from stanford import CoreNLP
from dependency_tree import build_tree
from dependency_similarity import *
from feature import *
from NeuralLearner import *
import torch
import torch.nn as nn
import numpy as np
import sys
import xgboost as xgb
# data pre-processing
if False:
reader = CorpusReader('data/test-set.txt')
train_data = reader.data()
for _, item in train_data.items():
item['token1'] = tokenized_sentence(item['Sentence1'])
item['token2'] = tokenized_sentence(item['Sentence2'])
corenlp = CoreNLP(sys.argv)
corenlp.start_server()
for k, item in train_data.items():
print(k)
item['d-tree1'] = corenlp.dependency_parse_tree(
list_to_string(item['token1']))
item['d-tree2'] = corenlp.dependency_parse_tree(
list_to_string(item['token2']))
corenlp.stop_server()
