机器学习学习笔记（十一）之sklearn模型保存与加载

一、API

• from sklearn.externals import joblib
  • 保存：joblib.dump(rf,‘test.pkl’)
  • 加载：estimator = joblib.load(‘test.pkl’)

二、案例

from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression,SGDRegressor
from sklearn.metrics import mean_squared_error
from sklearn.linear_model import Ridge
from sklearn.externals import joblib

def linear3():
    '''
    梯岭回归对波士顿房价进行预测
    :return:
    '''
    # 1、获取数据
    boston = load_boston()

    # 2、划分数据集
    x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
    # 训练集的特征值x_train 测试集的特征值 x_test 训练集的目标值y_train 测试集的目标值y_test

    # 3、标准化
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)

    # # 4、预估器
    # estimator = Ridge(max_iter=10000,alpha=0.5)
    # estimator.fit(x_train, y_train)
    #
    # # 保存模型
    # joblib.dump(estimator,'my_ridge.pkl')

    # 加载模型
    estimator = joblib.load('my_ridge.pkl')

    # 5、得出模型
    print('岭回归权重系数为：\n', estimator.coef_)
    print('岭回归偏置为：\n', estimator.intercept_)

    # 6、模型评估
    y_predict = estimator.predict(x_test)
    print('预测房价：\n',y_predict)
    error = mean_squared_error(y_test,y_predict)
    print('岭回归均方误差为：\n',error)
    return None

if __name__ == '__main__':
    linear3()