From 15be09ceb00a4fb7364e6347d37c02035249b37c Mon Sep 17 00:00:00 2001 From: Jeno Date: Tue, 6 Aug 2019 05:01:25 -0400 Subject: [PATCH] Raise error if annotation dict in simple training style has unexpected keys #4074 (#4079) * adding enhancement #4074. * modified behavior to strictly require top level dictionary keys - issue #4074 * pass expected keys to error message and add links as expected top level key --- .github/contributors/jenojp.md | 106 +++++++++++++++++++++++++++++++++ spacy/errors.py | 4 ++ spacy/language.py | 4 ++ spacy/tests/test_language.py | 3 + 4 files changed, 117 insertions(+) create mode 100644 .github/contributors/jenojp.md diff --git a/.github/contributors/jenojp.md b/.github/contributors/jenojp.md new file mode 100644 index 000000000..3ba5ed296 --- /dev/null +++ b/.github/contributors/jenojp.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 | Jeno Pizarro | +| Company name (if applicable) | IBM | +| Title or role (if applicable) | Data Scientist and Software Developer | +| Date | 3 August 2019 | +| GitHub username | jenojp | +| Website (optional) | https://www.linkedin.com/in/jenojp/ | diff --git a/spacy/errors.py b/spacy/errors.py index 945d3364a..79b9cbdf4 100644 --- a/spacy/errors.py +++ b/spacy/errors.py @@ -417,6 +417,10 @@ class Errors(object): "component matches the model being loaded.") E150 = ("The language of the `nlp` object and the `vocab` should be the same, " "but found '{nlp}' and '{vocab}' respectively.") + E151 = ("Trying to call nlp.update without required annotation types. " + "Expected top-level keys: {expected_keys}." + " Got: {unexpected_keys}.") + @add_codes class TempErrors(object): diff --git a/spacy/language.py b/spacy/language.py index f87cb4e31..411727f70 100644 --- a/spacy/language.py +++ b/spacy/language.py @@ -445,6 +445,10 @@ class Language(object): if isinstance(doc, basestring_): doc = self.make_doc(doc) if not isinstance(gold, GoldParse): + expected_keys = ("words", "tags", "heads", "deps", "entities", "cats", "links") + unexpected_keys = [k for k in gold if k not in expected_keys] + if unexpected_keys: + raise ValueError(Errors.E151.format(unexpected_keys=unexpected_keys, expected_keys=expected_keys)) gold = GoldParse(doc, **gold) doc_objs.append(doc) gold_objs.append(gold) diff --git a/spacy/tests/test_language.py b/spacy/tests/test_language.py index 00175fe9a..94c37d4ab 100644 --- a/spacy/tests/test_language.py +++ b/spacy/tests/test_language.py @@ -22,6 +22,7 @@ def nlp(): def test_language_update(nlp): text = "hello world" annots = {"cats": {"POSITIVE": 1.0, "NEGATIVE": 0.0}} + wrongkeyannots = {"LABEL": True} doc = Doc(nlp.vocab, words=text.split(" ")) gold = GoldParse(doc, **annots) # Update with doc and gold objects @@ -37,6 +38,8 @@ def test_language_update(nlp): nlp.update([doc], []) with pytest.raises(IndexError): nlp.update([], [gold]) + with pytest.raises(ValueError): + nlp.update([text], [wrongkeyannots]) def test_language_evaluate(nlp):