第3节:K邻近法原理即numpy实现版

# -*- coding:utf-8 -*-
# /usr/bin/python
'''
-------------------------------------------------------------------------
   @File Name      :  knn.py
   @Description    :  
   @Run Script     :  python  knn.py 
   @Envs           :  pip install 
   @Change Activity:
        1.  2021/12/3  下午1:48  : build
-------------------------------------------------------------------------
   @CodeStyle      :  standard, simple, readable, maintainable, and portable!
   @Author         :  Yan Errol 13075851954
   @Email          :  260187357@qq.com
   @Copyright      :  "Copyright 2021, Yan Errol"
-------------------------------------------------------------------------
'''
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from collections import Counter
# 加载读取数据

data = pd.read_csv("dataset.csv")
print(data.label.value_counts())
print("data\n",data)

# 数据可视化 验证线性可分性
plt.scatter(data[:50]['sepal length'], data[:50]['sepal width'], label='0')
plt.scatter(data[50:100]['sepal length'], data[50:100]['sepal width'], label='1')
plt.xlabel('sepal length')
plt.ylabel('sepal width')
plt.legend()
plt.show()
plt.savefig("show.png")

# 数据集拆分
data = np.array(data.iloc[:100,[0,1,-1]])
X,Y = data[:,:-1],data[:, -1]
XTrain,xtest,YTrain,ytest = train_test_split(X,Y,test_size=0.2)
class KNN():
    def __init__(self,XTrain,YTrain,nNeighbors=5,p=2):
        self.XTrain = XTrain
        self.YTrain = YTrain
        self.nNeighbors = nNeighbors
        self.p = p

    def predict(self,X):
        '''预测'''
        # 全局遍历
        knnlist = []
        for i in range(len(self.XTrain)):
            dist = np.linalg.norm(X - self.XTrain[i], ord=self.p)
            knnlist.append([round(dist,2), self.YTrain[i]])
        knnlist = sorted(knnlist,key=lambda x:x[0])
        minKnnlist = knnlist[0:self.nNeighbors]

        # 统计
        knn = [k[-1] for k in minKnnlist]
        count_pairs = Counter(knn)
        max_count = sorted(count_pairs, key=lambda x: x)[-1]
        return max_count

    def score(self,X_test, y_test):
        right_count = 0
        n = 10
        for X, y in zip(X_test, y_test):
            label = self.predict(X)
            if label == y:
                right_count += 1
        return right_count / len(X_test)

clf = KNN(XTrain, YTrain)
resultScore = clf.score(xtest, ytest)
print(resultScore)