From e599ed9ef8c687c35f9a25f178f19b568e84413f Mon Sep 17 00:00:00 2001 From: Mark Neumann Date: Mon, 14 Jan 2019 14:48:30 -0800 Subject: [PATCH] Allow vectors to be optional in init-model, more robust string counting (#3155) * more robust init-model * key not word * add license agreement --- .github/contributors/DeNeutoy.md | 106 +++++++++++++++++++++++++++++++ spacy/cli/init_model.py | 25 +++++--- 2 files changed, 121 insertions(+), 10 deletions(-) create mode 100644 .github/contributors/DeNeutoy.md diff --git a/.github/contributors/DeNeutoy.md b/.github/contributors/DeNeutoy.md new file mode 100644 index 000000000..4cb3fbf16 --- /dev/null +++ b/.github/contributors/DeNeutoy.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 |Mark Neumann | +| Company name (if applicable) |Allen Institute for AI | +| Title or role (if applicable) |Research Engineer | +| Date | 13/01/2019 | +| GitHub username |@Deneutoy | +| Website (optional) |markneumann.xyz | diff --git a/spacy/cli/init_model.py b/spacy/cli/init_model.py index 87c3033ad..e945e0fbb 100644 --- a/spacy/cli/init_model.py +++ b/spacy/cli/init_model.py @@ -90,15 +90,16 @@ def create_model(lang, probs, oov_prob, clusters, vectors_data, vector_keys, pru lexeme.cluster = 0 lex_added += 1 nlp.vocab.cfg.update({'oov_prob': oov_prob}) - for word in vector_keys: - if word not in nlp.vocab: - lexeme = nlp.vocab[word] - lexeme.is_oov = False - lex_added += 1 - if len(vectors_data): - nlp.vocab.vectors = Vectors(data=vectors_data, keys=vector_keys) - if prune_vectors >= 1: - nlp.vocab.prune_vectors(prune_vectors) + if vector_keys is not None: + for word in vector_keys: + if word not in nlp.vocab: + lexeme = nlp.vocab[word] + lexeme.is_oov = False + lex_added += 1 + if len(vectors_data): + nlp.vocab.vectors = Vectors(data=vectors_data, keys=vector_keys) + if prune_vectors >= 1: + nlp.vocab.prune_vectors(prune_vectors) vec_added = len(nlp.vocab.vectors) prints(Messages.M039.format(entries=lex_added, vectors=vec_added), title=Messages.M038) @@ -141,7 +142,11 @@ def read_freqs(freqs_loc, max_length=100, min_doc_freq=5, min_freq=50): doc_freq = int(doc_freq) freq = int(freq) if doc_freq >= min_doc_freq and freq >= min_freq and len(key) < max_length: - word = literal_eval(key) + try: + word = literal_eval(key) + except SyntaxError: + # Take odd strings literally. + word = literal_eval("'%s'" % key) smooth_count = counts.smoother(int(freq)) probs[word] = math.log(smooth_count) - log_total oov_prob = math.log(counts.smoother(0)) - log_total