def eval_instances():
instance_file = os.path.join(DATA, 'twitter/self_reveal/user_pool0.csv')
filtered_file = os.path.join(DATA, 'twitter/self_reveal/user_pool2.csv')
first_model = getModel()
fout = open(filtered_file, 'w')
for line in open(instance_file):
user_id, target = line.rstrip('\n').split('\t')
context = getTrTWContext(user_id)
if context is None:
continue
weight = 1
score = first_model.eval(context, target)
if score > .25:
fout.write(user_id + '\t' + target + '\n')
fout.close()
if context is None:
continue
weight = 1.0
predictions = model.eval_all(context)
for label, score in predictions:
all_buckets[int(label)][int(20 * score)] += 1
if label == target:
correct_buckets[int(label)][int(20 * score)] += 1
print 'correct buckets'
print correct_buckets
print 'all buckets'
print all_buckets
print 'caliplot'
print correct_buckets / all_buckets
if __name__ == "__main__":
maxent.set_verbose(1)
test_file = '../data/semi/ver2.8-hardLabel.csv'
distant_model = getModel()
caliplot(test_file, distant_model)
