def get_features(ptree: nltk.ParentedTree, conn_idxs):
leave_list = ptree.leaves()
lca_loc = ptree.treeposition_spanning_leaves(conn_idxs[0], conn_idxs[-1] + 1)[:-1]
self_category = ptree[lca_loc].label()
parent_category = ptree[lca_loc].parent().label() if lca_loc else self_category
left_sibling = get_sibling_label(ptree[lca_loc], 'left')
right_sibling = get_sibling_label(ptree[lca_loc], 'right')
labels = {n.label() for n in ptree.subtrees(lambda t: t.height() > 2)}
bool_vp = 'VP' in labels
bool_trace = 'T' in labels
c = ' '.join(leave_list[conn_idxs[0]:conn_idxs[-1] + 1]).lower()
prev, prev_conn, prev_pos, prev_pos_conn_pos = get_pos_features(ptree, conn_idxs, c, -1)
next, next_conn, next_pos, next_pos_conn_pos = get_pos_features(ptree, conn_idxs, c, 1)
prev = lemmatizer.lemmatize(prev)
next = lemmatizer.lemmatize(next)
r2l = [ptree[lca_loc[:i + 1]].label() for i in range(len(lca_loc))]
r2lcomp = get_compressed_chain(r2l)
feat = {'connective': c, 'connectivePOS': self_category,
'prevWord': prev, 'prevPOSTag': prev_conn, 'prevPOS+cPOS': prev_pos_conn_pos,
'nextWord': next, 'nextPOSTag': next_pos, 'cPOS+nextPOS': next_pos_conn_pos,
'root2LeafCompressed': ','.join(r2lcomp), 'root2Leaf': ','.join(r2l),
'left_sibling': left_sibling, 'right_sibling': right_sibling,
'parentCategory': parent_category, 'boolVP': bool_vp, 'boolTrace': bool_trace}
return feat
def get_production_rules(ptree: nltk.ParentedTree):
return [
"{} <- {}".format(t.label(), ' '.join([tt.label() for tt in t]))
for t in ptree.subtrees(lambda t: t.height() > 2)
]
count=0
print('\n>>1st pass of process the trees')
for tree in Forest:
count +=1
if count%int(len(Forest)/10)==0:
print('progress------->',str(count/len(Forest)*100)[:2], '% finished')
new_tree=ParentedTree(tree.pprint())
for subtree in new_tree.subtrees(): #update current tree
string=''.join(subtree.leaves())
if string in Vec: #leaves/string in the record
tag, subscript= decompose_tag(subtree.node)
tag_vec_str=set2str(Vec[string]) #get the tag-set of the node according to the leaves and convert it to str
subtree.node=tag_vec_str+'_'+subscript #update the node with the new_tag
NewForest.append(new_tree)