不知道写的对不对。先放到这里,有空了再改改。
'''
Created on Jul 31, 2013
@author: Nie
'''
import numpy
class LDA:
def __init__(self, K, alpha, beta, docs, visula, V, N, smartinit=True):
self.K = K
self.alpha = alpha # parameter of topics prior
self.beta = beta # parameter of words prior
self.docs = docs
self.visual = visula
self.V = V
self.z_m_n = [] # topics of words of documents
self.n_m_z = numpy.zeros((len(self.docs), K)) + alpha # word count of each document and topic
self.n_z_t = numpy.zeros((K, V)) + beta # word count of each topic and vocabulary
self.n_z = numpy.zeros(K) + V * beta # word count of each topic
self.z_m_n_v = [] # topics of words of documents
self.n_m_z_v = numpy.zeros((len(self.visual), K)) + alpha # word count of each document and topic
self.n_z_t_v = numpy.zeros((K, N)) + beta # word count of each topic and vocabulary
self.n_z_v = numpy.zeros(K) + N * beta
self.N = 0
self.N_v = 0
for m, (doc, visual) in enumerate(zip(docs, visula)):
self.N += len(doc)
self.N_v += len(visual)
z_n = []
z_n_v = []
for t in doc:
if smartinit:
p_z = self.n_z_t[:, t] * self.n_m_z[m] / self.n_z
z = numpy.random.multinomial(1, p_z / p_z.sum()).argmax()
else:
z = numpy.random.randint(0, K)
z_n.append(z)
self.n_m_z[m, z] += 1
self.n_z_t[z, t] += 1
self.n_z[z] += 1
self.z_m_n.append(numpy.array(z_n))
for t in visual:
if smartinit:
p_z = self.n_z_t_v[:, t] * self.n_m_z_v[m] / self.n_z_v
z = numpy.random.multinomial(1, p_z / p_z.sum()).argmax()
else:
z = numpy.random.randint(0, K)
z_n_v.append(z)
self.n_m_z_v[m, z] += 1
self.n_z_t_v[z, t] += 1
self.n_z_v[z] += 1
self.z_m_n_v.append(numpy.array(z_n_v))
def inference(self):
"""learning once iteration"""
for m, doc in enumerate(self.docs):
z_n = self.z_m_n[m]
n_m_z = self.n_m_z[m]
for n, t in enumerate(doc):
# discount for n-th word t with topic z
z = z_n[n]
n_m_z[z] -= 1
self.n_z_t[z, t] -= 1
self.n_z[z] -= 1
# sampling topic new_z for t
p_z = self.n_z_t[:, t] * n_m_z / self.n_z
new_z = numpy.random.multinomial(1, p_z / p_z.sum()).argmax()
# set z the new topic and increment counters
z_n[n] = new_z
n_m_z[new_z] += 1
self.n_z_t[new_z, t] += 1
self.n_z[new_z] += 1
for m, doc in enumerate(self.visual):
z_n = self.z_m_n_v[m]
n_m_z = self.n_m_z_v[m]
for n, t in enumerate(doc):
# discount for n-th word t with topic z
z = z_n[n]
n_m_z[z] -= 1
self.n_z_t_v[z, t] -= 1
self.n_z_v[z] -= 1
# sampling topic new_z for t
p_z = self.n_z_t_v[:, t] * n_m_z / self.n_z_v
new_z = numpy.random.multinomial(1, p_z / p_z.sum()).argmax()
# set z the new topic and increment counters
z_n[n] = new_z
n_m_z[new_z] += 1
self.n_z_t_v[new_z, t] += 1
self.n_z_v[new_z] += 1
def worddist(self):
"""get topic-word distribution"""
return self.n_z_t / self.n_z[:, numpy.newaxis]
def worddist_v(self):
"""get topic-word distribution"""
return self.n_z_t_v / self.n_z_v[:, numpy.newaxis]
def perplexity(self, docs=None):
if docs == None: docs = self.docs
phi = self.worddist()
log_per = 0
N = 0
Kalpha = self.K * self.alpha
for m, doc in enumerate(docs):
theta = self.n_m_z[m] / (len(self.docs[m]) + Kalpha)
for w in doc:
log_per -= numpy.log(numpy.inner(phi[:,w], theta))
N += len(doc)
return numpy.exp(log_per / N)
def lda_learning(lda, iteration, voca):
pre_perp = lda.perplexity()
print "initial perplexity=%f" % pre_perp
for i in range(iteration):
lda.inference()
perp = lda.perplexity()
print "-%d p=%f" % (i + 1, perp)
if pre_perp:
if pre_perp < perp:
output_word_topic_dist(lda, voca)
pre_perp = None
else:
pre_perp = perp
output_word_topic_dist(lda, voca)
def lda_learning_visula(lda, iteration, voca):
pre_perp = lda.perplexity()
print "initial perplexity=%f" % pre_perp
for i in range(iteration):
lda.inference()
perp = lda.perplexity()
print "-%d p=%f" % (i + 1, perp)
if pre_perp:
if pre_perp < perp:
output_word_topic_dist_visual(lda, voca)
pre_perp = None
else:
pre_perp = perp
output_word_topic_dist_visual(lda, voca)
