def summarize4(self, df): #http://ai.intelligentonlinetools.com/ml/text-summarization/ LANGUAGE = "english" SENTENCES_COUNT = 10 stopwords = nltk.corpus.stopwords.words('english') for row in df['conclusion']: if row == '0' or row == '': continue parser = PlaintextParser(row, Tokenizer(LANGUAGE)) print("--LsaSummarizer--") summarizer = LsaSummarizer() summarizer = LsaSummarizer(Stemmer(LANGUAGE)) summarizer.stop_words = get_stop_words(LANGUAGE) for sentence in summarizer(parser.document, SENTENCES_COUNT): print(sentence) print("--LuhnSummarizer--") summarizer = LuhnSummarizer() summarizer.stop_words = stopwords for sentence in summarizer(parser.document, SENTENCES_COUNT): print(sentence) print("--EdmundsonSummarizer--") summarizer = EdmundsonSummarizer() words = ("deep", "learning", "neural") summarizer.bonus_words = words words = ( "another", "and", "some", "next", ) summarizer.stigma_words = words words = ( "another", "and", "some", "next", ) summarizer.null_words = words for sentence in summarizer(parser.document, SENTENCES_COUNT): print(sentence)
summarizer.stop_words = get_stop_words(LANGUAGE) for sentence in summarizer(parser.document, SENTENCES_COUNT): summary2+=str(sentence) summary2+=" " with open("summarised_text.txt", "a", encoding="utf8") as myfile: myfile.write("\n\nLuhn:\n") myfile.write(summary2) summary3 = "" print("\n\n") print ("--EdmundsonSummarizer--") summarizer = EdmundsonSummarizer() words = ("deep", "learning", "neural" ) summarizer.bonus_words = words words = ("another", "and", "some", "next",) summarizer.stigma_words = words words = ("another", "and", "some", "next",) summarizer.null_words = words for sentence in summarizer(parser.document, SENTENCES_COUNT): summary3+=str(sentence) summary3+=" " with open("summarised_text.txt", "a", encoding="utf8") as myfile: myfile.write("\n\nEdmundson:\n") myfile.write(summary3)