【机器学习】无监督学习--（降维）主成分分析PCA

注：数据集在文章末尾

1. PCA简单例子

import numpy as np
import matplotlib.pyplot as plt# 载入数据
data = np.genfromtxt("data.csv", delimiter=",")
x_data = data[:,0]
y_data = data[:,1]
plt.scatter(x_data,y_data)
plt.show()
print(x_data.shape)

输出：

# 数据中心化
def zeroMean(dataMat):# 按列求平均，即各个特征的平均meanVal = np.mean(dataMat, axis=0) newData = dataMat - meanValreturn newData, meanValnewData,meanVal=zeroMean(data)
# np.cov用于求协方差矩阵，参数rowvar=0说明数据一行代表一个样本
covMat = np.cov(newData, rowvar=0)
# 输出协方差矩阵
print(covMat)

输出：

# np.linalg.eig求矩阵的特征值和特征向量
eigVals, eigVects = np.linalg.eig(np.mat(covMat))
# 输出特征值
print(eigVals)
# 输出特征向量
print(eigVects)

输出：

# 对特征值从小到大排序
eigValIndice = np.argsort(eigVals)top = 1
# 最大的n个特征值的下标
n_eigValIndice = eigValIndice[-1:-(top+1):-1]# 最大的n个特征值对应的特征向量
n_eigVect = eigVects[:,n_eigValIndice]
print(n_eigVect)

输出：

# 低维特征空间的数据
lowDDataMat = newData*n_eigVect
# 利用低纬度数据来重构数据
reconMat = (lowDDataMat*n_eigVect.T) + meanVal# 载入数据
data = np.genfromtxt("data.csv", delimiter=",")
x_data = data[:,0]
y_data = data[:,1]
plt.scatter(x_data,y_data)# 重构的数据
x_data = np.array(reconMat)[:,0]
y_data = np.array(reconMat)[:,1]
plt.scatter(x_data,y_data,c='r')
plt.show()plt.show()

2. PCA手写数字降维可视化

from sklearn.neural_network import MLPClassifier
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report,confusion_matrix
import numpy as np
import matplotlib.pyplot as pltdigits = load_digits()#载入数据
x_data = digits.data #数据
y_data = digits.target #标签## x_data.shape = (1797,64)x_train,x_test,y_train,y_test = train_test_split(x_data,y_data) #分割数据1/4为测试数据，3/4为训练数据## 模型
mlp = MLPClassifier(hidden_layer_sizes=(100,50) ,max_iter=500)
mlp.fit(x_train,y_train)# 数据中心化
def zeroMean(dataMat):# 按列求平均，即各个特征的平均meanVal = np.mean(dataMat, axis=0) newData = dataMat - meanValreturn newData, meanValdef pca(dataMat,top):# 数据中心化newData,meanVal=zeroMean(dataMat) # np.cov用于求协方差矩阵，参数rowvar=0说明数据一行代表一个样本covMat = np.cov(newData, rowvar=0)# np.linalg.eig求矩阵的特征值和特征向量eigVals, eigVects = np.linalg.eig(np.mat(covMat))# 对特征值从小到大排序eigValIndice = np.argsort(eigVals)# 最大的n个特征值的下标n_eigValIndice = eigValIndice[-1:-(top+1):-1]# 最大的n个特征值对应的特征向量n_eigVect = eigVects[:,n_eigValIndice]# 低维特征空间的数据lowDDataMat = newData*n_eigVect# 利用低纬度数据来重构数据reconMat = (lowDDataMat*n_eigVect.T) + meanVal# 返回低维特征空间的数据和重构的矩阵return lowDDataMat,reconMat # 降成两维
lowDDataMat,reconMat = pca(x_data,2)# 重构的数据
x = np.array(lowDDataMat)[:,0]
y = np.array(lowDDataMat)[:,1]
plt.scatter(x,y,c='r')
plt.show()

输出：

predictions = mlp.predict(x_data)# 重构的数据
x = np.array(lowDDataMat)[:,0]
y = np.array(lowDDataMat)[:,1]
plt.scatter(x,y,c=y_data)
plt.show()

