random_projection.py 文件源码

def plot_distortion(training_data_instances):
    # dimension of a training data instance
    d = training_data_instances.shape[1]
    # first m instances considered
    m = 20

    fig, axes = plt.subplots(1, 1)
    fig.suptitle("Distortion of random projection", fontsize = "x-large")

    for k in [50, 100, 500]:
        ## generate random projection matrix
        random_projection_matrix =  generate_random_projection_matrix(k, d)
        ## random projection
        m_instances = training_data_instances[0:m]
        projected_m_instances = np.dot(m_instances, np.transpose(random_projection_matrix))
        # print random_projected_matrix[0], random_projected_matrix.shape
        ## evaluate distortion - line chart
        m_instances_distortions = []
        for i in range(m):
            for j in range(i + 1, m):
                m_instances_distortions.append(euclidean(projected_m_instances[i], projected_m_instances[j]) / euclidean(m_instances[i], m_instances[j]))
        m_instances_distortions = np.array(m_instances_distortions)
        mean, std = np.mean(m_instances_distortions), np.std(m_instances_distortions)
        # line chart
        axes.plot(m_instances_distortions, label = "k=" + str(k))
        axes.plot([0, m_instances_distortions.size], [mean, mean], label = "k=" + str(k) + ", mean = " + str(round(mean, 4)))

        print "k = ", k, "distortion =", mean, "+-", std
    axes.set_xlabel("pairs of instances", fontsize = "large")
    axes.set_ylabel("distortion", fontsize = "large")
    axes.legend(loc = "center right", fontsize = "medium")
    plt.show()