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 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 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')
def plotSingleLineAcrossJobsByXVar(jpathPattern,
label='',
xvar=None,
xvals=None,
xlabel=None,
yvar='evidence',
lineStyle='.-',
taskids='all',
lineID=0,
lvar='',
**kwargs):
''' Create line plot in current figure for job matching the pattern
Iterates over each xval in provided list of values.
Each one corresponds to a single saved job.
Post Condition
--------------
Current axes have one line added.
'''
prefixfilepath = os.path.sep.join(jpathPattern.split(os.path.sep)[:-1])
PPListMap = makePPListMapFromJPattern(jpathPattern)
if xvals is None:
xvals = PPListMap[xvar]
xs = np.zeros(len(xvals))
ys = np.zeros(len(xvals))
jpathList = makeListOfJPatternsWithSpecificVals(
PPListMap,
prefixfilepath=prefixfilepath,
key=xvar,
vals=xvals,
**kwargs)
plotargs = copy.deepcopy(DefaultLinePlotKwArgs)
# Plot all tasks as faint points with no connections
for i, jobpath in enumerate(jpathList):
if not os.path.exists(jobpath):
raise ValueError("PATH NOT FOUND: %s" % (jobpath))
x = float(xvals[i])
for key in plotargs:
if key in kwargs:
plotargs[key] = kwargs[key]
plotargs['markeredgecolor'] = plotargs['color']
alltaskids = BNPYArgParser.parse_task_ids(jobpath, taskids)
for tid in alltaskids:
y = loadYValFromDisk(jobpath, tid, yvar=yvar)
pylab.plot(x, y, '.', **plotargs)
# Plot top-ranked tasks as solid points connected by line
for i, jobpath in enumerate(jpathList):
rankTasksForSingleJobOnDisk(os.path.join(jobpath))
x = float(xvals[i])
y = loadYValFromDisk(jobpath, '.best', yvar=yvar)
assert isinstance(x, float)
assert isinstance(y, float)
xs[i] = x
ys[i] = y
plotargs = copy.deepcopy(DefaultLinePlotKwArgs)
for key in plotargs:
if key in kwargs:
plotargs[key] = kwargs[key]
plotargs['markeredgecolor'] = plotargs['color']
plotargs['label'] = label
pylab.plot(xs, ys, lineStyle, **plotargs)
if lineID == 0:
if xlabel is None:
xlabel = xvar
pylab.xlabel(xlabel)
pylab.ylabel(LabelMap[yvar])
def plot_all_tasks_for_job(jobpath, label, taskids=None,
color=None,
colorID=0,
density=2,
yvar='evidence',
markersize=10,
linewidth=2,
linestyle='-',
drawLineToXMax=None,
showOnlyAfterLap=0,
xvar='laps',
**kwargs):
''' Create line plot in current figure for each task/run of jobpath
'''
if not os.path.exists(jobpath):
if not jobpath.startswith(os.path.sep):
jobpath_tmp = os.path.join(os.environ['BNPYOUTDIR'], jobpath)
if not os.path.exists(jobpath_tmp):
raise ValueError("PATH NOT FOUND: %s" % (jobpath))
jobpath = jobpath_tmp
if color is None:
color = Colors[colorID % len(Colors)]
taskids = BNPYArgParser.parse_task_ids(jobpath, taskids)
if yvar == 'hamming-distance':
yspfile = os.path.join(jobpath, taskids[0], yvar + '-saved-params.txt')
if xvar == 'laps' and os.path.isfile(yspfile):
xvar = 'laps-saved-params'
for tt, taskid in enumerate(taskids):
xs = None
ys = None
laps = None
try:
var_ext = ''
ytxtfile = os.path.join(jobpath, taskid, yvar + '.txt')
if not os.path.isfile(ytxtfile):
var_ext = '-saved-params'
ytxtfile = os.path.join(
jobpath, taskid, yvar + var_ext + '.txt')
ys = np.loadtxt(ytxtfile)
if ytxtfile.count('saved-params'):
laptxtfile = os.path.join(jobpath, taskid, 'laps-saved-params.txt')
else:
laptxtfile = os.path.join(jobpath, taskid, 'laps.txt')
except IOError as e:
# TODO: when is this code needed?
# xs, ys = loadXYFromTopicModelFiles(jobpath, taskid)
try:
if isinstance(xs, np.ndarray) and yvar.count('Keff'):
ys = loadKeffForTask(
os.path.join(jobpath, taskid), **kwargs)
assert xs.size == ys.size
else:
# Heldout metrics
xs, ys = loadXYFromTopicModelSummaryFiles(
jobpath, taskid, xvar=xvar, yvar=yvar)
if showOnlyAfterLap and showOnlyAfterLap > 0:
laps, _ = loadXYFromTopicModelSummaryFiles(
jobpath, taskid, xvar='laps', yvar=yvar)
except ValueError:
try:
xs, ys = loadXYFromTopicModelSummaryFiles(jobpath, taskid)
except ValueError:
raise e
if yvar == 'hamming-distance' or yvar == 'Keff':
if xvar == 'laps-saved-params':
# fix off-by-one error, if we save an extra dist on final lap
if xs.size == ys.size - 1:
ys = ys[:-1]
elif ys.size == xs.size - 1:
xs = xs[:-1] # fix off-by-one error, if we quit early
elif xs.size != ys.size:
# Try to subsample both time series at laps where they
# intersect
laps_x = np.loadtxt(os.path.join(jobpath, taskid, 'laps.txt'))
laps_y = np.loadtxt(os.path.join(jobpath, taskid,
'laps-saved-params.txt'))
assert xs.size == laps_x.size
if ys.size == laps_y.size - 1:
laps_y = laps_y[:-1]
xs = xs[np.in1d(laps_x, laps_y)]
ys = ys[np.in1d(laps_y, laps_x)]
if xs.size != ys.size:
raise ValueError('Dimension mismatch. len(xs)=%d, len(ys)=%d'
% (xs.size, ys.size))
# Cleanup laps data. Verify that it is sorted, with no collisions.
if xvar == 'laps':
diff = xs[1:] - xs[:-1]
goodIDs = np.flatnonzero(diff >= 0)
if len(goodIDs) < xs.size - 1:
print( 'WARNING: looks like multiple runs writing to this file!')
print( jobpath)
print( 'Task: ', taskid)
print( len(goodIDs), xs.size - 1)
xs = np.hstack([xs[goodIDs], xs[-1]])
ys = np.hstack([ys[goodIDs], ys[-1]])
if xvar == 'laps' and yvar == 'evidence':
mask = xs >= 1.0
xs = xs[mask]
ys = ys[mask]
elif showOnlyAfterLap:
# print "Filtering for data recorded at lap >= %s" % (
# showOnlyAfterLap)
if laps is None:
laps = np.loadtxt(laptxtfile)
mask = laps >= showOnlyAfterLap
xs = xs[mask]
ys = ys[mask]
# Force plot density (data points per lap) to desired specification
# This avoids making plots that have huge file sizes,
# due to too much content in the given display space
if xvar == 'laps' and xs.size > 20 and np.sum(xs > 5) > 10:
if (xs[-1] - xs[9]) != 0:
curDensity = (xs.size - 10) / (xs[-1] - xs[9])
else:
curDensity = density
while curDensity > density and xs.size > 11:
# Thin xs and ys data by a factor of 2
# while preserving the first 10 data points
xs = np.hstack([xs[:10], xs[10::2]])
ys = np.hstack([ys[:10], ys[10::2]])
curDensity = (xs.size - 10) / (xs[-1] - xs[9])
plotargs = dict(
markersize=markersize,
linewidth=linewidth,
linestyle=linestyle,
label=None,
color=color, markeredgecolor=color)
for key in kwargs:
if key in plotargs:
plotargs[key] = kwargs[key]
if tt == 0:
plotargs['label'] = label
pylab.plot(xs, ys, **plotargs)
if drawLineToXMax:
xs_dashed = np.asarray([xs[-1], drawLineToXMax])
ys_dashed = np.asarray([ys[-1], ys[-1]])
plotargs['label'] = None
