def inferDocTopicCountForDocFromHModel(docData, hmodel, alpha=0.5, **LPkwargs):
# Lik_d : 2D array, size N x K
# Each row is non-negative
LP = hmodel.obsModel.calc_local_params(docData)
Lik_d = LP['E_log_soft_ev']
Lik_d -= Lik_d.max(axis=1)[:, np.newaxis]
np.exp(Lik_d, out=Lik_d)
# alphaEbeta : 1D array, size K
alphaEbeta = alpha * hmodel.allocModel.get_active_comp_probs()
DocTopicCount_d, _, _, Info = calcLocalParams_SingleDoc(1.0,
Lik_d,
alphaEbeta,
alphaEbetaRem=None,
**LPkwargs)
assert np.allclose(DocTopicCount_d.sum(), Lik_d.shape[0])
return DocTopicCount_d, Info
def inferDocTopicCountForDoc(word_id, word_ct, topics, probs, alpha,
**LPkwargs):
K = probs.size
K2, W = topics.shape
assert K == K2
# topics : 2D array, vocab_size x K
# Each col is non-negative and sums to one.
topics = topics.T.copy()
assert np.allclose(np.sum(topics, axis=0), 1.0)
# Lik_d : 2D array, size N x K
# Each row is non-negative
Lik_d = np.asarray(topics[word_id, :].copy(), dtype=np.float64)
# alphaEbeta : 1D array, size K
alphaEbeta = np.asarray(alpha * probs, dtype=np.float64)
DocTopicCount_d, _, _, Info = calcLocalParams_SingleDoc(word_ct,
Lik_d,
alphaEbeta,
alphaEbetaRem=None,
**LPkwargs)
assert np.allclose(DocTopicCount_d.sum(), word_ct.sum())
return DocTopicCount_d, Info
def calcLocalParams(Data,
LP,
alphaEbeta=None,
alphaEbetaRem=None,
alpha=None,
initDocTopicCountLP='setDocProbsToEGlobalProbs',
cslice=(0, None),
nnzPerRowLP=0,
doSparseOnlyAtFinalLP=0,
**kwargs):
''' Calculate all local parameters for provided dataset under a topic model
Kwargs
------
initDocTopicCountLP : str, must be one of the options below
'useDocTopicCountIfProvided'
If provided LP contains 'DocTopicCount' array,
will use that to initialize the per-doc counts.
Otherwise, will default back to 'setDocProbsToEGlobalProbs'.
'setDocProbsToEGlobalProbs'
Initialize doc-topic probas directly using global probas.
Recommended for the first time a document is processed.
'setDocTopicCountToAllZeros'
Initialize doc-topic counts to all zeros.
Returns
-------
LP : dict
Local parameter fields
resp : 2D array, N x K
DocTopicCount : 2D array, nDoc x K
model-specific fields for doc-topic probabilities
'''
assert isinstance(cslice, tuple)
if len(cslice) != 2:
cslice = (0, None)
elif cslice[0] is None:
cslice = (0, None)
nDoc = calcNumDocFromSlice(Data, cslice)
if 'obsModelName' in LP:
obsModelName = LP['obsModelName']
elif hasattr(Data, 'word_count'):
obsModelName = 'Mult'
else:
obsModelName = 'Gauss'
