def calcLocalParams(Data,
LP,
aModel,
methodLP='scratch',
routineLP='simple',
**kwargs):
''' Calculate all local parameters for provided dataset under a topic model
Returns
-------
LP : dict of local params, with fields
* DocTopicCount
* resp
* model-specific fields for doc-topic probabilities
'''
kwargs['methodLP'] = methodLP
## Prepare the log soft ev matrix
## Make sure it is C-contiguous, so that matrix ops are very fast
Lik = np.asarray(LP['E_log_soft_ev'], order='C')
Lik -= Lik.max(axis=1)[:, np.newaxis]
NumericUtil.inplaceExp(Lik)
K = Lik.shape[1]
hasDocTopicCount = 'DocTopicCount' in LP \
and LP['DocTopicCount'].shape == (Data.nDoc, K)
if methodLP == 'memo' and hasDocTopicCount:
initDocTopicCount = LP['DocTopicCount']
else:
initDocTopicCount = None
if routineLP == 'simple':
DocTopicCount, Prior, sumR, AI = calcDocTopicCountForData_Simple(
Data, aModel, Lik, initDocTopicCount=initDocTopicCount, **kwargs)
elif routineLP == 'fast':
DocTopicCount, Prior, sumR = calcDocTopicCountForData_Fast(
Data, aModel, Lik, initDocTopicCount=initDocTopicCount, **kwargs)
else:
raise ValueError('Unrecognized routine ' + routineLP)
LP['DocTopicCount'] = DocTopicCount
LP = aModel.updateLPGivenDocTopicCount(LP, DocTopicCount)
LP = updateLPWithResp(LP, Data, Lik, Prior, sumR)
if kwargs['restartremovejunkLP'] == 1:
LP, RInfo = removeJunkTopicsFromAllDocs(aModel, Data, LP, **kwargs)
if 'lapFrac' in kwargs and 'batchID' in kwargs:
if hasattr(Data, 'batchID') and Data.batchID == kwargs['batchID']:
perc = [0, 5, 10, 50, 90, 95, 100]
siter = ' '.join(
['%4d' % np.percentile(AI['iter'], p) for p in perc])
sdiff = ['%6.4f' % np.percentile(AI['maxDiff'], p) for p in perc]
sdiff = ' '.join(sdiff)
nFail = np.sum(AI['maxDiff'] > kwargs['convThrLP'])
msg = '%4.2f %3d %4d %s %s' % (kwargs['lapFrac'], Data.batchID,
nFail, siter, sdiff)
if kwargs['restartremovejunkLP'] == 1:
msg += " %4d/%4d %4d/%4d" % (
RInfo['nDocRestartsAccepted'], RInfo['nDocRestartsTried'],
RInfo['nRestartsAccepted'], RInfo['nRestartsTried'])
elif kwargs['restartremovejunkLP'] == 2:
msg += " %4d/%4d" % (AI['nRestartsAccepted'],
AI['nRestartsTried'])
LP['Info'] = AI
return LP
def calcLocalParams(Data,
LP,
alphaEbeta=None,
alphaEbetaRem=None,
alpha=None,
initDocTopicCountLP='scratch',
cslice=(0, None),
nnzPerRowLP=0,
doSparseOnlyAtFinalLP=0,
**kwargs):
''' Calculate all local parameters for provided dataset under a topic model
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'):
#tstart = time.time()
init_spR = calcInitSparseResp(LP,
alphaEbeta,
nnzPerRowLP=nnzPerRowLP,
**kwargs)
#tstop = time.time()
#telapsed = tstop - tstart
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 xrange(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 == 'memo':
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'):
#tstart = time.time()
DocTopicCount[d, :] = wc_d * init_spR[Data.word_id[start:stop]]
#telapsed += time.time() - tstart
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'):
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
