comparison chemfp_clustering/nxn_clustering.py @ 21:7c84cfa515e0

ChemicalToolBoX update.

20:21d29a7f13d8

import os
import chemfp
import scipy.cluster.hierarchy as hcluster
import pylab
import numpy


def distance_matrix(arena, tanimoto_threshold = 0.0):
    n = len(arena)
    # Start off a similarity matrix with 1.0s along the diagonal

    parser.add_argument('-p', '--processors', type=int, 
        default=4)

    args = parser.parse_args()


    arena = chemfp.load_fingerprints( args.input_path )
    distances  = distance_matrix( arena, args.tanimoto_threshold )
    linkage = hcluster.linkage( distances, method="single", metric="euclidean" )

    hcluster.dendrogram(linkage, labels=arena.ids)

21:7c84cfa515e0

import os
import chemfp
import scipy.cluster.hierarchy as hcluster
import pylab
import numpy
import tempfile


def distance_matrix(arena, tanimoto_threshold = 0.0):
    n = len(arena)
    # Start off a similarity matrix with 1.0s along the diagonal

    parser.add_argument('-p', '--processors', type=int, 
        default=4)

    args = parser.parse_args()

    # make sure that the file ending is fps
    temp_file = tempfile.NamedTemporaryFile()
    temp_link = "%s.%s" % (temp_file.name, 'fps')
    temp_file.close()
    os.symlink(args.input_path, temp_link)

    arena = chemfp.load_fingerprints( temp_link )
    distances  = distance_matrix( arena, args.tanimoto_threshold )
    linkage = hcluster.linkage( distances, method="single", metric="euclidean" )

    hcluster.dendrogram(linkage, labels=arena.ids)