《模式识别与智能计算》二值化的夹角余弦距离法分类

def erzhianglecos(x_train,y_train,sample):
    """
    :function 按照二值夹角余弦距离法计算待测样品与样品库中的相似度
    :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
    """
    #二值化
    spit  = 0.5*(np.max(x_train) - np.min(x_train))
    train = np.where(x_train>spit,1,0)
    sample = np.where(sample>spit,1,0)
    #计算夹角余弦
    erZhiAng = np.sum(train*sample)/np.sqrt(np.sum(train^2)*np.sum(sample^2))
    #值越大越相似
    disMaxId = np.argmax(erZhiAng)
    label = y_train[disMaxId]
    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, :]


ans = function.anglecos(x_train,y_train,sample)
print(ans==y_test[testId])

True