学习曲线函数

1.定义学习曲线函数

def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
                        n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
    plt.figure()
    plt.title(title)
    if ylim is not None:
        plt.ylim(*ylim)
    plt.xlabel("Training examples")
    plt.ylabel("Score")
    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes)
    train_scores_mean = np.mean(train_scores, axis=1)
    train_scores_std = np.std(train_scores, axis=1)
    test_scores_mean = np.mean(test_scores, axis=1)
    test_scores_std = np.std(test_scores, axis=1)
    
    print(train_scores_mean)
    print(test_scores_mean)
    
    plt.grid()
 
    plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
                     train_scores_mean + train_scores_std, alpha=0.1,
                     color="r")
    plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
                     test_scores_mean + test_scores_std, alpha=0.1, color="g")
    plt.plot(train_sizes, train_scores_mean, 'o-', color="r",
             label="Training score")
    plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
             label="Cross-validation score")
 
    plt.legend(loc="best")
    return plt

2.绘制线性回归学习曲线

X = train_data.values
y = train_target.values
 
# 图一
title = r"LinearRegression"
cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)
estimator = LinearRegression()    #建模
plot_learning_curve(estimator, title, X, y, ylim=(0.5, 0.8), cv=cv, n_jobs=1)

3.绘制K近邻回归学习曲线

X = train_data.values
y = train_target.values
 
# K近邻回归
title = r"KNeighborsRegressor"
cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)

estimator = KNeighborsRegressor(n_neighbors=8)    #建模
plot_learning_curve(estimator, title, X, y, ylim=(0.3, 0.9), cv=cv, n_jobs=1)

4.绘制决策树的学习曲线

X = train_data.values
y = train_target.values
 
# 决策树回归
title = r"DecisionTreeRegressor"
cv = ShuffleSplit(n_splits=100, test_size=0.2, random_state=0)

estimator = DecisionTreeRegressor()    #建模
plot_learning_curve(estimator, title, X, y, ylim=(0.1, 1.3), cv=cv, n_jobs=1)