def cluster_word():
n_clusters = Entry_N_Clusters.get()
if n_clusters == '':
messagebox.showinfo('Message', '请输入词汇聚类的类别数！')
return
n_clusters = int(n_clusters)
top_words_list = counter.get_most_common_words(
df_rank_i['content_cut'], top_n=5000, min_frequency=1)
model = news_pandas.load_element(
os.path.join(models_path, 'word2vec_model.pkl'))
word_list, wordvec_list = modeling.get_word_and_wordvec(
model, top_words_list)
kmeans = modeling.get_cluster(wordvec_list,
cluster='KMeans',
cluster_args={
'n_clusters': n_clusters,
'random_state': 9
})
word_label = kmeans.labels_
word_df = pd.DataFrame()
word_df['word'] = word_list
word_df['wordvec'] = wordvec_list
word_df['word_label'] = word_label
news_pandas.save_news(word_df, os.path.join(results_path,
'word_df.csv'))
messagebox.showinfo('Message', '词汇聚类完成！')
def wordsimilar():
model = news_pandas.load_element(os.path.join(models_path, 'word2vec_model.pkl'))
word = Entry_Word.get()
if word == '':
messagebox.showinfo('Message', '请输入词语！')
return
try:
model.wv.get_vector(word)
except:
messagebox.showinfo('Message', '词库中没有此词语！')
return
similar_words = model.wv.most_similar(word, topn=100)
similar_words = str(similar_words)[1:-1]
similar_words = re.sub(r'\), \(', '),\n(', similar_words)
news_pandas.save_text(similar_words, os.path.join(texts_path, 'similar_words.txt'))
filename = os.path.join(texts_path, 'similar_words.txt')
editor(filename)