def show_word_pie():
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 = [word_df[word_df['word_label'] == i]['word'][:5].tolist() for i in range(n_clusters)]
drawing.draw_clustering_analysis_pie(n_clusters, word_label_value, word_label_yticks)
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_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 show_cluster_result():
try:
df_non_outliers = news_pandas.load_news(os.path.join(results_path, 'news_non_outliers.csv'))
df_non_outliers['pca_tsne'] = df_non_outliers['pca_tsne'].map(eval)
except FileNotFoundError:
messagebox.showinfo('Message', '请先对新闻内容文本进行聚类！')
return
drawing.draw_clustering_result(df_non_outliers['pca_tsne'], df_non_outliers['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！')
def cut_content():
try:
news_df = news_pandas.load_news(os.path.join(news_path, 'news_df.csv'))
except FileNotFoundError:
messagebox.showinfo('Message', '没有选择新闻内容文本！')
return
document = '\n'.join([str(content) for content in news_df['content']])
preprocessing.document2txt(document, userdict_path=os.path.join(extra_dict_path, 'self_userdict.txt'),
text_path=os.path.join(texts_path, 'document_segment.txt'))
messagebox.showinfo('Message', '新闻内容文本分词完成！')
def select_news():
filename = filedialog.askopenfilename(filetypes=[("csv file", "*.csv")])
if len(filename) == 0:
return
news_df = news_pandas.load_news(filename)
news_pandas.save_news(news_df, os.path.join(news_path, 'news_df.csv'))
global filter_df
filter_df = preprocessing.data_filter(news_df)
news_pandas.save_news(filter_df, os.path.join(temp_news_path, 'filter_news.csv'))
news_num = filter_df.shape[0]
sum_top_n.set(news_num)
def load_data():
"""加载数据"""
# sina_news_df = news_crawler.load_news(os.path.join(news_path, 'sample_sina_latest_news.csv'))
# sohu_news_df = news_crawler.load_news(os.path.join(news_path, 'sample_sohu_latest_news.csv'))
# xinhuanet_news_df = news_crawler.load_news(os.path.join(news_path, 'sample_xinhuanet_latest_news.csv'))
# sina_news_df = news_crawler.load_news(os.path.join(news_path, 'sina_latest_news.csv'))
# sohu_news_df = news_crawler.load_news(os.path.join(news_path, 'sohu_latest_news.csv'))
# xinhuanet_news_df = news_crawler.load_news(os.path.join(news_path, 'xinhuanet_latest_news.csv'))
# news_df = pd.concat([sina_news_df, sohu_news_df, xinhuanet_news_df], ignore_index=True)
save_file_path = os.path.join(news_path, 'news_df.csv')
news_df = news_pandas.load_news(save_file_path)
return news_df
def crawler():
sina_top_n = Entry_Sina.get()
sohu_top_n = Entry_Sohu.get()
xinhuanet_top_n = Entry_XinhuaNet.get()
sina_top_n = 0 if sina_top_n == '' else int(sina_top_n)
sohu_top_n = 0 if sohu_top_n == '' else int(sohu_top_n)
xinhuanet_top_n = 0 if xinhuanet_top_n == '' else int(xinhuanet_top_n)
sina_top_n = 0 if sina_top_n <= 0 else sina_top_n
sohu_top_n = 0 if sohu_top_n <= 0 else sohu_top_n
xinhuanet_top_n = 0 if xinhuanet_top_n <= 0 else xinhuanet_top_n
if sina_top_n + sohu_top_n + xinhuanet_top_n == 0:
messagebox.showinfo('Message', '新闻数量不能全部为非正数！')
return
news_crawler.threaded_crawler(sina_top_n, sohu_top_n, xinhuanet_top_n)
sina_news_df = pd.DataFrame()
sohu_news_df = pd.DataFrame()
xinhuanet_news_df = pd.DataFrame()
if sina_top_n > 0:
sina_news_df = news_pandas.load_news(
os.path.join(news_path, 'sina_latest_news.csv'))
if sohu_top_n > 0:
sohu_news_df = news_pandas.load_news(
os.path.join(news_path, 'sohu_latest_news.csv'))
if xinhuanet_top_n > 0:
xinhuanet_news_df = news_pandas.load_news(
os.path.join(news_path, 'xinhuanet_latest_news.csv'))
