodel,
compListToPlot=None,
compsToHighlight=None,
proba_thr=0.001,
ax_handle=None,
**kwargs):
''' Plot square image of covariance matrix for each component.
Parameters
-------
hmodel : bnpy HModel object
compListToPlot : array-like of integer IDs of components within hmodel
compsToHighlight : int or array-like
integer IDs to highlight
if None, all components get unique colors
if not None, only highlighted components get colors.
proba_thr : float
Minimum weight assigned to component in order to be plotted.
All components with weight below proba_thr are ignored.
'''
nRow = 2
nCol = int(np.ceil(hmodel.obsModel.K / 2.0))
if ax_handle is None:
ax_handle = pylab.subplots(nrows=nRow,
ncols=nCol,
figsize=(nCol * 2, nRow * 2))
else:
pylab.subplots(nrows=nRow, ncols=nCol, num=ax_handle.number)
if compsToHighlight is not None:
compsToHighlight = np.asarray(compsToHighlight)
if compsToHighlight.ndim == 0:
compsToHighlight = np.asarray([compsToHighlight])
else:
compsToHighlight = list()
if compListToPlot is None:
compListToPlot = np.arange(0, hmodel.obsModel.K)
if hmodel.allocModel.K == hmodel.obsModel.K:
w = hmodel.allocModel.get_active_comp_probs()
else:
w = np.ones(hmodel.obsModel.K)
colorID = 0
for plotID, kk in enumerate(compListToPlot):
if w[kk] < proba_thr and kk not in compsToHighlight:
Sigma = getEmptyCompSigmaImage(hmodel.obsModel.D)
clim = [0, 1]
else:
Sigma = hmodel.obsModel.get_covar_mat_for_comp(kk)
clim = [-.25, 1]
pylab.subplot(nRow, nCol, plotID + 1)
pylab.imshow(Sigma, interpolation='nearest', cmap='hot', clim=clim)
pylab.xticks([])
pylab.yticks([])
pylab.xlabel('%.2f' % (w[kk]))
if kk in compsToHighlight:
pylab.xlabel('***')
for emptyID in xrange(plotID + 1, nRow * nCol):
aH = pylab.subplot(nRow, nCol, emptyID + 1)
aH.axis('off')