knn_regression_model(Python)

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn import preprocessing
from sklearn.model_selection import train_test_split,GridSearchCV
from sklearn.linear_model import Lasso
from sklearn.linear_model import Ridge
from sklearn.ensemble import RandomForestRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.metrics import mean_squared_error

dataset = datasets.load_boston()
featurenames = list(dataset.feature_names)
X,y = dataset.data,dataset.target

scaler = preprocessing.StandardScaler()
x = scaler.fit_transform(X)

#基于Lasso(L1)的特征选择方法
clf = Lasso(alpha=0.3)
clf.fit(x,y)
coefs = clf.coef_
string = ''
for name,coef in zip(featurenames,coefs):
    string = string + '{}*{}'.format(round(coef,4),name)
print('Lasso Model:\n',string)

#基于Ridge(L2)的特征选择方法
clf = Ridge(10)
clf.fit(x,y)
coefs = clf.coef_
string = ''
for name,coef in zip(featurenames,coefs):
    string = string + '{}*{}'.format(round(coef,4),name)
print('Ridge Model:\n',string)

#基于随机森林的特征选择方法
clf = RandomForestRegressor()
clf.fit(x,y)
item = {}
for attr,score in zip(featurenames,clf.feature_importances_):
    item[attr] = round(score,4)
print(item)

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2,random_state=1)

#寻找最优参数
param = {'n_neighbors':range(2,50),
             'weights':['uniform','distance'],
             'algorithm':['ball_tree','kd_tree','brute','auto']
        }
model = GridSearchCV(KNeighborsRegressor(weights='uniform'),param)
model.fit(x_train,y_train)
print('最佳模型为:\n',model.best_estimator_)
print('最佳参数为:\n',model.best_params_)

#训练模型
clf = KNeighborsRegressor(n_neighbors=3,weights='distance')
clf.fit(x_train,y_train)
predict_train = clf.predict(x_train)
predict_test = clf.predict(x_test)
train_mse = mean_squared_error(y_train,predict_train)
test_mse = mean_squared_error(y_test,predict_test)
print('Train MSE = ',train_mse,' Test MSE = ',test_mse)