#!/usr/bin/python
import sys
sys.path.append('python/cap')
sys.path.append('python')
import Features
fe = Features.FeatureExtractor()
cap = Features.CapClassifier()
entityConf = {}
#First pass; confidence
for line in open(sys.argv[1]):
line = line.rstrip('\n')
fields = line.split('\t')
sid = fields[0]
date = fields[9][0:10]
confidence = 1.0 / float(fields[-1])
eType = fields[-2]
entity = fields[-3]
neTags = fields[-4].split(' ')
pos = fields[-5].split(' ')
words = fields[-6].split(' ')
key = "%s\t%s\t%s" % (entity, eType, date)
if entityConf.has_key(key):
entityConf[key] = max(entityConf.get(key), confidence)
else:
