def test_classifier():
username = "******" # the only one with annotated data
# get the ranked resources
temp = get_ranked_dataset(username)
# split in two equal parts
training_set, real_set = temp[:len(temp)/2], temp[len(temp)/2:]
rankings = get_rankings([username,], lambda x: training_set, lambda x: real_set)
# now compare the returned rankings with the real ones
with_labels = {}
for resource in real_set:
with_labels[resource['url']] = \
int(db.views.find({ 'url': resource['url'],
'user.username': username }).distinct('feedback')[0])
def _confusion_matrix(values):
matrix = defaultdict(int)
for url, value in values.items():
matrix[round(value)] += 1
return matrix
#actual = _confusion_matrix(with_labels)
#jpredicted = _confusion_matrix(dict([(k, v) for k,v in rankings[username].items()
# if k in with_labels.keys()]))
rmse = root_mean_squared_error(rankings['alexis'], with_labels)
mae = mean_absolute_error(rankings['alexis'], with_labels)
return mae, rmse
def test_estimator():
username = '******'
dataset = get_ranked_dataset(username)
rankings = get_rankings([username,], lambda x: [], lambda x:dataset)
with_labels = {}
for resource in dataset:
with_labels[resource['url']] = \
int(db.views.find({ 'url': resource['url'],
'user.username': username }).distinct('feedback')[0])
# once we get the estimations, compare them to the actual values
rmse = root_mean_squared_error(rankings['alexis'], with_labels)
mae = mean_absolute_error(rankings['alexis'], with_labels)
return mae, rmse