def _get_dict_for_user(user):
"""
Get the file containing revision entries for the user "user"
If the file is present, load its json which is effectively a dict
Otherwise create the file
:param user:
:type user:
:return:
:rtype:
"""
if FILE_MODE:
filename = _get_file_name(user)
if os.path.isfile(filename):
with open(filename, 'rb') as inp:
user_dict = Serializable.loads(json.load(inp))
else:
user_dict = {user: {}}
else:
filename = os.path.join(os.getcwd(), 'results', WIKINAME,
'user_graph.json')
with open(filename, 'rb') as inp:
user_dict = Serializable.loads(json.load(inp))
if not user_dict.has_key(user):
user_dict[user] = {}
return user_dict[user]
def _update_dict_for_user(user, dict_for_user):
"""
Write the dict into user's specific file
:param user:
:type user:
:return:
:rtype:
"""
if FILE_MODE:
dict_to_dump = {user: dict_for_user}
filename = _get_file_name(user)
with open(filename, 'wb') as outp:
json.dump(Serializable.dumps(dict_to_dump), outp)
else:
filename = os.path.join(os.getcwd(), 'results', WIKINAME,
'user_graph.json')
with open(filename, 'rb') as inp:
user_dict = Serializable.loads(json.load(inp))
user_dict[user] = dict_for_user
with open(filename, 'wb') as outp:
json.dump(Serializable.dumps(user_dict), outp)
def loads(s, device):
d = Serializable.loads(s)
m = StdNet(d['args'], empty=True)
for i, ms in enumerate(d['layers']):
l = LinearWithSensitivity.loads(ms, device)
m.layers.append(l)
m.add_module('layer_%d' % i, l)
return m
def loads(s, device):
d = Serializable.loads(s)
m = LinearExtended(d['in_features'],
d['out_features'],
bias=d['bias'] is not None)
m.weight.data = torch.from_numpy(d['weight']).to(device)
if d['bias'] is not None:
m.bias.data = torch.from_numpy(d['bias']).to(device)
return m
def loads(s, device):
d = Serializable.loads(s)
args = Storage(d['args'])
m = RBFNet(args, empty=True)
for i, ms in enumerate(d['layers']):
l = RBFI.loads(ms, device)
m.layers.append(l)
m.add_module('layer_%d' % i, l)
return m
def loads(s, device):
d = Serializable.loads(s)
args = dict(n_classes=10)
args.update(d['args'])
args = Storage(args)
m = MWDNet(args, empty=True)
for i, ms in enumerate(d['layers']):
l = MWD.loads(ms, device)
m.layers.append(l)
m.add_module('layer_%d' % i, l)
return m
def loads(s, device):
"""Reads itself from string s."""
d = Serializable.loads(s)
m = RBFI(d['in_features'],
d['out_features'],
andor=d['andor'],
modinf=d['modinf'],
regular_deriv=d['regular_deriv'],
min_input=d['min_input'],
max_input=d['max_input'],
min_slope=d['min_slope'],
max_slope=d['max_slope'])
m.u.data = torch.from_numpy(d['u']).to(device)
m.w.data = torch.from_numpy(d['w']).to(device)
m.andor01.data = torch.from_numpy(d['andor01']).to(device)
return m
learning_rate_vector=LEARNING_RATE_VECTOR)
t2 = time.clock()
precision_dict, recall_dict, recall_list, all_labels = lstm_stack.test_model_simple(
test_set, max_depth=DEPTH - 1)
t3 = time.clock()
results_file = os.path.join(
os.getcwd(), 'results', WIKINAME,
'results_breadth_%d_depth_%d_instances_%d.json' %
(BREADTH, DEPTH, NUMBER_OF_INSTANCES))
print "Training completed in %r" % (t2 - t1)
if os.path.isfile(results_file):
with open(results_file, 'rb') as inp:
results = (Serializable.loads(inp.read()))
else:
results = {}
for label in all_labels:
label = str(label)
# total_prec_list[label].append(precision_dict[label])
# total_recall_list[label].append(recall_dict[label])
# total_avg_recall_list.append(np.mean(recall_list))
# total_f1_list[label].append(_f1(precision_dict[label], recall_dict[label]))
for keyname in ['prec', 'rec', 'f1']:
if not results.has_key(keyname):
results[keyname] = {}
if not results[keyname].has_key(label):
results[keyname][label] = []
if not results.has_key('avg_rec'):
p_value, z_left_tail = statistical_significance(a, b, level=level)
if __name__ == "__main__":
WIKINAME = 'astwiki'
NUMBER_OF_INSTANCES = 50000
BREADTH = 15
DEPTH = 1
# results_file = os.path.join(os.getcwd(), 'results', WIKINAME, 'results_breadth_%d_depth_%d.json' % (BREADTH, DEPTH))
results_file = os.path.join(os.getcwd(), 'results', WIKINAME,
'results_breadth_%d_depth_%d_instances_%d.json' % (BREADTH, DEPTH, NUMBER_OF_INSTANCES))
with open(results_file, 'rb') as inp:
r1 = Serializable.loads(inp.read())
BREADTH = 3
DEPTH = 1
results_file = os.path.join(os.getcwd(), 'results', WIKINAME,
'results_breadth_%d_depth_%d_instances_%d.json' % (BREADTH, DEPTH, NUMBER_OF_INSTANCES))
# results_file = os.path.join(os.getcwd(), 'results', WIKINAME, 'results_breadth_%d_depth_%d.json' % (BREADTH, DEPTH))
with open(results_file, 'rb') as inp:
r2 = Serializable.loads(inp.read())
#
# f1_label1_d1 = r1['f1']['0']
# f1_label1_d2 = r2['f1']['0']
f1_label1_d1 = r1['avg_rec']
f1_label1_d2 = r2['avg_rec']