def _identify_partial_matches(self, cohort_id, last_name):
"""Search for partial matches to identify students.
Pulls data from a special set of memcache keys, which are updated by
cron, and provide the names of all students in the school. All the
names are examined to see if the typed name is contained in or
contained by the existing name ("containment matching"), which are
considered partial matches. Then the matches are ordered by their
similarity (Levenshtein distance) to the typed name.
"""
stripped_last_name = util.clean_string(last_name)
match_data, from_memcache = self.internal_api.get_roster(cohort_id)
# White list necessary properties (no sense in releasing status codes
# like 'Parent Refusal' to the public).
def clean_properties(d):
white_list = [
'first_name', 'last_name', 'classroom_name', 'id',
'stripped_last_name'
]
return {k: v for k, v in d.items() if k in white_list}
# Containment matching.
matches = [
clean_properties(u) for u in match_data
if u['stripped_last_name'] in stripped_last_name
or stripped_last_name in u['stripped_last_name']
]
# Order by edit (Levenshtein) distance from the submitted name.
sort_func = lambda n: util.levenshtein_distance(
n['stripped_last_name'], stripped_last_name)
return sorted(matches, key=sort_func)
def get_contributors_list(self):
"""
Creates a list of dicts containing the collaborators for the repository.
This list is aggregated based following the algorithm on Valente's 2016
paper "A Novel Approach for Estimating Truck Factor", namely step #2 "Detect
Developer Aliases.
The collaborators are indexed by email and the names is a list of developer
aliases that the user might have. The user is considered the same user
if the leveshtein distance for the two users names is equal or less than
one.
Returns:
list: A list of dictionaries containing the fields 'email' and 'dev_aliases'.
"""
contributors_list = []
if self.api_repository is not None:
for collaborator in self.api_repository.get_collaborators():
email = collaborator.email
name = collaborator.name
list_entry = {
self.EMAIL_FIELD: email,
self.DEV_ALIASES: [name]
}
fresh_user = True
for contributor in contributors_list:
for alias in contributor.dev_aliases:
if levenshtein_distance(alias, name) <= 1:
contributor.dev_aliases.append(name)
fresh_user = False
break
if not fresh_user:
break
if fresh_user:
contributors_list.append(list_entry)
return contributors_list
def test_saturday_sunday(self):
"""compare Saturday with Sunday"""
self.assertEquals(3, util.levenshtein_distance('Sunday', 'Saturday'))
def test_kitten_sitting(self):
"""compare kitten with sitting"""
self.assertEquals(3, util.levenshtein_distance('sitting', 'kitten'))
def distance(a, b):
return levenshtein_distance(a, b) / float(max(len(a), len(b), 1))
def test():
# Getting settings from config.py
max_len = cfg.MAX_TOKEN_LEN
num_token = cfg.NUM_OF_TOKEN
imw = cfg.IMW
imh = cfg.IMH
# Training params
is_train = False
batch_size = 1
# Tracking/Saving
num_ite_to_log = cfg.NUM_ITE_TO_LOG
num_ite_to_vis = cfg.NUM_ITE_TO_VIS
save_name = cfg.SAVE_NAME
test_name = cfg.TEST_NAME
vis_path = cfg.VIS_PATH
use_cuda = cfg.CUDA and torch.cuda.is_available()
save_path = cfg.MODEL_FOLDER
dataset_path = cfg.DATASET_PATH + 'CROHME2013_data/TestINKML/'
scale_factor = cfg.TEST_SCALE_FACTOR
# Load the vocab dictionary for display purpose
word_to_id, id_to_word = get_gt.build_vocab('mathsymbolclass.txt')
start_id = word_to_id['<s>']
stop_id = word_to_id['</s>']
# Initialize the network and load its weights
net = AGRU()
save_files = glob.glob(save_path + save_name + '*.dat')
if (len(save_files) > 0):
save_file = sorted(save_files)[-1]
print('Loading network weights saved at %s...' % save_file)
loadobj = torch.load(save_file)
net.load_state_dict(loadobj['state_dict'])
print('Loading done.')
