spaCy/spacy/tests/regression/test_issue3830.py
Sofie Van Landeghem c0f4a1e43b
train is from-config by default (#5575)
* verbose and tag_map options

* adding init_tok2vec option and only changing the tok2vec that is specified

* adding omit_extra_lookups and verifying textcat config

* wip

* pretrain bugfix

* add replace and resume options

* train_textcat fix

* raw text functionality

* improve UX when KeyError or when input data can't be parsed

* avoid unnecessary access to goldparse in TextCat pipe

* save performance information in nlp.meta

* add noise_level to config

* move nn_parser's defaults to config file

* multitask in config - doesn't work yet

* scorer offering both F and AUC options, need to be specified in config

* add textcat verification code from old train script

* small fixes to config files

* clean up

* set default config for ner/parser to allow create_pipe to work as before

* two more test fixes

* small fixes

* cleanup

* fix NER pickling + additional unit test

* create_pipe as before
2020-06-12 02:02:07 +02:00

25 lines
990 B
Python

from spacy.pipeline.pipes import DependencyParser
from spacy.vocab import Vocab
from spacy.pipeline.defaults import default_parser
def test_issue3830_no_subtok():
"""Test that the parser doesn't have subtok label if not learn_tokens"""
config = {"learn_tokens": False, "min_action_freq": 30, "beam_width": 1, "beam_update_prob": 1.0}
parser = DependencyParser(Vocab(), default_parser(), **config)
parser.add_label("nsubj")
assert "subtok" not in parser.labels
parser.begin_training(lambda: [])
assert "subtok" not in parser.labels
def test_issue3830_with_subtok():
"""Test that the parser does have subtok label if learn_tokens=True."""
config = {"learn_tokens": True, "min_action_freq": 30, "beam_width": 1, "beam_update_prob": 1.0}
parser = DependencyParser(Vocab(), default_parser(), **config)
parser.add_label("nsubj")
assert "subtok" not in parser.labels
parser.begin_training(lambda: [])
assert "subtok" in parser.labels