diff --git a/.github/contributors/emulbreh.md b/.github/contributors/emulbreh.md new file mode 100644 index 000000000..60388d22a --- /dev/null +++ b/.github/contributors/emulbreh.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 | Johannes Dollinger | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2018-02-13 | +| GitHub username | emulbreh | +| Website (optional) | | diff --git a/spacy/cli/evaluate.py b/spacy/cli/evaluate.py index 551689413..43edd858d 100644 --- a/spacy/cli/evaluate.py +++ b/spacy/cli/evaluate.py @@ -3,8 +3,6 @@ from __future__ import unicode_literals, division, print_function import plac from timeit import default_timer as timer -import random -import numpy.random from ..gold import GoldCorpus from ..util import prints @@ -12,10 +10,6 @@ from .. import util from .. import displacy -random.seed(0) -numpy.random.seed(0) - - @plac.annotations( model=("model name or path", "positional", None, str), data_path=("location of JSON-formatted evaluation data", "positional", @@ -31,6 +25,8 @@ def evaluate(model, data_path, gpu_id=-1, gold_preproc=False, displacy_path=None Evaluate a model. To render a sample of parses in a HTML file, set an output directory as the displacy_path argument. """ + + util.fix_random_seed() if gpu_id >= 0: util.use_gpu(gpu_id) util.set_env_log(False) diff --git a/spacy/cli/train.py b/spacy/cli/train.py index f8363bde1..6c7b95682 100644 --- a/spacy/cli/train.py +++ b/spacy/cli/train.py @@ -6,8 +6,6 @@ from pathlib import Path import tqdm from thinc.neural._classes.model import Model from timeit import default_timer as timer -import random -import numpy.random from ..gold import GoldCorpus, minibatch from ..util import prints @@ -16,9 +14,6 @@ from .. import about from .. import displacy from ..compat import json_dumps -random.seed(0) -numpy.random.seed(0) - @plac.annotations( lang=("model language", "positional", None, str), @@ -45,6 +40,7 @@ def train(lang, output_dir, train_data, dev_data, n_iter=30, n_sents=0, """ Train a model. Expects data in spaCy's JSON format. """ + util.fix_random_seed() util.set_env_log(True) n_sents = n_sents or None output_path = util.ensure_path(output_dir) diff --git a/spacy/util.py b/spacy/util.py index 7676b33b2..dc51e467d 100644 --- a/spacy/util.py +++ b/spacy/util.py @@ -17,6 +17,7 @@ from thinc.neural._classes.model import Model import functools import cytoolz import itertools +import numpy.random from .symbols import ORTH from .compat import cupy, CudaStream, path2str, basestring_, input_, unicode_ @@ -623,3 +624,8 @@ def use_gpu(gpu_id): Model.ops = CupyOps() Model.Ops = CupyOps return device + + +def fix_random_seed(seed=0): + random.seed(seed) + numpy.random.seed(seed)