def compute_edit_distance(src_file, para_file):
src_data = load_conllu(src_file)
para_data = load_conllu(para_file)
assert len(src_data) == len(para_data)
edit_distances = []
for key in tqdm(src_data.keys(), total=len(src_data)):
src_sent = src_data[key]
para_sent = para_data[key]
src_root, _ = head_to_tree(src_sent['head'], src_sent['upos'])
para_root, _ = head_to_tree(para_sent['head'], para_sent['upos'])
src_tree_to_string = []
treeToString(src_root, src_tree_to_string)
src_tree_to_string = ['{'] + src_tree_to_string + ['}']
src_tree_to_string = ''.join(src_tree_to_string)
para_tree_to_string = []
treeToString(para_root, para_tree_to_string)
para_tree_to_string = ['{'] + para_tree_to_string + ['}']
para_tree_to_string = ''.join(para_tree_to_string)
# print(src_tree_to_string)
# print(para_tree_to_string)
apted = APTED(aptedTree.from_text(src_tree_to_string),
aptedTree.from_text(para_tree_to_string))
ted = apted.compute_edit_distance()
edit_distances.append(ted)
# mapping = apted.compute_edit_mapping()
# print(mapping)
return edit_distances
def ast_anytree_to_apted(cur_node):
"""
Converts an Anytree to an equivalent APTED Tree.
"""
children_apted_nodes = []
for child in list(cur_node.children):
children_apted_nodes.append(ast_anytree_to_apted(child))
return Tree(cur_node.op_name + " " + cur_node.op_class,
*children_apted_nodes)
def mid2tr(tactr, mdx):
return Tree("FOO").from_text(
tactr.mid_decoder.decode_exp_by_key(mdx).apted_tree())
def kern2tr(tactr, kdx):
return Tree("FOO").from_text(
tactr.decoder.decode_exp_by_key(kdx).apted_tree())
def gen_apted_tree(code):
from apted.helpers import Tree
tree_str = apted_ast_visit(ast.parse(code))
return Tree.from_text(tree_str)
x_embs1.append(embs1)
x_info_ids1.append(info_ids1)
c_loss = get_cluster_score(x_embs1, x_info_ids1)
c_loss = torch.Tensor([c_loss])
c_loss.requires_grad_()
c_loss = c_loss.cuda()
#------------loss_s--------------------#
s_len = len(samples_tree)
_loss = []
_losses = 0
for i in range(s_len): # 32
_uid = real_DT[i].split('_')[0]
tt1_i = train_DT_id.index(_uid)
tt1 = train_DT[tt1_i]
tree1 = Tree.from_text(tt1)
tt2 = samples_tree[i]
tree2 = Tree.from_text(tt2)
_apted = APTED(tree1, tree2, Config())
ted = _apted.compute_edit_distance()
_loss.append(ted)
_losses += ted
t_loss = torch.mean(torch.Tensor([_loss]))
t_loss.requires_grad_()
t_loss = t_loss.cuda()
#-------------------------------------------#
# construct the input to the genrator, add zeros before samples and delete the last column
zeros = torch.zeros((BATCH_SIZE, 1)).type(torch.LongTensor)
if samples.is_cuda: