# TF-IDF算法示例
# 0.引入依赖
import numpy as np
import pandas as pd
import math
# 1.定义数据和预处理
docA = "The cat sat on my bed"
docB = "The dog sat on my knees"
bowA = docA.split(" ")
bowB = docB.split(" ")
# print(bowA, bowB)
# 构建词库
wordSet = set(bowA).union(bowB)
# print(wordSet)
# 2.进行词数统计
# 用统计字典来保存词出现的次数
wordDictA = dict.fromkeys(wordSet, 0)
wordDictB = dict.fromkeys(wordSet,
TF-IDF算法示例代码
最新推荐文章于 2022-05-20 21:58:15 发布