Я использую большую библиотеку scikit-learn, применяя lda/nmf в моем наборе данных.Тема моделирования nmf/lda scikit-learn
from __future__ import print_function
from time import time
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.decomposition import NMF, LatentDirichletAllocation
from sklearn.datasets import fetch_20newsgroups
n_samples = 2000
n_features = 1000
n_topics = 5
n_top_words = 5
def print_top_words(model, feature_names, n_top_words):
for topic_idx, topic in enumerate(model.components_):
print("TopiC#%d:" % topic_idx)
print(" ".join([feature_names[i]
for i in topic.argsort()[:-n_top_words - 1:-1]]))
print()
# Load the 20 newsgroups dataset and vectorize it. We use a few heuristics
# to filter out useless terms early on: the posts are stripped of headers,
# footers and quoted replies, and common English words, words occurring in
# only one document or in at least 95% of the documents are removed.
print("Loading dataset...")
t0 = time()
dataset = fetch_20newsgroups(shuffle=True, random_state=1,
remove=('headers', 'footers', 'quotes'))
data_samples = dataset.data
print("done in %0.3fs." % (time() - t0))
# Use tf-idf features for NMF.
print("Extracting tf-idf features for NMF...")
tfidf_vectorizer = TfidfVectorizer(max_df=0.95, min_df=2, #max_features=n_features,
stop_words='english')
t0 = time()
tfidf = tfidf_vectorizer.fit_transform(data_samples)
print("done in %0.3fs." % (time() - t0))
# Use tf (raw term count) features for LDA.
print("Extracting tf features for LDA...")
tf_vectorizer = CountVectorizer(max_df=0.95, min_df=2, max_features=n_features,
stop_words='english')
t0 = time()
tf = tf_vectorizer.fit_transform(data_samples)
print("done in %0.3fs." % (time() - t0))
# Fit the NMF model
print("Fitting the NMF model with tf-idf features,"
"n_samples=%d and n_features=%d..."
% (n_samples, n_features))
t0 = time()
nmf = NMF(n_components=n_topics, random_state=1, alpha=.1, l1_ratio=.5).fit(tfidf)
print("done in %0.3fs." % (time() - t0))
print("\nTopics in NMF model:")
tfidf_feature_names = tfidf_vectorizer.get_feature_names()
print_top_words(nmf, tfidf_feature_names, n_top_words)
print("Fitting LDA models with tf features, n_samples=%d and n_features=%d..."
% (n_samples, n_features))
lda = LatentDirichletAllocation(n_topics=n_topics, max_iter=5,
learning_method='online', learning_offset=50.,
random_state=0)
t0 = time()
lda.fit(tf)
print("done in %0.3fs." % (time() - t0))
print("\nTopics in LDA model:")
tf_feature_names = tf_vectorizer.get_feature_names()
print_top_words(lda, tf_feature_names, n_top_words)
где в наборе данных = fetch_20newsgroups Даю наборы данных, который является списком с темами. Программа хорошо работает и выходные темы (NMF/LDA) в виде обычного текста, как здесь:
Topics in NMF model:
TopiC#0:
don people just think like
TopiC#1:
windows thanks card file dos
TopiC#2:
drive scsi ide drives disk
TopiC#3:
god jesus bible christ faith
TopiC#4:
geb dsl n3jxp chastity cadre
Как я могу представить там результаты? Я не могу понять векторный/математический код, стоящий за реализацией. Есть ли способ визуализировать вывод с графиками? мешок слов тоже? Меня интересуют только результаты nmf. Я очень плохо разбираюсь в вещах.
Посмотрите визуализации результатов тема модели [здесь] (http://stackoverflow.com/questions/30397550/visualizing-an-lda- модель-используя-Python) –