def sampler(self, i, TOPICS, xcounts, ycounts, docId, different_word):
ll = 0
adder = add_count(xcounts, ycounts)
probs = {}
for i in range(0, len(self.xcorpus)):
for j in range(0, len(self.xcorpus[i])):
x = self.xcorpus[i][j]
y = self.ycorpus[i][j]
adder.add_counter(x, y, i, -1)
for k in range(TOPICS):
if xcounts.has_key(k) and (x, k) in xcounts and ycounts.has_key(docId) \
and (y, docId) in ycounts:
if xcounts[k] != 0 and ycounts[docId] != 0:
p_x_y = 1.0 * xcounts[
(x, k)] + self.alpha / xcounts[
k] + self.alpha * len(different_word)
p_y_Y = 1.0 * ycounts[
(y, docId)] + self.beta / ycounts[
docId] + self.beta * TOPICS
probs.update({k: p_x_y * p_y_Y})
new_y = Sampling.sampleOne(probs)
print new_y
ll = ll + log(probs[new_y])
adder.add_counter(x, new_y, i, 1)
self.ycorpus[i][j] = new_y
print ll
def sampler(self, i, TOPICS, xcounts, ycounts, docId, different_word):
ll = 0
adder = add_count(xcounts, ycounts)
probs = {}
for i in range(0, len(self.xcorpus)):
for j in range(0, len(self.xcorpus[i])):
x = self.xcorpus[i][j]
y = self.ycorpus[i][j]
adder.add_counter(x, y, i, -1)
for k in range(TOPICS):
if xcounts.has_key(k) and (x, k) in xcounts and ycounts.has_key(docId) \
and (y, docId) in ycounts:
if xcounts[k] != 0 and ycounts[docId] != 0:
p_x_y = 1.0 * xcounts[(x, k)] + self.alpha / xcounts[k] + self.alpha * len(different_word)
p_y_Y = 1.0 * ycounts[(y, docId)] + self.beta / ycounts[docId] + self.beta * TOPICS
probs.update({k : p_x_y * p_y_Y})
new_y = Sampling.sampleOne(probs)
print new_y
ll = ll + log(probs[new_y])
adder.add_counter(x, new_y, i ,1)
self.ycorpus[i][j] = new_y
print ll
def initilize(self):
first_time = 1
adder = add_count(self.xcounts, self.ycounts)
self.docid = os.path.getsize("07-train.txt")
#for line in open("wiki-en-documents.word", "r"):
for line in open("07-train.txt", "r"):
rline = line.rstrip("¥n")
words = numpy.array(rline.split(" "))
topics_vector = []
self.different_word = set(words)
for word in words:
topic = randint(self.TOPICS) + 1
topics_vector.append(topic)
adder.add_counter(word, topic, self.docid, 1)
array_topics_vector = numpy.array(topics_vector)
if first_time == 1:
self.xcorpus = numpy.hstack((self.xcorpus, words))
self.ycorpus = numpy.hstack((self.ycorpus, array_topics_vector))
first_time = first_time + 1
else:
self.xcorpus = numpy.vstack((self.xcorpus, words))
self.ycorpus = numpy.vstack((self.ycorpus, array_topics_vector))
def initilize(self):
first_time = 1
adder = add_count(self.xcounts, self.ycounts)
self.docid = os.path.getsize("07-train.txt")
#for line in open("wiki-en-documents.word", "r"):
for line in open("07-train.txt", "r"):
rline = line.rstrip("¥n")
words = numpy.array(rline.split(" "))
topics_vector = []
self.different_word = set(words)
for word in words:
topic = randint(self.TOPICS) + 1
topics_vector.append(topic)
adder.add_counter(word, topic, self.docid, 1)
array_topics_vector = numpy.array(topics_vector)
if first_time == 1:
self.xcorpus = numpy.hstack((self.xcorpus, words))
self.ycorpus = numpy.hstack(
(self.ycorpus, array_topics_vector))
first_time = first_time + 1
else:
self.xcorpus = numpy.vstack((self.xcorpus, words))
self.ycorpus = numpy.vstack(
(self.ycorpus, array_topics_vector))
def test_add(self):
adder = add_count()
def test_add(self):
adder = add_count()