mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +03:00
968aff2f6a
<!--- Provide a general summary of your changes in the title. --> ## Description - [x] Replace marks in params for pytest 4.0 compat ([see here](https://docs.pytest.org/en/latest/deprecations.html#marks-in-pytest-mark-parametrize)) - [x] Un-xfail passing tests (some fixes in a recent update resolved a bunch of issues, but tests were apparently never updated here) ### Types of change <!-- What type of change does your PR cover? Is it a bug fix, an enhancement or new feature, or a change to the documentation? --> ## 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.
90 lines
3.2 KiB
Python
90 lines
3.2 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
import json
|
|
from tempfile import NamedTemporaryFile
|
|
import pytest
|
|
|
|
from ...cli.train import train
|
|
|
|
|
|
def test_cli_trained_model_can_be_saved(tmpdir):
|
|
lang = 'nl'
|
|
output_dir = str(tmpdir)
|
|
train_file = NamedTemporaryFile('wb', dir=output_dir, delete=False)
|
|
train_corpus = [
|
|
{
|
|
"id": "identifier_0",
|
|
"paragraphs": [
|
|
{
|
|
"raw": "Jan houdt van Marie.\n",
|
|
"sentences": [
|
|
{
|
|
"tokens": [
|
|
{
|
|
"id": 0,
|
|
"dep": "nsubj",
|
|
"head": 1,
|
|
"tag": "NOUN",
|
|
"orth": "Jan",
|
|
"ner": "B-PER"
|
|
},
|
|
{
|
|
"id": 1,
|
|
"dep": "ROOT",
|
|
"head": 0,
|
|
"tag": "VERB",
|
|
"orth": "houdt",
|
|
"ner": "O"
|
|
},
|
|
{
|
|
"id": 2,
|
|
"dep": "case",
|
|
"head": 1,
|
|
"tag": "ADP",
|
|
"orth": "van",
|
|
"ner": "O"
|
|
},
|
|
{
|
|
"id": 3,
|
|
"dep": "obj",
|
|
"head": -2,
|
|
"tag": "NOUN",
|
|
"orth": "Marie",
|
|
"ner": "B-PER"
|
|
},
|
|
{
|
|
"id": 4,
|
|
"dep": "punct",
|
|
"head": -3,
|
|
"tag": "PUNCT",
|
|
"orth": ".",
|
|
"ner": "O"
|
|
},
|
|
{
|
|
"id": 5,
|
|
"dep": "",
|
|
"head": -1,
|
|
"tag": "SPACE",
|
|
"orth": "\n",
|
|
"ner": "O"
|
|
}
|
|
],
|
|
"brackets": []
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
]
|
|
|
|
train_file.write(json.dumps(train_corpus).encode('utf-8'))
|
|
train_file.close()
|
|
train_data = train_file.name
|
|
dev_data = train_data
|
|
|
|
# spacy train -n 1 -g -1 nl output_nl training_corpus.json training \
|
|
# corpus.json
|
|
train(lang, output_dir, train_data, dev_data, n_iter=1)
|
|
|
|
assert True
|