pylab.plot(xs_dashed, ys_dashed, '--', **plotargs)
pylab.xlabel(LabelMap[xvar])
if yvar in LabelMap:
yLabelStr = LabelMap[yvar]
if yvar == 'Keff' and 'effCountThr' in kwargs:
effCountThr = float(kwargs['effCountThr'])
yLabelStr = yLabelStr + ' > %s' % (str(effCountThr))
pylab.ylabel(yLabelStr)
def plot_all_tasks_for_job(jobpath,
label,
taskids=None,
lineType='.-',
spreadLineType='--',
color=None,
yvar='avgLikScore',
xvar='laps',
markersize=10,
linewidth=2,
minLap=0,
showFinalPt=0,
fileSuffix='PredLik.mat',
xjitter=None,
prefix='predlik',
colorID=0,
**kwargs):
''' Create line plot in current figure for each task/run of jobpath
'''
if not os.path.exists(jobpath):
print('PATH NOT FOUND', jobpath)
return None
if not yvar.startswith('avg') and yvar.count('Kactive') == 0:
yvar = 'avg' + yvar
if not yvar.endswith('Score') and yvar.count('Kactive') == 0:
yvar = yvar + 'Score'
if color is None:
color = Colors[colorID % len(Colors)]
taskids = BNPYArgParser.parse_task_ids(jobpath, taskids)
for tt, taskid in enumerate(taskids):
taskoutpath = os.path.join(jobpath, taskid)
hpaths = glob.glob(os.path.join(taskoutpath, '*' + fileSuffix))
txtpaths = glob.glob(os.path.join(taskoutpath, 'predlik-*.txt'))
ys_hi = None
ys_lo = None
if len(txtpaths) > 0:
if fileSuffix.endswith('.txt'):
suffix = '-' + fileSuffix
else:
suffix = '.txt'
if xvar.count('lap'):
xs = np.loadtxt(
os.path.join(taskoutpath, prefix + '-lapTrain.txt'))
elif xvar.count('K'):
xs = np.loadtxt(os.path.join(taskoutpath, prefix + '-K.txt'))
elif xvar.count('time'):
xs = np.loadtxt(
os.path.join(taskoutpath, prefix + '-timeTrain.txt'))
else:
raise ValueError("Unrecognized xvar: " + xvar)
if yvar.count('Kactive') and not yvar.count('Percentile'):
ys = np.loadtxt(
os.path.join(taskoutpath,
prefix + '-' + yvar + 'Percentile50.txt'))
ys_lo = np.loadtxt(
os.path.join(taskoutpath,
prefix + '-' + yvar + 'Percentile10.txt'))
ys_hi = np.loadtxt(
os.path.join(taskoutpath,
prefix + '-' + yvar + 'Percentile90.txt'))
else:
ys = np.loadtxt(
os.path.join(taskoutpath, prefix + '-' + yvar + suffix))
if minLap > 0 and taskoutpath.count('fix'):
mask = laps > minLap
xs = xs[mask]
ys = ys[mask]
elif len(hpaths) > 0:
hpaths.sort()
basenames = [x.split(os.path.sep)[-1] for x in hpaths]
xs = np.asarray([float(x[3:11]) for x in basenames])
ys = np.zeros_like(xs)
for ii, hpath in enumerate(hpaths):
MatVars = scipy.io.loadmat(hpath)
ys[ii] = float(MatVars['avgPredLL'])
else:
raise ValueError('Pred Lik data unavailable for job\n' +
taskoutpath)
plotargs = dict(
markersize=markersize,
linewidth=linewidth,
label=None,
color=color,
markeredgecolor=color,
)
plotargs.update(kwargs)
if tt == 0:
plotargs['label'] = label
if xjitter is not None:
xs = xs + xjitter
pylab.plot(xs, ys, lineType, **plotargs)
if ys_lo is not None:
del plotargs['label']
pylab.plot(xs, ys_lo, spreadLineType, **plotargs)
pylab.plot(xs, ys_hi, spreadLineType, **plotargs)
if showFinalPt:
pylab.plot(xs[-1], ys[-1], '.', **plotargs)
pylab.xlabel(XLabelMap[xvar])
pylab.ylabel(YLabelMap[yvar])