runDBSCAN.py 文件源码

def main():   
    """
    Entry point for the script.
    """

    ###########################################################################
    # Load the corpus
    ###########################################################################

    # Load the pre-built corpus.
    print('Loading the saved SimSearch and corpus...')
    (ksearch, ssearch) = SimSearch.load(save_dir='./mhc_corpus/')

    print '    %d documents.' % len(ssearch.index.index)

    # Step 1: Run a technique to find a good 'eps' value.
    #findEps(ssearch)
    #eps = 0.5
    eps = 0.44

    # Step 2: Run a technique to find a good 'MinPts' value.    
    # TODO - This took ~17 min. on my desktop!
    #findMinPts(ssearch, eps)
    #min_samples = 8
    min_samples = 4

    # Step 3: Run DBSCAN
    runClustering(ssearch, eps, min_samples)