if (use_cuda):
net.cuda()
# For debugging
if (not is_train):
net.train(False)
# Get full paths to test inkml files, create a list of scale factors to be used for rendering test images
inkml_list = glob.glob(dataset_path + '*.inkml')
scale_list = [scale_factor] * len(inkml_list)
inkml_list = np.asarray(inkml_list)
scale_list = np.asarray(scale_list)
#inkml_list = inkml_list[0:120]
#scale_list = scale_list[0:120]
num_test = len(inkml_list)
num_ite = int(np.ceil(1.0 * num_test / batch_size))
# Exact match and word error rate
em = []
wer = []
all_pred = []
all_gt = []
# Main test loop
for i in range(num_ite):
batch_idx = range(i * batch_size, (i + 1) * batch_size)
if (batch_idx[-1] >= num_test):
batch_idx = range(i * batch_size, num_test)
batch_size = len(batch_idx)
batch_x = util.batch_data(inkml_list[batch_idx], scale_list[batch_idx],
is_train)
batch_y_np = util.batch_target(inkml_list[batch_idx])
batch_y = util.np_to_var(batch_y_np, use_cuda)
#pred_y, attention = net(batch_x, batch_y)
pred_y, attention = net.beam_search(batch_x, start_id, stop_id)
pred_y = util.var_to_np(pred_y, use_cuda)
pred_y = np.argmax(pred_y, 2)
batch_y = np.reshape(batch_y_np, (batch_size, max_len))
print('Finished ite %d/%d.' % (i, num_ite))
j = 0
pred_string = pred_y[j, :]
pred_string = [id_to_word[idx] for idx in list(pred_string)]
gt_string = batch_y[0, :]
gt_string = [id_to_word[idx] for idx in list(gt_string)]
all_pred.append(pred_string)
all_gt.append(gt_string)
em.append(util.exact_match(pred_string, gt_string))
if ('</s>' in pred_string):
pred_string = pred_string[0:pred_string.index('</s>') + 1]
gt_string = gt_string[0:gt_string.index('</s>') + 1]
wer.append(util.levenshtein_distance(pred_string, gt_string))
if (i % 4 == 0):
continue
# Printing stuffs to console
print('Prediction: %s' % ' '.join(pred_string))
print('Target: %s\n' % ' '.join(gt_string))
# Save attention to files for visualization
file_name = ntpath.basename(inkml_list[batch_idx[j]])[:-6]
vis_path_j = vis_path + file_name + '/'
if (not os.path.exists(vis_path_j)):
os.makedirs(vis_path_j)
tmp_x = np.sum(batch_x.data.cpu().numpy()[j, :, :, :], axis=0)
attention_np = attention.data.cpu().numpy()[j, 1:, :, :]
pred_string = pred_string[1:]
for k, word in enumerate(pred_string):
word = word.replace('/', 'slash_')
attention_k = attention_np[k, :, :] / np.max(
attention_np[k, :, :]) * 0.8
attention_k = (scipy.misc.imresize(attention_k, 16.0)) / 255.0
tmp_x = scipy.misc.imresize(tmp_x, attention_k.shape)
attention_k += tmp_x
attention_k[attention_k > 1] = 1
try:
scipy.misc.imsave(vis_path_j + ('%02d_%s.jpg' % (k, word)),
attention_k)
except FileNotFoundError:
pdb.set_trace()
if (word == '<slash_s>'):
break
#pdb.set_trace()
print("Exact match count: %d/%d" % (sum(em), len(em)))
print("Word error rate: %.5f" % (np.mean(wer)))
pdb.set_trace()
util.save_list([em, wer, all_pred, all_gt], save_path + test_name + '.dat')
pdb.set_trace()
