基于 Python 的 11 种经典数据降维算法|线性-LDA(Linear Discriminant Analysis)降维算法

线性- LDA(Linear Discriminant Analysis)降维算法

LDA 是一种可作为特征抽取的技术，其目标是向最大化类间差异，最小化类内差异的方向投影，以利于分类等任务即将不同类的样本有效的分开。LDA 可以提高数据分析过程中的计算效率，对于未能正则化的模型，可以降低维度灾难带来的过拟合。

LDA 降维算法展示

• 详细内容可参见《数据降维—线性判别分析(LDA)》：
  https://blog.csdn.net/ChenVast/article/details/79227945
• 代码参考：

#coding:utf-8
import numpy as np
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.datasets import load_iris
import matplotlib.pyplot as plt

'''
author: heucoder
email: 812860165@qq.com
date: 2019.6.13
'''


def lda(data, target, n_dim):
    '''
    :param data: (n_samples, n_features)
    :param target: data class
    :param n_dim: target dimension
    :return: (n_samples, n_dims)
    '''

    clusters = np.unique(target)

    if n_dim > len(clusters)-1:
        print("K is too much")
        print("please input again")
        exit(0)

    #within_class scatter matrix
    Sw = np.zeros((data.shape[1],data.shape[1]))
    for i in clusters:
        datai = data[target == i]
        datai = datai-datai.mean(0)
        Swi = np.mat(datai).T*np.mat(datai)
        Sw += Swi

    #between_class scatter matrix
    SB = np.zeros((data.shape[1],data.shape[1]))
    u = data.mean(0)  #所有样本的平均值
    for i in clusters:
        Ni = data[target == i].shape[0]
        ui = data[target == i].mean(0)  #某个类别的平均值
        SBi = Ni*np.mat(ui - u).T*np.mat(ui - u)
        SB += SBi
    S = np.linalg.inv(Sw)*SB
    eigVals,eigVects = np.linalg.eig(S)  #求特征值，特征向量
    eigValInd = np.argsort(eigVals)
    eigValInd = eigValInd[:(-n_dim-1):-1]
    w = eigVects[:,eigValInd]
    data_ndim = np.dot(data, w)

    return data_ndim

if __name__ == '__main__':
    iris = load_iris()
    X = iris.data
    Y = iris.target
    data_1 = lda(X, Y, 2)

    data_2 = LinearDiscriminantAnalysis(n_components=2).fit_transform(X, Y)


    plt.figure(figsize=(8,4))
    plt.subplot(121)
    plt.title("my_LDA")
    plt.scatter(data_1[:, 0], data_1[:, 1], c = Y)

    plt.subplot(122)
    plt.title("sklearn_LDA")
    plt.scatter(data_2[:, 0], data_2[:, 1], c = Y)
    plt.savefig("LDA.png")
    plt.show()

• 代码地址：https://github.com/heucoder/dimensionality_reduction_alo_codes/tree/master/codes/LDA