def setUpClass(self):
cfg = Config()
cfg.popcon_index = "test_data/.sample_pxi"
cfg.popcon_dir = "test_data/popcon_dir"
cfg.clusters_dir = "test_data/clusters_dir"
cfg.popcon = 0
self.rec = Recommender()
def setUpClass(self):
cfg = Config()
cfg.popcon_index = "test_data/.sample_pxi"
cfg.popcon_dir = "test_data/popcon_dir"
cfg.clusters_dir = "test_data/clusters_dir"
cfg.popcon = 0
self.rec = Recommender()
import os
import logging
sys.path.insert(0, '../')
from apprecommender.config import Config
from apprecommender.data import PopconXapianIndex
if __name__ == '__main__':
cfg = Config()
cfg.index_mode = "recluster"
logging.info("Starting clustering experiments")
logging.info("Medoids: %d\t Max popcon:%d" %
(cfg.k_medoids, cfg.max_popcon))
cfg.popcon_dir = os.path.expanduser(
"~/org/popcon.debian.org/popcon-mail/popcon-entries/")
cfg.popcon_index = cfg.popcon_index + ("_%dmedoids%dmax" %
(cfg.k_medoids, cfg.max_popcon))
cfg.clusters_dir = cfg.clusters_dir + ("_%dmedoids%dmax" %
(cfg.k_medoids, cfg.max_popcon))
pxi = PopconXapianIndex(cfg)
logging.info("Overall dispersion: %f\n" % pxi.cluster_dispersion)
# Write clustering log
output = open(("results/clustering/%dmedoids%dmax" %
(cfg.k_medoids, cfg.max_popcon)), 'w')
output.write("# k_medoids\tmax_popcon\tdispersion\n")
output.write("%d %f\n" %
(cfg.k_medoids, cfg.max_popcon, pxi.cluster_dispersion))
output.close()
def load(self):
config = Config()
short_options = "hdvo:f:b:a:e:p:m:u:l:c:x:w:s:z:r:n:idvo:tdvo"
long_options = ["help", "debug", "verbose", "output=", "filtersdir=",
"pkgsfilter=", "axi=", "dde=", "popconindex=",
"popcondir=", "indexmode=", "clustersdir=",
"kmedoids=", "maxpopcon=", "weight=", "strategy=",
"profile_size=", "profiling=", "neighbors=", "init",
"train"]
try:
opts, args = getopt.getopt(sys.argv[1:], short_options,
long_options)
self.options = opts
except getopt.GetoptError as error:
config.set_logger()
logging.error("Bad syntax: %s" % str(error))
self.usage()
sys.exit()
for o, p in opts:
if o in ("-h", "--help"):
self.usage()
sys.exit()
elif o in ("-d", "--debug"):
config.debug = 1
elif o in ("-v", "--verbose"):
config.verbose = 1
elif o in ("-o", "--output"):
config.output = p
elif o in ("-f", "--filtersdir"):
config.filters_dir = p
elif o in ("-b", "--pkgsfilter"):
config.pkgs_filter = p
elif o in ("-a", "--axi"):
config.axi = p
elif o in ("-e", "--dde"):
config.dde_url = p
elif o in ("-p", "--popconindex"):
config.popcon_index = p
elif o in ("-m", "--popcondir"):
config.popcon_dir = p
elif o in ("-u", "--index_mode"):
config.index_mode = p
elif o in ("-l", "--clustersdir"):
config.clusters_dir = p
elif o in ("-c", "--kmedoids"):
config.k_medoids = int(p)
elif o in ("-x", "--max_popcon"):
config.max_popcon = int(p)
elif o in ("-w", "--weight"):
config.weight = p
elif o in ("-s", "--strategy"):
config.strategy = p
elif o in ("-z", "--profile_size"):
config.profile_size = int(p)
elif o in ("-z", "--profiling"):
config.profiling = p
elif o in ("-n", "--neighbors"):
config.k_neighbors = int(p)
elif o in ("-i", "--init"):
continue
elif o in ("-t", "--train"):
continue
else:
assert False, "unhandled option"
def load(self):
config = Config()
short_options = "hdvo:f:b:a:e:p:m:u:l:c:x:w:s:z:r:n:idvo:tdvo"
long_options = [
"help", "debug", "verbose", "output=", "filtersdir=",
"pkgsfilter=", "axi=", "dde=", "popconindex=", "popcondir=",
"indexmode=", "clustersdir=", "kmedoids=", "maxpopcon=", "weight=",
"strategy=", "profile_size=", "profiling=", "neighbors=", "init",
"train"
]
try:
opts, args = getopt.getopt(sys.argv[1:], short_options,
long_options)
self.options = opts
except getopt.GetoptError as error:
config.set_logger()
logging.error("Bad syntax: %s" % str(error))
self.usage()
sys.exit()
for o, p in opts:
if o in ("-h", "--help"):
self.usage()
sys.exit()
elif o in ("-d", "--debug"):
config.debug = 1
elif o in ("-v", "--verbose"):
config.verbose = 1
elif o in ("-o", "--output"):
config.output = p
elif o in ("-f", "--filtersdir"):
config.filters_dir = p
elif o in ("-b", "--pkgsfilter"):
config.pkgs_filter = p
elif o in ("-a", "--axi"):
config.axi = p
elif o in ("-e", "--dde"):
config.dde_url = p
elif o in ("-p", "--popconindex"):
config.popcon_index = p
elif o in ("-m", "--popcondir"):
config.popcon_dir = p
elif o in ("-u", "--index_mode"):
config.index_mode = p
elif o in ("-l", "--clustersdir"):
config.clusters_dir = p
elif o in ("-c", "--kmedoids"):
config.k_medoids = int(p)
elif o in ("-x", "--max_popcon"):
config.max_popcon = int(p)
elif o in ("-w", "--weight"):
config.weight = p
elif o in ("-s", "--strategy"):
config.strategy = p
elif o in ("-z", "--profile_size"):
config.profile_size = int(p)
elif o in ("-z", "--profiling"):
config.profiling = p
elif o in ("-n", "--neighbors"):
config.k_neighbors = int(p)
elif o in ("-i", "--init"):
continue
elif o in ("-t", "--train"):
continue
else:
assert False, "unhandled option"