From d7ae54ff442e6a142ac23b15dd789db174313b9c Mon Sep 17 00:00:00 2001 From: Daniel Hershcovich Date: Wed, 8 Nov 2017 16:06:28 +0200 Subject: [PATCH 1/7] Fix typo in message --- spacy/tokenizer.pyx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spacy/tokenizer.pyx b/spacy/tokenizer.pyx index 3996819ff..67ff47743 100644 --- a/spacy/tokenizer.pyx +++ b/spacy/tokenizer.pyx @@ -63,7 +63,7 @@ cdef class Tokenizer: cpdef Doc tokens_from_list(self, list strings): util.deprecated( - "Tokenizer.from_from list is now deprecated. Create a new Doc " + "Tokenizer.from_list is now deprecated. Create a new Doc " "object instead and pass in the strings as the `words` keyword " "argument, for example:\nfrom spacy.tokens import Doc\n" "doc = Doc(nlp.vocab, words=[...])") From 6eb4a4131660f980343f54f2cb23ec749af6d48c Mon Sep 17 00:00:00 2001 From: Daniel Hershcovich Date: Wed, 8 Nov 2017 16:28:56 +0200 Subject: [PATCH 2/7] Signed contributor agreement --- .github/contributors/danielhers.md | 106 +++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/danielhers.md diff --git a/.github/contributors/danielhers.md b/.github/contributors/danielhers.md new file mode 100644 index 000000000..1a43dde47 --- /dev/null +++ b/.github/contributors/danielhers.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 | Daniel Hershcovich | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 8 November 2017 | +| GitHub username | danielhers | +| Website (optional) | www.cs.huji.ac.il/~danielh | From f0bdfb44714ef09c92fb837b9ad22e40996a2feb Mon Sep 17 00:00:00 2001 From: ines Date: Wed, 8 Nov 2017 16:24:27 +0100 Subject: [PATCH 3/7] Fix vector listing for core sm models in list overview (see #1513) --- website/models/_data.json | 1 + website/usage/_models/_available-models.jade | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/website/models/_data.json b/website/models/_data.json index a477747df..00c126fc6 100644 --- a/website/models/_data.json +++ b/website/models/_data.json @@ -52,6 +52,7 @@ "MODEL_META": { "core": "Vocabulary, syntax, entities, vectors", + "core_sm": "Vocabulary, syntax, entities", "dep": "Vocabulary, syntax", "ent": "Named entities", "vectors": "Word vectors", diff --git a/website/usage/_models/_available-models.jade b/website/usage/_models/_available-models.jade index 80cd9aedd..3a5e318d0 100644 --- a/website/usage/_models/_available-models.jade +++ b/website/usage/_models/_available-models.jade @@ -10,9 +10,10 @@ p for models, lang in MODELS for model, i in models - var comps = getModelComponents(model) + - var type = comps.size == "sm" && comps.type == "core" ? "core_sm" : comps.type +row +cell #[+a("/models/" + lang + "#" + model) #[code=model]] if i == 0 +icon("star", 16).o-icon--inline.u-color-theme +cell #{LANGUAGES[comps.lang]} - +cell #{MODEL_META[comps.type]} + +cell #{MODEL_META[type]} From 9b09b6b0cdf352df195a89c6051887d79a8c07cd Mon Sep 17 00:00:00 2001 From: ines Date: Wed, 8 Nov 2017 16:30:23 +0100 Subject: [PATCH 4/7] Fix formatting --- website/usage/_v2/_incompat.jade | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/website/usage/_v2/_incompat.jade b/website/usage/_v2/_incompat.jade index daaa6141b..8b3e257a2 100644 --- a/website/usage/_v2/_incompat.jade +++ b/website/usage/_v2/_incompat.jade @@ -10,10 +10,8 @@ p +cell #[+api("cli#download") #[code cli.download]] +row - +cell - | #[code spacy.en] etc. - +cell - | #[code spacy.lang.en] etc. + +cell #[code spacy.en] etc. + +cell #[code spacy.lang.en] etc. +row +cell #[code spacy.orth] From c0a7a32bf82104a8ae4faeab09e456b3d718067d Mon Sep 