K近邻算法的代码实现

0.引入依赖

import numpy as np
import pandas as pd

//这里直接引入sklearn里的数据集，iris
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split  //切分数据集为训练集和测试集
from sklearn.metrics import accuracy_score  //计算分类预测的准确率

1.数据的加载和预处理

iris = load_iris()
//iris
df = pd.DataFrame(iris.data,columns  = iris.feature_names)
df['class'] = iris.target
df['class'] = df['class'].map({0:iris.target_names[0],1:iris.target_names[1],2:iris.target_names[2]})
df.describe()

x = iris.data
y = iris.target.reshape(-1,1)

//划分训练集和测试集
x_train,x_test,y_train,y_test = train_test_split(x, y, test_size = 0.3, random_state = 35,stratify = y)

2.核心算法实现

//距离函数定义
def l1_distance(a, b):
    return np.sum(np.abs(a-b), axis = 1) //axis的作用是将运算结果保存成一列

def l2_distance(a, b):
    return np.sqrt(np.sum((a-b) ** 2, axis = 1))

//分类器的实现
class KNN(object):
    //定义一个初始化方法，__init__是类的构造方法
    def __init__(self, n_neighbors = 1, dist_func = l1_distance):
        self.n_neighbors = n_neighbors
        self.dist_func  = dist_func
    
    //训练模型方法
    def fit(self, x, y):
        self.x_train = x
        self.y_train = y
    
    //模型预测方法
    def predict(self, x):
        //初始化预测分类数组
        y_pred = np.zeros( (x.shape[0], 1), dtype = self.y_train.dtype )
        
        //遍历输入的x数据点，取出每一个数据点的i和数据x_test
        for i, x_test in enumerate(x):
            //x_test跟所有训练数据计算距离
            distances = self.dist_func(self.x_train, x_test)
            
            //得到的距离按照由近到远排序
            nn_index = np.argsort(distances)
            
            //选取最近的k个点，保存他们对应的分类类别
            nn_y = self.y_train[nn_index[:self.n_neighbors]].ravel() //对nn_index做一个切片将前k个取出来
            
            //统计类别中出现频率最高的那个，赋给y_pred[i]
            y_pred[i] = np.argmax( np.bincount(nn_y) )
        
        return y_pred

3.测试

knn = KNN(n_neighbors = 3)
//训练模型
knn.fit(x_train, y_train)
//传入测试数据，做预测
y_pred = knn.predict(x_test)

//求出预测准确率
accuracy = accuracy_score(y_test, y_pred)

print("预测准确率： ",accuracy)

预测准确率： 0.9333333333333333

//实例化一个knn对象
knn = KNN(n_neighbors = 3)
//训练模型
knn.fit(x_train, y_train)

//保存结果list
result_list = []

//针对不同的参数选取，做预测
for p in [1, 2]:
    knn.dist_func = l1_distance if p==1 else l2_distance
    
    //考虑不同的k取值
    for k in range(1, 10 ,2):  //二元分类一般需要规定步长为2
        knn.n_neighbors = k
        //传入测试数据，做预测
        y_pred = knn.predict(x_test)
        
        //求出预测准确率
        accuracy = accuracy_score(y_test, y_pred)
        result_list.append([k, 'l1_distance' if p==1 else 'l2_distance', accuracy])
df = pd.DataFrame(result_list, columns = ['k', '距离函数', '预测准确率'])
df