mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 09:57:26 +03:00
37c7c85a86
* Support nowrap setting in util.prints * Tidy up and fix whitespace * Simplify script and use read_jsonl helper * Add JSON schemas (see #2928) * Deprecate Doc.print_tree Will be replaced with Doc.to_json, which will produce a unified format * Add Doc.to_json() method (see #2928) Converts Doc objects to JSON using the same unified format as the training data. Method also supports serializing selected custom attributes in the doc._. space. * Remove outdated test * Add write_json and write_jsonl helpers * WIP: Update spacy train * Tidy up spacy train * WIP: Use wasabi for formatting * Add GoldParse helpers for JSON format * WIP: add debug-data command * Fix typo * Add missing import * Update wasabi pin * Add missing import * 💫 Refactor CLI (#2943) To be merged into #2932. ## Description - [x] refactor CLI To use [`wasabi`](https://github.com/ines/wasabi) - [x] use [`black`](https://github.com/ambv/black) for auto-formatting - [x] add `flake8` config - [x] move all messy UD-related scripts to `cli.ud` - [x] make converters function that take the opened file and return the converted data (instead of having them handle the IO) ### Types of change enhancement ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [x] My changes don't require a change to the documentation, or if they do, I've added all required information. * Update wasabi pin * Delete old test * Update errors * Fix typo * Tidy up and format remaining code * Fix formatting * Improve formatting of messages * Auto-format remaining code * Add tok2vec stuff to spacy.train * Fix typo * Update wasabi pin * Fix path checks for when train() is called as function * Reformat and tidy up pretrain script * Update argument annotations * Raise error if model language doesn't match lang * Document new train command
86 lines
2.7 KiB
Python
86 lines
2.7 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...gold import iob_to_biluo
|
|
|
|
|
|
def conllubio2json(input_data, n_sents=10, use_morphology=False, lang=None):
|
|
"""
|
|
Convert conllu files into JSON format for use with train cli.
|
|
use_morphology parameter enables appending morphology to tags, which is
|
|
useful for languages such as Spanish, where UD tags are not so rich.
|
|
"""
|
|
# by @dvsrepo, via #11 explosion/spacy-dev-resources
|
|
docs = []
|
|
sentences = []
|
|
conll_tuples = read_conllx(input_data, use_morphology=use_morphology)
|
|
for i, (raw_text, tokens) in enumerate(conll_tuples):
|
|
sentence, brackets = tokens[0]
|
|
sentences.append(generate_sentence(sentence))
|
|
# Real-sized documents could be extracted using the comments on the
|
|
# conluu document
|
|
if len(sentences) % n_sents == 0:
|
|
doc = create_doc(sentences, i)
|
|
docs.append(doc)
|
|
sentences = []
|
|
return docs
|
|
|
|
|
|
def read_conllx(input_data, use_morphology=False, n=0):
|
|
i = 0
|
|
for sent in input_data.strip().split("\n\n"):
|
|
lines = sent.strip().split("\n")
|
|
if lines:
|
|
while lines[0].startswith("#"):
|
|
lines.pop(0)
|
|
tokens = []
|
|
for line in lines:
|
|
|
|
parts = line.split("\t")
|
|
id_, word, lemma, pos, tag, morph, head, dep, _1, ner = parts
|
|
if "-" in id_ or "." in id_:
|
|
continue
|
|
try:
|
|
id_ = int(id_) - 1
|
|
head = (int(head) - 1) if head != "0" else id_
|
|
dep = "ROOT" if dep == "root" else dep
|
|
tag = pos if tag == "_" else tag
|
|
tag = tag + "__" + morph if use_morphology else tag
|
|
ner = ner if ner else "O"
|
|
tokens.append((id_, word, tag, head, dep, ner))
|
|
except: # noqa: E722
|
|
print(line)
|
|
raise
|
|
tuples = [list(t) for t in zip(*tokens)]
|
|
yield (None, [[tuples, []]])
|
|
i += 1
|
|
if n >= 1 and i >= n:
|
|
break
|
|
|
|
|
|
def generate_sentence(sent):
|
|
(id_, word, tag, head, dep, ner) = sent
|
|
sentence = {}
|
|
tokens = []
|
|
ner = iob_to_biluo(ner)
|
|
for i, id in enumerate(id_):
|
|
token = {}
|
|
token["orth"] = word[i]
|
|
token["tag"] = tag[i]
|
|
token["head"] = head[i] - id
|
|
token["dep"] = dep[i]
|
|
token["ner"] = ner[i]
|
|
tokens.append(token)
|
|
sentence["tokens"] = tokens
|
|
return sentence
|
|
|
|
|
|
def create_doc(sentences, id):
|
|
doc = {}
|
|
paragraph = {}
|
|
doc["id"] = id
|
|
doc["paragraphs"] = []
|
|
paragraph["sentences"] = sentences
|
|
doc["paragraphs"].append(paragraph)
|
|
return doc
|