def output_word_topic_dist(lda, voca):
zcount = numpy.zeros(lda.K, dtype=int)
wordcount = [dict() for k in xrange(lda.K)]
for xlist, zlist in zip(lda.docs, lda.z_m_n):
for x, z in zip(xlist, zlist):
zcount[z] += 1
if x in wordcount[z]:
wordcount[z][x] += 1
else:
wordcount[z][x] = 1
zcount_v = numpy.zeros(lda.K, dtype=int)
wordcount_v = [dict() for k in xrange(lda.K)]
for xlist, zlist in zip(lda.visual, lda.z_m_n_v):
for x, z in zip(xlist, zlist):
zcount_v[z] += 1
if x in wordcount_v[z]:
wordcount_v[z][x] += 1
else:
wordcount_v[z][x] = 1
phi = lda.worddist()
phi_v = lda.worddist_v()
for k in xrange(lda.K):
print "\n-- topic: %d (%d words)" % (k, zcount[k])
for w in numpy.argsort(-phi[k])[:20]:
print "%s: %f (%d)" % (voca[w], phi[k,w], wordcount[k].get(w,0))
for w in numpy.argsort(-phi_v[k])[:20]:
print "%d: %f (%d)" % (w, phi_v[k,w], wordcount_v[k].get(w,0))
def output_word_topic_dist_visual(lda, voca):
zcount = numpy.zeros(lda.K, dtype=int)
wordcount = [dict() for k in xrange(lda.K)]
for xlist, zlist in zip(lda.docs, lda.z_m_n):
for x, z in zip(xlist, zlist):
zcount[z] += 1
if x in wordcount[z]:
wordcount[z][x] += 1
else:
wordcount[z][x] = 1
phi = lda.worddist()
phi_v = lda.worddist_v()
for k in xrange(lda.K):
print "\n-- topic: %d (%d words)" % (k, zcount[k])
for w in numpy.argsort(-phi[k])[:20]:
print "%s: %f (%d)" % (voca[w], phi[k,w], wordcount[k].get(w,0))
for w in numpy.argsort(-phi_v[k])[:20]:
print "%d: %f (%d)" % (w, phi[k,w], wordcount[k].get(w,0))
def main():
import optparse
import vocabulary
parser = optparse.OptionParser()
parser.add_option("-f", dest="filename", help="corpus filename")
parser.add_option("-c", dest="corpus", help="using range of Brown corpus' files(start:end)")
parser.add_option("--alpha", dest="alpha", type="float", help="parameter alpha", default=0.5)
parser.add_option("--beta", dest="beta", type="float", help="parameter beta", default=0.5)
parser.add_option("-k", dest="K", type="int", help="number of topics", default=20)
parser.add_option("-i", dest="iteration", type="int", help="iteration count", default=4)
parser.add_option("-s", dest="smartinit", action="store_true", help="smart initialize of parameters", default=False)
parser.add_option("--stopwords", dest="stopwords", help="exclude stop words", action="store_true", default=False)
parser.add_option("--seed", dest="seed", type="int", help="random seed")
parser.add_option("--df", dest="df", type="int", help="threshold of document freaquency to cut words", default=0)
(options, args) = parser.parse_args()
#if not (options.filename or options.corpus): parser.error("need corpus filename(-f) or corpus range(-c)")
if 1:
corpus = vocabulary.load_file('ap.txt')
else:
corpus = vocabulary.load_corpus(options.corpus)
if not corpus: parser.error("corpus range(-c) forms 'start:end'")
if options.seed != None:
numpy.random.seed(options.seed)
f = open('visual.txt','r')
visuallist = []
for line in f.readlines():
#visuallist.append(0)
line = line[:-2]
temp = line.split(' ')
#temp.append(0)
visuallist.append(temp)
# voca = vocabulary.Vocabulary(False)
# lda = LDA(options.K, options.alpha, options.beta, visuallist, 1001, options.smartinit)
# print "corpus=%d, words=%d, K=%d, a=%f, b=%f" % (len(corpus), len(voca.vocas), options.K, options.alpha, options.beta)
# lda_learning_visula(lda, options.iteration, voca)
voca = vocabulary.Vocabulary(False)
docs = [voca.doc_to_ids(doc) for doc in corpus]
if options.df > 0: docs = voca.cut_low_freq(docs, options.df)
lda = LDA(options.K, options.alpha, options.beta, docs, visuallist, voca.size(), 1001, options.smartinit)
print "corpus=%d, words=%d, K=%d, a=%f, b=%f" % (len(corpus), len(voca.vocas), options.K, options.alpha, options.beta)
#import cProfile
#cProfile.runctx('lda_learning(lda, options.iteration, voca)', globals(), locals(), 'lda.profile')
lda_learning(lda, options.iteration, voca)
if __name__ == "__main__":
main()