def testPerplexityOnRealDataWithCtm(self):
dtype = np.float64 # DTYPE
rd.seed(0xBADB055)
data = DataSet.from_files(words_file=AclWordPath, links_file=AclCitePath)
with open(AclDictPath, "rb") as f:
d = pkl.load(f)
data.convert_to_dtype(dtype)
data.prune_and_shuffle(min_doc_len=MinDocLen, min_link_count=MinLinkCount)
# IDF frequency for when we print out the vocab later
freq = np.squeeze(np.asarray(data.words.sum(axis=0)))
scale = np.reciprocal(1 + freq)
# Initialise the model
K = 10 # TopicCount
model = ctm.newModelAtRandom(data, K, dtype=dtype)
queryState = ctm.newQueryState(data, model)
trainPlan = ctm.newTrainPlan(iterations=200, logFrequency=10, fastButInaccurate=False, debug=False)
# Train the model, and the immediately save the result to a file for subsequent inspection
model, query, (bndItrs, bndVals, bndLikes) = ctm.train (data, model, queryState, trainPlan)
# with open(newModelFileFromModel(model), "wb") as f:
# pkl.dump ((model, query, (bndItrs, bndVals, bndLikes)), f)
# Plot the evolution of the bound during training.
fig, ax1 = plt.subplots()
ax1.plot(bndItrs, bndVals, 'b-')
ax1.set_xlabel('Iterations')
ax1.set_ylabel('Bound', color='b')
ax2 = ax1.twinx()
ax2.plot(bndItrs, bndLikes, 'r-')
ax2.set_ylabel('Likelihood', color='r')
fig.show()
plt.show()
fig, ax1 = plt.subplots()
ax1.imshow(model.sigT, interpolation="nearest", cmap=cm.Greys_r)
fig.show()
plt.show()
# Print out the most likely topic words
# scale = np.reciprocal(1 + np.squeeze(np.array(data.words.sum(axis=0))))
vocab = ctm.wordDists(model)
topWordCount = 10
kTopWordInds = [self.topWordInds(vocab[k,:], topWordCount) for k in range(K)]
like = ctm.log_likelihood(data, model, query)
perp = perplexity_from_like(like, data.word_count)
print ("Perplexity: %f\n\n" % perp)
for k in range(model.K):
print("\nTopic %d\n=============================" % k)
print("\n".join("%-20s\t%0.4f" % (d[kTopWordInds[k][c]], vocab[k][kTopWordInds[k][c]]) for c in range(topWordCount)))
def testCrossValPerplexityOnRealDataWithCtmInc(self):
dtype = np.float64 # DTYPE
rd.seed(0xBADB055)
data = DataSet.from_files(words_file=AclWordPath, links_file=AclCitePath)
data.convert_to_dtype(dtype)
data.prune_and_shuffle(min_doc_len=MinDocLen, min_link_count=MinLinkCount)
# Initialise the model
trainPlan = ctm.newTrainPlan(iterations=800, logFrequency=10, fastButInaccurate=False, debug=False)
queryPlan = ctm.newTrainPlan(iterations=100, logFrequency=10, fastButInaccurate=False, debug=False)
topicCounts = [5, 10, 15, 20, 25, 30, 35, 40, 45, 50]
for K in topicCounts:
trainPerps = []
queryPerps = []
for fold in range(1): # range(NumFolds):
trainData, queryData = data.cross_valid_split(fold, NumFolds)
model = ctm.newModelAtRandom(trainData, K, dtype=dtype)
query = ctm.newQueryState(trainData, model)
# Train the model, and the immediately save the result to a file for subsequent inspection
model, trainResult, (_, _, _) = ctm.train (trainData, model, query, trainPlan)
like = ctm.log_likelihood(trainData, model, trainResult)
perp = perplexity_from_like(like, trainData.word_count)
trainPerps.append(perp)
query = ctm.newQueryState(queryData, model)
model, queryResult = ctm.query(queryData, model, query, queryPlan)
like = ctm.log_likelihood(queryData, model, queryResult)
perp = perplexity_from_like(like, queryData.word_count)
queryPerps.append(perp)
trainPerps.append(sum(trainPerps) / NumFolds)
queryPerps.append(sum(queryPerps) / NumFolds)
print("K=%d,Segment=Train,%s" % (K, ",".join([str(p) for p in trainPerps])))
print("K=%d,Segment=Query,%s" % (K, ",".join([str(p) for p in queryPerps])))
def _testOnModelDerivedExample(self):
print("Cross-validated likelihoods on model-derived example")
rd.seed(0xBADB055) # Global init for repeatable test
D, T, K = 1000, 100, 7 # Document count, vocabularly size ("term count") and topic count
tpcs, vocab, docLens, W = self._sampleFromModel(D, T, K)
W = W.astype(DTYPE)
plt.imshow(vocab, interpolation="none", cmap = cm.Greys_r)
plt.show()
# Create the cross-validation folds
folds = 5
foldSize = ceil(D / 5)
querySize = foldSize
trainSize = D - querySize
for useDiagonalPriorCov in [False, True]:
trainLikely = []
trainWordCount = []
queryLikely = []
queryWordCount = []
for fold in range(folds):
# Split the datasets
start = fold * foldSize
end = start + trainSize
trainSet = np.arange(start,end) % D
querySet = np.arange(end, end + querySize) % D
W_train = W[trainSet,:]
W_query = W[querySet,:]
# Train the model
model = ctm.newModelAtRandom(W_train, K, dtype=DTYPE)
queryState = ctm.newQueryState(W_train, model)
plan = ctm.newTrainPlan(iterations=20, logFrequency=1, fastButInaccurate=useDiagonalPriorCov)
model, queryState, (bndItrs, bndVals) = ctm.train (W_train, None, model, queryState, plan)
# Plot the evoluation of the bound during training.
plt.plot(bndItrs[5:], bndVals[5:])
plt.xlabel("Iterations")
plt.ylabel("Variational Bound")
plt.show()
# Plot the topic covariance
self._plotCov(model)
# Plot the vocab
plt.imshow(model.vocab, interpolation="none", cmap = cm.Greys_r)
plt.show()
# Calculating the training set likelihood
trainLikely.append(ctm.log_likelihood(W_train, model, queryState))
trainWordCount.append(W_train.data.sum())
# Now query the model.
plan = ctm.newTrainPlan(iterations=10, fastButInaccurate=useDiagonalPriorCov)
queryState = ctm.newQueryState(W_query, model)
model, queryState = ctm.query(W_query, None, model, queryState, plan)
queryLikely.append(ctm.log_likelihood(W_query, model, queryState))
queryWordCount.append(W_query.data.sum())
# Print out the likelihood and perplexity for each fold.
print ("\n\n\nWith " + ("diagonal" if useDiagonalPriorCov else "full") + " covariances")
for fold in range(folds):
trainPerp = np.exp(-trainLikely[fold]/trainWordCount[fold])
queryPerp = np.exp(-queryLikely[fold]/queryWordCount[fold])
print("Fold %3d: Train-set Likelihood: %12f \t Query-set Likelihood: %12f" % (fold, trainLikely[fold], queryLikely[fold]))
print(" Perplexity: %12.2f \t Perplexity: %12.2f" % (trainPerp, queryPerp))
self.assertTrue(queryPerp < 60.0) # Maximum perplexity.
self.assertTrue(trainPerp < 60.0)
print ("\n\n")
print("End of Test")
