def train (data, model, query, plan):
iterations, burnIn, thin, _, debug = \
plan.iterations, plan.burnIn, plan.thin, plan.logFrequency, plan.debug
w_list, z_list, docLens, _, _ = \
query.w_list, query.z_list, query.docLens, query.topicSum, query.numSamples
K, T, topicPrior, vocabPrior, _, _, _, dtype, name = \
model.K, model.T, model.topicPrior, model.vocabPrior, model.topicSum, model.vocabSum, model.numSamples, model.dtype, model.name
assert model.dtype == np.float64, "This is only implemented for 64-bit floats"
D = docLens.shape[0]
ndk = np.zeros((D,K), dtype=np.int32)
nkv = np.zeros((K,T), dtype=np.int32)
nk = np.zeros((K,), dtype=np.int32)
topicSum = np.zeros((D,K), dtype=dtype)
vocabSum = np.zeros((K,T), dtype=dtype)
compiled.initGlobalRng(0xC0FFEE)
compiled.sumSuffStats(w_list, z_list, docLens, ndk, nkv, nk)
# Burn in
if debug: print ("Burning")
compiled.sample (burnIn, burnIn + 1, w_list, z_list, docLens, \
ndk, nkv, nk, topicSum, vocabSum, \
topicPrior, vocabPrior, False, debug)
# True samples
if debug: print ("Sampling")
numSamples = compiled.sample (iterations - burnIn, thin, w_list, z_list, docLens, \
ndk, nkv, nk, topicSum, vocabSum, \
topicPrior, vocabPrior, False, debug)
# compiled.freeGlobalRng()
return \
ModelState (K, T, topicPrior, vocabPrior, topicSum, vocabSum, numSamples, True, dtype, name), \
QueryState (w_list, z_list, docLens, topicSum, numSamples, True), \
(np.zeros(1), np.zeros(1), np.zeros(1))
def query (data, model, query, plan):
iterations, burnIn, thin, _, debug = \
plan.iterations, plan.burnIn, plan.thin, plan.logFrequency, plan.debug
w_list, z_list, docLens, _, _ = \
query.w_list, query.z_list, query.docLens, query.topicSum, query.numSamples
K, T, topicPrior, vocabPrior, _, _, _, dtype, name = \
model.K, model.T, model.topicPrior, model.vocabPrior, model.topicSum, model.vocabSum, model.numSamples, model.dtype, model.name
assert model.dtype == np.float64, "This is only implements for 64-bit floats"
D = docLens.shape[0]
compiled.initGlobalRng(0xC0FFEE)
ndk = np.zeros((D, K), dtype=np.int32)
nkv = (wordDists(model) * 1000000).astype(np.int32)
nk = nkv.sum(axis=1).astype(np.int32)
adjustedVocabPrior = np.zeros((T,), dtype=model.dtype) # already incorporated into nkv
topicSum = np.zeros((D,K), dtype=dtype)
vocabSum = model.vocabSum
compiled.sumSuffStats(w_list, z_list, docLens, ndk, nkv, nk)
# Burn in
compiled.sample (burnIn, burnIn + 1, w_list, z_list, docLens, \
ndk, nkv, nk, topicSum, vocabSum, \
topicPrior, adjustedVocabPrior, True, debug)
# True samples
numSamples = compiled.sample (iterations - burnIn, thin, w_list, z_list, docLens, \
ndk, nkv, nk, topicSum, vocabSum, \
topicPrior, adjustedVocabPrior, True, debug)
return \
ModelState (K, T, topicPrior, vocabPrior, topicSum, vocabSum, numSamples, model.processed, dtype, name), \
QueryState (w_list, z_list, docLens, topicSum, numSamples, True)