File size: 2,981 Bytes
366b225 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
from conllu import parse_incr, parse
from nltk.parse import DependencyGraph, DependencyEvaluator
from nltk.parse.transitionparser import TransitionParser
import pickle
import pygraphviz as pgv
from test_hn_pos import test_fn
import os
def Process(sentence):
words = sentence.replace('|','।').split()
tags = test_fn(words)
text = []
i = 0
for word, tag in zip(words,tags):
i += 1
fill = '_'
text.append('\t'.join([str(i),word,fill,fill,fill,fill,fill,fill,fill,fill]))
dg = DependencyGraph('\n'.join(text))
text = '\n'.join(text)
text = text + '\n\n' + text
with open('biaffine-parser-master/data/naive3.conllx','w') as f:
f.write(text)
os.chdir('biaffine-parser-master')
os.system('python3.7 run.py predict --feat=bert --fdata=data/naive3.conllx --fpred=data/naive3.conllx')
txt = ''
os.chdir('..')
with open('biaffine-parser-master/data/naive3.conllx','r') as f:
txt = f.read().split('\n\n')[0]
# parser = TransitionParser('arc-eager')
# with open('models/parser.pkl','rb') as in_file:
# parser = pickle.load(in_file)
# predictions = parser.parse([dg],'models/arc_eager.model')
# txt = predictions[0].to_conll(4)
err = False
try:
out = DependencyGraph(txt)
out_dot = out.to_dot()
G = pgv.AGraph(out_dot)
G.layout(prog='dot') # use dot
G.draw('static/process.png')
except:
err = True
txt += '''Error generating graph.\n'''
return txt, err
## creates dependency graph list according to nltk library specification
def DepGraphList(sentenceList):
dgList = []
i = 0
j = 0
for sentence in sentenceList:
text = []
for token in sentence:
text.append(' '.join([token['form'],token['upostag'],str(token['head']),token['deprel'].upper()]))
try:
dg = DependencyGraph('\n'.join(text))
except:
j += 1
continue
i += 1
dgList.append(dg)
print(i,j)
return dgList
def main():
#data_file = open('data/test.conllu','r',encoding='utf-8')
#sentence_iter = parse_incr(data_file)
#sentences = []
#for s in sentence_iter:
# sentences.append(s)
#training_set = DepGraphList(sentences[len(sentences)//4:])
#test_set = DepGraphList(sentences[0:len(sentences)//4])
#parser = TransitionParser('arc-eager')
## Training
# parser.train(training_set,'models/arc_eager.model')
# with open('models/parser2.pkl','wb') as out:
# pickle.dump(parser,out)
# # ## Evaluation
# with open('models/parser2.pkl','rb') as in_file:
# parser = pickle.load(in_file)
# predictions = parser.parse(test_set,'models/arc_eager.model')
# de = DependencyEvaluator(predictions,test_set)
# print(de.eval())
Process('राम अच्छा पुरुष है |')
return
if __name__=='__main__':
main()
|