mirror of https://github.com/explosion/spaCy.git
104 lines
3.5 KiB
Python
104 lines
3.5 KiB
Python
|
# coding: utf-8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
from . import wikipedia_processor as wp, kb_creator, training_set_creator
|
||
|
|
|
||
|
|
import spacy
|
||
|
|
from spacy.vocab import Vocab
|
||
|
|
from spacy.kb import KnowledgeBase
|
||
|
|
import datetime
|
||
|
|
|
||
|
|
"""
|
||
|
|
Demonstrate how to build a knowledge base from WikiData and run an Entity Linking algorithm.
|
||
|
|
"""
|
||
|
|
|
||
|
|
PRIOR_PROB = 'C:/Users/Sofie/Documents/data/wikipedia/prior_prob.csv'
|
||
|
|
ENTITY_COUNTS = 'C:/Users/Sofie/Documents/data/wikipedia/entity_freq.csv'
|
||
|
|
ENTITY_DEFS = 'C:/Users/Sofie/Documents/data/wikipedia/entity_defs.csv'
|
||
|
|
|
||
|
|
KB_FILE = 'C:/Users/Sofie/Documents/data/wikipedia/kb'
|
||
|
|
VOCAB_DIR = 'C:/Users/Sofie/Documents/data/wikipedia/vocab'
|
||
|
|
|
||
|
|
TRAINING_OUTPUT_SET_DIR = 'C:/Users/Sofie/Documents/data/wikipedia/training_nel/'
|
||
|
|
TRAINING_INPUT_SET_DIR = 'C:/Users/Sofie/Documents/data/wikipedia/training_nel_sample_3may2019/'
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
print("START", datetime.datetime.now())
|
||
|
|
print()
|
||
|
|
my_kb = None
|
||
|
|
|
||
|
|
# one-time methods to create KB and write to file
|
||
|
|
to_create_prior_probs = False
|
||
|
|
to_create_entity_counts = False
|
||
|
|
to_create_kb = False
|
||
|
|
|
||
|
|
# read KB back in from file
|
||
|
|
to_read_kb = True
|
||
|
|
to_test_kb = False
|
||
|
|
|
||
|
|
create_wp_training = False
|
||
|
|
|
||
|
|
# STEP 1 : create prior probabilities from WP
|
||
|
|
# run only once !
|
||
|
|
if to_create_prior_probs:
|
||
|
|
print("STEP 1: to_create_prior_probs", datetime.datetime.now())
|
||
|
|
wp.read_wikipedia_prior_probs(prior_prob_output=PRIOR_PROB)
|
||
|
|
print()
|
||
|
|
|
||
|
|
# STEP 2 : deduce entity frequencies from WP
|
||
|
|
# run only once !
|
||
|
|
if to_create_entity_counts:
|
||
|
|
print("STEP 2: to_create_entity_counts", datetime.datetime.now())
|
||
|
|
wp.write_entity_counts(prior_prob_input=PRIOR_PROB, count_output=ENTITY_COUNTS, to_print=False)
|
||
|
|
print()
|
||
|
|
|
||
|
|
# STEP 3 : create KB and write to file
|
||
|
|
# run only once !
|
||
|
|
if to_create_kb:
|
||
|
|
print("STEP 3a: to_create_kb", datetime.datetime.now())
|
||
|
|
my_nlp = spacy.load('en_core_web_sm')
|
||
|
|
my_vocab = my_nlp.vocab
|
||
|
|
my_kb = kb_creator.create_kb(my_vocab,
|
||
|
|
max_entities_per_alias=10,
|
||
|
|
min_occ=5,
|
||
|
|
entity_output=ENTITY_DEFS,
|
||
|
|
count_input=ENTITY_COUNTS,
|
||
|
|
prior_prob_input=PRIOR_PROB,
|
||
|
|
to_print=False)
|
||
|
|
print("kb entities:", my_kb.get_size_entities())
|
||
|
|
print("kb aliases:", my_kb.get_size_aliases())
|
||
|
|
print()
|
||
|
|
|
||
|
|
print("STEP 3b: write KB", datetime.datetime.now())
|
||
|
|
my_kb.dump(KB_FILE)
|
||
|
|
my_vocab.to_disk(VOCAB_DIR)
|
||
|
|
print()
|
||
|
|
|
||
|
|
# STEP 4 : read KB back in from file
|
||
|
|
if to_read_kb:
|
||
|
|
print("STEP 4: to_read_kb", datetime.datetime.now())
|
||
|
|
my_vocab = Vocab()
|
||
|
|
my_vocab.from_disk(VOCAB_DIR)
|
||
|
|
my_kb = KnowledgeBase(vocab=my_vocab)
|
||
|
|
my_kb.load_bulk(KB_FILE)
|
||
|
|
print("kb entities:", my_kb.get_size_entities())
|
||
|
|
print("kb aliases:", my_kb.get_size_aliases())
|
||
|
|
print()
|
||
|
|
|
||
|
|
# test KB
|
||
|
|
if to_test_kb:
|
||
|
|
kb_creator.test_kb(my_kb)
|
||
|
|
print()
|
||
|
|
|
||
|
|
# STEP 5: create a training dataset from WP
|
||
|
|
if create_wp_training:
|
||
|
|
print("STEP 5: create training dataset", datetime.datetime.now())
|
||
|
|
training_set_creator.create_training(kb=my_kb, entity_input=ENTITY_DEFS, training_output=TRAINING_OUTPUT_SET_DIR)
|
||
|
|
|
||
|
|
# TODO coreference resolution
|
||
|
|
# add_coref()
|
||
|
|
|
||
|
|
print()
|
||
|
|
print("STOP", datetime.datetime.now())
|