mirror of
https://github.com/explosion/spaCy.git
synced 2025-01-28 02:04:07 +03:00
e48a09df4e
* OrigAnnot class instead of gold.orig_annot list of zipped tuples * from_orig to replace from_annot_tuples * rename to RawAnnot * some unit tests for GoldParse creation and internal format * removing orig_annot and switching to lists instead of tuple * rewriting tuples to use RawAnnot (+ debug statements, WIP) * fix pop() changing the data * small fixes * pop-append fixes * return RawAnnot for existing GoldParse to have uniform interface * clean up imports * fix merge_sents * add unit test for 4402 with new structure (not working yet) * introduce DocAnnot * typo fixes * add unit test for merge_sents * rename from_orig to from_raw * fixing unit tests * fix nn parser * read_annots to produce text, doc_annot pairs * _make_golds fix * rename golds_to_gold_annots * small fixes * fix encoding * have golds_to_gold_annots use DocAnnot * missed a spot * merge_sents as function in DocAnnot * allow specifying only part of the token-level annotations * refactor with Example class + underlying dicts * pipeline components to work with Example objects (wip) * input checking * fix yielding * fix calls to update * small fixes * fix scorer unit test with new format * fix kwargs order * fixes for ud and conllu scripts * fix reading data for conllu script * add in proper errors (not fixed numbering yet to avoid merge conflicts) * fixing few more small bugs * fix EL script
65 lines
2.0 KiB
Python
65 lines
2.0 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
import random
|
|
import numpy.random
|
|
from spacy.language import Language
|
|
from spacy.pipeline import TextCategorizer
|
|
from spacy.tokens import Doc
|
|
from spacy.gold import GoldParse
|
|
|
|
|
|
@pytest.mark.skip(reason="Test is flakey when run with others")
|
|
def test_simple_train():
|
|
nlp = Language()
|
|
nlp.add_pipe(nlp.create_pipe("textcat"))
|
|
nlp.get_pipe("textcat").add_label("answer")
|
|
nlp.begin_training()
|
|
for i in range(5):
|
|
for text, answer in [
|
|
("aaaa", 1.0),
|
|
("bbbb", 0),
|
|
("aa", 1.0),
|
|
("bbbbbbbbb", 0.0),
|
|
("aaaaaa", 1),
|
|
]:
|
|
nlp.update((text, {"cats": {"answer": answer}}))
|
|
doc = nlp("aaa")
|
|
assert "answer" in doc.cats
|
|
assert doc.cats["answer"] >= 0.5
|
|
|
|
|
|
@pytest.mark.skip(reason="Test is flakey when run with others")
|
|
def test_textcat_learns_multilabel():
|
|
random.seed(5)
|
|
numpy.random.seed(5)
|
|
docs = []
|
|
nlp = Language()
|
|
letters = ["a", "b", "c"]
|
|
for w1 in letters:
|
|
for w2 in letters:
|
|
cats = {letter: float(w2 == letter) for letter in letters}
|
|
docs.append((Doc(nlp.vocab, words=["d"] * 3 + [w1, w2] + ["d"] * 3), cats))
|
|
random.shuffle(docs)
|
|
model = TextCategorizer(nlp.vocab, width=8)
|
|
for letter in letters:
|
|
model.add_label(letter)
|
|
optimizer = model.begin_training()
|
|
for i in range(30):
|
|
losses = {}
|
|
Ys = [GoldParse(doc, cats=cats) for doc, cats in docs]
|
|
Xs = [doc for doc, cats in docs]
|
|
model.update(Xs, Ys, sgd=optimizer, losses=losses)
|
|
random.shuffle(docs)
|
|
for w1 in letters:
|
|
for w2 in letters:
|
|
doc = Doc(nlp.vocab, words=["d"] * 3 + [w1, w2] + ["d"] * 3)
|
|
truth = {letter: w2 == letter for letter in letters}
|
|
model(doc)
|
|
for cat, score in doc.cats.items():
|
|
if not truth[cat]:
|
|
assert score < 0.5
|
|
else:
|
|
assert score > 0.5
|