机器学习实战-PCA算法-26

PCA算法-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 plt

digits = load_digits()#载入数据
x_data = digits.data #数据
y_data = digits.target #标签

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

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 - meanVal
    return newData, meanVal

def 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