diff --git a/.github/contributors/free-variation.md b/.github/contributors/free-variation.md new file mode 100644 index 000000000..81dc455cc --- /dev/null +++ b/.github/contributors/free-variation.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: + + * [ ] 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 | John Stewart | +| Company name (if applicable) | Amplify | +| Title or role (if applicable) | SVP Research | +| Date | 14/09/2018 | +| GitHub username | free-variation | +| Website (optional) | | diff --git a/examples/deep_learning_keras.py b/examples/deep_learning_keras.py index 45faf0d98..4d328f96d 100644 --- a/examples/deep_learning_keras.py +++ b/examples/deep_learning_keras.py @@ -92,11 +92,13 @@ def get_features(docs, max_length): def train(train_texts, train_labels, dev_texts, dev_labels, lstm_shape, lstm_settings, lstm_optimizer, batch_size=100, nb_epoch=5, by_sentence=True): + print("Loading spaCy") nlp = spacy.load('en_vectors_web_lg') nlp.add_pipe(nlp.create_pipe('sentencizer')) embeddings = get_embeddings(nlp.vocab) model = compile_lstm(embeddings, lstm_shape, lstm_settings) + print("Parsing texts...") train_docs = list(nlp.pipe(train_texts)) dev_docs = list(nlp.pipe(dev_texts)) @@ -107,7 +109,7 @@ def train(train_texts, train_labels, dev_texts, dev_labels, train_X = get_features(train_docs, lstm_shape['max_length']) dev_X = get_features(dev_docs, lstm_shape['max_length']) model.fit(train_X, train_labels, validation_data=(dev_X, dev_labels), - nb_epoch=nb_epoch, batch_size=batch_size) + epochs=nb_epoch, batch_size=batch_size) return model @@ -138,15 +140,9 @@ def get_embeddings(vocab): def evaluate(model_dir, texts, labels, max_length=100): - def create_pipeline(nlp): - ''' - This could be a lambda, but named functions are easier to read in Python. - ''' - return [nlp.tagger, nlp.parser, SentimentAnalyser.load(model_dir, nlp, - max_length=max_length)] - - nlp = spacy.load('en') - nlp.pipeline = create_pipeline(nlp) + nlp = spacy.load('en_vectors_web_lg') + nlp.add_pipe(nlp.create_pipe('sentencizer')) + nlp.add_pipe(SentimentAnalyser.load(model_dir, nlp, max_length=max_length)) correct = 0 i = 0 @@ -186,7 +182,7 @@ def main(model_dir=None, train_dir=None, dev_dir=None, is_runtime=False, nr_hidden=64, max_length=100, # Shape dropout=0.5, learn_rate=0.001, # General NN config - nb_epoch=5, batch_size=100, nr_examples=-1): # Training params + nb_epoch=5, batch_size=256, nr_examples=-1): # Training params if model_dir is not None: model_dir = pathlib.Path(model_dir) if train_dir is None or dev_dir is None: @@ -219,7 +215,7 @@ def main(model_dir=None, train_dir=None, dev_dir=None, if model_dir is not None: with (model_dir / 'model').open('wb') as file_: pickle.dump(weights[1:], file_) - with (model_dir / 'config.json').open('wb') as file_: + with (model_dir / 'config.json').open('w') as file_: file_.write(lstm.to_json())