def cluster_paragraphs(paragraphs, num_clusters=2):
word_lists = make_word_lists(paragraphs)
word_set = make_word_set(word_lists)
word_vectors = make_word_vectors(word_set, word_lists)
paragraph_map = dict(zip(map(str, word_vectors), paragraphs))
k_means = KMeans(num_clusters, word_vectors)
k_means.main_loop()
return translator(k_means.clusters, paragraph_map)
def cluster_paragraphs(paragraphs, num_clusters=2):
word_lists = make_word_lists(paragraphs)
word_set = make_word_set(word_lists)
word_vectors = make_word_vectors(word_set, word_lists)
paragraph_map = dict(zip(map(str, word_vectors), paragraphs))
k_means = KMeans(num_clusters, word_vectors)
k_means.main_loop()
return translator(k_means.clusters, paragraph_map)
def cluster_paragraphs(paragraphs):
word_lists = make_word_lists(paragraphs) #二维列表
word_lists1 = []
for i in range(len(word_lists)):
str1 = " ".join(word_lists[i])
word_lists1.append(str1)
# print "word_lists1:",word_lists1
word_set = make_word_set(word_lists) #所有词的集合
vec_df = tfidf(word_lists1)
word_vectors = make_word_vectors(word_set, word_lists) #将每一条数据处理成一个固定长度的向量
# print "word_vectors:",word_vectors
paragraph_map = dict(zip(map(str, word_vectors), paragraphs))
optimum_k = find_optimum_k(vec_df)
k_means = KMeans(optimum_k, word_vectors)
k_means.main_loop()
return translator(k_means.clusters, paragraph_map)
