document_clustering.py 文件源码

def plot_clusters(num_clusters, feature_matrix,
                  cluster_data, movie_data,
                  plot_size=(16,8)):
    # generate random color for clusters                  
    def generate_random_color():
        color = '#%06x' % random.randint(0, 0xFFFFFF)
        return color
    # define markers for clusters    
    markers = ['o', 'v', '^', '<', '>', '8', 's', 'p', '*', 'h', 'H', 'D', 'd']
    # build cosine distance matrix
    cosine_distance = 1 - cosine_similarity(feature_matrix) 
    # dimensionality reduction using MDS
    mds = MDS(n_components=2, dissimilarity="precomputed", 
              random_state=1)
    # get coordinates of clusters in new low-dimensional space
    plot_positions = mds.fit_transform(cosine_distance)  
    x_pos, y_pos = plot_positions[:, 0], plot_positions[:, 1]
    # build cluster plotting data
    cluster_color_map = {}
    cluster_name_map = {}
    for cluster_num, cluster_details in cluster_data.items():
        # assign cluster features to unique label
        cluster_color_map[cluster_num] = generate_random_color()
        cluster_name_map[cluster_num] = ', '.join(cluster_details['key_features'][:5]).strip()
    # map each unique cluster label with its coordinates and movies
    cluster_plot_frame = pd.DataFrame({'x': x_pos,
                                       'y': y_pos,
                                       'label': movie_data['Cluster'].values.tolist(),
                                       'title': movie_data['Title'].values.tolist()
                                        })
    grouped_plot_frame = cluster_plot_frame.groupby('label')
    # set plot figure size and axes
    fig, ax = plt.subplots(figsize=plot_size) 
    ax.margins(0.05)
    # plot each cluster using co-ordinates and movie titles
    for cluster_num, cluster_frame in grouped_plot_frame:
         marker = markers[cluster_num] if cluster_num < len(markers) \
                  else np.random.choice(markers, size=1)[0]
         ax.plot(cluster_frame['x'], cluster_frame['y'], 
                 marker=marker, linestyle='', ms=12,
                 label=cluster_name_map[cluster_num], 
                 color=cluster_color_map[cluster_num], mec='none')
         ax.set_aspect('auto')
         ax.tick_params(axis= 'x', which='both', bottom='off', top='off',        
                        labelbottom='off')
         ax.tick_params(axis= 'y', which='both', left='off', top='off',         
                        labelleft='off')
    fontP = FontProperties()
    fontP.set_size('small')    
    ax.legend(loc='upper center', bbox_to_anchor=(0.5, -0.01), fancybox=True, 
              shadow=True, ncol=5, numpoints=1, prop=fontP) 
    #add labels as the film titles
    for index in range(len(cluster_plot_frame)):
        ax.text(cluster_plot_frame.ix[index]['x'], 
                cluster_plot_frame.ix[index]['y'], 
                cluster_plot_frame.ix[index]['title'], size=8)  
    # show the plot           
    plt.show()