mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 11:29:13 +03:00
e559867605
* Add utils for working with remote storage * WIP add remote_cache for project * WIP add push and pull commands * Use pathy in remote_cache * Updarte util * Update remote_cache * Update util * Update project assets * Update pull script * Update push script * Fix type annotation in util * Work on remote storage * Remove site and env hash * Fix imports * Fix type annotation * Require pathy * Require pathy * Fix import * Add a util to handle project variable substitution * Import push and pull commands * Fix pull command * Fix push command * Fix tarfile in remote_storage * Improve printing * Fiddle with status messages * Set version to v3.0.0a9 * Draft docs for spacy project remote storages * Update docs [ci skip] * Use Thinc config to simplify and unify template variables * Auto-format * Don't import Pathy globally for now Causes slow and annoying Google Cloud warning * Tidy up test * Tidy up and update tests * Update to latest Thinc * Update docs * variables -> vars * Update docs [ci skip] * Update docs [ci skip] Co-authored-by: Ines Montani <ines@ines.io>
360 lines
14 KiB
Python
360 lines
14 KiB
Python
import pytest
|
|
from spacy.gold import docs_to_json, biluo_tags_from_offsets
|
|
from spacy.gold.converters import iob2docs, conll_ner2docs, conllu2docs
|
|
from spacy.lang.en import English
|
|
from spacy.schemas import ProjectConfigSchema, RecommendationSchema, validate
|
|
from spacy.cli.pretrain import make_docs
|
|
from spacy.cli.init_config import init_config, RECOMMENDATIONS
|
|
from spacy.cli._util import validate_project_commands, parse_config_overrides
|
|
from spacy.cli._util import load_project_config, substitute_project_variables
|
|
from thinc.config import ConfigValidationError
|
|
import srsly
|
|
|
|
from .util import make_tempdir
|
|
|
|
|
|
def test_cli_converters_conllu2json():
|
|
# from NorNE: https://github.com/ltgoslo/norne/blob/3d23274965f513f23aa48455b28b1878dad23c05/ud/nob/no_bokmaal-ud-dev.conllu
|
|
lines = [
|
|
"1\tDommer\tdommer\tNOUN\t_\tDefinite=Ind|Gender=Masc|Number=Sing\t2\tappos\t_\tO",
|
|
"2\tFinn\tFinn\tPROPN\t_\tGender=Masc\t4\tnsubj\t_\tB-PER",
|
|
"3\tEilertsen\tEilertsen\tPROPN\t_\t_\t2\tname\t_\tI-PER",
|
|
"4\tavstår\tavstå\tVERB\t_\tMood=Ind|Tense=Pres|VerbForm=Fin\t0\troot\t_\tO",
|
|
]
|
|
input_data = "\n".join(lines)
|
|
converted_docs = conllu2docs(input_data, n_sents=1)
|
|
assert len(converted_docs) == 1
|
|
converted = [docs_to_json(converted_docs)]
|
|
assert converted[0]["id"] == 0
|
|
assert len(converted[0]["paragraphs"]) == 1
|
|
assert len(converted[0]["paragraphs"][0]["sentences"]) == 1
|
|
sent = converted[0]["paragraphs"][0]["sentences"][0]
|
|
assert len(sent["tokens"]) == 4
|
|
tokens = sent["tokens"]
|
|
assert [t["orth"] for t in tokens] == ["Dommer", "Finn", "Eilertsen", "avstår"]
|
|
assert [t["tag"] for t in tokens] == ["NOUN", "PROPN", "PROPN", "VERB"]
|
|
assert [t["head"] for t in tokens] == [1, 2, -1, 0]
|
|
assert [t["dep"] for t in tokens] == ["appos", "nsubj", "name", "ROOT"]
|
|
ent_offsets = [
|
|
(e[0], e[1], e[2]) for e in converted[0]["paragraphs"][0]["entities"]
|
|
]
|
|
biluo_tags = biluo_tags_from_offsets(converted_docs[0], ent_offsets, missing="O")
|
|
assert biluo_tags == ["O", "B-PER", "L-PER", "O"]
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"lines",
|
|
[
|
|
(
|
|
"1\tDommer\tdommer\tNOUN\t_\tDefinite=Ind|Gender=Masc|Number=Sing\t2\tappos\t_\tname=O",
|
|
"2\tFinn\tFinn\tPROPN\t_\tGender=Masc\t4\tnsubj\t_\tSpaceAfter=No|name=B-PER",
|
|
"3\tEilertsen\tEilertsen\tPROPN\t_\t_\t2\tname\t_\tname=I-PER",
|
|
"4\tavstår\tavstå\tVERB\t_\tMood=Ind|Tense=Pres|VerbForm=Fin\t0\troot\t_\tSpaceAfter=No|name=O",
|
|
"5\t.\t$.\tPUNCT\t_\t_\t4\tpunct\t_\tname=B-BAD",
|
|
),
|
|
(
|
|
"1\tDommer\tdommer\tNOUN\t_\tDefinite=Ind|Gender=Masc|Number=Sing\t2\tappos\t_\t_",
|
|
"2\tFinn\tFinn\tPROPN\t_\tGender=Masc\t4\tnsubj\t_\tSpaceAfter=No|NE=B-PER",
|
|
"3\tEilertsen\tEilertsen\tPROPN\t_\t_\t2\tname\t_\tNE=L-PER",
|
|
"4\tavstår\tavstå\tVERB\t_\tMood=Ind|Tense=Pres|VerbForm=Fin\t0\troot\t_\tSpaceAfter=No",
|
|
"5\t.\t$.\tPUNCT\t_\t_\t4\tpunct\t_\tNE=B-BAD",
|
|
),
|
|
],
|
|
)
|
|
def test_cli_converters_conllu2json_name_ner_map(lines):
|
|
input_data = "\n".join(lines)
|
|
converted_docs = conllu2docs(
|
|
input_data, n_sents=1, ner_map={"PER": "PERSON", "BAD": ""}
|
|
)
|
|
assert len(converted_docs) == 1
|
|
converted = [docs_to_json(converted_docs)]
|
|
assert converted[0]["id"] == 0
|
|
assert len(converted[0]["paragraphs"]) == 1
|
|
assert converted[0]["paragraphs"][0]["raw"] == "Dommer FinnEilertsen avstår. "
|
|
assert len(converted[0]["paragraphs"][0]["sentences"]) == 1
|
|
sent = converted[0]["paragraphs"][0]["sentences"][0]
|
|
assert len(sent["tokens"]) == 5
|
|
tokens = sent["tokens"]
|
|
assert [t["orth"] for t in tokens] == ["Dommer", "Finn", "Eilertsen", "avstår", "."]
|
|
assert [t["tag"] for t in tokens] == ["NOUN", "PROPN", "PROPN", "VERB", "PUNCT"]
|
|
assert [t["head"] for t in tokens] == [1, 2, -1, 0, -1]
|
|
assert [t["dep"] for t in tokens] == ["appos", "nsubj", "name", "ROOT", "punct"]
|
|
ent_offsets = [
|
|
(e[0], e[1], e[2]) for e in converted[0]["paragraphs"][0]["entities"]
|
|
]
|
|
biluo_tags = biluo_tags_from_offsets(converted_docs[0], ent_offsets, missing="O")
|
|
assert biluo_tags == ["O", "B-PERSON", "L-PERSON", "O", "O"]
|
|
|
|
|
|
def test_cli_converters_conllu2json_subtokens():
|
|
# https://raw.githubusercontent.com/ohenrik/nb_news_ud_sm/master/original_data/no-ud-dev-ner.conllu
|
|
lines = [
|
|
"1\tDommer\tdommer\tNOUN\t_\tDefinite=Ind|Gender=Masc|Number=Sing\t2\tappos\t_\tname=O",
|
|
"2-3\tFE\t_\t_\t_\t_\t_\t_\t_\t_",
|
|
"2\tFinn\tFinn\tPROPN\t_\tGender=Masc\t4\tnsubj\t_\tname=B-PER",
|
|
"3\tEilertsen\tEilertsen\tX\t_\tGender=Fem|Tense=past\t2\tname\t_\tname=I-PER",
|
|
"4\tavstår\tavstå\tVERB\t_\tMood=Ind|Tense=Pres|VerbForm=Fin\t0\troot\t_\tSpaceAfter=No|name=O",
|
|
"5\t.\t$.\tPUNCT\t_\t_\t4\tpunct\t_\tname=O",
|
|
]
|
|
input_data = "\n".join(lines)
|
|
converted_docs = conllu2docs(
|
|
input_data, n_sents=1, merge_subtokens=True, append_morphology=True
|
|
)
|
|
assert len(converted_docs) == 1
|
|
converted = [docs_to_json(converted_docs)]
|
|
|
|
assert converted[0]["id"] == 0
|
|
assert len(converted[0]["paragraphs"]) == 1
|
|
assert converted[0]["paragraphs"][0]["raw"] == "Dommer FE avstår. "
|
|
assert len(converted[0]["paragraphs"][0]["sentences"]) == 1
|
|
sent = converted[0]["paragraphs"][0]["sentences"][0]
|
|
assert len(sent["tokens"]) == 4
|
|
tokens = sent["tokens"]
|
|
print(tokens)
|
|
assert [t["orth"] for t in tokens] == ["Dommer", "FE", "avstår", "."]
