def calcHrespForSpecificMergePairs(LP, Data, mPairIDs):
''' Calculate resp entropy terms for all candidate merge pairs
Returns
---------
Hresp : 1D array, size M
where each entry corresponds to one merge pair in mPairIDs
'''
assert mPairIDs is not None
if 'resp' in LP:
N = LP['resp'].shape[0]
if hasattr(Data, 'word_count') and N == Data.word_count.size:
m_Hresp = -1 * calcRlogRdotv_specificpairs(
LP['resp'], Data.word_count, mPairIDs)
else:
m_Hresp = -1 * calcRlogR_specificpairs(LP['resp'], mPairIDs)
else:
if LP['nnzPerRow'] == 1:
return None
N = LP['spR'].shape[0]
if hasattr(Data, 'word_count') and N == Data.word_count.size:
m_Hresp = calcSparseMergeRlogRdotv(
spR_csr=LP['spR'],
nnzPerRow=LP['nnzPerRow'],
v=Data.word_count,
mPairIDs=mPairIDs)
else:
m_Hresp = calcSparseMergeRlogR(
spR_csr=LP['spR'],
nnzPerRow=LP['nnzPerRow'],
mPairIDs=mPairIDs)
assert m_Hresp.size == len(mPairIDs)
return m_Hresp
def calcSummaryStats(Data,
LP,
doPrecompEntropy=False,
doPrecompMergeEntropy=False,
mPairIDs=None,
mergePairSelection=None,
trackDocUsage=False,
**kwargs):
""" Calculate sufficient statistics for global updates.
Parameters
-------
Data : bnpy data object
LP : local param dict with fields
resp : Data.nObs x K array,
where resp[n,k] = posterior resp of comp k
doPrecompEntropy : boolean flag
indicates whether to precompute ELBO terms in advance
used for memoized learning algorithms (moVB)
doPrecompMergeEntropy : boolean flag
indicates whether to precompute ELBO terms in advance
for certain merge candidates.
Returns
-------
SS : SuffStatBag with K components
Summarizes for this mixture model, with fields
* N : 1D array, size K
N[k] = expected number of items assigned to comp k
Also has optional ELBO field when precompELBO is True
* ElogqZ : 1D array, size K
Vector of entropy contributions from each comp.
ElogqZ[k] = \sum_{n=1}^N resp[n,k] log resp[n,k]
Also has optional Merge field when precompMergeELBO is True
* ElogqZ : 2D array, size K x K
Each term is scalar entropy of merge candidate
"""
if mPairIDs is not None and len(mPairIDs) > 0:
M = len(mPairIDs)
else:
M = 0
if 'resp' in LP:
Nvec = np.sum(LP['resp'], axis=0)
K = Nvec.size
else:
# Sparse assignment case
Nvec = as1D(toCArray(LP['spR'].sum(axis=0)))
K = LP['spR'].shape[1]
if hasattr(Data, 'dim'):
SS = SuffStatBag(K=K, D=Data.dim, M=M)
else:
SS = SuffStatBag(K=K, D=Data.vocab_size, M=M)
SS.setField('N', Nvec, dims=('K'))
if doPrecompEntropy:
Mdict = calcELBO_NonlinearTerms(LP=LP, returnMemoizedDict=1)
if type(Mdict['Hresp']) == float:
# SPARSE HARD ASSIGNMENTS
SS.setELBOTerm('Hresp', Mdict['Hresp'], dims=None)
else:
SS.setELBOTerm('Hresp', Mdict['Hresp'], dims=('K', ))
if doPrecompMergeEntropy:
m_Hresp = None
if 'resp' in LP:
m_Hresp = -1 * NumericUtil.calcRlogR_specificpairs(
LP['resp'], mPairIDs)
elif 'spR' in LP:
if LP['nnzPerRow'] > 1:
m_Hresp = calcSparseMergeRlogR(spR_csr=LP['spR'],
nnzPerRow=LP['nnzPerRow'],
mPairIDs=mPairIDs)
else:
raise ValueError("Need resp or spR in LP")
if m_Hresp is not None:
assert m_Hresp.size == len(mPairIDs)
SS.setMergeTerm('Hresp', m_Hresp, dims=('M'))
if trackDocUsage:
Usage = np.sum(LP['resp'] > 0.01, axis=0)
SS.setSelectionTerm('DocUsageCount', Usage, dims='K')
return SS