From e188b6196024d0939ef27b41b31e2a4d4048d7f5 Mon Sep 17 00:00:00 2001 From: Isaac Sijaranamual Date: Sun, 10 Dec 2017 22:52:26 +0100 Subject: [PATCH 1/5] Make cli/train.py not eat exception --- spacy/cli/train.py | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/spacy/cli/train.py b/spacy/cli/train.py index 6697ed6c0..fff890ca1 100644 --- a/spacy/cli/train.py +++ b/spacy/cli/train.py @@ -165,12 +165,9 @@ def train(cmd, lang, output_dir, train_data, dev_data, n_iter=30, n_sents=0, gpu_wps=gpu_wps) finally: print("Saving model...") - try: - with (output_path / 'model-final.pickle').open('wb') as file_: - with nlp.use_params(optimizer.averages): - dill.dump(nlp, file_, -1) - except: - print("Error saving model") + with (output_path / 'model-final.pickle').open('wb') as file_: + with nlp.use_params(optimizer.averages): + dill.dump(nlp, file_, -1) def _render_parses(i, to_render): From 568130ce7cd071af634db5c3128d7b36f1b9db45 Mon Sep 17 00:00:00 2001 From: Isaac Sijaranamual Date: Sun, 10 Dec 2017 22:20:12 +0100 Subject: [PATCH 2/5] Adds regression test_issue1622 --- spacy/tests/regression/test_issue1622.py | 89 ++++++++++++++++++++++++ 1 file changed, 89 insertions(+) create mode 100644 spacy/tests/regression/test_issue1622.py diff --git a/spacy/tests/regression/test_issue1622.py b/spacy/tests/regression/test_issue1622.py new file mode 100644 index 000000000..e555242af --- /dev/null +++ b/spacy/tests/regression/test_issue1622.py @@ -0,0 +1,89 @@ +# coding: utf-8 +from __future__ import unicode_literals +import json +from tempfile import TemporaryDirectory, NamedTemporaryFile + +from ...cli.train import train + + +def test_cli_trained_model_can_be_saved(): + cmd = None + lang = 'nl' + with TemporaryDirectory() as output_dir: + train_file = NamedTemporaryFile('wb', dir=output_dir, delete=False) + train_corpus = [ + { + "id": "identifier_0", + "paragraphs": [ + { + "raw": "Jan houdt van Marie.\n", + "sentences": [ + { + "tokens": [ + { + "id": 0, + "dep": "nsubj", + "head": 1, + "tag": "NOUN", + "orth": "Jan", + "ner": "B-PER" + }, + { + "id": 1, + "dep": "ROOT", + "head": 0, + "tag": "VERB", + "orth": "houdt", + "ner": "O" + }, + { + "id": 2, + "dep": "case", + "head": 1, + "tag": "ADP", + "orth": "van", + "ner": "O" + }, + { + "id": 3, + "dep": "obj", + "head": -2, + "tag": "NOUN", + "orth": "Marie", + "ner": "B-PER" + }, + { + "id": 4, + "dep": "punct", + "head": -3, + "tag": "PUNCT", + "orth": ".", + "ner": "O" + }, + { + "id": 5, + "dep": "", + "head": -1, + "tag": "SPACE", + "orth": "\n", + "ner": "O" + } + ], + "brackets": [] + } + ] + } + ] + } + ] + + train_file.write(json.dumps(train_corpus).encode('utf-8')) + train_file.close() + train_data = train_file.name + dev_data = train_data + + # spacy train -n 1 -g -1 nl output_nl training_corpus.json training \ + # corpus.json + train(cmd, lang, output_dir, train_data, dev_data, n_iter=1) + + assert True From 20ae0c459ad3bbf4cc1df8f93954c64d954c102a Mon Sep 17 00:00:00 2001 From: Isaac Sijaranamual Date: Sun, 10 Dec 2017 21:29:50 +0100 Subject: [PATCH 3/5] Fixes "Error saving model" #1622 --- spacy/cli/train.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/spacy/cli/train.py b/spacy/cli/train.py index fff890ca1..2d71e94d4 100644 --- a/spacy/cli/train.py +++ b/spacy/cli/train.py @@ -3,7 +3,6 @@ from __future__ import unicode_literals, division, print_function import plac from pathlib import Path -import dill import tqdm from thinc.neural._classes.model import Model from timeit import default_timer as timer @@ -165,9 +164,9 @@ def train(cmd, lang, output_dir, train_data, dev_data, n_iter=30, n_sents=0, gpu_wps=gpu_wps) finally: print("Saving model...") - with (output_path / 'model-final.pickle').open('wb') as file_: - with nlp.use_params(optimizer.averages): - dill.dump(nlp, file_, -1) + with nlp.use_params(optimizer.averages): + final_model_path = output_path / 'model-final' + nlp.to_disk(final_model_path) def _render_parses(i, to_render): From f32c6630cb4e6480e20ec5bb3a9dfcc02d2003e6 Mon Sep 17 00:00:00 2001 From: Isaac Sijaranamual Date: Sun, 10 Dec 2017 23:15:06 +0100 Subject: [PATCH 4/5] Adds contributor agreement IsaacHaze --- .github/contributors/IsaacHaze.md | 106 ++++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/IsaacHaze.md diff --git a/.github/contributors/IsaacHaze.md b/.github/contributors/IsaacHaze.md new file mode 100644 index 000000000..6e1ebd97a --- /dev/null +++ b/.github/contributors/IsaacHaze.