def show_hot_barh():
try:
df_non_outliers = news_pandas.load_news(
os.path.join(results_path, 'news_non_outliers.csv'))
df_non_outliers['content_cut'] = df_non_outliers['content_cut'].map(
eval)
except FileNotFoundError:
messagebox.showinfo('Message', '请先对新闻内容文本进行聚类！')
return
rank_num = counter.get_num_of_value_no_repeat(df_non_outliers['rank'])
value = [
df_non_outliers[df_non_outliers['rank'] == i].shape[0]
for i in range(1, rank_num + 1)
]
yticks1 = [
str(
counter.get_most_common_words(
df_non_outliers[df_non_outliers['rank'] == i]['content_cut'],
top_n=10)) + str(i) for i in range(1, rank_num + 1)
]
# yticks2 = [modeling.get_key_sentences('\n'.join(df_non_outliers[df_non_outliers['rank'] == i]['title_']),
# num=1) for i in range(1, rank_num + 1)]
drawing.draw_clustering_analysis_barh(rank_num,
value,
yticks1,
title='热点新闻分布饼图')
def show_word_barh():
word_df = news_pandas.load_news(os.path.join(results_path, 'word_df.csv'))
word_df['wordvec'] = word_df['wordvec'].map(eval)
n_clusters = counter.get_num_of_value_no_repeat(word_df['word_label'])
word_label_value = [word_df[word_df['word_label'] == i].shape[0] for i in range(n_clusters)]
word_label_yticks = [str(word_df[word_df['word_label'] == i]['word'][:10].tolist()) +
str(i + 1) for i in range(n_clusters)]
drawing.draw_clustering_analysis_barh(n_clusters, word_label_value, word_label_yticks, title='词汇聚类条形图')