corpus_explorer.py 文件源码

def visualize_tweets(W, topic_number, color):
    '''
    INPUT
         - W matrix of observations
         - topic_number - this is the number of the topic to be checked
         - color - this is the color to be used in creating the scatterplot
    OUTPUT
         - a scatter plot of the relative location of the different topics
         from each other in a flattened space using multidimensional scaling
    Returns none
    '''
    # mds = MDS(n_jobs=-1)
    topic_list = np.apply_along_axis(np.argmax, 1, W)
    Wsubset = W[topic_list == topic_number]
    pca = PCA(n_components=2)
    pca = PCA(n_components=2)
    hflat = pca.fit_transform(Wsubset)
    plt.scatter(hflat[:, 0], hflat[:, 1], color=color, alpha=.1)
    plt.title('these are the {} tweets in topic # {}'.format(Wsubset.shape[0],
                                                             topic_number+1))
    # plt.show()