KNN（K近邻算法）

API应用

分类

from sklearn.neighbors import KNeighborsClassifier

knn = KNeighborsClassifier(n_neighbors=2) #KNN分类模型，K值为2

X = np.array([[2,1],[3,1],[1,4],[2,6]]) #特征
y = np.array([0,0,1,1])#标签

knn.fit(X,y) #模型训练
X = np.array([[4,9]])
X_class = knn.predict(X)#预测
print(X_class)

#画图
fig,ax = plt.subplots()
ax.axis('equal')
#使用布尔索引将两类点分开
X1 = X[y==0]
X2 = X[y==1]

#定义不同的颜色，画两组点
colors = ["C0","C1"]
plt.scatter(X1[:,0],X1[:,1],c=colors[0])
plt.scatter(X2[:,0],X2[:,1],c=colors[1])

#新点的颜色
x_color = colors[0] if x_class == 0 else colors[1]
plt.scatter(X[:,0],X[:,1],c=x_color)
plt.show()

回归

from sklearn.neighbors import KNeighborsRegressor

knn = KNeighborsRegressor(n_neighbors=2,weights='distance') #KNN回归模型，K为2

X = [[2,1],[3,1],[1,4],[2,6]] 
y = [0.5,0.33,4,3]
knn.fig(X,y)
knn.predict([4,9])

常见距离度量方法

归一化与标准化

归一化：

from sklearn.preprocessing import MinMaxScaler

X = [[2,1],[3,1],[1,4],[2,6]]

#定义归一化类的对象
scaler = MinMaxScaler(feature_range=(-1,1))

#将缩放器应用到特征上
X_scaled = scaler.fit_transform(X)
print(X_scaled)

标准化：

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
print(X_scaled)

#均值和方差
print(np.mean(X,axis=0))
print(np.std(X,axis=0))

案例：心脏病预测

import pandas as pd
import sklearn.model_selection import train_test_split

#加载数据集
heart_disease_data = pd.read_csv("heart_disease.csv")

#处理缺失值
heart_disease_data.dropna(inplace=True)

heart_disease_data.info()
print(heart_disease_data.head())

#数据集划分
X = heart_disease_data.drop("是否患有心脏病",axis=1)
y = heart_disease_data["是否患有心脏病"]

X_tain,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3,random_state=42)

#如何处理13中特征？

from sklearn.preprocessing import StandardScaler,OneHotEncoder
from sklearn.compose import ColumnTransformer

#数值特征
numerical_features = ["年龄","静息血压","胆固醇","最大心率","运动后的ST下降","主血管数量"]
#类别型特征
categorical_features = ["胸痛类型","静息心电图结果","峰值ST段的斜率","地中黑贫血"]

#二元特征
binary_features = ["性别","空腹血糖","运动性心绞痛"]

#创建列转换器
preprocessor = ColumnTransformer(
	transformers=[
		#对数值型特征进行标准化
		("num",StandardScaler(),numerical_features),
		#对类别型特征进行独热编码，使用drop="first"避免多重共线性
		("cat",OneHotEncoder(drop="first"),categorical_features),
		#二元特征不进行处理
		("binary","passthrouth",binary_features),
	]
)

#执行特征转换
x_train = preprocessor.fit_trainsform(X_train)#计算训练集的统计信息并进行转换
x_test = preprocessor.transform(X_test) #使用训练集计算的信息对测试集进行转换

print(x_train)
print(x_test)

from sklearn.neighbors import KNeighborsClassifier
import joblib

#创建模型
knn = KNeighborsClassifier(n_neighbors=3)

knn.fit(X_train,y_train)

#模型评估，计算预测准确率
score = knn.score(X_test,y_test)
print(score)

#保存模型
joblib.dump(value=knn,filename="knn_model")

#加载保存好的模型做预测
knn_loaded = joblib.load("knn_model")
y_pred = knn_loaded.predict(X_test[10:11])
print(f"预测类别：{y_pred},真实类别：{y_test[10]}")

交叉验证

from sklearn.model_selection import GridSearchCV

#创建KNN分类器
knn = KNeighborsClassifier()

#定义网络搜索参数列表
param_grid = {"n_neigobors":list(range(1,11))}

grid_search_cv = GridSearchCV(estimator=knn,param_grid=param_grid,dv=10)

#模型训练
grid_search_cv.fit(X_train,y_train)

#打印模型评估结果
# results = grid_search_cv.cv_results_
# results = pd.DataFrame(grid_search_cv.cv_results_)
results = pd.DataFrame(grid_search_cv.cv_results_).toString()
print(results)

#获取最佳模型、参数和最佳得分
print(grid_search_cv.test_estimator_)
print(grid_search_cv.test_params_)
print(grid_search_cv.best_score_)

#使用最佳模型进行测试评估
knn = grid_search_cv.test_estimater_
print(knn.score(X_test,y_test))

除了上述K值决定的模型优化，此外还有权重影响

#定义网络搜索参数列表
pram_grid = {"n_neighbors":list(range(1,11)),"weights":["uniform","distance"]}