Commit c490e149577c78481ae850c53066f889103e4f0c
1 parent
f3bda937
Exists in
master
and in
1 other branch
Added script to index popcon data.
Showing
1 changed file
with
51 additions
and
0 deletions
Show diff stats
| @@ -0,0 +1,51 @@ | @@ -0,0 +1,51 @@ | ||
| 1 | +#!/usr/bin/env python | ||
| 2 | +""" | ||
| 3 | + Clustering - A python script to perform clustering of popcon data. | ||
| 4 | +""" | ||
| 5 | +__author__ = "Tassia Camoes Araujo <tassia@gmail.com>" | ||
| 6 | +__copyright__ = "Copyright (C) 2011 Tassia Camoes Araujo" | ||
| 7 | +__license__ = """ | ||
| 8 | + This program is free software: you can redistribute it and/or modify | ||
| 9 | + it under the terms of the GNU General Public License as published by | ||
| 10 | + the Free Software Foundation, either version 3 of the License, or | ||
| 11 | + (at your option) any later version. | ||
| 12 | + | ||
| 13 | + This program is distributed in the hope that it will be useful, | ||
| 14 | + but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
| 15 | + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
| 16 | + GNU General Public License for more details. | ||
| 17 | + | ||
| 18 | + You should have received a copy of the GNU General Public License | ||
| 19 | + along with this program. If not, see <http://www.gnu.org/licenses/>. | ||
| 20 | +""" | ||
| 21 | +import os | ||
| 22 | +import sys | ||
| 23 | +sys.path.insert(0,'../') | ||
| 24 | +import logging | ||
| 25 | +import datetime | ||
| 26 | +from datetime import timedelta | ||
| 27 | + | ||
| 28 | +from config import * | ||
| 29 | +from data import * | ||
| 30 | +from dissimilarity import * | ||
| 31 | +from error import Error | ||
| 32 | + | ||
| 33 | +if __name__ == '__main__': | ||
| 34 | + try: | ||
| 35 | + cfg = Config() | ||
| 36 | + begin_time = datetime.datetime.now() | ||
| 37 | + logging.info("Popcon indexing started at %s" % begin_time) | ||
| 38 | + | ||
| 39 | + pxi = PopconXapianIndex(cfg) | ||
| 40 | + | ||
| 41 | + end_time = datetime.datetime.now() | ||
| 42 | + logging.info("Popcon indexing completed at %s" % end_time) | ||
| 43 | + delta = end_time - begin_time | ||
| 44 | + logging.info("Time elapsed: %d seconds." % delta.seconds) | ||
| 45 | + if cfg.index_mode=="cluster" or cfg.index_mode=="recluster": | ||
| 46 | + logging.info("Medoids: %d\tDispersion:%f" % | ||
| 47 | + (cfg.k_medoids,pxi.cluster_dispersion)) | ||
| 48 | + | ||
| 49 | + except Error: | ||
| 50 | + logging.critical("Aborting proccess. Use '--debug' for more details.") | ||
| 51 | + |