《模式识别与智能计算》基于类中心的欧式距离法分类

import numpy as np
import random
def train_test_split(x,y,ratio = 3):
    """
    :function: 对数据集划分为训练集、测试集
    :param x: m*n维 m表示数据个数 n表示特征个数
    :param y: 标签
    :param ratio: 产生比例 train:test = 3:1(默认比例)
    :return: x_train y_train  x_test y_test
    """
    n_samples , n_train = x.shape[0] , int(x.shape[0]*(ratio)/(1+ratio))
    train_id = random.sample(range(0,n_samples),n_train)
    x_train = x[train_id,:]
    y_train = y[train_id]
    x_test = np.delete(x,train_id,axis = 0)
    y_test = np.delete(y,train_id,axis = 0)
    return x_train,y_train,x_test,y_test
    
def euclid(x_train,y_train,sample):
    """
    :function: 基于类中心的模板匹配法
    :param x_train:训练集 M*N  M为样本个数 N为特征个数
    :param y_train:训练集标签 1*M
    :param sample: 待识别样品
    :return: 返回判断类别
    """
    disMin = np.inf
    label = 0
    #去除标签重复元素
    target = np.unique(y_train)
    for i in target:
        #将同一类别的数据下标集中到一起
        trainId =([j for j,y in enumerate(y_train) if y==i])
        train = x_train[trainId,:]
        trainMean = np.mean(train, axis=0)
        dis = np.dot((sample-trainMean),(sample - trainMean).T)
        if(disMin>dis):
            disMin = dis
            label = i
    return label

from sklearn import datasets
from Include.chapter3 import function
import numpy as np

#读取数据
digits = datasets.load_digits()
x , y = digits.data,digits.target

#划分数据集
x_train, y_train, x_test, y_test = function.train_test_split(x,y)
testId = np.random.randint(0, x_test.shape[0])
sample = x_test[testId, :]

#基于类中心的欧式距离法分类
ans = function.euclid(x_train,y_train,sample)
y_test[testId]
print("预测的数字类型",ans)
print("真实的数字类型",y_test[testId])

预测的数字类型 4
真实的数字类型 4