知识卡片
矩阵命名不能替代实际行列核验
本章实际tfidf_docs为5000行评论、19169列词项,属于文档×词项。术语term-document在其他记法可能正好相反;检查shape、行索引和列词表再计算,不能根据名字把文档与词项轴交换。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 从词数到语义分析
原书出处 · 1 处
- · 查看原书依据
Let’s start with the dataset itself. You’ll use the same comment corpus you used for the LDA classifier in section 4.1 and transform it into a matrix, using TF–IDF. You might remember that the result is called a term-document matrix. This name is useful because it gives you an intuition about what the rows and the columns of the matrix contain: the rows contain terms—your
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第04章《从词数到语义分析》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-4.html)
- 结论依据:摘录中关于矩阵命名不能替代实际行列核验的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:Let’s start with the dataset itself. You’ll use the same comment corpus you used for the LDA classifier in section 4.1 and transform it into a matrix, using TF–IDF. You might remember that the result is called a term-document matrix. This name is useful because it gives you an intuition about what the rows and the columns of the matrix contain: the rows contain terms—your