python保存和加载机器学习模型

素颜马尾好姑娘i 2022-02-09 14:21 337阅读 0赞

一：使用pickle实现

# Save Model Using Pickle
    import pandas
    from sklearn import model_selection
    from sklearn.linear_model import LogisticRegression
    import pickle
    url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv"
    names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
    dataframe = pandas.read_csv(url, names=names)
    array = dataframe.values
    X = array[:,0:8]
    Y = array[:,8]
    test_size = 0.33
    seed = 7
    X_train, X_test, Y_train, Y_test = model_selection.train_test_split(X, Y, test_size=test_size, random_state=seed)
    # Fit the model on 33%
    model = LogisticRegression()
    model.fit(X_train, Y_train)
    # save the model to disk
    filename = 'finalized_model.sav'
    pickle.dump(model, open(filename, 'wb'))#保存模型
    
    # some time later...
    
    # load the model from disk
    loaded_model = pickle.load(open(filename, 'rb'))#加载保存的模型
    result = loaded_model.score(X_test, Y_test)
    print(result)

二：使用Joblib实现

# Save Model Using joblib
    import pandas
    from sklearn import model_selection
    from sklearn.linear_model import LogisticRegression
    from sklearn.externals import joblib
    url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv"
    names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
    dataframe = pandas.read_csv(url, names=names)
    array = dataframe.values
    X = array[:,0:8]
    Y = array[:,8]
    test_size = 0.33
    seed = 7
    X_train, X_test, Y_train, Y_test = model_selection.train_test_split(X, Y, test_size=test_size, random_state=seed)
    # Fit the model on 33%
    model = LogisticRegression()
    model.fit(X_train, Y_train)
    # save the model to disk
    filename = 'finalized_model.sav'
    joblib.dump(model, filename)
    
    # some time later...
    
    # load the model from disk
    loaded_model = joblib.load(filename)
    result = loaded_model.score(X_test, Y_test)
    print(result)

[原文][Link 1]

[Link 1]: https://machinelearningmastery.com/save-load-machine-learning-models-python-scikit-learn/