机器学习——K-NN算法

 # 导入相关模块

    
 import numpy as np
    
 from collections import Counter
    
 import matplotlib.pyplot as plt
    
 from sklearn import datasets
    
 from sklearn.utils import shuffle
    
 # 导入sklearn iris数据集
    
 iris = datasets.load_iris()
    
 # 打乱数据后的数据与标签
    
 X, y = shuffle(iris.data, iris.target, random_state=13)
    
 # 数据转换为float32格式
    
 X = X.astype(np.float32)
    
 # 训练集与测试集的简单划分，训练-测试比例为7：3
    
 offset = int(X.shape[0] * 0.7)
    
 X_train, y_train = X[:offset], y[:offset]
    
 X_test, y_test = X[offset:], y[offset:]
    
 # 将标签转换为竖向量
    
 y_train = y_train.reshape((-1,1))
    
 y_test = y_test.reshape((-1,1))
    
 # 打印训练集和测试集大小
    
 print('X_train=', X_train.shape)
    
 print('X_test=', X_test.shape)
    
 print('y_train=', y_train.shape)
    
 print('y_test=', y_test.shape)

 ### 定义欧氏距离

    
 def compute_distances(X, X_train):
    
     '''
    
     输入：
    
     X：测试样本实例矩阵
    
     X_train：训练样本实例矩阵
    
     输出：
    
     dists：欧式距离
    
     '''
    
     # 测试实例样本量
    
     num_test = X.shape[0]
    
     # 训练实例样本量
    
     num_train = X_train.shape[0]
    
     # 基于训练和测试维度的欧氏距离初始化
    
     dists = np.zeros((num_test, num_train)) 
    
     # 测试样本与训练样本的矩阵点乘
    
     M = np.dot(X, X_train.T)
    
     # 测试样本矩阵平方
    
     te = np.square(X).sum(axis=1)
    
     # 训练样本矩阵平方
    
     tr = np.square(X_train).sum(axis=1)
    
     # 计算欧式距离
    
     dists = np.sqrt(-2 * M + tr + np.matrix(te).T)    
    
     return dists
    
  
    
 dists = compute_distances(X_test, X_train)
    
 plt.imshow(dists, interpolation='none')
    
 plt.show();

 ### 定义预测函数

    
 def predict_labels(y_train, dists, k=1):
    
     '''
    
     输入：
    
     y_train：训练集标签
    
     dists：测试集与训练集之间的欧氏距离矩阵
    
     k：k值
    
     输出：
    
     y_pred：测试集预测结果
    
     '''
    
     # 测试样本量
    
     num_test = dists.shape[0]
    
     # 初始化测试集预测结果
    
     y_pred = np.zeros(num_test) 
    
     # 遍历   
    
     for i in range(num_test):
    
     # 初始化最近邻列表
    
     closest_y = []
    
     # 按欧氏距离矩阵排序后取索引，并用训练集标签按排序后的索引取值
    
     # 最后拉平列表
    
     # 注意np.argsort函数的用法
    
     labels = y_train[np.argsort(dists[i, :])].flatten()
    
     # 取最近的k个值
    
     closest_y = labels[0:k]
    
     # 对最近的k个值进行计数统计
    
     # 这里注意collections模块中的计数器Counter的用法
    
     c = Counter(closest_y)
    
     # 取计数最多的那一个类别
    
     y_pred[i] = c.most_common(1)[0][0]    
    
     return y_pred
    
  
    
 # 测试集预测结果
    
 y_test_pred = predict_labels(y_train, dists, k=1)
    
 y_test_pred = y_test_pred.reshape((-1, 1))
    
 # 找出预测正确的实例
    
 num_correct = np.sum(y_test_pred == y_test)
    
 # 计算准确率
    
 accuracy = float(num_correct) / X_test.shape[0]
    
 print('Got %d/%d correct=>accuracy:%f'% (num_correct, X_test.shape[0], accuracy))

 # 导入KneighborsClassifier模块

    
 from sklearn.neighbors import KNeighborsClassifier
    
 # 创建k近邻实例
    
 knn_model = KNeighborsClassifier(n_neighbors=10)
    
 # k近邻模型拟合
    
 knn_model.fit(X_train, y_train)
    
 # k近邻模型预测
    
 y_pred = knn_model.predict(X_test)
    
 # 预测结果数组重塑
    
 y_pred = y_pred.reshape((-1, 1))
    
 # 统计预测正确的个数
    
 num_correct = np.sum(y_pred == y_test)
    
 # 计算准确率
    
 accuracy = float(num_correct) / X_test.shape[0]
    
 print('Got %d / %d correct => accuracy: %f' % (num_correct, X_test.shape[0], accuracy))