diff --git a/.github/contributors/BigstickCarpet.md b/.github/contributors/BigstickCarpet.md new file mode 100644 index 000000000..07b356495 --- /dev/null +++ b/.github/contributors/BigstickCarpet.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 UG (haftungsbeschränkt)](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 | James Messinger | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | May 23, 2018 | +| GitHub username | BigstickCarpet | +| Website (optional) | | diff --git a/spacy/cli/train.py b/spacy/cli/train.py index 310b30de0..8dce873ad 100644 --- a/spacy/cli/train.py +++ b/spacy/cli/train.py @@ -116,7 +116,7 @@ def train(lang, output_dir, train_data, dev_data, n_iter=30, n_sents=0, optimizer = nlp.begin_training(lambda: corpus.train_tuples, device=use_gpu) nlp._optimizer = None - print("Itn.\tP.Loss\tN.Loss\tUAS\tNER P.\tNER R.\tNER F.\tTag %\tToken %") + print("Itn. Dep Loss NER Loss UAS NER P. NER R. NER F. Tag % Token % CPU WPS GPU WPS") try: train_docs = corpus.train_docs(nlp, projectivize=True, noise_level=0.0, gold_preproc=gold_preproc, max_length=0) @@ -207,17 +207,17 @@ def print_progress(itn, losses, dev_scores, cpu_wps=0.0, gpu_wps=0.0): scores.update(dev_scores) scores['cpu_wps'] = cpu_wps scores['gpu_wps'] = gpu_wps or 0.0 - tpl = '\t'.join(( - '{:d}', - '{dep_loss:.3f}', - '{ner_loss:.3f}', - '{uas:.3f}', - '{ents_p:.3f}', - '{ents_r:.3f}', - '{ents_f:.3f}', - '{tags_acc:.3f}', - '{token_acc:.3f}', - '{cpu_wps:.1f}', + tpl = ''.join(( + '{:<6d}', + '{dep_loss:<10.3f}', + '{ner_loss:<10.3f}', + '{uas:<8.3f}', + '{ents_p:<8.3f}', + '{ents_r:<8.3f}', + '{ents_f:<8.3f}', + '{tags_acc:<8.3f}', + '{token_acc:<9.3f}', + '{cpu_wps:<9.1f}', '{gpu_wps:.1f}', )) print(tpl.format(itn, **scores)) diff --git a/website/usage/_linguistic-features/_rule-based-matching.jade b/website/usage/_linguistic-features/_rule-based-matching.jade index 094f15b90..e0080ca2d 100644 --- a/website/usage/_linguistic-features/_rule-based-matching.jade +++ b/website/usage/_linguistic-features/_rule-based-matching.jade @@ -184,7 +184,7 @@ p p | In versions before v2.1.0, the semantics of the #[code +] and #[code *] operators - | behave inconsistently. They were usually interpretted + | behave inconsistently. They were usually interpreted | "greedily", i.e. longer matches are returned where possible. However, if | you specify two #[code +] and #[code *] patterns in a row and their | matches overlap, the first operator will behave non-greedily. This quirk