NLP(自然言語処理) Stanzaによる構文解析の結果を取得する

with io.open('articles_u.txt', encoding='utf-8') as f:
    text = f.read()
texts = text.replace('eos', '.\n').splitlines()

stanza.download('en')

nlp = stanza.Pipeline(lang='en')

for line in range(3):

texts[0] = 'i expect all of you to be here five minutes before the test begins without fail .'
texts[1] = 'the poor old woman had her bag stolen again .'
texts[2] = 'a rush-hour traffic jam delayed my arrival by two hours .'

    doc = nlp(texts[line])

doc =
  [
    {
      "id": 1,
      "text": "i",
      "lemma": "i",
      "upos": "PRON",
      "xpos": "PRP",
      "feats": "Case=Nom|Number=Sing|Person=1|PronType=Prs",
      "head": 2,
      "deprel": "nsubj",
      "misc": "start_char=0|end_char=1",
      "ner": "O"
    },
    {
      "id": 2,
      "text": "expect",
      "lemma": "expect",
      "upos": "VERB",
      "xpos": "VBP",
      "feats": "Mood=Ind|Tense=Pres|VerbForm=Fin",
      "head": 0,
      "deprel": "root",
      "misc": "start_char=2|end_char=8",
      "ner": "O"
    },
    {
      "id": 3,
      "text": "all",
      "lemma": "all",
      "upos": "DET",
      "xpos": "DT",
      "head": 2,
      "deprel": "obj",
      "misc": "start_char=9|end_char=12",
      "ner": "O"
    }, ......

    for word in doc.sentences[0].words:
        char.append(word.text)
        lemma.append(word.lemma)
        pos.append(word.pos)
        xpos.append(word.xpos)
        deprel.append(word.deprel)

    for word in doc.sentences[0].words:
        head.extend([lemma[word.head-1] if word.head > 0 else "root"])

    chars.append(char)
    lemmas.append(lemma)
    poses.append(pos)
    xposes.append(xpos)
    heads.append(head)
    deprels.append(deprel)

chars =
  [['i', 'expect', 'all', 'of', 'you', 'to', 'be', 'here', 'five', 'minutes', 'before', 'the', 'test', 'begins', 'without', 'fail', '.'],
   ['the', 'poor', 'old', 'woman', 'had', 'her', 'bag', 'stolen', 'again', '.'],
   ['a', 'rush', '-', 'hour', 'traffic', 'jam', 'delayed', 'my', 'arrival', 'by', 'two', 'hours', '.']]
lemmas =
  [['i', 'expect', 'all', 'of', 'you', 'to', 'be', 'here', 'five', 'minute', 'before', 'the', 'test', 'begin', 'without', 'fail', '.'],
   ['the', 'poor', 'old', 'woman', 'have', 'she', 'bag', 'steal', 'again', '.'],
   ['a', 'rush', '-', 'hour', 'traffic', 'jam', 'delay', 'my', 'arrival', 'by', 'two', 'hour', '.']]
poses =
  [['PRON', 'VERB', 'DET', 'ADP', 'PRON', 'PART', 'AUX', 'ADV', 'NUM', 'NOUN', 'SCONJ', 'DET', 'NOUN', 'VERB', 'ADP', 'NOUN', 'PUNCT'],
   ['DET', 'ADJ', 'ADJ', 'NOUN', 'VERB', 'PRON', 'NOUN', 'VERB', 'ADV', 'PUNCT'],
   ['DET', 'NOUN', 'PUNCT', 'NOUN', 'NOUN', 'NOUN', 'VERB', 'PRON', 'NOUN', 'ADP', 'NUM', 'NOUN', 'PUNCT']]
xposes =
  [['PRP', 'VBP', 'DT', 'IN', 'PRP', 'TO', 'VB', 'RB', 'CD', 'NNS', 'IN', 'DT', 'NN', 'VBZ', 'IN', 'NN', '.'],
   ['DT', 'JJ', 'JJ', 'NN', 'VBD', 'PRP$', 'NN', 'VBN', 'RB', '.'],
   ['DT', 'NN', 'HYPH', 'NN', 'NN', 'NN', 'VBD', 'PRP$', 'NN', 'IN', 'CD', 'NNS', '.']]
heads =
  [['expect', 'root', 'expect', 'you', 'all', 'here', 'here', 'expect', 'minute', 'here', 'begin', 'test', 'begin', 'here', 'fail', 'begin', 'expect'],
   ['woman', 'woman', 'woman', 'have', 'root', 'bag', 'have', 'have', 'steal', 'have'],
   ['jam', 'hour', 'hour', 'jam', 'jam', 'delay', 'root', 'arrival', 'delay', 'hour', 'hour', 'delay', 'delay']]
deprels =
  [['nsubj', 'root', 'obj', 'case', 'nmod', 'mark', 'cop', 'xcomp', 'nummod', 'obl:tmod', 'mark', 'det', 'nsubj', 'advcl', 'case', 'obl', 'punct'],
   ['det', 'amod', 'amod', 'nsubj', 'root', 'nmod:poss', 'obj', 'xcomp', 'advmod', 'punct'],
   ['det', 'compound', 'punct', 'compound', 'compound', 'nsubj', 'root', 'nmod:poss', 'obj', 'case', 'nummod', 'obl', 'punct']]

import numpy as np
import sys
import io
import os
import stanza
#read the text
with io.open('articles_u.txt', encoding='utf-8') as f:
    text = f.read()
texts = text.replace('eos', '.\n').splitlines()
#load stanza
stanza.download('en')
nlp = stanza.Pipeline(lang='en')
chars = []
lemmas = []
poses = []
xposes = []
heads = []
deprels = []
for line in range(3):
    char = []
    lemma = []
    pos = []
    xpos = []
    head = []
    deprel = []
    print('analyzing: '+str(line+1)+' / '+str(len(texts)), end='\r')
    doc = nlp(texts[line])
    for word in doc.sentences[0].words:
        char.append(word.text)
        lemma.append(word.lemma)
        pos.append(word.pos)
        xpos.append(word.xpos)
        deprel.append(word.deprel)
    for word in doc.sentences[0].words:
        head.extend([lemma[word.head-1] if word.head > 0 else "root"])
    chars.append(char)
    lemmas.append(lemma)
    poses.append(pos)
    xposes.append(xpos)
    heads.append(head)
    deprels.append(deprel)