candidates.py 文件源码

def merge_candidates_scan(candidates, seriesuid, distance=5.):
    distances = pdist(candidates, metric='euclidean')
    adjacency_matrix = squareform(distances)

    # Determine nodes within distance, replace by 1 (=adjacency matrix)
    adjacency_matrix = np.where(adjacency_matrix<=distance,1,0)

    # Determine all connected components in the graph
    n, labels = connected_components(adjacency_matrix)
    new_candidates = np.zeros((n,3))

    # Take the mean for these connected components
    for cluster_i in range(n):
        points = candidates[np.where(labels==cluster_i)]
        center = np.mean(points,axis=0)
        new_candidates[cluster_i,:] = center

    x = new_candidates[:,0]
    y = new_candidates[:,1]
    z = new_candidates[:,2]
    labels = [seriesuid]*len(x)
    class_name = [0]*len(x)

    data= zip(labels,x,y,z,class_name)

    new_candidates = pd.DataFrame(data,columns=CANDIDATES_COLUMNS)

    return new_candidates