mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 02:46:35 +03:00
c68e6b8a96
* WIP
* rm ipython embeds
* rm total
* WIP
* cleanup
* cleanup + reword
* rm component function
* remove migration support form
* fix reference dataset for dev data
* additional fixes
- set approach to identifying unique trees
- adjust line length on messages
- add logic for detecting docs without annotations
* use 0 instead of none for no annotation
* partial annotation support
* initial tests for _compile_gold lemma attributes
Using the example data from the edit tree lemmatizer tests for:
- lemmatizer_trees
- partial_lemma_annotations
- n_low_cardinality_lemmas
- no_lemma_annotations
* adds output test for cli app
* switch msg level
* rm unclear uniqueness check
* Revert "rm unclear uniqueness check"
This reverts commit 6ea2b3524b.
* remove good message on uniqueness
* formatting
* use en_vocab fixture
* clarify data set source in messages
* remove unnecessary import
Co-authored-by: svlandeg <svlandeg@github.com>
92 lines
3.2 KiB
Python
92 lines
3.2 KiB
Python
import os
|
|
from pathlib import Path
|
|
from typer.testing import CliRunner
|
|
from spacy.tokens import DocBin, Doc
|
|
|
|
from spacy.cli._util import app
|
|
from .util import make_tempdir
|
|
|
|
|
|
def test_convert_auto():
|
|
with make_tempdir() as d_in, make_tempdir() as d_out:
|
|
for f in ["data1.iob", "data2.iob", "data3.iob"]:
|
|
Path(d_in / f).touch()
|
|
|
|
# ensure that "automatic" suffix detection works
|
|
result = CliRunner().invoke(app, ["convert", str(d_in), str(d_out)])
|
|
assert "Generated output file" in result.stdout
|
|
out_files = os.listdir(d_out)
|
|
assert len(out_files) == 3
|
|
assert "data1.spacy" in out_files
|
|
assert "data2.spacy" in out_files
|
|
assert "data3.spacy" in out_files
|
|
|
|
|
|
def test_convert_auto_conflict():
|
|
with make_tempdir() as d_in, make_tempdir() as d_out:
|
|
for f in ["data1.iob", "data2.iob", "data3.json"]:
|
|
Path(d_in / f).touch()
|
|
|
|
# ensure that "automatic" suffix detection warns when there are different file types
|
|
result = CliRunner().invoke(app, ["convert", str(d_in), str(d_out)])
|
|
assert "All input files must be same type" in result.stdout
|
|
out_files = os.listdir(d_out)
|
|
assert len(out_files) == 0
|
|
|
|
|
|
def test_benchmark_accuracy_alias():
|
|
# Verify that the `evaluate` alias works correctly.
|
|
result_benchmark = CliRunner().invoke(app, ["benchmark", "accuracy", "--help"])
|
|
result_evaluate = CliRunner().invoke(app, ["evaluate", "--help"])
|
|
assert result_benchmark.stdout == result_evaluate.stdout.replace(
|
|
"spacy evaluate", "spacy benchmark accuracy"
|
|
)
|
|
|
|
|
|
def test_debug_data_trainable_lemmatizer_cli(en_vocab):
|
|
train_docs = [
|
|
Doc(en_vocab, words=["I", "like", "cats"], lemmas=["I", "like", "cat"]),
|
|
Doc(
|
|
en_vocab,
|
|
words=["Dogs", "are", "great", "too"],
|
|
lemmas=["dog", "be", "great", "too"],
|
|
),
|
|
]
|
|
dev_docs = [
|
|
Doc(en_vocab, words=["Cats", "are", "cute"], lemmas=["cat", "be", "cute"]),
|
|
Doc(en_vocab, words=["Pets", "are", "great"], lemmas=["pet", "be", "great"]),
|
|
]
|
|
with make_tempdir() as d_in:
|
|
train_bin = DocBin(docs=train_docs)
|
|
train_bin.to_disk(d_in / "train.spacy")
|
|
dev_bin = DocBin(docs=dev_docs)
|
|
dev_bin.to_disk(d_in / "dev.spacy")
|
|
# `debug data` requires an input pipeline config
|
|
CliRunner().invoke(
|
|
app,
|
|
[
|
|
"init",
|
|
"config",
|
|
f"{d_in}/config.cfg",
|
|
"--lang",
|
|
"en",
|
|
"--pipeline",
|
|
"trainable_lemmatizer",
|
|
],
|
|
)
|
|
result_debug_data = CliRunner().invoke(
|
|
app,
|
|
[
|
|
"debug",
|
|
"data",
|
|
f"{d_in}/config.cfg",
|
|
"--paths.train",
|
|
f"{d_in}/train.spacy",
|
|
"--paths.dev",
|
|
f"{d_in}/dev.spacy",
|
|
],
|
|
)
|
|
# Instead of checking specific wording of the output, which may change,
|
|
# we'll check that this section of the debug output is present.
|
|
assert "= Trainable Lemmatizer =" in result_debug_data.stdout
|