From 999ff03b192169e676ac6c1f74e03545d2d35136 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ren=C3=A9=20Octavio=20Queiroz=20Dias?= Date: Thu, 4 Feb 2021 19:37:13 -0300 Subject: [PATCH] fix: Fix textcat labels to expect a Optional[Iterable[str]] instead of Optional[Dict] (#6911) * docs: Add agreement * bug: Regression test Issue #6908 * fix: Changed from Dict to Iterable[str] Fix #6908 * Update test to use make_tempdir * fix: Fix WindowsPath error Co-authored-by: Adriane Boyd --- .github/contributors/reneoctavio.md | 106 +++++++++++++++++++++++ spacy/pipeline/textcat.py | 2 +- spacy/pipeline/textcat_multilabel.py | 2 +- spacy/tests/regression/test_issue6908.py | 102 ++++++++++++++++++++++ 4 files changed, 210 insertions(+), 2 deletions(-) create mode 100644 .github/contributors/reneoctavio.md create mode 100644 spacy/tests/regression/test_issue6908.py diff --git a/.github/contributors/reneoctavio.md b/.github/contributors/reneoctavio.md new file mode 100644 index 000000000..c0a4d1a76 --- /dev/null +++ b/.github/contributors/reneoctavio.md @@ -0,0 +1,106 @@ +# spaCy contributor agreement + +This spaCy Contributor Agreement (**"SCA"**) is based on the +[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf). +The SCA applies to any contribution that you make to any product or project +managed by us (the **"project"**), and sets out the intellectual property rights +you grant to us in the contributed materials. The term **"us"** shall mean +[ExplosionAI GmbH](https://explosion.ai/legal). The term +**"you"** shall mean the person or entity identified below. + +If you agree to be bound by these terms, fill in the information requested +below and include the filled-in version with your first pull request, under the +folder [`.github/contributors/`](/.github/contributors/). The name of the file +should be your GitHub username, with the extension `.md`. For example, the user +example_user would create the file `.github/contributors/example_user.md`. + +Read this agreement carefully before signing. These terms and conditions +constitute a binding legal agreement. + +## Contributor Agreement + +1. The term "contribution" or "contributed materials" means any source code, + object code, patch, tool, sample, graphic, specification, manual, + documentation, or any other material posted or submitted by you to the project. + +2. With respect to any worldwide copyrights, or copyright applications and + registrations, in your contribution: + + * you hereby assign to us joint ownership, and to the extent that such + assignment is or becomes invalid, ineffective or unenforceable, you hereby + grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge, + royalty-free, unrestricted license to exercise all rights under those + copyrights. This includes, at our option, the right to sublicense these same + rights to third parties through multiple levels of sublicensees or other + licensing arrangements; + + * you agree that each of us can do all things in relation to your + contribution as if each of us were the sole owners, and if one of us makes + a derivative work of your contribution, the one who makes the derivative + work (or has it made will be the sole owner of that derivative work; + + * you agree that you will not assert any moral rights in your contribution + against us, our licensees or transferees; + + * you agree that we may register a copyright in your contribution and + exercise all ownership rights associated with it; and + + * you agree that neither of us has any duty to consult with, obtain the + consent of, pay or render an accounting to the other for any use or + distribution of your contribution. + +3. With respect to any patents you own, or that you can license without payment + to any third party, you hereby grant to us a perpetual, irrevocable, + non-exclusive, worldwide, no-charge, royalty-free license to: + + * make, have made, use, sell, offer to sell, import, and otherwise transfer + your contribution in whole or in part, alone or in combination with or + included in any product, work or materials arising out of the project to + which your contribution was submitted, and + + * at our option, to sublicense these same rights to third parties through + multiple levels of sublicensees or other licensing arrangements. + +4. Except as set out above, you keep all right, title, and interest in your + contribution. The rights that you grant to us under these terms are effective + on the date you first submitted a contribution to us, even if your submission + took place before the date you sign these terms. + +5. You covenant, represent, warrant and agree that: + + - Each contribution that you submit is and shall be an original work of + authorship and you can legally grant the rights set out