From ff1e73e35c493d5e7542d7a5511ec1a43ba26db9 Mon Sep 17 00:00:00 2001 From: Falak Asad Date: Thu, 18 Jul 2019 03:20:32 +0500 Subject: [PATCH] Bugfix/issue 3968 (#3982) * Fix for issue-3968 * Added contributor agreement * Made suggested changes --- .github/contributors/FallakAsad.md | 106 +++++++++++++++++++++++ spacy/scorer.py | 8 +- spacy/tests/regression/test_issue3968.py | 34 ++++++++ 3 files changed, 142 insertions(+), 6 deletions(-) create mode 100644 .github/contributors/FallakAsad.md create mode 100644 spacy/tests/regression/test_issue3968.py diff --git a/.github/contributors/FallakAsad.md b/.github/contributors/FallakAsad.md new file mode 100644 index 000000000..0a0b00f7e --- /dev/null +++ b/.github/contributors/FallakAsad.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 | | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | | +| GitHub username | | +| Website (optional) | | \ No newline at end of file diff --git a/spacy/scorer.py b/spacy/scorer.py index b9994e3f2..34a9b7620 100644 --- a/spacy/scorer.py +++ b/spacy/scorer.py @@ -172,12 +172,8 @@ class Scorer(object): self.ner_per_ents[ent.label_].fp += 1 else: cand_ents.add((ent.label_, first, last)) - current_ent[ent.label_].add( - tuple(x for x in cand_ents if x[0] == ent.label_) - ) - current_gold[ent.label_].add( - tuple(x for x in gold_ents if x[0] == ent.label_) - ) + current_ent[ent.label_].update([x for x in cand_ents if x[0] == ent.label_]) + current_gold[ent.label_].update([x for x in gold_ents if x[0] == ent.label_]) # Scores per ent [ v.score_set(current_ent[k], current_gold[k]) diff --git a/spacy/tests/regression/test_issue3968.py b/spacy/tests/regression/test_issue3968.py new file mode 100644 index 000000000..7e970a3a9 --- /dev/null +++ b/spacy/tests/regression/test_issue3968.py @@ -0,0 +1,34 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from spacy.gold import GoldParse +from spacy.scorer import Scorer +from ..util import get_doc + +test_samples = [ + [ + "100 - 200", + { + "entities": [ + [0, 3, "CARDINAL"], + [6, 9, "CARDINAL"] + ] + } + ] +] + +def test_issue3625(en_vocab): + scorer = Scorer() + for input_, annot in test_samples: + doc = get_doc(en_vocab, words = input_.split(' '), ents = [[0,1,'CARDINAL'], [2,3,'CARDINAL']]); + gold = GoldParse(doc, entities = annot['entities']) + scorer.score(doc, gold) + results = scorer.scores + + # Expects total accuracy and accuracy for each each entity to be 100% + assert results['ents_p'] == 100 + assert results['ents_f'] == 100 + assert results['ents_r'] == 100 + assert results['ents_per_type']['CARDINAL']['p'] == 100 + assert results['ents_per_type']['CARDINAL']['f'] == 100 + assert results['ents_per_type']['CARDINAL']['r'] == 100