sklearn模型的保存和加载

sklearn模型的保存和加载API

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

线性回归的模型保存加载案例

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, Ridge, RidgeCV
from sklearn.metrics import mean_squared_error
from sklearn.externals import joblib


def dump_load_demo():
    """
    模型保存和加载
    :return: None
    """
    # 1.获取数据
    boston = load_boston()

    # 2.数据基本处理
    # 2.1 数据集划分
    x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22, test_size=0.2)

    # 3.特征工程 --标准化
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.fit_transform(x_test)
    #
    # # 4.机器学习(线性回归)
    # # 4.1 模型训练
    # estimator = Ridge()
    #
    # estimator.fit(x_train, y_train)
    # print("这个模型的偏置是:
", estimator.intercept_)
    #
    # # 4.2 模型保存
    # joblib.dump(estimator, "../../data/test.pkl")

    # 4.3 模型加载
    estimator = joblib.load("../../data/test.pkl")

    # 5.模型评估
    # 5.1 预测值和准确率
    y_pre = estimator.predict(x_test)
    print("预测值是:
", y_pre)

    score = estimator.score(x_test, y_test)
    print("准确率是:
", score)

    # 5.2 均方误差
    ret = mean_squared_error(y_test, y_pre)
    print("均方误差是:
", ret)


if __name__ == '__main__':
    dump_load_demo()