pca 因子分析 lda tsne做数据降维效果比较

最新推荐文章于 2023-11-13 15:35:58 发布

weixin_41044499

最新推荐文章于 2023-11-13 15:35:58 发布

阅读量698

点赞数

文章标签： pca 因子分析 lda 数据降维

本文链接：https://blog.csdn.net/weixin_41044499/article/details/97394935

版权

用鸢尾花的4维数据，尝试不同的降维方式，观察变为两维数据后的效果

#!/usr/bin/python
# -*- coding:utf-8 -*-
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.decomposition import FactorAnalysis
from sklearn import metrics

if __name__ == "__main__":
    mpl.rcParams['font.sans-serif'] = [u'SimHei']
    mpl.rcParams['axes.unicode_minus'] = False

    iris_feature = '花萼长度', '花萼宽度', '花瓣长度', '花瓣宽度'
    path = 'iris.data'  # 数据文件路径
    data = pd.read_csv(path, header=None)
    x_prime = data.iloc[:,0:3]
    y = pd.Categorical(data[4]).codes
    from sklearn.decomposition import PCA
    from sklearn.manifold import TSNE

    pca = PCA(n_components=2)
    titles = ['原始数据','PCA','因子分析','tsne','lda']
    fa = FactorAnalysis(n_components=2)
    tsne = TSNE(n_components=2)
    from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
    lda = LinearDiscriminantAnalysis(n_components=2)
    model = [pca,fa,tsne,lda]
    plt.figure(figsize=(10,10))
    for i in [1,2,3,4,5]:
        plt.subplot(2,3,i)
        if i == 1:
            plt.scatter(x_prime.iloc[:, 0], x_prime.iloc[:, 1], c=y)
        elif i ==5:
            X_new = model[i - 2].fit_transform(x_prime,y)
            plt.scatter(X_new[:, 0], X_new[:, 1], c=y)
        else:
            X_new = model[i-2].fit_transform(x_prime)
            plt.scatter(X_new[:, 0], X_new[:, 1], c=y)
        plt.title(titles[i-1])
    plt.show()