3.3 Bernoulli NB.py 文件源码

def test_BernoulliNB_binarize(*data):
    '''
    test the performance with different binarize
    :param data: train_data, test_data, train_value, test_value
    :return: None
    '''
    X_train,X_test,y_train,y_test=data
    min_x=min(np.min(X_train.ravel()),np.min(X_test.ravel()))-0.1
    max_x=max(np.max(X_train.ravel()),np.max(X_test.ravel()))+0.1
    binarizes=np.linspace(min_x,max_x,endpoint=True,num=100)
    train_scores=[]
    test_scores=[]
    for binarize in binarizes:
        cls=naive_bayes.BernoulliNB(binarize=binarize)
        cls.fit(X_train,y_train)
        train_scores.append(cls.score(X_train,y_train))
        test_scores.append(cls.score(X_test, y_test))

    ## graph
    fig=plt.figure()
    ax=fig.add_subplot(1,1,1)
    ax.plot(binarizes,train_scores,label="Training Score")
    ax.plot(binarizes,test_scores,label="Testing Score")
    ax.set_xlabel("binarize")
    ax.set_ylabel("score")
    ax.set_ylim(0,1.0)
    ax.set_xlim(min_x-1,max_x+1)
    ax.set_title("BernoulliNB")
    ax.legend(loc="best")
    plt.show()