modify readme

README.md

@@ -110,20 +110,26 @@ import codecs
 from textrank4zh import TextRank4Keyword, TextRank4Sentence
 
 text = codecs.open('./text/01.txt', 'r', 'utf-8').read()
-tr4w = TextRank4Keyword(stop_words_file='./stopword.data')
-tr4w.train(text=text, speech_tag_filter=True, lower=True, window=2)
+tr4w = TextRank4Keyword(stop_words_file='./stopword.data')  # 导入停止词
+
+#使用词性过滤，文本小写，窗口为2
+tr4w.train(text=text, speech_tag_filter=True, lower=True, window=2)  
 
 print '关键词：'
-print '/'.join(tr4w.get_keywords(10, word_min_len=2))
+# 10个关键词且每个的长度最小为2
+print '/'.join(tr4w.get_keywords(10, word_min_len=2))  
 
 print '关键短语：'
-print '/'.join(tr4w.get_keyphrases(keywords_num=20, min_occur_num= 2))
+# 20个关键词去构造短语，短语在原文本中出现次数最少为2
+print '/'.join(tr4w.get_keyphrases(keywords_num=20, min_occur_num= 2))  
     
 tr4s = TextRank4Sentence(stop_words_file='./stopword.data')
+
+# 使用词性过滤，文本小写，使用words_all_filters生成句子之间的相似性
 tr4s.train(text=text, speech_tag_filter=True, lower=True, source = 'all_filters')
 
 print '摘要：'
-print '\n'.join(tr4s.get_key_sentences(num=3))
+print '\n'.join(tr4s.get_key_sentences(num=3)) # 重要性最高的三个句子
 ```
 
 得到的关键词：

test.py

@@ -8,17 +8,23 @@
 from textrank4zh import TextRank4Keyword, TextRank4Sentence
 
 text = codecs.open('./text/01.txt', 'r', 'utf-8').read()
-tr4w = TextRank4Keyword(stop_words_file='./stopword.data')
-tr4w.train(text=text, speech_tag_filter=True, lower=True, window=2)
+tr4w = TextRank4Keyword(stop_words_file='./stopword.data')  # 导入停止词
+
+#使用词性过滤，文本小写，窗口为2
+tr4w.train(text=text, speech_tag_filter=True, lower=True, window=2)  
 
 print '关键词：'
-print '/'.join(tr4w.get_keywords(10, word_min_len=2))
+# 10个关键词且每个的长度最小为2
+print '/'.join(tr4w.get_keywords(10, word_min_len=2))  
 
 print '关键短语：'
-print '/'.join(tr4w.get_keyphrases(keywords_num=20, min_occur_num= 2))
+# 20个关键词去构造短语，短语在原文本中出现次数最少为2
+print '/'.join(tr4w.get_keyphrases(keywords_num=20, min_occur_num= 2))  
 
 tr4s = TextRank4Sentence(stop_words_file='./stopword.data')
+
+# 使用词性过滤，文本小写，使用words_all_filters生成句子之间的相似性
 tr4s.train(text=text, speech_tag_filter=True, lower=True, source = 'all_filters')
 
 print '摘要：'
-print '\n'.join(tr4s.get_key_sentences(num=3))
+print '\n'.join(tr4s.get_key_sentences(num=3)) # 重要性最高的三个句子