Python提取文本tf、idf

"""python提取文本的tfidf特徵"""

import math
from collections import Counter

# 1.語料庫
corpus = [
    'this is the first document',
    'this is the second second document',
    'and the third one',
    'is this the first document'
]

# 2.對語料進行分詞
word_list = []
for i in range(len(corpus)):
    word_list.append(corpus[i].split(' '))
print('2-->', word_list)

# 3.統計詞頻
countlist = []
for i in range(len(word_list)):
    count = Counter(word_list[i])
    countlist.append(count)
print('3詞頻-->', countlist)


# 4.定義計算tfidf公式的函數
# count[word]可以得到每個單詞的詞頻， sum(count.values())得到整個句子的單詞總數
def tf(word, count):
    return count[word] / sum(count.values())


# 統計的是含有該單詞的句子數
def n_containing(word, count_list):
    return sum(1 for count in count_list if word in count)


# len(count_list)是指句子的總數，n_containing(word, count_list)是指含有該單詞的句子的總數，加1是爲了防止分母爲0
def idf(word, count_list):
    return math.log(len(count_list) / (1 + n_containing(word, count_list)))


# 將tf和idf相乘
def tfidf(word, count, count_list):
    return tf(word, count) * idf(word, count_list)


all_dict = {}
for counte in countlist:
    counter = dict(counte)
    for k, v in counter.items():
        try:
            all_dict[k] += v
        except:
            all_dict[k] = v
print('merge-->', all_dict)

with open('tf.txt', 'w+') as tfin, open('idf.txt', 'w+') as idfin:
    for k in all_dict.keys():
        # k_tf = tf(k, all_dict)
        tfin.write(k + ' ' + str(all_dict[k]) + '\n')
        k_idf = idf(k, countlist)
        idfin.write(k + ' ' + str(k_idf) + '\n')