知识卡片
关闭逆频率仍可能保留归一化
TfidfVectorizer设置use_idf=False仅关闭IDF乘权,默认L2归一化通常仍在,因此输出不等于原始计数。出生计数作为损失样本权重是另一环节,不会自动成为字符n-gram的DF;不能混同这两类频率。
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
- · 神经网络基础
原书出处 · 1 处
- · 查看原书依据
>>> vectorizer = TfidfVectorizer( ... use_idf=False, #1 ... analyzer='char', ... ngram_range=(1, 3) #2 ... ) >>> vectorizer TfidfVectorizer(analyzer='char', ngram_range=(1, 3), use_idf=False) #1 Prevents the vectorizer from dividing each row vector by the inverse document frequency #2 PostgreSQL and other full-text search features use a “trigram index” of 1-, 2-, and 3-character n-grams. Shouldn’t you normalize the token counts by something like document frequency? You will
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第05章《神经网络基础》(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-5.html)
- 结论依据:摘录中关于关闭逆频率仍可能保留归一化的定义、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:>>> vectorizer = TfidfVectorizer( ... use_idf=False, #1 ... analyzer='char', ... ngram_range=(1, 3) #2 ... ) >>> vectorizer TfidfVectorizer(analyzer='char', ngram_range=(1, 3), use_idf=False) #1 Prevents the vectorizer from dividing each row vector by the inverse document frequency #2 PostgreSQL and other full-text search features use a “trigram index” of 1-, 2-, and 3-character n-grams. Shouldn’t you normalize the token counts by something like document frequency? You will