python: 단어 빈도수 통계

 

https://blog.naver.com/PostView.nhn?isHttpsRedirect=true&blogId=baek2sm&logNo=221371816296&categoryNo=0&parentCategoryNo=0&viewDate=&currentPage=1&postListTopCurrentPage=1&from=postView 

파이썬 웹사이트 단어 빈도수 통계내기

https://code.tutsplus.com/ko/tutorials/counting-word-frequency-in-a-file-using-python--cms-25965

파이썬을 이용해 파일에서 단어 빈도 계산하기

1.

 

from collections import Counter
import re

txt_path = '/Users/l.smin/PycharmProjects/pythonProject/img_object/detected_words.txt'
text = open(txt_path,'r')
text_str= text.read()
words = re.findall("\w+",text_str)
#print(words)

frequency = Counter(words).most_common()
#print(frequency)

frequency = dict(frequency)
print(frequency)

['bowl', 'bowl', 'bowl', 'dining', 'table', 'person', 'car', 'vase', 'potted', 'plant', 'bottle', 'bottle', 'bowl', 'bowl', 'bowl', 'cup', 'person', 'cup', 'person', 'dining', 'table', 'dog', 'person', 'car', 'person', 'truck', 'chair', 'dining', 'table', 'horse', 'dog', 'person', 'person', 'car', 'car', 'car', 'car', 'car', 'dining', 'table', 'person', 'person', 'car', 'car', 'truck', 'person', 'person', 'tie', 'bowl', 'sandwich', 'bowl', 'dining', 'table', 'bowl', 'tv', 'person', 'laptop', 'laptop', 'car', 'person', 'person', 'person', 'fire', 'hydrant', 'person', 'person', 'car', 'car', 'car', 'car', 'car', 'car', 'car', 'car', 'person', 'car', 'car', 'car', 'car', 'car', 'cat', 'cat', 'bowl', 'person', 'bowl', 'person', 'person', 'person', 'person', 'person', 'person', 'sandwich', 'broccoli', 'bowl', 'bowl', 'donut', 'dining', 'table', 'donut', 'person', 'chair', 'person', 'person', 'cat', 'airplane', 'wine', 'glass', 'cup', 'bowl', 'cup', 'dining', 'table', 'cup', 'pizza', 'bottle', 'person', 'person', 'frisbee', 'cup', 'bottle', 'person', 'banana', 'banana', 'banana', 'bottle', 'bottle', 'cup', 'person', 'person', 'person', 'person', 'person', 'person', 'bowl', 'dining', 'table', 'bowl', 'book', 'person', 'cat', 'vase', 'vase', 'vase', 'bed', 'person', 'bird', 'person', 'person', 'car', 'person', 'person', 'motorcycle', 'person', 'person', 'bicycle', 'bird', 'horse', 'cup', 'bottle', 'cat', 'horse', 'cow', 'person', 'suitcase', 'cake', 'bowl', 'bowl', 'dining', 'table', 'bowl', 'bowl']

[('person', 46), ('car', 24), ('bowl', 20), ('dining', 9), ('table', 9), ('cup', 8), ('bottle', 7), ('cat', 5), ('vase', 4), ('horse', 3), ('banana', 3), ('dog', 2), ('truck', 2), ('chair', 2), ('sandwich', 2), ('laptop', 2), ('donut', 2), ('bird', 2), ('potted', 1), ('plant', 1), ('tie', 1), ('tv', 1), ('fire', 1), ('hydrant', 1), ('broccoli', 1), ('airplane', 1), ('wine', 1), ('glass', 1), ('pizza', 1), ('frisbee', 1), ('book', 1), ('bed', 1), ('motorcycle', 1), ('bicycle', 1), ('cow', 1), ('suitcase', 1), ('cake', 1)]

{'person': 46, 'car': 24, 'bowl': 20, 'dining': 9, 'table': 9, 'cup': 8, 'bottle': 7, 'cat': 5, 'vase': 4, 'horse': 3, 'banana': 3, 'dog': 2, 'truck': 2, 'chair': 2, 'sandwich': 2, 'laptop': 2, 'donut': 2, 'bird': 2, 'potted': 1, 'plant': 1, 'tie': 1, 'tv': 1, 'fire': 1, 'hydrant': 1, 'broccoli': 1, 'airplane': 1, 'wine': 1, 'glass': 1, 'pizza': 1, 'frisbee': 1, 'book': 1, 'bed': 1, 'motorcycle': 1, 'bicycle': 1, 'cow': 1, 'suitcase': 1, 'cake': 1}

#save
total_txt_path = 'total.txt'
text_t = open(total_txt_path,'w+')
print(frequency, file=text_t)