|
|
assert [t["tag"] for t in tokens] == [
|
|
"NOUN__Definite=Ind|Gender=Masc|Number=Sing",
|
|
"PROPN_X__Gender=Fem,Masc|Tense=past",
|
|
"VERB__Mood=Ind|Tense=Pres|VerbForm=Fin",
|
|
"PUNCT",
|
|
]
|
|
assert [t["pos"] for t in tokens] == ["NOUN", "PROPN", "VERB", "PUNCT"]
|
|
assert [t["morph"] for t in tokens] == [
|
|
"Definite=Ind|Gender=Masc|Number=Sing",
|
|
"Gender=Fem,Masc|Tense=past",
|
|
"Mood=Ind|Tense=Pres|VerbForm=Fin",
|
|
"",
|
|
]
|
|
assert [t["lemma"] for t in tokens] == ["dommer", "Finn Eilertsen", "avstå", "$."]
|
|
assert [t["head"] for t in tokens] == [1, 1, 0, -1]
|
|
assert [t["dep"] for t in tokens] == ["appos", "nsubj", "ROOT", "punct"]
|
|
ent_offsets = [
|
|
(e[0], e[1], e[2]) for e in converted[0]["paragraphs"][0]["entities"]
|
|
]
|
|
biluo_tags = biluo_tags_from_offsets(converted_docs[0], ent_offsets, missing="O")
|
|
assert biluo_tags == ["O", "U-PER", "O", "O"]
|
|
|
|
|
|
def test_cli_converters_iob2json(en_vocab):
|
|
lines = [
|
|
"I|O like|O London|I-GPE and|O New|B-GPE York|I-GPE City|I-GPE .|O",
|
|
"I|O like|O London|B-GPE and|O New|B-GPE York|I-GPE City|I-GPE .|O",
|
|
"I|PRP|O like|VBP|O London|NNP|I-GPE and|CC|O New|NNP|B-GPE York|NNP|I-GPE City|NNP|I-GPE .|.|O",
|
|
"I|PRP|O like|VBP|O London|NNP|B-GPE and|CC|O New|NNP|B-GPE York|NNP|I-GPE City|NNP|I-GPE .|.|O",
|
|
]
|
|
input_data = "\n".join(lines)
|
|
converted_docs = iob2docs(input_data, en_vocab, n_sents=10)
|
|
assert len(converted_docs) == 1
|
|
converted = docs_to_json(converted_docs)
|
|
assert converted["id"] == 0
|
|
assert len(converted["paragraphs"]) == 1
|
|
assert len(converted["paragraphs"][0]["sentences"]) == 4
|
|
for i in range(0, 4):
|
|
sent = converted["paragraphs"][0]["sentences"][i]
|
|
assert len(sent["tokens"]) == 8
|
|
tokens = sent["tokens"]
|
|
expected = ["I", "like", "London", "and", "New", "York", "City", "."]
|
|
assert [t["orth"] for t in tokens] == expected
|
|
assert len(converted_docs[0].ents) == 8
|
|
for ent in converted_docs[0].ents:
|
|
assert ent.text in ["New York City", "London"]
|
|
|
|
|
|
def test_cli_converters_conll_ner2json():
|
|
lines = [
|
|
"-DOCSTART- -X- O O",
|
|
"",
|
|
"I\tO",
|
|
"like\tO",
|
|
"London\tB-GPE",
|
|
"and\tO",
|
|
"New\tB-GPE",
|
|
"York\tI-GPE",
|
|
"City\tI-GPE",
|
|
".\tO",
|
|
"",
|
|
"I O",
|
|
"like O",
|
|
"London B-GPE",
|
|
"and O",
|
|
"New B-GPE",
|
|
"York I-GPE",
|
|
"City I-GPE",
|
|
". O",
|
|
"",
|
|
"I PRP O",
|
|
"like VBP O",
|
|
"London NNP B-GPE",
|
|
"and CC O",
|
|
"New NNP B-GPE",
|
|
"York NNP I-GPE",
|
|
"City NNP I-GPE",
|
|
". . O",
|
|
"",
|
|
"I PRP _ O",
|
|
"like VBP _ O",
|
|
"London NNP _ B-GPE",
|
|
"and CC _ O",
|
|
"New NNP _ B-GPE",
|
|
"York NNP _ I-GPE",
|
|
"City NNP _ I-GPE",
|
|
". . _ O",
|
|
"",
|
|
"I\tPRP\t_\tO",
|
|
"like\tVBP\t_\tO",
|
|
"London\tNNP\t_\tB-GPE",
|
|
"and\tCC\t_\tO",
|
|
"New\tNNP\t_\tB-GPE",
|
|
"York\tNNP\t_\tI-GPE",
|
|
"City\tNNP\t_\tI-GPE",
|
|
".\t.\t_\tO",
|
|
]
|
|
input_data = "\n".join(lines)
|
|
converted_docs = conll_ner2docs(input_data, n_sents=10)
|
|
assert len(converted_docs) == 1
|
|
converted = docs_to_json(converted_docs)
|
|
assert converted["id"] == 0
|
|
assert len(converted["paragraphs"]) == 1
|
|
assert len(converted["paragraphs"][0]["sentences"]) == 5
|
|
for i in range(0, 5):
|
|
sent = converted["paragraphs"][0]["sentences"][i]
|
|
assert len(sent["tokens"]) == 8
|
|
tokens = sent["tokens"]
|
|
# fmt: off
|
|
assert [t["orth"] for t in tokens] == ["I", "like", "London", "and", "New", "York", "City", "."]
|
|
# fmt: on
|
|
assert len(converted_docs[0].ents) == 10
|
|
for ent in converted_docs[0].ents:
|
|
assert ent.text in ["New York City", "London"]
|
|
|
|
|
|
def test_pretrain_make_docs():
|
|
nlp = English()
|
|
|
|
valid_jsonl_text = {"text": "Some text"}
|
|
docs, skip_count = make_docs(nlp, [valid_jsonl_text], 1, 10)
|
|
assert len(docs) == 1
|
|
assert skip_count == 0
|
|
|
|
valid_jsonl_tokens = {"tokens": ["Some", "tokens"]}
|
|
docs, skip_count = make_docs(nlp, [valid_jsonl_tokens], 1, 10)
|
|
assert len(docs) == 1
|
|
assert skip_count == 0
|
|
|
|
invalid_jsonl_type = 0
|
|
with pytest.raises(TypeError):
|
|
make_docs(nlp, [invalid_jsonl_type], 1, 100)
|
|
|
|
invalid_jsonl_key = {"invalid": "Does not matter"}
|
|
with pytest.raises(ValueError):
|
|
make_docs(nlp, [invalid_jsonl_key], 1, 100)
|
|
|
|
empty_jsonl_text = {"text": ""}
|
|
docs, skip_count = make_docs(nlp, [empty_jsonl_text], 1, 10)
|
|
assert len(docs) == 0
|
|
assert skip_count == 1
|
|
|
|
empty_jsonl_tokens = {"tokens": []}
|
|
docs, skip_count = make_docs(nlp, [empty_jsonl_tokens], 1, 10)
|
|
assert len(docs) == 0
|
|
assert skip_count == 1
|
|
|
|
too_short_jsonl = {"text": "This text is not long enough"}
|
|
docs, skip_count = make_docs(nlp, [too_short_jsonl], 10, 15)
|
|
assert len(docs) == 0
|
|
assert skip_count == 0
|
|
|
|
too_long_jsonl = {"text": "This text contains way too much tokens for this test"}
|
|
docs, skip_count = make_docs(nlp, [too_long_jsonl], 1, 5)
|
|
assert len(docs) == 0
|
|
assert skip_count == 0
