import matplotlib.pyplot as plt
from sklearn import datasets

boston = datasets.load_boston()
x = boston.data
y = boston.target
x = x[y < 50.0]
y = y[y < 50.0]

Linear Regression

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=666)

from sklearn.linear_model import LinearRegression

lin_reg = LinearRegression()
lin_reg.fit(X_train, y_train)
lin_reg.score(X_test, y_test)

KNN Regressor

默认算法

from sklearn.neighbors import KNeighborsRegressor

knn_reg = KNeighborsRegressor()
knn_reg.fit(X_train, y_train)
knn_reg.score(X_test, y_test)

网络搜索

from sklearn.neighbors import KNeighborsRegressor
from sklearn.model_selection import GridSearchCV

param_grid = [
    {
        'weights':['uniform'],
        'n_neighbors': [i for i in range(1, 11)]
    },
    {   
        'weights':['distance'],
        'n_neighbors': [i for i in range(1, 11)],
        'p': [i for i in range(1, 6)]
    }
]

knn_reg = KNeighborsRegressor()
grid_search = GridSearchCV(knn_reg, param_grid, n_jobs=-1, verbose=1)
grid_search.fit(X_train, y_train)

输入：grid_search.best_params_
输出：{'n_neighbors': 5, 'p': 1, 'weights': 'distance'}

输入：grid_search.best_score_
输出：0.6340477954176972

输入：grid_search.best_estimator_.score(X_test, y_test)
输出：0.7044357727037996