visualize.py 文件源码

def DBN_visualize_pca_2d(doc_codes, doc_labels, classes_to_visual, save_file):
    """
        Visualize the input data on a 2D PCA plot. Depending on the number of components,
        the plot will contain an X amount of subplots.
        @param doc_codes:
        @param number_of_components: The number of principal components for the PCA plot.
    """

    # markers = ["p", "s", "h", "H", "+", "x", "D"]
    markers = ["o", "v", "8", "s", "p", "*", "h", "H", "+", "x", "D"]

    C = len(classes_to_visual)
    while True:
        if C <= len(markers):
            break
        markers += markers

    class_ids = dict(zip(classes_to_visual.keys(), range(C)))

    codes, labels = doc_codes, doc_labels

    X = np.r_[list(codes)]
    X = PCA(n_components=3).fit_transform(X)
    plt.figure(figsize=(10, 10), facecolor='white')

    x_pc, y_pc = 1, 2

    for c in classes_to_visual.keys():
        idx = np.array(labels) == c
        # idx = get_indices(labels, c)
        plt.plot(X[idx, x_pc], X[idx, y_pc], linestyle='None', alpha=0.6, marker=markers[class_ids[c]],
                        markersize=6, label=classes_to_visual[c])
        # plt.legend(c)
    plt.title('Projected on the first 2 PCs')
    plt.xlabel('PC %s' % x_pc)
    plt.ylabel('PC %s' % y_pc)
    # legend = plt.legend(loc='upper center', shadow=True)
    plt.savefig(save_file)
    plt.show()