# Unpack the problem size
N, K = LP['E_log_soft_ev'].shape
# Prepare the initial DocTopicCount matrix,
# Useful for warm starts of the local step.
initDocTopicCount = None
if 'DocTopicCount' in LP:
if LP['DocTopicCount'].shape == (nDoc, K):
initDocTopicCount = LP['DocTopicCount'].copy()
sumRespTilde = np.zeros(N)
DocTopicCount = np.zeros((nDoc, K))
DocTopicProb = np.zeros((nDoc, K))
# Prepare the extra terms
if alphaEbeta is None:
assert alpha is not None
alphaEbeta = alpha * np.ones(K)
else:
alphaEbeta = alphaEbeta[:K]
# Prepare the likelihood matrix
# Make sure it is C-contiguous, so that matrix ops are very fast
Lik = np.asarray(LP['E_log_soft_ev'], order='C')
if (nnzPerRowLP <= 0 or nnzPerRowLP >= K) or doSparseOnlyAtFinalLP:
DO_DENSE = True
# Dense Representation
Lik -= Lik.max(axis=1)[:, np.newaxis]
NumericUtil.inplaceExp(Lik)
else:
DO_DENSE = False
nnzPerRowLP = np.minimum(nnzPerRowLP, K)
spR_data = np.zeros(N * nnzPerRowLP, dtype=np.float64)
spR_colids = np.zeros(N * nnzPerRowLP, dtype=np.int32)
slice_start = Data.doc_range[cslice[0]]
if not DO_DENSE and obsModelName.count('Mult'):
if initDocTopicCountLP.count('fastfirstiter'):
init_spR = calcInitSparseResp(LP,
alphaEbeta,
nnzPerRowLP=nnzPerRowLP,
**kwargs)
AggInfo = dict()
AggInfo['maxDiff'] = np.zeros(Data.nDoc)
AggInfo['iter'] = np.zeros(Data.nDoc, dtype=np.int32)
if 'restartLP' in kwargs and kwargs['restartLP']:
AggInfo['nRestartsAccepted'] = np.zeros(1, dtype=np.int32)
AggInfo['nRestartsTried'] = np.zeros(1, dtype=np.int32)
else:
AggInfo['nRestartsAccepted'] = None
AggInfo['nRestartsTried'] = None
for d in range(nDoc):
start = Data.doc_range[cslice[0] + d]
stop = Data.doc_range[cslice[0] + d + 1]
if hasattr(Data, 'word_count') and obsModelName.count('Bern'):
lstart = d * Data.vocab_size
lstop = (d + 1) * Data.vocab_size
else:
lstart = start - slice_start
lstop = stop - slice_start
if hasattr(Data, 'word_count') and not obsModelName.count('Bern'):
wc_d = Data.word_count[start:stop].copy()
else:
wc_d = 1.0
initDTC_d = None
if initDocTopicCountLP == 'useDocTopicCountIfProvided':
if initDocTopicCount is not None:
if DO_DENSE:
initDTC_d = initDocTopicCount[d]
else:
DocTopicCount[d] = initDocTopicCount[d]
else:
initDocTopicCountLP = 'setDocProbsToEGlobalProbs'
if not DO_DENSE and initDocTopicCountLP.count('fastfirstiter'):
if obsModelName.count('Mult'):
DocTopicCount[d, :] = wc_d * init_spR[Data.word_id[start:stop]]
if not DO_DENSE:
m_start = nnzPerRowLP * start
m_stop = nnzPerRowLP * stop
# SPARSE RESP
calcSparseLocalParams_SingleDoc(
wc_d,
Lik[lstart:lstop],
alphaEbeta,
topicCount_d_OUT=DocTopicCount[d],
spResp_data_OUT=spR_data[m_start:m_stop],
spResp_colids_OUT=spR_colids[m_start:m_stop],
nnzPerRowLP=nnzPerRowLP,
initDocTopicCountLP=initDocTopicCountLP,
d=d,
maxDiffVec=AggInfo['maxDiff'],
numIterVec=AggInfo['iter'],
nRAcceptVec=AggInfo['nRestartsAccepted'],
nRTrialVec=AggInfo['nRestartsTried'],
**kwargs)
else:
Lik_d = Lik[lstart:lstop].copy() # Local copy
(DocTopicCount[d], DocTopicProb[d],
sumRespTilde[lstart:lstop], Info_d) \
= calcLocalParams_SingleDoc(
wc_d, Lik_d, alphaEbeta, alphaEbetaRem,
DocTopicCount_d=initDTC_d,
initDocTopicCountLP=initDocTopicCountLP,
**kwargs)
AggInfo = updateConvergenceInfoForDoc_d(d, Info_d, AggInfo, Data)
#if initDocTopicCountLP.startswith('fast'):
# AggInfo['time_extra'] = telapsed
LP['DocTopicCount'] = DocTopicCount
if hasattr(Data, 'word_count') and LP['obsModelName'] == 'MultObsModel':
if cslice is None or (cslice[0] == 0 and cslice[1] is None):
assert np.allclose(np.sum(DocTopicCount), np.sum(Data.word_count))
LP = updateLPGivenDocTopicCount(LP, DocTopicCount, alphaEbeta,
alphaEbetaRem)
if DO_DENSE:
LP = updateLPWithResp(LP,
Data,
Lik,
DocTopicProb,
sumRespTilde,
cslice,
nnzPerRowLP=nnzPerRowLP,
doSparseOnlyAtFinalLP=doSparseOnlyAtFinalLP)
else:
indptr = np.arange(0, (N + 1) * nnzPerRowLP,
nnzPerRowLP,
dtype=np.int32)
LP['spR'] = scipy.sparse.csr_matrix((spR_data, spR_colids, indptr),
shape=(N, K))
LP['nnzPerRow'] = nnzPerRowLP
LP['Info'] = AggInfo
writeLogMessageForManyDocs(Data, AggInfo, LP, **kwargs)
return LP