[Py3.5] Chunking w/ NLTK

/*******************************************************************************************************************
-- Title : [Py3.5] Chunking/Chinking w/ NLTK
-- Reference : pythonprogramming.net
-- Key word : nltk nlp pos 자연어 처리 state_union corpus tokenize 형태소 품사 tokenize open txt 텍스트
                  punktsentencetokenizer word_tokenize pos_tag regexpparser chunkparser parse chinking chink
*******************************************************************************************************************/

-- Figure

-- Python
# -*- coding: utf-8 -*- import nltk from nltk.corpus import state_union from nltk.tokenize import PunktSentenceTokenizer print("[0]" + "-"*200) # -- train text open train_text = open('train_text.txt', 'r').read() print (train_text) print ("[1]" + "-"*200) # -- sample text open sample_text = open('sample_text.txt', 'r').read() print (sample_text) print ("[2]" + "-"*200) # # -- nltk 제공 데이터셋 호출 # train_text = state_union.raw("2005-GWBush.txt") # sample_text = state_union.raw("2006-GWBush.txt") # -- Punkt tokenizer Training(Unsupervised ML처리) custom_sent_tokenizer = PunktSentenceTokenizer(train_text) tokenized = custom_sent_tokenizer.tokenize(sample_text) print (tokenized) print ("[3]" + "-"*200) """ [ 'January 31, 2006\n\nTHE PRESIDENT: Thank you all.' , 'Mr. Speaker, Vice President Cheney, members of Congress, members of the Supreme Court and diplomatic corps , distinguished guests, and fellow citizens: Today our nation lost a beloved, graceful, courageous woman who called America to its founding ideals and carried on a noble dream.' , 'Tonight we are comforted by the hope of a glad reunion with the husband who was taken so long ago, and we are grateful for the good life of Coretta Scott King.' , '(Applause.)' , 'May God bless America.' , '(Applause.)' ] """ # -- Chunking def process_content(): try: for i in tokenized: print ("<tokenized> " + i.replace('\n','<BR>')) # toenized 건건이 출력 words = nltk.word_tokenize(i) print ("<word_tokenize> ") print (words) # 단어 토근 출력 tagged = nltk.pos_tag(words) print ("<tagged> ") print (tagged) # 형태소 출력 print("-" * 50) chunkGram = r"""Chunk: {<RB.?>*<VB.?>*<NNP>+<NN>?}""" # Chunking # chunkGram = r"""Chunk: {<.*>+} # }<VB.?|IN|DT|TO>+{""" # Chinking chunkParser = nltk.RegexpParser(chunkGram) chunked = chunkParser.parse(tagged) print(chunked) # Chunk 출력 chunked.draw() except Exception as e: print(str(e)) process_content() # -- 정규식 설명 """ <RB.?>* = "0 or more of any tense of adverb," followed by: <VB.?>* = "0 or more of any tense of verb," followed by: <NNP>+ = "One or more proper nouns," followed by <NN>? = "zero or one singular noun." """

-- Files

train_text.txt

sample_text.txt