news_df = pd.concat([sina_news_df, sohu_news_df, xinhuanet_news_df],
ignore_index=True)
news_pandas.save_news(news_df, os.path.join(news_path, 'news_df.csv'))
global filter_df
filter_df = preprocessing.data_filter(news_df)
news_pandas.save_news(filter_df,
os.path.join(temp_news_path, 'filter_news.csv'))
news_num = filter_df.shape[0]
sum_top_n.set(news_num)
messagebox.showinfo('Message', '爬取即时新闻完成！共{}条有效新闻！'.format(news_num))
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_details():
top_num = Entry_TopHot.get()
if top_num == '':
messagebox.showinfo('Message', '请输入想查看的热点属于第几簇！')
return
top_num = int(top_num)
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
global df_rank_i
df_rank_i = df_non_outliers[df_non_outliers['rank'] == top_num]
all_title = '\n'.join(df_rank_i['title_'].tolist())
hot_title = modeling.get_key_sentences(all_title, num=1)
detail_tk = tk.Tk()
detail_tk.option_add("*Font", "helvetica 12 bold")
detail_tk.geometry("720x540+323+114")
detail_tk.title("第{}簇热点详情".format(top_num))
Label_Title = tk.Label(detail_tk, text='''话题：''')
Label_Title.place(relx=0.2, rely=0.1, height=26, width=66)
# Label_HotTitle = tk.Label(detail_tk, text=hot_title, font=('SimHei', 12, 'bold'), fg='red')
Label_HotTitle = tk.Label(detail_tk, text=hot_title, font=('helvetica', 12, 'bold'), fg='red')
Label_HotTitle.place(relx=0.25, rely=0.15)
Button_HotWords = tk.Button(detail_tk, text='''该处热点相关词汇''', command=show_hot_words_details)
Button_HotWords.place(relx=0.25, rely=0.25, height=26, width=140)
Button_HotTitles = tk.Button(detail_tk, text='''该处热点热门话题''', command=show_hot_titles)
Button_HotTitles.place(relx=0.55, rely=0.25, height=26, width=140)
Label_L_6 = tk.Label(detail_tk, text='''热点词汇分''')
Label_L_6.place(relx=0.25, rely=0.4, height=18, width=90)
n_to_cluster = tk.StringVar()
Entry_N_Clusters = tk.Entry(detail_tk, textvariable=n_to_cluster)
# n_to_cluster.set('15')
Entry_N_Clusters.place(relx=0.37, rely=0.4, height=20, relwidth=0.07)
Label_R_6 = tk.Label(detail_tk, text='''类聚类''')
Label_R_6.place(relx=0.44, rely=0.4, height=18, width=50)
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！')
Button_WordsCluster = tk.Button(detail_tk, text='''词汇聚类''', command=cluster_word)
Button_WordsCluster.place(relx=0.55, rely=0.4, height=26, width=80)
Button_Show_Word_Cluster_Result = tk.Button(detail_tk, text='''查看词汇聚类效果''', command=show_word_cluster_result)
Button_Show_Word_Cluster_Result.place(relx=0.38, rely=0.51, height=26, width=140)
Button_Word_Barh = tk.Button(detail_tk, text='''查看词汇聚类条形图''', command=show_word_barh)
Button_Word_Barh.place(relx=0.38, rely=0.61, height=26, width=154)
Button_Word_Pie = tk.Button(detail_tk, text='''查看词汇聚类饼图''', command=show_word_pie)
Button_Word_Pie.place(relx=0.38, rely=0.71, height=26, width=140)
Label_L_7 = tk.Label(detail_tk, text='''第''')
Label_L_7.place(relx=0.3, rely=0.84, height=18, width=16)
cluster_n = tk.StringVar()
Entry_Cluster_N = tk.Entry(detail_tk, textvariable=cluster_n)
# cluster_n.set('1')
Entry_Cluster_N.place(relx=0.34, rely=0.84, height=20, relwidth=0.07)
Label_R_7 = tk.Label(detail_tk, text='''类词汇''')
Label_R_7.place(relx=0.42, rely=0.84, height=18, width=50)
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)
Button_Show_Cluster_N_Word = tk.Button(detail_tk, text='''查询''', command=show_cluster_n_words)
Button_Show_Cluster_N_Word.place(relx=0.55, rely=0.84, height=26, width=50)
detail_tk.mainloop()
def load_data():
"""加载数据"""
save_file_path = os.path.join(news_path, 'news_df.csv')
news_df = news_pandas.load_news(save_file_path)
return news_df
