import numpy as np
import matplotlib.pyplot as plt
#训练样本(前4个为A类,后3个为B类)
x_train = np.array([[4, 5], [6, 7], [4.8, 7], [5.5, 8], [7, 8], [10, 11], [9, 14]])
y_train = ['A', 'A', 'A', 'A', 'B', 'B', 'B']
#测试样本(6个)
x_test = np.array([[3.5, 7], [9, 13], [8.7, 10], [5, 6], [7.5, 8], [9.5, 12]])
plt.xlabel("X")
plt.ylabel("Y")
plt.title("KNN")
plt.plot(x_train[0:4,0],x_train[0:4,1],color='pink',marker='o',label='One Class A',linestyle='None')
plt.plot(x_train[4:7,0],x_train[4:7,1],color='c',marker='s',label='Two Class B',linestyle='None')
plt.plot(x_test[:,0],x_test[:,1],color='g',marker='^',label='?',linestyle='None')
for i in range(len(x_test)):
plt.text(x_test[i,0]-0.3,x_test[i,1]+0.3, str(i) + '->?')
plt.legend(loc='upper left')
plt.grid(True)
plt.show()
#KNN分类
class KNN():
#导入训练样本
def fit(self, x_train, y_train):
self.x_train = x_train
self.y_train = y_train
#使用反函数为近邻分配权重
def inverse_weight(self,dist,num=1.0,const=0.1):
return num/(dist+const)
# 预测1个样本的类别
def predict_once(self, x_test, k, T=0): # T:普通/加权
N = self.x_train.shape[0] #shape[0] :读取行数;shape[1]:读取列数
x_test_ext = np.tile(x_test, [N, 1]) #就是把x_test先沿x轴复制1倍,即没有复制,仍然是 x_test。 再把结果沿y方向复制N倍
euclidean_distance = np.sqrt(np.sum(np.power(np.subtract(x_test_ext, self.x_train), 2), 1)) #subtract:逐个元素对应相减
inx = np.argsort(euclidean_distance) #返回列表中数值从小到大的索引
if T == 0: # 根据K个近邻中对应样本最多的类别进行分类
# 累计每个类别对应的样本数
class_predict = np.zeros(2)
for i in range(k):
idx = inx[i]
if self.y_train[idx] == 'A':
class_predict[0] += 1
else:
class_predict[1] += 1
class_label = 'B' if np.argmax(class_predict) else 'A' #argmax判断最大值的索引,并返回索引下的A,B值
return class_label
else: # 根据K个近邻中对应样本的距离权重进行分类
distance_weight = np.zeros(2) # 累加权重
for i in range(k):
idx = inx[i]
if self.y_train[idx] == 'A':
distance_weight[0] += self.inverse_weight(euclidean_distance[idx])
else:
distance_weight[1] += self.inverse_weight(euclidean_distance[idx])
class_label = 'B' if np.argmax(distance_weight) else 'A'
return class_label
def predict(self, x_test, k, T=0):
class_predict = []
for i in range(len(x_test)):
class_predict.append(self.predict_once(x_test[i, :], k, T))
return class_predict
#KNN分类预测
knn = KNN()
knn.fit(x_train, y_train)
y_predict = knn.predict(x_test, 3, 0) #T=0/1
print(y_predict)
print("================")
#显示结果
plt.xlabel('X')
plt.ylabel('Y')
plt.title('KNN')
plt.plot(x_train[0:4,0], x_train[0:4,1], color='pink', marker='o', label='One Class (A)', linestyle='None') #显示”A”类
plt.plot(x_train[4:8,0], x_train[4:8,1], color='c', marker='s', label='Two Class (B)', linestyle='None') #显示”B”类
for i in range(len(x_test)): #显示预测结果
if y_predict[i] == 'A':
plt.plot(x_test[i,0], x_test[i,1], color='pink', marker='o')
plt.text(x_test[i,0]-0.3, x_test[i,1]+0.3, str(i) + '->A')
else:
plt.plot(x_test[i,0], x_test[i,1], color='c', marker='s')
plt.text(x_test[i,0]-0.3, x_test[i,1]+0.3, str(i) + '->B')
plt.legend(loc='upper left')
plt.grid(True)
plt.show()
预测分类结果:
['A', 'B', 'B', 'A', 'A', 'B']