def getMappingDicts_reGen(corpusdir, mapsdir, cons):
# check the old constraint.dict exists or not
cons_file = corpusdir + "/constraint.set"
if (not os.path.exists(cons_file)):
# Regenerate
(word_wid_dic, wid_did_dic, did_doc_dic) = \
getNewMappingDicts(corpusdir, mapsdir)
else:
# check whether the old constraint is the same as consdict
old_cons = read_pickle(cons_file)
if checkSame(cons, old_cons):
# check the mapping dicts exist or not
word_wid = mapsdir + "/word_wid.dict"
wid_did = mapsdir + "/wid_did.dict"
did_doc = mapsdir + "/did_doc.dict"
if (os.path.exists(word_wid) and os.path.exists(wid_did) \
and os.path.exists(did_doc)):
word_wid_dic = read_pickle(word_wid)
wid_did_dic = read_pickle(wid_did)
did_doc_dic = read_pickle(did_doc)
else:
(word_wid_dic, wid_did_dic, did_doc_dic) = \
getNewMappingDicts(corpusdir, mapsdir)
else:
(word_wid_dic, wid_did_dic, did_doc_dic) = \
getNewMappingDicts(corpusdir, mapsdir)
write_pickle(cons, cons_file)
return (word_wid_dic, wid_did_dic, did_doc_dic)
def getMappingDicts(corpusdir, mapsdir):
# check the mapping dicts exist or not
word_wid = mapsdir + "/word_wid.dict"
wid_did = mapsdir + "/wid_did.dict"
did_doc = mapsdir + "/did_doc.dict"
if (os.path.exists(word_wid) and os.path.exists(wid_did) \
and os.path.exists(did_doc)):
word_wid_dic = read_pickle(word_wid)
wid_did_dic = read_pickle(wid_did)
did_doc_dic = read_pickle(did_doc)
else:
(word_wid_dic, wid_did_dic, did_doc_dic) = \
getNewMappingDicts(corpusdir, mapsdir)
return (word_wid_dic, wid_did_dic, did_doc_dic)
def getNewAddedCons(corpusdir, cons_set, cons_list):
# check the old constraint.list exists or not
cons_file = corpusdir + "/constraint.set"
if (not os.path.exists(cons_file)):
cons_added_set = cons_set
else:
cons_old_set = read_pickle(cons_file)
cons_added_set = cons_set.difference(cons_old_set)
# save the new cons set to file
write_pickle(cons_set, cons_file)
cons_file = corpusdir + "/constraint.list"
write_pickle(cons_list, cons_file)
return cons_added_set
flags.define_int("num_topics", 0, "Current number of topics")
if __name__ == "__main__":
flags.InitFlags()
if re.search("doc", flags.update_strategy):
update_strategy = 1
elif re.search("term", flags.update_strategy):
update_strategy = 0
else:
print "Wrong update strategy!"
exit()
# Build index if it doesn't already exist
if os.path.exists(flags.mapping):
index = read_pickle(flags.mapping)
else:
index = build_index(flags.corpus, flags.mapping)
# Remove offending assignments
if re.search("clear", flags.resume_type):
# Read in constraints
cons_set = get_constraints(flags.cons_file)
print cons_set
clear_assignments(flags.input_base, flags.output_base, index,
cons_set, update_strategy)
elif re.search("split", flags.resume_type):
# Read in constraints
print flags.wordnet
[cons_list, cons_set] = get_constraints_from_wn(flags.wordnet)
print cons_set
