[PYTHON] 100 language processing knocks (2020): 31

"""
31.verb
Extract all the surface forms of the verb.

[[{'surface': '', 'base': '*', 'pos': 'BOS/EOS', 'pos1': '*'},
  {'surface': 'one', 'base': 'one', 'pos': 'noun', 'pos1': 'number'},
  {'surface': '', 'base': '*', 'pos': 'BOS/EOS', 'pos1': '*'}],
 [{'surface': '', 'base': '*', 'pos': 'BOS/EOS', 'pos1': '*'},
  {'surface': 'I', 'base': 'I', 'pos': 'noun', 'pos1': '代noun'},
  {'surface': 'Is', 'base': 'Is', 'pos': 'Particle', 'pos1': '係Particle'},
  {'surface': 'Cat', 'base': 'Cat', 'pos': 'noun', 'pos1': 'General'},
  {'surface': 'so', 'base': 'Is', 'pos': 'Auxiliary verb', 'pos1': '*'},
  {'surface': 'is there', 'base': 'is there', 'pos': 'Auxiliary verb', 'pos1': '*'},
  {'surface': '。', 'base': '。', 'pos': 'symbol', 'pos1': 'Kuten'},
  {'surface': '', 'base': '*', 'pos': 'BOS/EOS', 'pos1': '*'}],
"""

import itertools
from typing import List

import utils


def get_verb(sentence: List[dict]) -> List:
    result = []
    for word in sentence:
        if word["pos"] == "verb":
            result.append(word["surface"])
    return result


data = utils.read_json("30_neko_mecab.json")
verbs = [get_verb(sentence) for sentence in data if get_verb(sentence)]
# [['Born', 'Tsuka'], ['Shi', 'Crying', 'Shi', 'Is'], ['start', 'You see'], ['listen'], ['Catch', 'Boiled', 'Eat']]
flat = list(itertools.chain(*verbs))
#  ['Born', 'Tsuka', 'Shi', 'Crying', 'Shi']

Recommended Posts