def show_content_cut():
try:
filename = os.path.join(texts_path, 'document_segment.txt')
editor(filename)
except FileNotFoundError:
messagebox.showinfo('Message', '没有分词后的文件！')
return
def show_hot_titles():
all_title = '\n'.join(df_rank_i['title_'].tolist())
hot_titles = modeling.get_key_sentences(all_title, num=200)
news_pandas.save_text(hot_titles, os.path.join(texts_path,
'hot_titles.txt'))
filename = os.path.join(texts_path, 'hot_titles.txt')
editor(filename)
def show_hot_words_details():
top_words_list = counter.get_most_common_words(df_rank_i['content_cut'],
top_n=5000,
min_frequency=1)
top_words = '\n'.join(top_words_list)
news_pandas.save_text(top_words, os.path.join(texts_path, 'top_words.txt'))
filename = os.path.join(texts_path, 'top_words.txt')
editor(filename)
def show_wordlib():
try:
document_segment = news_pandas.load_text(os.path.join(texts_path, 'document_segment.txt'))
except FileNotFoundError:
messagebox.showinfo('Message', '没有分词后的文件！')
return
words = document_segment.split()
word_library = counter.get_most_common_words(words)
word_library = [word for word in word_library if re.match(r'^[0-9A-Za-z\u4E00-\u9FFF]+$', word)]
word_library = '\n'.join(word_library)
news_pandas.save_text(word_library, os.path.join(texts_path, 'word_library.txt'))
filename = os.path.join(texts_path, 'word_library.txt')
editor(filename)
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)
def show_cluster_n_words():
n = Entry_Cluster_N.get()
if n == '':
messagebox.showinfo('Message', '请先输入想要查看的词汇属于第几类！')
return
n = int(n)
try:
word_df = news_pandas.load_news(os.path.join(results_path, 'word_df.csv'))
except FileNotFoundError:
messagebox.showinfo('Message', '请先对新闻内容文本进行聚类！')
return
word_df['wordvec'] = word_df['wordvec'].map(eval)
words_i_df = word_df[word_df['word_label'] == n - 1].copy()
cluster_i_words = '\n'.join(words_i_df['word'].tolist())
news_pandas.save_text(cluster_i_words, os.path.join(texts_path, 'cluster_i_words.txt'))
filename = os.path.join(texts_path, 'cluster_i_words.txt')
editor(filename)
def show_singlewords():
filename = os.path.join(extra_dict_path, 'self_individual_character_dict.txt')
editor(filename)
def show_disambiguation_dict():
filename = os.path.join(extra_dict_path, 'self_disambiguation_dict.json')
editor(filename)
def show_stopwords():
filename = os.path.join(extra_dict_path, 'self_stop_words.txt')
editor(filename)
def show_userdict():
filename = os.path.join(extra_dict_path, 'self_userdict.txt')
editor(filename)
