训练模型的保存与加载

1.目的：

    将训练好的模型保存下来，已备下次使用，节省训练时间，提高效率

2.API:

from sklearn.externals import joblib

保存:
joblib.dump(rf,"test.pkl")

加载:
estimator = joblib.load("test.pkl")

3.Python代码实现:

# -*- coding: UTF-8 -*-
'''
@Author ：Jason
波士顿房价预测，将模型保存到
'''
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import Ridge
from sklearn.metrics import mean_squared_error
from sklearn.externals import joblib


def model_save_fetch():
    """
    岭回归对波士顿房价进行预测
    :return:
    """
    # 1）获取数据
    boston = load_boston()
    print("特征数量：\n", boston.data.shape)

    # 2）划分数据集
    x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)

    # 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(alpha=0.5, max_iter=10000)
    # estimator.fit(x_train, y_train)
    #
    # # 保存模型
    # joblib.dump(estimator, "./files/test.pkl")
    # 加载模型
    estimator = joblib.load("./files/test.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__":
    model_save_fetch()