comparison Marea/marea_cluster.py @ 33:abf0bfe01c78 draft

Uploaded

32:b795e3e163e0

                        type = str,
                        required = True,
                        help = 'your tool directory')
                        
    parser.add_argument('-ms', '--min_samples',
                        type = int,
                        help = 'min samples for dbscan (optional)')
                        
    parser.add_argument('-ep', '--eps',
                        type = int,
                        help = 'eps for dbscan (optional)')
                        
    parser.add_argument('-bc', '--best_cluster',
                        type = str,
                        help = 'output of best cluster tsv')

            
        plt.savefig(path, bbox_inches='tight')
            
######################## dbscan ##############################################
    
def dbscan(dataset, eps, min_samples):
    if not os.path.exists('clustering'):
        os.makedirs('clustering')
        
    if eps is not None:
    	clusterer = DBSCAN(eps = eps, min_samples = min_samples)

    n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
    
    
    ##TODO: PLOT SU DBSCAN (no centers) e HIERARCHICAL
    
    
    write_to_csv(dataset, labels, 'clustering/dbscan_results.tsv')
    
########################## hierachical #######################################
    
def hierachical_agglomerative(dataset, k_min, k_max):

    if not os.path.exists('clustering'):
        os.makedirs('clustering')
    
    plt.figure(figsize=(10, 7))  

    fig = plt.gcf()
    fig.savefig('clustering/dendogram.png', dpi=200)
    
    range_n_clusters = [i for i in range(k_min, k_max+1)]

    for n_clusters in range_n_clusters:
        
        cluster = AgglomerativeClustering(n_clusters=n_clusters, affinity='euclidean', linkage='ward')  
        cluster.fit_predict(dataset)  
        cluster_labels = cluster.labels_
        
        silhouette_avg = silhouette_score(dataset, cluster_labels)
        write_to_csv(dataset, cluster_labels, 'clustering/hierarchical_with_' + str(n_clusters) + '_clusters.tsv')
        #warning("For n_clusters =", n_clusters,
              #"The average silhouette_score is :", silhouette_avg)
        
        
       

    

    
    if args.cluster_type == 'kmeans':
        kmeans(args.k_min, args.k_max, X, args.elbow, args.silhouette, args.davies, args.best_cluster)
    
    if args.cluster_type == 'dbscan':
        dbscan(X, args.eps, args.min_samples)
        
    if args.cluster_type == 'hierarchy':
        hierachical_agglomerative(X, args.k_min, args.k_max)
        
##############################################################################

if __name__ == "__main__":
    main()

33:abf0bfe01c78

                        type = str,
                        required = True,
                        help = 'your tool directory')
                        
    parser.add_argument('-ms', '--min_samples',
                        type = float,
                        help = 'min samples for dbscan (optional)')
                        
    parser.add_argument('-ep', '--eps',
                        type = float,
                        help = 'eps for dbscan (optional)')
                        
    parser.add_argument('-bc', '--best_cluster',
                        type = str,
                        help = 'output of best cluster tsv')

            
        plt.savefig(path, bbox_inches='tight')
            
######################## dbscan ##############################################
    
def dbscan(dataset, eps, min_samples, best_cluster):
    if not os.path.exists('clustering'):
        os.makedirs('clustering')
        
    if eps is not None:
    	clusterer = DBSCAN(eps = eps, min_samples = min_samples)

    n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
    
    
    ##TODO: PLOT SU DBSCAN (no centers) e HIERARCHICAL
    
    labels = labels
    predict = [x+1 for x in labels]
    classe = (pd.DataFrame(list(zip(dataset.index, predict)))).astype(str)
    classe.to_csv(best_cluster, sep = '\t', index = False, header = ['Patient_ID', 'Class'])
  
    
########################## hierachical #######################################
    
def hierachical_agglomerative(dataset, k_min, k_max, best_cluster):

    if not os.path.exists('clustering'):
        os.makedirs('clustering')
    
    plt.figure(figsize=(10, 7))  

    fig = plt.gcf()
    fig.savefig('clustering/dendogram.png', dpi=200)
    
    range_n_clusters = [i for i in range(k_min, k_max+1)]

    scores = []
    labels = []
    for n_clusters in range_n_clusters:    
        cluster = AgglomerativeClustering(n_clusters=n_clusters, affinity='euclidean', linkage='ward')  
        cluster.fit_predict(dataset)  
        cluster_labels = cluster.labels_
        labels.append(cluster_labels)
        silhouette_avg = silhouette_score(dataset, cluster_labels)
        write_to_csv(dataset, cluster_labels, 'clustering/hierarchical_with_' + str(n_clusters) + '_clusters.tsv')
        scores.append(silhouette_avg)
        #warning("For n_clusters =", n_clusters,
              #"The average silhouette_score is :", silhouette_avg)
              
    best = max_index(scores) + k_min
     
    for i in range(len(labels)):
        if (i + k_min == best):
            labels = labels[i]
            predict = [x+1 for x in labels]
            classe = (pd.DataFrame(list(zip(dataset.index, predict)))).astype(str)
            classe.to_csv(best_cluster, sep = '\t', index = False, header = ['Patient_ID', 'Class'])
     
        
        
       

    

    
    if args.cluster_type == 'kmeans':
        kmeans(args.k_min, args.k_max, X, args.elbow, args.silhouette, args.davies, args.best_cluster)
    
    if args.cluster_type == 'dbscan':
        dbscan(X, args.eps, args.min_samples, args.best_cluster)
        
    if args.cluster_type == 'hierarchy':
        hierachical_agglomerative(X, args.k_min, args.k_max, args.best_cluster)
        
##############################################################################

if __name__ == "__main__":
    main()