Boston数据集随机森林

import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
data_url = "http://lib.stat.cmu.edu/datasets/boston"
raw_df = pd.read_csv(data_url, sep="\\s+", skiprows=22, header=None)
data = np.hstack([raw_df.values[::2, :], raw_df.values[1::2, :2]])
target = raw_df.values[1::2, 2]
boston = pd.DataFrame(data, columns=['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PTRATIO','B','LSTAT'])
boston['MEDV'] = target
X = boston.drop('MEDV', axis=1)
y = boston['MEDV']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=1)
for n_est in [50, 100, 200]:
    rf = RandomForestRegressor(n_estimators=n_est, random_state=1)
    rf.fit(X_train, y_train)
    pred = rf.predict(X_test)
    mse = mean_squared_error(y_test, pred)
    print(f'n_estimators={n_est}的测试MSE: {mse:.2f}')