Skip to content

Instantly share code, notes, and snippets.

View Hironsan's full-sized avatar
💤
Zzz

Hiroki Nakayama Hironsan

💤
Zzz
View GitHub Profile
[paths]
train = "./train.spacy"
dev = "./dev.spacy"
init_tok2vec = null
vectors = null
[corpora]
[corpora.train]
@readers = "spacy.Corpus.v1"
import spacy
from spacy.tokens import DocBin
from spacy_partial_tagger.tokenizer import CharacterTokenizer
text = "Selegiline - induced postural hypotension in Parkinson's disease: a longitudinal study on the effects of drug withdrawal."
patterns = [
{"label": "Chemical", "pattern": [{"LOWER": "selegiline"}]},
{"label": "Disease", "pattern": [{"LOWER": "hypotension"}]},
{
"label": "Disease",
This file has been truncated, but you can view the full file.
{"0": {"points": [0, 0, 0, 1, 0, 2, 0, 3, 0, 4, 0, 5, 0, 6, 0, 7, 0, 8, 0, 9, 0, 10, 0, 11, 0, 12, 0, 13, 0, 14, 0, 15, 0, 16, 0, 17, 0, 18, 0, 19, 0, 20, 0, 21, 0, 22, 0, 23, 0, 24, 0, 25, 0, 26, 0, 27, 0, 28, 0, 29, 0, 30, 0, 31, 0, 32, 0, 33, 0, 34, 0, 35, 0, 36, 0, 37, 0, 38, 0, 39, 1, 0, 1, 1, 1, 2, 1, 3, 1, 4, 1, 5, 1, 6, 1, 7, 1, 8, 1, 9, 1, 10, 1, 11, 1, 12, 1, 13, 1, 14, 1, 15, 1, 16, 1, 17, 1, 18, 1, 19, 1, 20, 1, 21, 1, 22, 1, 23, 1, 24, 1, 25, 1, 26, 1, 27, 1, 28, 1, 29, 1, 30, 1, 31, 1, 32, 1, 33, 1, 34, 1, 35, 1, 36, 1, 37, 1, 38, 2, 0, 2, 1, 2, 2, 2, 3, 2, 4, 2, 5, 2, 6, 2, 7, 2, 8, 2, 9, 2, 10, 2, 11, 2, 12, 2, 13, 2, 14, 2, 15, 2, 16, 2, 17, 2, 18, 2, 19, 2, 20, 2, 21, 2, 22, 2, 23, 2, 24, 2, 25, 2, 26, 2, 27, 2, 28, 2, 29, 2, 30, 2, 31, 2, 32, 2, 33, 2, 34, 2, 35, 2, 36, 2, 37, 2, 38, 3, 0, 3, 1, 3, 2, 3, 3, 3, 4, 3, 5, 3, 6, 3, 7, 3, 8, 3, 9, 3, 10, 3, 11, 3, 12, 3, 13, 3, 14, 3, 15, 3, 16, 3, 17, 3, 18, 3, 19, 3, 20, 3, 21, 3, 22, 3, 23, 3, 24, 3, 25, 3, 26, 3, 27, 3, 28, 3, 29, 3, 30, 3,
@Hironsan
Hironsan / lambda_function.py
Created June 30, 2020 08:59
spaCy for Lambda
import os
import urllib.request
import spacy
import tarfile
from pathlib import Path
def maybe_download(model, dest):
save_path = Path(dest) / model
if not os.path.exists(save_path):
#!/bin/bash
REGION=us-east-1
RUNTIME=python3.7
while getopts :n:r:p: OPT
do
case $OPT in
n) PACKAGE=$OPTARG;;
r) REGION=$OPTARG;;
p) RUNTIME=$OPTARG;;
REGION=us-west-1
RUNTIME=python3.7
docker run \
-v $(pwd):/opt \
-it lambci/lambda:build-$RUNTIME \
pip install spacy -t /opt/python
zip -r spacy.zip python/
@Hironsan
Hironsan / todo.md
Last active January 28, 2021 11:49
「機械学習・深層学習による自然言語処理入門」の誤植等の管理

「機械学習・深層学習による自然言語処理入門」の誤植等

  • より良い本にするため、誤植や誤り、改善点等の洗い出しと反映を行う。
  • サポートページへ反映されるまで時間がかかるので、一旦ここで管理する。
  • 正式な内容は編集に依頼してサポートページへ掲載する。
  • フィードバック、指摘、マサカリ、感謝します。

誤植

| ページ | 誤 | 正しい | 備考 |

1444062497
284862083
762630884
1188614369
1104161854
1280855887
586449534
1206728554
468429333
566799704
@Hironsan
Hironsan / corpus_reader.py
Created September 11, 2018 20:46
chABSA-dataset corpus reader
# -*- coding: utf-8 -*-
import json
from collections import defaultdict
from pathlib import Path
def find_corpus_fileids(root, regexp):
p = Path(root)
return list(p.glob(regexp))