输出：

# 降成三维
lowDDataMat,reconMat = pca(x_data,3)from mpl_toolkits.mplot3d import Axes3D
x = np.array(lowDDataMat)[:,0]
y = np.array(lowDDataMat)[:,1]
z = np.array(lowDDataMat)[:,2]
ax = plt.figure().add_subplot(111, projection = '3d')
ax.scatter(x, y, z, c = y_data, s = 10) #点为红色三角形 plt.show()

输出：

数据集：“data.csv”：

32.502345269453031,31.70700584656992
53.426804033275019,68.77759598163891
61.530358025636438,62.562382297945803
47.475639634786098,71.546632233567777
59.813207869512318,87.230925133687393
55.142188413943821,78.211518270799232
52.211796692214001,79.64197304980874
39.299566694317065,59.171489321869508
48.10504169176825,75.331242297063056
52.550014442733818,71.300879886850353
45.419730144973755,55.165677145959123
54.351634881228918,82.478846757497919
44.164049496773352,62.008923245725825
58.16847071685779,75.392870425994957
56.727208057096611,81.43619215887864
48.955888566093719,60.723602440673965
44.687196231480904,82.892503731453715
60.297326851333466,97.379896862166078
45.618643772955828,48.847153317355072
38.816817537445637,56.877213186268506
66.189816606752601,83.878564664602763
65.41605174513407,118.59121730252249
47.48120860786787,57.251819462268969
41.57564261748702,51.391744079832307
51.84518690563943,75.380651665312357
59.370822011089523,74.765564032151374
57.31000343834809,95.455052922574737
63.615561251453308,95.229366017555307
46.737619407976972,79.052406169565586
50.556760148547767,83.432071421323712
52.223996085553047,63.358790317497878
35.567830047746632,41.412885303700563
42.436476944055642,76.617341280074044
58.16454011019286,96.769566426108199
57.504447615341789,74.084130116602523
45.440530725319981,66.588144414228594
61.89622268029126,77.768482417793024
33.093831736163963,50.719588912312084
36.436009511386871,62.124570818071781
37.675654860850742,60.810246649902211
44.555608383275356,52.682983366387781
43.318282631865721,58.569824717692867
50.073145632289034,82.905981485070512
43.870612645218372,61.424709804339123
62.997480747553091,115.24415280079529
32.669043763467187,45.570588823376085
40.166899008703702,54.084054796223612
53.575077531673656,87.994452758110413
33.864214971778239,52.725494375900425
64.707138666121296,93.576118692658241
38.119824026822805,80.166275447370964
44.502538064645101,65.101711570560326
40.599538384552318,65.562301260400375
41.720676356341293,65.280886920822823
51.088634678336796,73.434641546324301
55.078095904923202,71.13972785861894
41.377726534895203,79.102829683549857
62.494697427269791,86.520538440347153
49.203887540826003,84.742697807826218
41.102685187349664,59.358850248624933
41.182016105169822,61.684037524833627
50.186389494880601,69.847604158249183
52.378446219236217,86.098291205774103
50.135485486286122,59.108839267699643
33.644706006191782,69.89968164362763
39.557901222906828,44.862490711164398
56.130388816875467,85.498067778840223
57.362052133238237,95.536686846467219
60.269214393997906,70.251934419771587
35.678093889410732,52.721734964774988
31.588116998132829,50.392670135079896
53.66093226167304,63.642398775657753
46.682228649471917,72.247251068662365
43.107820219102464,57.812512976181402
70.34607561504933,104.25710158543822
44.492855880854073,86.642020318822006
57.50453330326841,91.486778000110135
36.930076609191808,55.231660886212836
55.805733357942742,79.550436678507609
38.954769073377065,44.847124242467601
56.901214702247074,80.207523139682763
56.868900661384046,83.14274979204346
34.33312470421609,55.723489260543914
59.04974121466681,77.634182511677864
57.788223993230673,99.051414841748269
54.282328705967409,79.120646274680027
51.088719898979143,69.588897851118475
50.282836348230731,69.510503311494389
44.211741752090113,73.687564318317285
38.005488008060688,61.366904537240131
32.940479942618296,67.170655768995118
53.691639571070056,85.668203145001542
68.76573426962166,114.85387123391394
46.230966498310252,90.123572069967423
68.319360818255362,97.919821035242848
50.030174340312143,81.536990783015028
49.239765342753763,72.111832469615663
50.039575939875988,85.232007342325673
48.149858891028863,66.224957888054632
25.128484647772304,53.454394214850524