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 | Isaac Sijaranamual | +| Company name (if applicable) | - | +| Title or role (if applicable) | - | +| Date | 2017-12-10 | +| GitHub username | IsaacHaze | +| Website (optional) | - | From 38021fbb0063a5def3ba0d2de425cf8d2ee0cb08 Mon Sep 17 00:00:00 2001 From: Isaac Sijaranamual Date: Mon, 11 Dec 2017 00:16:04 +0100 Subject: [PATCH 5/5] Switch from python 3 only TemporaryDirectory to pytest's tmpdir --- spacy/tests/regression/test_issue1622.py | 154 +++++++++++------------ 1 file changed, 77 insertions(+), 77 deletions(-) diff --git a/spacy/tests/regression/test_issue1622.py b/spacy/tests/regression/test_issue1622.py index e555242af..3715c0dfe 100644 --- a/spacy/tests/regression/test_issue1622.py +++ b/spacy/tests/regression/test_issue1622.py @@ -1,89 +1,89 @@ # coding: utf-8 from __future__ import unicode_literals import json -from tempfile import TemporaryDirectory, NamedTemporaryFile +from tempfile import NamedTemporaryFile from ...cli.train import train -def test_cli_trained_model_can_be_saved(): +def test_cli_trained_model_can_be_saved(tmpdir): cmd = None lang = 'nl' - with TemporaryDirectory() as output_dir: - train_file = NamedTemporaryFile('wb', dir=output_dir, delete=False) - train_corpus = [ - { - "id": "identifier_0", - "paragraphs": [ - { - "raw": "Jan houdt van Marie.\n", - "sentences": [ - { - "tokens": [ - { - "id": 0, - "dep": "nsubj", - "head": 1, - "tag": "NOUN", - "orth": "Jan", - "ner": "B-PER" - }, - { - "id": 1, - "dep": "ROOT", - "head": 0, - "tag": "VERB", - "orth": "houdt", - "ner": "O" - }, - { - "id": 2, - "dep": "case", - "head": 1, - "tag": "ADP", - "orth": "van", - "ner": "O" - }, - { - "id": 3, - "dep": "obj", - "head": -2, - "tag": "NOUN", - "orth": "Marie", - "ner": "B-PER" - }, - { - "id": 4, - "dep": "punct", - "head": -3, - "tag": "PUNCT", - "orth": ".", - "ner": "O" - }, - { - "id": 5, - "dep": "", - "head": -1, - "tag": "SPACE", - "orth": "\n", - "ner": "O" - } - ], - "brackets": [] - } - ] - } - ] - } - ] + output_dir = str(tmpdir) + train_file = NamedTemporaryFile('wb', dir=output_dir, delete=False) + train_corpus = [ + { + "id": "identifier_0", + "paragraphs": [ + { + "raw": "Jan houdt van Marie.\n", + "sentences": [ + { + "tokens": [ + { + "id": 0, + "dep": "nsubj", + "head": 1, + "tag": "NOUN", + "orth": "Jan", + "ner": "B-PER" + }, + { + "id": 1, + "dep": "ROOT", + "head": 0, + "tag": "VERB", + "orth": "houdt", + "ner": "O" + }, + { + "id": 2, + "dep": "case", + "head": 1, + "tag": "ADP", + "orth": "van", + "ner": "O" + }, + { + "id": 3, + "dep": "obj", + "head": -2, + "tag": "NOUN", + "orth": "Marie", + "ner": "B-PER" + }, + { + "id": 4, + "dep": "punct", + "head": -3, + "tag": "PUNCT", + "orth": ".", + "ner": "O" + }, + { + "id": 5, + "dep": "", + "head": -1, + "tag": "SPACE", + "orth": "\n", + "ner": "O" + } + ], + "brackets": [] + } + ] + } + ] + } + ] - train_file.write(json.dumps(train_corpus).encode('utf-8')) - train_file.close() - train_data = train_file.name - dev_data = train_data + train_file.write(json.dumps(train_corpus).encode('utf-8')) + train_file.close() + train_data = train_file.name + dev_data = train_data - # spacy train -n 1 -g -1 nl output_nl training_corpus.json training \ - # corpus.json - train(cmd, lang, output_dir, train_data, dev_data, n_iter=1) + # spacy train -n 1 -g -1 nl output_nl training_corpus.json training \ + # corpus.json + train(cmd, lang, output_dir, train_data, dev_data, n_iter=1) - assert True + assert True