KNN算法和实现

 

 KNN要用到欧氏距离

 

 KNN下面的缺点很容易使分类出错（比如下面黑色的点）

 

 下面是KNN算法的三个例子demo，

第一个例子是根据算法原理实现

 

import matplotlib.pyplot as plt
import numpy as np
import operator
# 已知分类的数据
x1 = np.array([3,2,1])
y1 = np.array([104,100,81])
x2 = np.array([101,99,98])
y2 = np.array([10,5,2])
scatter1 = plt.scatter(x1,y1,c='r')
scatter2 = plt.scatter(x2,y2,c='b')
# 未知数据
x = np.array([18])
y = np.array([90])
scatter3 = plt.scatter(x,y,c='k')
#画图例
plt.legend(handles=[scatter1,scatter2,scatter3],labels=['labelA','labelB','X'],loc='best')
plt.show()
# 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'])
x_test = np.array([18,90])
# 计算样本数量
x_data_size = x_data.shape[0]
print(x_data_size)
# 复制x_test
print(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
diffMat
# 计算差值的平方
sqDiffMat = diffMat**2
sqDiffMat
# 求和
sqDistances = sqDiffMat.sum(axis=1)
sqDistances
# 开方
distances = sqDistances**0.5
print(distances)
# 从小到大排序
sortedDistances = distances.argsort()#返回distances里的数据从小到大的下标数组
print(sortedDistances)
classCount = {}
# 设置k
k = 5
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#)0表示没有该字典里没有该值时默认为0
classCount
# 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)
print(sortedClassCount)
# 获取数量最多的标签
knnclass = sortedClassCount[0][0]#第一个0表示取第一个键值对('A', 3)，第二个0表示取('A', 3)的‘A’
print(knnclass)

 1 import numpy as np#对iris数据集进行训练分类
from sklearn import  datasets
from sklearn.model_selection import  train_test_split
from sklearn.metrics import  classification_report,confusion_matrix#对模型分类结果进行评估的两个模型
import operator#https://blog.csdn.net/u010339879/article/details/98304292，关于operator的使用
import  random
def knn(x_test, x_data, y_data, k):
    x_data_size = x_data.shape[0]  # 计算样本数量
    diffMat = np.tile(x_test,(x_data_size,1)) - x_data# 复制x_test，计算x_test与每一个样本的差值
    sqDiffMat = diffMat**2# # 计算差值的平方
    sqDistance = sqDiffMat.sum(axis= 1) # 求和
    distances = sqDistance**0.5 # 开方
    sortedDistance = distances.argsort()# 从小到大排序
    classCount = {}
    for i in range(k):
        vlabel = y_data[sortedDistance[i]] # 获取标签
        classCount[vlabel] = classCount.get(vlabel,0)+1# 统计标签数量
    sortedClassCount = sorted(classCount.items(),key = operator.itemgetter(1), reverse = True) # 根据operator.itemgetter(1)-第1个值对classCount排序，然后再取倒序
    return  sortedClassCount[0][0]
iris = datasets.load_iris()# 载入数据
x_train,x_test,y_train,y_test = train_test_split(iris.data, iris.target, test_size=0.3)
#打乱数据
# data_size = iris.data.shape[0]
# index = [i for i in range(data_size)]
# random.shuffle(index)
# iris.data = iris.data[index]
# iris.target = iris.target[index]
# test_size = 40#切分数据集
# x_train = iris.data[test_size:]
# x_test = iris.data[:test_size]
# y_train = iris.target[test_size:]
# y_test = iris.target[:test_size]
prodictions = []
for i in range(x_test.shape[0]):
    prodictions.append(knn(x_test[i],x_train,y_train,5))
print(prodictions)
print(classification_report(y_test, prodictions))
print(confusion_matrix(y_test,prodictions))
#关于混淆矩阵可以看这篇博客，#https://www.cnblogs.com/missidiot/p/9450662.html

 

# 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
import random
# 载入数据
iris = datasets.load_iris()
#print(iris)
# 打乱数据切分数据集
# 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

#打乱数据
data_size = iris.data.shape[0]
index = [i for i in range(data_size)]
random.shuffle(index)
iris.data = iris.data[index]
iris.target = iris.target[index]

#切分数据集
test_size = 40
x_train = iris.data[test_size:]
x_test =  iris.data[:test_size]
y_train = iris.target[test_size:]
y_test = iris.target[:test_size]

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

这三个代码第一个，第二个是根据底层原理实现knn算法，第三个则是调用库函数处理数据。

 下面一个代码是利用第三个代码中用到的库实现第一个代码功能，可以发现使用系统提供的库，简单许多

from sklearn import  neighbors
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
import numpy as np
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'])
x_test1 = np.array([[18,90]])
x_train, x_test, y_train,y_test = train_test_split(x_data, y_data,test_size= 0.3)
model = neighbors.KNeighborsClassifier(n_neighbors=3)
model.fit(x_train, y_train)
print(x_test1)
prediction = model.predict(x_test1)
print(prediction)

 

对字典进行排序：dic = sorted(dic.items(),key = operator.itemgetter(1),reverse=True)