NO.PZ2023091601000105
问题如下：
Suppose that we have the following data on three features for each
of three banks, A, B, and C:
Scale the features
using normalization and standardization.
解释：
Standardization
involves subtracting the mean of the observations across the three banks and
dividing by their standard deviation separately for each feature. The
normalization involves subtracting the minimum and dividing by the difference
between the maximum and minimum.
As an example,
undertaking the standardization for bank A and the customers feature, the
calculation would be
Similarly, the
normalization calculation for bank A and the customers feature would be
The full set of
standardizations and normalizations is
同学你好，1.2 6 0.5这三个数的均值是2.566667。这里标准化分子可以取绝对值的，所以2.56667-1.2=1.36667。
分母其实就是样本标准差，因为所有的银行才是全集，这三家银行只是样本。
样本标准差的计算就是1.2 、 6 、 0.5 这三个数分别减去2.56667，得到的三个数的平方和即17.92667
除以n-1，这里3个样本，所以n=3，得到8.96333再开方等于2.993883即是样本标准差。
1.36667/2.993883=0.456486
老师这是您对其他学生的解答
您是不是算反了？讲的公式是“（X-均值）/标准差”您算的是（均值-X）/标准差。而且知识框架图给的公式，分母是总体方差，您这里用的又是样本方差…到底该用啥？
