def calcSummaryStats(Data, LP,
doPrecompEntropy=0,
doPrecompMergeEntropy=0,
mPairIDs=None,
trackDocUsage=0,
**kwargs):
''' Calculate summary statistics for given data slice and local params.
Returns
-------
SS : SuffStatBag
'''
if mPairIDs is None:
M = 0
else:
M = len(mPairIDs)
resp = LP['resp']
K = resp.shape[1]
startLocIDs = Data.doc_range[:-1]
StartStateCount = np.sum(resp[startLocIDs], axis=0)
N = np.sum(resp, axis=0)
if 'TransCount' in LP:
TransStateCount = np.sum(LP['TransCount'], axis=0)
else:
respPair = LP['respPair']
TransStateCount = np.sum(respPair, axis=0)
SS = SuffStatBag(K=K, D=Data.dim, M=M)
SS.setField('StartStateCount', StartStateCount, dims=('K'))
SS.setField('TransStateCount', TransStateCount, dims=('K', 'K'))
SS.setField('N', N, dims=('K'))
SS.setField('nDoc', Data.nDoc, dims=None)
if doPrecompEntropy or 'Htable' in LP:
# Compute entropy terms!
# 'Htable', 'Hstart' will both be in Mdict
Mdict = calcELBO_NonlinearTerms(Data=Data,
LP=LP, returnMemoizedDict=1)
SS.setELBOTerm('Htable', Mdict['Htable'], dims=('K', 'K'))
SS.setELBOTerm('Hstart', Mdict['Hstart'], dims=('K'))
if doPrecompMergeEntropy:
subHstart, subHtable = HMMUtil.PrecompMergeEntropy_SpecificPairs(
LP, Data, mPairIDs)
SS.setMergeTerm('Hstart', subHstart, dims=('M'))
SS.setMergeTerm('Htable', subHtable, dims=('M', 2, 'K'))
SS.mPairIDs = np.asarray(mPairIDs)
if trackDocUsage:
# Track how often topic appears in a seq. with mass > thresh.
DocUsage = np.zeros(K)
for n in range(Data.nDoc):
start = Data.doc_range[n]
stop = Data.doc_range[n + 1]
DocUsage += np.sum(LP['resp'][start:stop], axis=0) > 0.01
SS.setSelectionTerm('DocUsageCount', DocUsage, dims='K')
return SS
