unsupervised.py 文件源码

def main():
    Xtrain, Ytrain, Xtest, Ytest = getKaggleMNIST()
    dbn = DBN([1000, 750, 500], UnsupervisedModel=AutoEncoder)
    # dbn = DBN([1000, 750, 500, 10])
    output = dbn.fit(Xtrain, pretrain_epochs=2)
    print "output.shape", output.shape

    # sample before using t-SNE because it requires lots of RAM
    sample_size = 600
    tsne = TSNE()
    reduced = tsne.fit_transform(output[:sample_size])
    plt.scatter(reduced[:,0], reduced[:,1], s=100, c=Ytrain[:sample_size], alpha=0.5)
    plt.title("t-SNE visualization")
    plt.show()

    # t-SNE on raw data
    reduced = tsne.fit_transform(Xtrain[:sample_size])
    plt.scatter(reduced[:,0], reduced[:,1], s=100, c=Ytrain[:sample_size], alpha=0.5)
    plt.title("t-SNE visualization")
    plt.show()

    pca = PCA()
    reduced = pca.fit_transform(output)
    plt.scatter(reduced[:,0], reduced[:,1], s=100, c=Ytrain, alpha=0.5)
    plt.title("PCA visualization")
    plt.show()