知识卡片
缩放公式必须随输入值变化
常见Min–Max缩放为zᵢ=(xᵢ−min_train)/(max_train−min_train)。原式分子仅写min(x),会使整列得到常数,必须纠正;常量特征分母为零还需明确处理规则。
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
- · 使用数据
原书出处 · 1 处
- · 查看原书依据
Data normalization in machine learning is a part of data preprocessing and data preparation. Normalization involves rescaling the values of all the features so that they lie in the range of 0 and 1 with a maximum of 1. The equation to normalize the values of a feature is given by:
参考来源
- 位置:《Machine Learning Fundamentals: Concepts, Models, and Applications》第05章《使用数据》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Machine Learning Fundamentals: Concepts, Models, and Applications/_epub-src/OEBPS/xhtml/17_chapter05.xhtml)
- 结论依据:摘录中关于缩放公式必须随输入值变化的定义、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:Data normalization in machine learning is a part of data preprocessing and data preparation. Normalization involves rescaling the values of all the features so that they lie in the range of 0 and 1 with a maximum of 1. The equation to normalize the values of a feature is given by:
- 生成时纠错核验:[官方文档](https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.MinMaxScaler.html)(2026-11-06;定义与接口职责,未执行书中示例)。