[Py3.5] Tokenizing, POS Tagging, Chunking, Lemmatizing /w TextBlob

/*******************************************************************************************************************
-- Title : [Py3.5] Tokenizing, POS Tagging, Chunking, Lemmatizing /w TextBlob
-- Reference : textblob.readthedocs.io/en/dev/quickstart.html
-- Key word : textblob tokenizing pos tagging chunking lemmatizing sentences words tags non-phrases
                  lemmatize singularize pluralize 자연어 처리 품사 태깅 청킹 len
*******************************************************************************************************************/

■ TextBlob Script

from textblob import TextBlob
 
# TextBlob API : textblob.readthedocs.io/en/dev/api_reference.html#textblob.blob.TextBlob.noun_phrases
 
# ------------------------------
# -- Blob Raw Text
# ------------------------------
raw_blob = TextBlob("""Python is a high-level, general-purpose programming language.
This Programm is made by DdolI in Netherland.
Part-of-speech tags can be accessed through the tags property.
octopi went""")
 
print(raw_blob)
print("... blob_raw_text", "." * 100, "\n")
 
 
# ------------------------------
# -- Tokenizing
# ------------------------------
 
# -- sentence tokenizing
print(raw_blob.sentences)
print(",,, sent_tokenizing", "," * 100, "\n")
 
# -- word tokenizing
print(raw_blob.words)
print(",,, word_tokenizing", "," * 100, "\n")
 
# -- token words counting
print (len(raw_blob.words))
print(",,, word_token counting", "," * 100, "\n")
 
 
# ------------------------------
# -- POS Tagging and Chunking
# ------------------------------
 
# -- POS Tagging
print(raw_blob.tags)
print(";;; pos_tagging", ";" * 100, "\n")
 
# -- Noun Phrase Chunking
print(raw_blob.noun_phrases)
print(";;; np chunking", ";" * 100, "\n")
 
 
# ------------------------------
# -- Lemmatizing
# ------------------------------
 
print("복수:", raw_blob.words[16], "   단수:", raw_blob.words[6])
print("---------------------------------------")
print("단수화:", raw_blob.words[16].singularize())
print("복수화:", raw_blob.words[6].pluralize())
print("")
 
print("과거형:", raw_blob.words[-1], "   복수:", raw_blob.words[-2])
print("---------------------------------------")
print("현재형:", raw_blob.words[-1].lemmatize('v'))
print("단수형:", raw_blob.words[-2].lemmatize())  # = print (raw_blob.words[-2].lemmatize('n'))
 
print("!!! lemmatizing", "!" * 100, "\n")