k近邻——kNN回归

模型原型
sklearn.neighbors.KNeighborsRegressor(n_neighbors=5,weights=’uniform’,
algorithm=’auto’,leaf_size=30,p=2, metric=’minkowski’,metric_params=None,n_jobs=1,**kwargs)
参数

• n_neighbors
• weights
• algorithm
• leaf_size
• p
• n_jobs

方法

• fit(X,y)
• predict(X)
• score(X,y)
• predict_proba(X)
• kneighbors([X,n_neighbors,return_distance])
• kneighbors_graph([X,n_neighbors,mode])

import numpy as np
import matplotlib.pyplot as plt
from sklearn import neighbors,datasets,cross_validation

def create_regression_data(n):
    X=5*np.random.rand(n,1)
    y=np.sin(X).ravel()
    y[::5]+=1*(0.5-np.random.rand(int(n/5)))
    return cross_validation.train_test_split(X,y,test_size=0.25,
        random_state=0)

使用KNeighborsRegressor

def test_KNeighborsRegressor(*data):
    X_train,X_test,y_train,y_test=data
    regr=neighbors.KNeighborsRegressor()
    regr.fit(X_train,y_train)
    print('Training Score:%f'%regr.score(X_train,y_train))
    print('Testing Score:%f'%regr.score(X_test,y_test))

X_train,X_test,y_train,y_test=create_regression_data(1000)
test_KNeighborsRegressor(X_train,X_test,y_train,y_test)

k值以及投票策略的影响

def test_KNeighborsRegressor_k_w(*data):
    X_train,X_test,y_train,y_test=data
    Ks=np.linspace(1,y_train.size,num=100,endpoint=False,dtype='int')
    weights=['uniform','distance']
    #绘图
    fig=plt.figure()
    ax=fig.add_subplot(1,1,1)
    for weight in weights:
        training_scores=[]
        testing_scores=[]
        for K in Ks:
            regr=neighbors.KNeighborsRegressor(weights=weight,
                n_neighbors=K)
            regr.fit(X_train,y_train.astype('int'))
            testing_scores.append(regr.score(X_test,y_test.astype('int')))
            training_scores.append(regr.score(X_train,
                y_train.astype('int')))
        ax.plot(Ks,testing_scores,label='testing score:weight=%s'%weight)
        ax.plot(Ks,training_scores,label='training score:weight=%s'%weight)
        ax.legend(loc='best')
        ax.set_xlabel('K')
        ax.set_ylabel('score')
        ax.set_ylim(0,1.05)
        ax.set_title('KNeighborsRegressor')
        plt.show()

test_KNeighborsRegressor_k_w(X_train,X_test,y_train,y_test)

p值的影响

def test_KNeighborsRegressor_k_p(*data):
    X_train,X_test,y_train,y_test=data
    Ks=np.linspace(1,y_train.size,endpoint=False,dtype='int')
    Ps=[1,2,10]
    fig=plt.figure()
    ax=fig.add_subplot(1,1,1)
    for P in Ps:
        training_scores=[]
        testing_scores=[]
        for K in Ks:
            clf=neighbors.KNeighborsRegressor(p=P,n_neighbors=K)
            clf.fit(X_train,y_train)
            testing_scores.append(clf.score(X_test,y_test))
            training_scores.append(clf.score(X_train,y_train))
        ax.plot(Ks,testing_scores,label='testing score:p=%d'%P)
        ax.plot(Ks,training_scores,label='training score:p=%d'%P)
    ax.legend(loc='best')
    ax.set_xlabel("K")
    ax.set_ylabel('score')
    ax.set_ylim(0,1.05)
    ax.set_title('KNeighborsRegressor')
    plt.show()

test_KNeighborsRegressor_k_p(X_train,X_test,y_train,y_test)