学ぶ Eigenvalues and Eigenvectors | Mathematical Foundations of PCA

メニューを表示するにはスワイプしてください

Definition

An eigenvector of a matrix is a nonzero vector whose direction remains unchanged when a linear transformation (represented by the matrix) is applied to it; only its length is scaled. The amount of scaling is given by the corresponding eigenvalue.

For covariance matrix $\Sigma$ , eigenvectors point in the directions of maximum variance, and eigenvalues tell you how much variance is in those directions.

Mathematically, for matrix $A$ , eigenvector $v$ and eigenvalue $λ$ :

A v = \lambda v

In PCA, the eigenvectors of the covariance matrix are the principal axes, and the eigenvalues are the variances along those axes.


              12345678910111213
            
import numpy as np

# Using the covariance matrix from the previous code
X = np.array([[2.5, 2.4],
              [0.5, 0.7],
              [2.2, 2.9]])
X_centered = X - np.mean(X, axis=0)
cov_matrix = (X_centered.T @ X_centered) / X_centered.shape[0]

# Compute eigenvalues and eigenvectors
values, vectors = np.linalg.eig(cov_matrix)
print("Eigenvalues:", values)
print("Eigenvectors:\n", vectors)

Note

The eigenvector with the largest eigenvalue points in the direction of greatest variance in the data. This is the first principal component.

すべて明確でしたか？

フィードバックありがとうございます！

セクション 2. 章 2

AIに質問する

何でも質問するか、提案された質問の1つを試してチャットを始めてください

セクション 2. 章 2