added missing file

Author: g

tseeder

@@ -0,0 +1,56 @@
+#!/usr/bin/python2
+
+"""
+This file is part of VDISCOVER.
+
+VDISCOVER is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+VDISCOVER is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with VDISCOVER. If not, see <http://www.gnu.org/licenses/>.
+
+Copyright 2015 by G.Grieco
+"""
+
+import os
+import argparse
+import sys
+import csv
+
+from vdiscover.Utils import *
+from vdiscover.Sampling import *
+
+csv.field_size_limit(sys.maxsize)
+
+if __name__ == "__main__":
+
+    # Arguments
+    parser = argparse.ArgumentParser(description='A small utility to perform seed selection for fuzzig')
+    parser.add_argument("infile", help="A csv with the features to train or predict", type=str, default=None)
+    parser.add_argument("outdir", help="A directory with the seeds", type=str, default=None)
+    parser.add_argument("-n", help="Number of seeds to select per cluster", type=int, default=1)
+    parser.add_argument("--random", help="Sample randomly", action="store_true", default=None)
+
+    options = parser.parse_args()
+    in_file = options.infile
+    outdir = options.outdir
+    nseeds = options.n
+
+    reader = load_csv(in_file)
+    clusters = []
+    for [label, cluster] in reader:
+      clusters.append((label.split(":")[-1], cluster))
+
+    selected = cluster_sampler(clusters, nseeds)
+
+    for seed in selected:
+      print "cp", seed, outdir
+
+