in this SCA; + + - to the best of your knowledge, each contribution will not violate any + third party's copyrights, trademarks, patents, or other intellectual + property rights; and + + - each contribution shall be in compliance with U.S. export control laws and + other applicable export and import laws. You agree to notify us if you + become aware of any circumstance which would make any of the foregoing + representations inaccurate in any respect. We may publicly disclose your + participation in the project, including the fact that you have signed the SCA. + +6. This SCA is governed by the laws of the State of California and applicable + U.S. Federal law. Any choice of law rules will not apply. + +7. Please place an “x” on one of the applicable statement below. Please do NOT + mark both statements: + + * [x] I am signing on behalf of myself as an individual and no other person + or entity, including my employer, has or will have rights with respect to my + contributions. + + * [ ] I am signing on behalf of my employer or a legal entity and I have the + actual authority to contractually bind that entity. + +## Contributor Details + +| Field | Entry | +| ----------------------------- | -------------------- | +| Name | Rene Octavio Q. Dias | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2020-02-03 | +| GitHub username | reneoctavio | +| Website (optional) | | diff --git a/spacy/pipeline/textcat.py b/spacy/pipeline/textcat.py index a16508865..f94bde84f 100644 --- a/spacy/pipeline/textcat.py +++ b/spacy/pipeline/textcat.py @@ -308,7 +308,7 @@ class TextCategorizer(TrainablePipe): get_examples: Callable[[], Iterable[Example]], *, nlp: Optional[Language] = None, - labels: Optional[Dict] = None, + labels: Optional[Iterable[str]] = None, positive_label: Optional[str] = None, ) -> None: """Initialize the pipe for training, using a representative set diff --git a/spacy/pipeline/textcat_multilabel.py b/spacy/pipeline/textcat_multilabel.py index 3cb0f4567..dc4b17940 100644 --- a/spacy/pipeline/textcat_multilabel.py +++ b/spacy/pipeline/textcat_multilabel.py @@ -137,7 +137,7 @@ class MultiLabel_TextCategorizer(TextCategorizer): get_examples: Callable[[], Iterable[Example]], *, nlp: Optional[Language] = None, - labels: Optional[Dict] = None, + labels: Optional[Iterable[str]] = None, ): """Initialize the pipe for training, using a representative set of data examples. diff --git a/spacy/tests/regression/test_issue6908.py b/spacy/tests/regression/test_issue6908.py new file mode 100644 index 000000000..a12ae9e13 --- /dev/null +++ b/spacy/tests/regression/test_issue6908.py @@ -0,0 +1,102 @@ +import pytest +import spacy +from spacy.language import Language +from spacy.tokens import DocBin +from spacy import util +from spacy.schemas import ConfigSchemaInit + +from spacy.training.initialize import init_nlp + +from ..util import make_tempdir + +TEXTCAT_WITH_LABELS_ARRAY_CONFIG = """ +[paths] +train = "TRAIN_PLACEHOLDER" +raw = null +init_tok2vec = null +vectors = null + +[system] +seed = 0 +gpu_allocator = null + +[nlp] +lang = "en" +pipeline = ["textcat"] +tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} +disabled = [] +before_creation = null +after_creation = null +after_pipeline_creation = null +batch_size = 1000 + +[components] + +[components.textcat] +factory = "TEXTCAT_PLACEHOLDER" + +[corpora] + +[corpora.train] +@readers = "spacy.Corpus.v1" +path = ${paths:train} + +[corpora.dev] +@readers = "spacy.Corpus.v1" +path = ${paths:train} + + +[training] +train_corpus = "corpora.train" +dev_corpus = "corpora.dev" +seed = ${system.seed} +gpu_allocator = ${system.gpu_allocator} +frozen_components = [] +before_to_disk = null + +[pretraining] + +[initialize] +vectors = ${paths.vectors} +init_tok2vec = ${paths.init_tok2vec} +vocab_data = null +lookups = null +before_init = null +after_init = null + +[initialize.components] + +[initialize.components.textcat] +labels = ['label1', 'label2'] + +[initialize.tokenizer] +""" + + +@pytest.mark.parametrize( + "component_name", + ["textcat", "textcat_multilabel"], +) +def test_textcat_initialize_labels_validation(component_name): + """Test intializing textcat with labels in a list""" + + def create_data(out_file): + nlp = spacy.blank("en") + doc = nlp.make_doc("Some text") + doc.cats = {"label1": 0, "label2": 1} + + out_data = DocBin(docs=[doc]).to_bytes() + with out_file.open("wb") as file_: + file_.write(out_data) + + with make_tempdir() as tmp_path: + train_path = tmp_path / "train.spacy" + create_data(train_path) + + config_str = TEXTCAT_WITH_LABELS_ARRAY_CONFIG.replace( + "TEXTCAT_PLACEHOLDER", component_name + ) + config_str = config_str.replace("TRAIN_PLACEHOLDER", train_path.as_posix()) + + config = util.load_config_from_str(config_str) + init_nlp(config)