版权声明:本文为博主原创文章,转载请注明出处。 https://blog.csdn.net/qq_32768743/article/details/89487052
import numpy as np
import lda
import lda.datasets
# document-term matrix
X = lda.datasets.load_reuters()
print("type(X): {}".format(type(X)))
print("shape: {}\n".format(X.shape))
print(X[:5, :5])
'''输出:
type(X): <type 'numpy.ndarray'>
shape: (395L, 4258L)
[[ 1 0 1 0 0]
[ 7 0 2 0 0]
[ 0 0 0 1 10]
[ 6 0 1 0 0]
[ 0 0 0 2 14]]
'''
读的文件内容
# the vocab
vocab = lda.datasets.load_reuters_vocab()
print("type(vocab): {}".format(type(vocab)))
print("len(vocab): {}\n".format(len(vocab)))
print(vocab[:6])
'''输出
type(vocab): <type 'tuple'>
len(vocab): 4258
('church', 'pope', 'years', 'people', 'mother', 'last')
'''
读的文件是
全部代码
import numpy as np
import lda
import lda.datasets
# document-term matrix
X = lda.datasets.load_reuters()
print("type(X): {}".format(type(X)))
print("shape: {}\n".format(X.shape))
print(X[:5, :5])
'''输出:
type(X): <type 'numpy.ndarray'>
shape: (395L, 4258L)
[[ 1 0 1 0 0]
[ 7 0 2 0 0]
[ 0 0 0 1 10]
[ 6 0 1 0 0]
[ 0 0 0 2 14]]
'''
# the vocab
vocab = lda.datasets.load_reuters_vocab()
print("type(vocab): {}".format(type(vocab)))
print("len(vocab): {}\n".format(len(vocab)))
print(vocab[:6])
'''输出
type(vocab): <type 'tuple'>
len(vocab): 4258
('church', 'pope', 'years', 'people', 'mother', 'last')
'''
model = lda.LDA(n_topics=20, n_iter=500, random_state=1)
model.fit(X)
topic_word = model.topic_word_
print("type(topic_word): {}".format(type(topic_word)))
print("shape: {}".format(topic_word.shape))
'''输出:
type(topic_word): <type 'numpy.ndarray'>
shape: (20L, 4258L)
'''
print(topic_word[:, :3])
n = 5
for i, topic_dist in enumerate(topic_word):
topic_words = np.array(vocab)[np.argsort(topic_dist)][:-(n+1):-1]
print('*Topic {}\n- {}'.format(i, ' '.join(topic_words)))
'''输出:
*Topic 0
- government british minister west group
*Topic 1
- church first during people political
*Topic 2
- elvis king wright fans presley
*Topic 3
- yeltsin russian russia president kremlin
*Topic 4
- pope vatican paul surgery pontiff
*Topic 5
- family police miami versace cunanan
*Topic 6
- south simpson born york white
*Topic 7
- order church mother successor since
*Topic 8
- charles prince diana royal queen
*Topic 9
- film france french against actor
*Topic 10
- germany german war nazi christian
*Topic 11
- east prize peace timor quebec
*Topic 12
- n't told life people church
*Topic 13
- years world time year last
*Topic 14
- mother teresa heart charity calcutta
*Topic 15
- city salonika exhibition buddhist byzantine
*Topic 16
- music first people tour including
*Topic 17
- church catholic bernardin cardinal bishop
*Topic 18
- harriman clinton u.s churchill paris
*Topic 19
- century art million museum city
'''
doc_topic = model.doc_topic_
print("type(doc_topic): {}".format(type(doc_topic)))
print("shape: {}".format(doc_topic.shape))
'''输出:
type(doc_topic): <type 'numpy.ndarray'>
shape: (395, 20)
'''
for n in range(10):
topic_most_pr = doc_topic[n].argmax()
print("doc: {} topic: {}".format(n, topic_most_pr))
'''输出:
doc: 0 topic: 8
doc: 1 topic: 1
doc: 2 topic: 14
doc: 3 topic: 8
doc: 4 topic: 14
doc: 5 topic: 14
doc: 6 topic: 14
doc: 7 topic: 14
doc: 8 topic: 14
doc: 9 topic: 8
'''
参考
https://my.oschina.net/letiantian/blog/616413?fromerr=ThbaouNJ
https://blog.csdn.net/Eastmount/article/details/50824215