In [24]:
from matplotlib import pyplot
from pandas import read_csv
from sklearn.datasets import load_boston
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import Ridge
from sklearn.linear_model import Lasso
from sklearn.linear_model import ElasticNet
from sklearn.neighbors import KNeighborsRegressor
from sklearn.tree import DecisionTreeRegressor
from sklearn.svm import SVR
# 导入数据
boston = load_boston()
# 将数据分为输入数据和输出结果
X = boston.data
Y = boston.target
num_folds = 10
seed = 7
kfold = KFold(n_splits=n_splits, random_state=seed)
models = {}
# 线性回归
models['LR'] = LinearRegression()
# 岭回归
models['RD'] = Ridge()
# 套索
models['LO'] = Lasso()
# 弹性网络
models['EN'] = ElasticNet()
# K近邻
models['KNN'] = KNeighborsRegressor()
# 分类与决策树
models['DT'] = DecisionTreeRegressor()
# 支持向量机
models['SVM'] = SVR()
scoring = 'neg_mean_squared_error'
results = []
for name in models:
result = cross_val_score(models[name], X, Y, cv=kfold, scoring=scoring)
results.append(result)
msg = '%s: %.3f (%.3f)' % (name, result.mean(), result.std())
print(msg)
# 图表显示
fig = pyplot.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
pyplot.boxplot(results)
ax.set_xticklabels(models.keys())
pyplot.show()