doc1 = "Sugar is bad to consume. My sister likes to have sugar, but not my father."
doc2 = "My father spends a lot of time driving my sister around to dance practice."
doc3 = "Doctors suggest that driving may cause increased stress and blood pressure."
doc4 = "Sometimes I feel pressure to perform well at school, but my father never seems to drive my sister to do better."
doc5 = "Health experts say that Sugar isnot good for your lifestyle."
# compile documents
doc_complete = [doc1, doc2, doc3, doc4, doc5]
清洗及预处理
清洗是任何文本挖掘任务前非常重要的一步，通常在这步中会清除标点符号、停用词和标准化语料库。
from nltk.corpus import stopwords
from nltk.stem.wordnet import WordNetLemmatizer
import string
stop = set(stopwords.words('english'))
exclude = set(string.punctuation)
lemma = WordNetLemmatizer()
defclean(doc):
stop_free = " ".join([i for i in doc.lower().split() if i notin stop])
punc_free = ''.join(ch for ch in stop_free if ch notin exclude)
normalized = " ".join(lemma.lemmatize(word) for word in punc_free.split())
return normalized
doc_clean = [clean(doc).split() for doc in doc_complete]
# Importing Gensim
import gensim
from gensim import corpora
# Creating the term dictionary of our courpus, where every unique term is assigned an index. dictionary = corpora.Dictionary(doc_clean)
# Converting list of documents (corpus) into Document Term Matrix using dictionary prepared above.
doc_term_matrix = [dictionary.doc2bow(doc) for doc in doc_clean]
# Creating the object for LDA model using gensim library
Lda = gensim.models.ldamodel.LdaModel# Running and Trainign LDA model on the document term matrix.
ldamodel = Lda(doc_term_matrix, num_topics=3, id2word = dictionary, passes=50)
转播
