Python之k近邻算法

k-近邻算法（kNN）：如果一个样本在特征空间的k个最相似（即特征空间中最近邻）的样本大多数属于某一类别，则该样本也属于这一类别。

• 样本的最近邻是根据欧氏距离公式定义的

import numpy as np
import operator

def knn(test, trains, labels, k):
    trainsSize = trains.shape[0]
    values = np.tile(test, (trainsSize, 1)) - trains
    sqValues = values ** 2
    sqDistances = sqValues.sum(axis = 1)
    distances = sqDistances ** 0.5
    sortedDists = np.argsort(distances)
    classCount = {}
    for i in range(k):
        voteLabel = labels[sortedDists[i]]
        classCount[voteLabel] = classCount.get(voteLabel,0) + 1
    classCount = classCount.items()
    sortClassCount = sorted(classCount, key=operator.itemgetter(1), reverse=True)
    return sortClassCount[0][0]

trains = [[3 , 104],
          [2 , 100],
          [1 , 81],
          [101 , 10],
          [99 , 5],
          [98 , 2]]
# ‘1’表示爱情片，‘2’表示动作片
labels = [1 , 1 , 1 , 2 , 2, 2]
test = [18 , 90]
k = 3

trains = np.array(trains)
labels = np.array(labels)
test = np.array(test)
print('测试样本的类别：' + str(knn(test, trains, labels, k)))