高斯贝叶斯分类器（GNB实战）

代码含学习曲线绘制。

from sklearn.datasets import load_breast_cancer
data=load_breast_cancer()
X,y=data.data,data.target

from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=38)

from sklearn.naive_bayes import GaussianNB
gnb=GaussianNB().fit(X_train,y_train)
print("the score of this model on training set:{}".format(gnb.score(X_train,y_train)))
print("the score of this model on test set:{}".format(gnb.score(X_test,y_test)))

from sklearn.model_selection import learning_curve
from matplotlib import pyplot as plt
import numpy as np
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)
    test_scores_mean=np.mean(test_scores,axis=1)
    plt.grid()
    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="lower right")
    return plt