Boston数据集随机森林特征重要性

import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
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)
rf = RandomForestRegressor(n_estimators=100, random_state=1)
rf.fit(X_train, y_train)
importance = pd.Series(rf.feature_importances_, index=X.columns)
plt.figure(figsize=(10, 6))
importance.sort_values().plot(kind='barh')
plt.xlabel('特征重要性')
plt.title('Boston数据集随机森林特征重要性')
plt.show()