def show_word_cluster_result():
word_df = news_pandas.load_news(os.path.join(results_path, 'word_df.csv'))
word_df['wordvec'] = word_df['wordvec'].map(eval)
wordvec_list = word_df['wordvec'].tolist()
word_label = word_df['word_label'].tolist()
word_pca_tsne = modeling.feature_reduction(wordvec_list, pca_n_components=3, tsne_n_components=2)
drawing.draw_clustering_result(word_pca_tsne, word_label)
def cluster_content():
eps_var = Entry_Eps.get()
min_samples_var = Entry_MinSamples.get()
if eps_var == '' or min_samples_var == '':
messagebox.showinfo('Message', '请输全聚类参数！')
return
eps_var = float(eps_var)
min_samples_var = int(min_samples_var)
try:
df = news_pandas.load_news(os.path.join(temp_news_path,
'news_cut.csv'))
df['content_cut'] = df['content_cut'].map(eval)
df['content_'] = df['content_'].map(str)
except FileNotFoundError:
messagebox.showinfo('Message', '请先对新闻内容文本进行预处理！')
return
word_library_list = counter.get_word_library(df['content_cut'])
single_frequency_words_list = counter.get_single_frequency_words(
df['content_cut'])
max_features = len(
word_library_list) - len(single_frequency_words_list) // 2
matrix = modeling.feature_extraction(df['content_'],
vectorizer='TfidfVectorizer',
vec_args={
'max_df': 0.95,
'min_df': 1,
'max_features': max_features
})
dbscan = modeling.get_cluster(matrix,
cluster='DBSCAN',
cluster_args={
'eps': eps_var,
'min_samples': min_samples_var,
'metric': 'cosine'
})
labels = modeling.get_labels(dbscan)
df['label'] = labels
ranks = modeling.label2rank(labels)
df['rank'] = ranks
news_pandas.save_news(df, os.path.join(results_path, 'news_label.csv'))
df['matrix'] = matrix.toarray().tolist()
df_non_outliers = df[df['label'] != -1].copy()
if df_non_outliers.shape[0] == 0:
messagebox.showinfo('Message', '不能聚类出任何热点，请重新设置聚类参数！')
return
data_pca_tsne = modeling.feature_reduction(
df_non_outliers['matrix'].tolist(),
pca_n_components=3,
tsne_n_components=2)
df_non_outliers['pca_tsne'] = data_pca_tsne.tolist()
del df_non_outliers['matrix']
news_pandas.save_news(df_non_outliers,
os.path.join(results_path, 'news_non_outliers.csv'))
rank_num = counter.get_num_of_value_no_repeat(df_non_outliers['rank'])
hot_num.set(rank_num)
messagebox.showinfo('Message', '按照新闻内容聚类完成！')