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"config",
|
|
[
|
|
{"commands": [{"name": "a"}, {"name": "a"}]},
|
|
{"commands": [{"name": "a"}], "workflows": {"a": []}},
|
|
{"commands": [{"name": "a"}], "workflows": {"b": ["c"]}},
|
|
],
|
|
)
|
|
def test_project_config_validation1(config):
|
|
with pytest.raises(SystemExit):
|
|
validate_project_commands(config)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"config,n_errors",
|
|
[
|
|
({"commands": {"a": []}}, 1),
|
|
({"commands": [{"help": "..."}]}, 1),
|
|
({"commands": [{"name": "a", "extra": "b"}]}, 1),
|
|
({"commands": [{"extra": "b"}]}, 2),
|
|
({"commands": [{"name": "a", "deps": [123]}]}, 1),
|
|
],
|
|
)
|
|
def test_project_config_validation2(config, n_errors):
|
|
errors = validate(ProjectConfigSchema, config)
|
|
assert len(errors) == n_errors
|
|
|
|
|
|
def test_project_config_interpolation():
|
|
variables = {"a": 10, "b": {"c": "foo", "d": True}}
|
|
commands = [
|
|
{"name": "x", "script": ["hello ${vars.a} ${vars.b.c}"]},
|
|
{"name": "y", "script": ["${vars.b.c} ${vars.b.d}"]},
|
|
]
|
|
project = {"commands": commands, "vars": variables}
|
|
with make_tempdir() as d:
|
|
srsly.write_yaml(d / "project.yml", project)
|
|
cfg = load_project_config(d)
|
|
assert cfg["commands"][0]["script"][0] == "hello 10 foo"
|
|
assert cfg["commands"][1]["script"][0] == "foo true"
|
|
commands = [{"name": "x", "script": ["hello ${vars.a} ${vars.b.e}"]}]
|
|
project = {"commands": commands, "vars": variables}
|
|
with pytest.raises(ConfigValidationError):
|
|
substitute_project_variables(project)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"args,expected",
|
|
[
|
|
# fmt: off
|
|
(["--x.foo", "10"], {"x.foo": 10}),
|
|
(["--x.foo=10"], {"x.foo": 10}),
|
|
(["--x.foo", "bar"], {"x.foo": "bar"}),
|
|
(["--x.foo=bar"], {"x.foo": "bar"}),
|
|
(["--x.foo", "--x.bar", "baz"], {"x.foo": True, "x.bar": "baz"}),
|
|
(["--x.foo", "--x.bar=baz"], {"x.foo": True, "x.bar": "baz"}),
|
|
(["--x.foo", "10.1", "--x.bar", "--x.baz", "false"], {"x.foo": 10.1, "x.bar": True, "x.baz": False}),
|
|
(["--x.foo", "10.1", "--x.bar", "--x.baz=false"], {"x.foo": 10.1, "x.bar": True, "x.baz": False})
|
|
# fmt: on
|
|
],
|
|
)
|
|
def test_parse_config_overrides(args, expected):
|
|
assert parse_config_overrides(args) == expected
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"args",
|
|
[["--foo"], ["--x.foo", "bar", "--baz"], ["--x.foo", "bar", "baz"], ["x.foo"]],
|
|
)
|
|
def test_parse_config_overrides_invalid(args):
|
|
with pytest.raises(SystemExit):
|
|
parse_config_overrides(args)
|
|
|
|
|
|
@pytest.mark.parametrize("lang", ["en", "nl"])
|
|
@pytest.mark.parametrize(
|
|
"pipeline", [["tagger", "parser", "ner"], [], ["ner", "textcat", "sentencizer"]]
|
|
)
|
|
@pytest.mark.parametrize("optimize", ["efficiency", "accuracy"])
|
|
def test_init_config(lang, pipeline, optimize):
|
|
# TODO: add more tests and also check for GPU with transformers
|
|
init_config("-", lang=lang, pipeline=pipeline, optimize=optimize, cpu=True)
|
|
|
|
|
|
def test_model_recommendations():
|
|
for lang, data in RECOMMENDATIONS.items():
|
|
assert RecommendationSchema(**data)
|