KNN算法

基本思想

具体实例：

Python实现KNN算法

import matplotlib.pyplot as plt
import numpy as np
import operator

def knn(x_test, x_data, y_data, k):
    # 计算样本数量
    x_data_size = x_data.shape[0]
    # 复制x_test
    np.tile(x_test, (x_data_size,1))
    # 计算x_test与每一个样本的差值
    diffMat = np.tile(x_test, (x_data_size,1)) - x_data
    # 计算差值的平方
    sqDiffMat = diffMat**2
    # 求和
    sqDistances = sqDiffMat.sum(axis=1)
    # 开方
    distances = sqDistances**0.5
    # 从小到大排序
    sortedDistances = distances.argsort()
    classCount = {}
    for i in range(k):
        # 获取标签
        votelabel = y_data[sortedDistances[i]]
        # 统计标签数量
        classCount[votelabel] = classCount.get(votelabel,0) + 1
    # 根据operator.itemgetter(1)-第1个值对classCount排序，然后再取倒序
    sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1), reverse=True)
    # 获取数量最多的标签
    return sortedClassCount[0][0]


# 已知分类的数据
x_data = np.array([[3,104],
                   [2,100],
                   [1,81],
                   [101,10],
                   [99,5],
                   [81,2]])
y_data = np.array(['A','A','A','B','B','B'])
#要分类的数据
x_test = np.array([18,90])

#调用knn得到分类
Type=knn(x_test, x_data, y_data, 5)

Sklearn调用KNN算法

# 导入算法包以及数据集
from sklearn import neighbors
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report

# 载入数据
iris = datasets.load_iris()

#切分数据集
x_train,x_test,y_train,y_test = train_test_split(iris.data, iris.target, test_size=0.2) #分割数据0.2为测试数据，0.8为训练数据

# 构建模型
model = neighbors.KNeighborsClassifier(n_neighbors=3)
model.fit(x_train, y_train)
prediction = model.predict(x_test)

print(classification_report(y_test, prediction))