KMeans算法

import numpy as np
import pandas as pd
# 引入sklearn里的iris鸢尾花数据集
from sklearn.datasets import load_iris
#切分数据集为训练集和测试集
from sklearn.model_selection import train_test_split
#计算分类预测的准确率
from sklearn.metrics import accuracy_score


### 1.数据加载和预处理
iris = load_iris()
df = pd.DataFrame(data=iris.data, columns=iris.feature_names)
# 可以动态添加列
df['class'] = iris.target
df['class'] = df['class'].map({0:iris.target_names[0],1:iris.target_names[1],2:iris.target_names[2]})

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

# 划分训练集和测试集
'''
test_size 设定 测试集和训练集的比例大小
random_state 设置随机分布的随机种子
stratify 设置测试集和训练集的y值等比例分布 使测试集和训练集的y值分布大致相同
'''
x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.3,random_state=35,stratify=y)

# 定义距离函数
def l1_distance(a,b):
	return np.sqrt(np.sum(np.abs(a-b),axis=1))
def l2_distance(a,b):
	return np.sqrt(np.sum((a-b)**2,axis=1))

# 分类器的实现
class KNN(object):
	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)

		#enumerate默认取元组(index,content)
		for i, x_test in enumerate(x):
			#x_test与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，取出索引值
			nn_index = np.argsort(distances)
			print(nn_index)

			# 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()

			print(nn_index[:self.n_neighbors])

			print(nn_y)
			# 统计类别中出现频率最高的那个，赋值给预测分类数组
			y_pred[i] = np.argmax(np.bincount(nn_y))
			print(np.bincount(nn_y))
			print(y_pred[i])

		return y_pred

# ##测试
# 定义实例
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)



'''
# 定义实例
knn = KNN()
# 训练模型
knn.fit(x_train,y_train)
# 传入测试数据，做预测
# 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 步长为2
	for k in range(1, 10, 2):
		knn.n_neighbors = k
		# 传入测试数据 做预测
		y_pred = knn.predict(x_test)
		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', '准确率'])
print(df)
'''