from?nltk.tokenize?import?sent_tokenize?word_tokenize
from?nltk.corpus?import?stopwords
import?math
from?itertools?import?product?count
from?string?import?punctuation
from?heapq?import?nlargest

stopwords?=?set（stopwords.words（‘english‘）?+?list（punctuation））


def?calculate_similarity（sen1?sen2）:

????counter?=?0
????for?word?in?sen1:
????????if?word?in?sen2:
????????????counter?+=?1
????return?counter?/?（math.log（（len（sen1）+1））?+?math.log（（len（sen2）+1））+1）


def?create_graph（word_sent）:
????num?=?len（word_sent）

????board?=?[[0.0?for?_?in?range（num）]?for?_?in?range（num）]

????for?i?j?in?product（range（num）?repeat=2）:
????????if?i?!=?j:
????????????board[i][j]?=?calculate_similarity（word_sent[i]?word_sent[j]）
????return?board


def?Summarize（textn）:
????#?首先分出句子
????sents?=?sent_tokenize（text）

????word_sent?=?[word_tokenize（s.lower（））?for?s?in?sents]

????#?把停用詞去除
????for?i?in?range（len（word_sent））:
????????for?word?in?word_sent[i]:
????????????if?word?in?stopwords:
????????????????word_sent[i].remove（word）
????similarity_graph?=?create_graph（word_sent）
????scores?=?weighted_pagerank（similarity_graph）
????sent_selected?=?nlargest（n?zip（scores?count（）））
????sent_index?=?[]
????for?i?in?range（n）:
????????sent_index.append（sent_selected[i][1]）
????return?[sents[i]?for?i?in?sent_index]



def?different（scores?old_scores）:
????flag?=?False
????for?i?in?range（len（scores））:
????????if?math.fabs（scores[i]?-?old_scores[i]）?>=?0.0001:
????????????flag?=?True
????????????break
????return?flag

def?weighted_pagerank（weight_graph）:
????#?把初始的分數值設置為0.5
????scores?=?[0.5?for?_?in?range（len（weight_graph））]
????old_scores?=?[0.0?for?_?in?range（len（weight_graph））]

????while?different（scores?old_scores）:
????????for?i?in?range（len（weight_graph））:
????????????old_scores[i]?=?scores[i]

????????for?i?in?range（len（weight_graph））:
????????????scores[i]?=?calculate_score（weight_graph?scores?i）

????return?scores

def?calculate_score（weight_graph?scores?i）:
????length?=?len（weight_graph）
????d?=?0.85
????added_score?=?0.0
????#?先計算分子
????for?j?in?range（length）:
????????fraction?=?0.0
????????denominator?=?0.0

????????fraction?=?weight_graph[j][i]?*?scores[j]
????????for?k?in?range（length）:
????????????denominator?+=?weight_graph[j][k]
????????added_score?+=?fraction?/?（denominator+1.0）
????weighted_score?=?（1?-?d）?+?d?*?added_score

????return?weighted_score



if?__name__?==?‘__main__‘:
????file_output=r“predtextank.txt“
????output=open（file_output“w“encoding=“utf8“）
????with?open（“srcT-val.txt“?“r“encoding=“utf8“）?as?myfile:
????????text?=?myfile.readlines（）
????????for?t?in?text:
????????????t=t.replace（‘\n‘??‘‘）
????????????summary?=?Summarize（t?1）
????????????line=“?“.join（summary）+“\n“
????????????output.write（line）
????output.close（）
????from?snownlp?import?SnowNLP
????with?open（r“D:\Tensorflow\nlp\bytedance\srcT-val.txt“?“r“?encoding=“u

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2019-01-16?18:22??文檔摘要解決方案\
?????文件??????460182??2019-01-16?18:21??文檔摘要解決方案\A?DEEP?REINFORCED?MODEL?FOR?ABSTRACTIVE?SUMMARIZATION.pdf
?????文件???????55446??2018-12-24?19:44??文檔摘要解決方案\A-DEEP-REINFORCED-MODEL-FOR-ABSTRACTIVE-SUMMARIZATION-master.zip
?????文件??????391109??2019-01-16?18:17??文檔摘要解決方案\Abstractive?Text?Summarization?using?Sequence-to-sequence?RNNs?and?Beyond.pdf
?????文件??????442103??2019-01-16?18:16??文檔摘要解決方案\Get?To?The?Point?Summarization?with?Pointer-Generator?Networks.pdf
?????文件??????987202??2018-10-15?22:22??文檔摘要解決方案\Neural?Response?Generation?with?Dynamic?Vocabularies.pdf
?????文件????????3631??2019-01-16?18:08??文檔摘要解決方案\NewsSummary.py
?????文件??????784434??2019-01-16?18:04??文檔摘要解決方案\NON-AUTOREGRESSIVE?NEURAL?MACHINE?TRANSLATION.pdf
?????文件??????161978??2019-01-16?18:09??文檔摘要解決方案\OpenNMT?Neural?Machine?Translation?Toolkit.pdf
?????文件?????????417??2019-01-16?18:22??文檔摘要解決方案\readme.txt
?????文件??????769595??2019-01-16?18:17??文檔摘要解決方案\Sequential?Copying?Networks.pdf
?????文件?????1815148??2018-12-28?19:43??文檔摘要解決方案\srcT-val.txt