document_clustering.py 文件源码

def plot_hierarchical_clusters(linkage_matrix, movie_data, figure_size=(8,12)):
    # set size
    fig, ax = plt.subplots(figsize=figure_size) 
    movie_titles = movie_data['Title'].values.tolist()
    # plot dendrogram
    ax = dendrogram(linkage_matrix, orientation="left", labels=movie_titles)
    plt.tick_params(axis= 'x',   
                    which='both',  
                    bottom='off',
                    top='off',
                    labelbottom='off')
    plt.tight_layout()
    plt.savefig('ward_hierachical_clusters.png', dpi=200)

# build ward's linkage matrix