dataset.py 文件源码

def read_tree(self, line, label_line):
        # FIXED: tree.idx, also tree dict() use base 1 as it was in dataset
        # parents is list base 0, keep idx-1
        # labels is list base 0, keep idx-1
        parents = map(int,line.split()) # split each number and turn to int
        trees = dict() # this is dict
        root = None
        labels = map(self.parse_dlabel_token, label_line.split())
        for i in xrange(1,len(parents)+1):
            #if not trees[i-1] and parents[i-1]!=-1:
            if i not in trees.keys() and parents[i-1]!=-1:
                idx = i
                prev = None
                while True:
                    parent = parents[idx-1]
                    if parent == -1:
                        break
                    tree = Tree()
                    if prev is not None:
                        tree.add_child(prev)
                    trees[idx] = tree
                    tree.idx = idx # -1 remove -1 here to prevent embs[tree.idx -1] = -1 while tree.idx = 0
                    tree.gold_label = labels[idx-1] # add node label
                    #if trees[parent-1] is not None:
                    if parent in trees.keys():
                        trees[parent].add_child(tree)
                        break
                    elif parent==0:
                        root = tree
                        break
                    else:
                        prev = tree
                        idx = parent
        return root