计算Documenttermmatrix矩阵中的标记数量

import numpy as np

# 假设有3个文档和5个词项
documents = [
    "This is the first document",
    "This document is the second document",
    "And this is the third one"
]

# 预处理文本数据，将文本转化为词项列表
tokenized_documents = [doc.lower().split() for doc in documents]

# 获取所有词项的列表
all_terms = list(set([term for doc in tokenized_documents for term in doc]))

# 创建空的文档-词项矩阵
document_term_matrix = np.zeros((len(tokenized_documents), len(all_terms)))

# 统计每个词项在每个文档中的出现次数
for i, doc in enumerate(tokenized_documents):
    for j, term in enumerate(all_terms):
        document_term_matrix[i, j] = doc.count(term)

# 计算每个词项在所有文档中的总出现次数
term_counts = np.sum(document_term_matrix, axis=0)

# 输出标记数量
for term, count in zip(all_terms, term_counts):
    print(f"词项 '{term}' 的标记数量为 {count}")