如何使用 scikit-learn 从线性判别分析中获取特征向量 [英] How to get eigenvectors from Linear Discriminant Analysis with scikit-learn

问题描述

如何从 scikit-learn 线性判别分析对象中获得基数变化矩阵?

How can one obtain the change-of-basis matrix from a scikit-learn linear discriminant analysis object?

对于具有形状 mxp(m 样本和 p 特征)和 N 的数组 X 类，缩放矩阵有 p 行和 N-1 列.该矩阵可用于将数据从原始空间变换到线性子空间.

For an array X with shape m x p (m samples and p features) and N classes, the scaling matrix has p rows and N-1 columns. This matrix can be used to transform the data from the original space to the linear subspace.

在艾莉亚的回答后

让我们考虑以下示例:

from sklearn.datasets import make_blobs
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA

X, label = make_blobs(n_samples=100, n_features=2, centers=5, cluster_std=0.10, random_state=0)
lda = LDA()
Xlda = lda.fit(X, label)
Xlda.scalings_
#array([[ 7.35157288,  6.76874473],
#       [-6.45391558,  7.97604449]])
Xlda.scalings_.shape
#(2, 2)

我希望 scales_ 矩阵形状为 (2,4)，因为我有 2 个特征，而 LDA 将提供 5-1 个组件.

I would expect the scalings_ matrix shape to be (2,4) as I have 2 features and the LDA would provide 5-1 components.

推荐答案

让我们调用您的 LinearDiscriminantAnalysis 对象 lda.您可以通过 lda.scalings_ 访问缩放矩阵.描述这一点的文档显示在这里.

Let's call your LinearDiscriminantAnalysis object lda. You can access the scaling matrix as lda.scalings_. The documentation that describes this is shown here.

import sklearn.datasets as ds
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA

iris = ds.load_iris()
iris.data.shape
# (150, 4)
len(iris.target_names)
# 3

lda = LDA()
lda.fit(iris.data, iris.target)
lda.scalings_
# array([[-0.81926852,  0.03285975],
#        [-1.5478732 ,  2.15471106],
#        [ 2.18494056, -0.93024679],
#        [ 2.85385002,  2.8060046 ]])
lda.scalings_.shape
# (4, 2)

这篇关于如何使用 scikit-learn 从线性判别分析中获取特征向量的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！