【机器学习】无监督学习--（降维）主成分分析PCA相关推荐

无监督学习与主成分分析（PCA）
无监督学习与主成分分析(PCA) 序在之前的文章中,我讲了很多监督学习的算法(线性模型,SVM,决策树,神经网络等),那么接下来,我们要开始接触无监督学习了.首先,我们先说下相关概念. 无监督学习 ...
【火炉炼AI】机器学习053-数据降维绝招-PCA和核PCA
[火炉炼AI]机器学习053-数据降维绝招-PCA和核PCA (本文所使用的Python库和版本号: Python 3.6, Numpy 1.14, scikit-learn 0.19, matplo ...
机器学习-Sklearn-04（降维算法PCA和SVD）
机器学习-Sklearn-04(降维算法PCA和SVD) 学习04 1 概述 1.1 从什么叫"维度"说开来对于数组和Series来说,维度就是功能shape返回的结果,shap ...
机器学习系列笔记六:主成分分析PCA[下]
机器学习系列笔记六:主成分分析PCA[下] 文章目录机器学习系列笔记六:主成分分析PCA[下] scikit-learn中的PCA 基本使用进阶操作对比实验设置合理的n_components ...
李宏毅（2020）作业9：无监督学习降维、聚类、自编码
文章目录数据集作业任务1 任务2 任务3 数据下载数据集准备训练数据一些工具函数模型训练降维和聚类问题1(作图) 问题2 问题3 数据集 valX.npy valY.npy tra ...
降维 ---- 主成分分析 (PCA)、奇异值分解 (SVD)
降维在机器学习或数据处理中,经常会碰到一些高维数据,而高维数据情形下经常出现样本稀疏.计算困难等问题,称之为"维度灾难". 对于一个高维数据数 D={X1,X2,...,XN}D ...
【机器学习】特征降维-主成分分析
主成分分析目标应用PCA实现特征的降维应用:用户与物品类别之间主成分分析什么是主成分分析(PCA) 定义:高维数据转化为低维数据的过程,在此过程中可能会舍弃原有数据.创造新的变量作用:是数据 ...
机器学习-无监督学习-聚类：聚类方法（一）--- k-Means（k-均值）算法，k-Means++算法【使用最大期望值算法（EM算法）来求解】
一.聚类算法 1.聚类算法概述聚类算法:一种典型的无监督学习算法(没有目标值),主要用于将相似的样本自动归到一个类别中.在聚类算法中根据样本之间的相似性,将样本划分到不同的类别中,对于不同的相似度计 ...
机器学习——特征选择（降维）PCA和MDA
实际的分类问题和回归问题中,都有可能遇到多达50个或100个(甚至更多)的特征问题.对于分类问题来说,特征若为二值变量,我们通常认为其中的任何一个特征对于实现正确的分类都有它自己的贡献.但是,有理由怀 ...
吴恩达|机器学习作业7.1.主成分分析(PCA)
7.1.主成分分析对人脸图像降维 1)题目: 在这个练习中,你将运用主成分分析(PCA)来实现降维.首先,你将用一个二维的样本集来实验,从而对PCA如何运行的有一个直观的感受,然后再在一个更大的由50 ...

【机器学习】无监督学习--（降维）主成分分析PCA

1. PCA简单例子

2. PCA手写数字降维可视化

【机器学习】无监督学习--（降维）主成分分析PCA相关推荐

最新文章

热门文章