说明：  PCA（Principal Component Analysis）不仅仅是对高维数据进行降维，更重要的是经过降维去除了噪声，发现了数据中的模式。 PCA把原先的n个特征用数目更少的m个特征取代，新特征是旧特征的线性组合，这些线性组合最大化样本方差，尽量使新的m个特征互不相关。从旧特征到新特征的映射捕获数据中的固有变异性。
(PCA (Principal Component Analysis) is not just for high-dimensional data dimensionality reduction, more importantly, is the result of dimensionality reduction removes noise and found patterns in the data. PCA of the original n features with less number of m feature substitution, the new feature is a linear combination of the old features, which maximize a linear combination of the sample variance, try to make the new features of m uncorrelated. Mapping feature to capture data the old to the new features inherent variability.)