17 00:00:00 2001 From: ines Date: Wed, 8 Nov 2017 16:30:46 +0100 Subject: [PATCH 5/7] Add en.stop_words change to v2 docs (resolves #1512) --- website/usage/_v2/_incompat.jade | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/website/usage/_v2/_incompat.jade b/website/usage/_v2/_incompat.jade index 8b3e257a2..d2434c4fa 100644 --- a/website/usage/_v2/_incompat.jade +++ b/website/usage/_v2/_incompat.jade @@ -13,6 +13,10 @@ p +cell #[code spacy.en] etc. +cell #[code spacy.lang.en] etc. + +row + +cell #[code spacy.en.word_sets] + +cell #[code spacy.lang.en.stop_words] + +row +cell #[code spacy.orth] +cell #[code spacy.lang.xx.lex_attrs] From 97a5892347d26c7fd82906a6bd25915ce0036614 Mon Sep 17 00:00:00 2001 From: ines Date: Wed, 8 Nov 2017 17:11:11 +0100 Subject: [PATCH 6/7] Document Vectors.resize() and update v2 incompatibilities (resolves #1514) --- website/api/vectors.jade | 32 ++++++++++++++++++++++++++++++++ website/usage/_v2/_incompat.jade | 4 ++++ 2 files changed, 36 insertions(+) diff --git a/website/api/vectors.jade b/website/api/vectors.jade index 9685188c5..e1976713e 100644 --- a/website/api/vectors.jade +++ b/website/api/vectors.jade @@ -188,6 +188,38 @@ p +cell int +cell The row the vector was added to. ++h(2, "resize") Vectors.resize + +tag method + +p + | Resize the underlying vectors array. If #[code inplace=True], the memory + | is reallocated. This may cause other references to the data to become + | invalid, so only use #[code inplace=True] if you're sure that's what you + | want. If the number of vectors is reduced, keys mapped to rows that have + | been deleted are removed. These removed items are returned as a list of + | #[code (key, row)] tuples. + ++aside-code("Example"). + removed = nlp.vocab.vectors.resize((10000, 300)) + ++table(["Name", "Type", "Description"]) + +row + +cell #[code shape] + +cell tuple + +cell + | A #[code (rows, dims)] tuple describing the number of rows and + | dimensions. + + +row + +cell #[code inplace] + +cell bool + +cell Reallocate the memory. + + +row("foot") + +cell returns + +cell list + +cell The removed items as a list of #[code (key, row)] tuples. + +h(2, "keys") Vectors.keys +tag method diff --git a/website/usage/_v2/_incompat.jade b/website/usage/_v2/_incompat.jade index d2434c4fa..0a441583f 100644 --- a/website/usage/_v2/_incompat.jade +++ b/website/usage/_v2/_incompat.jade @@ -45,6 +45,10 @@ p +cell #[code Language.create_make_doc] +cell #[+api("language#attributes") #[code Language.tokenizer]] + +row + +cell #[code Vocab.resize_vectors] + +cell #[+api("vectors#resize") #[code Vectors.resize]] + +row +cell | #[code Vocab.load] From 89bd40b82114c1044695d2eede2c5ea2a3cef6b3 Mon Sep 17 00:00:00 2001 From: ines Date: Wed, 8 Nov 2017 17:17:40 +0100 Subject: [PATCH 7/7] Fix print statement in textcat training example (resolves #1515) --- examples/training/train_textcat.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/examples/training/train_textcat.py b/examples/training/train_textcat.py index 0a55ab202..71622dc3e 100644 --- a/examples/training/train_textcat.py +++ b/examples/training/train_textcat.py @@ -48,7 +48,8 @@ def main(model=None, output_dir=None, n_iter=20, n_texts=2000): # load the IMBD dataset print("Loading IMDB data...") (train_texts, train_cats), (dev_texts, dev_cats) = load_data(limit=n_texts) - print("Using %d training examples" % n_texts) + print("Using {} examples ({} training, {} evaluation)" + .format(n_texts, len(train_texts), len(dev_texts))) train_data = list(zip(train_texts, [{'cats': cats} for cats in train_cats]))