From ed7d268e9391e7257fcc197a71a809b13471afaa Mon Sep 17 00:00:00 2001 From: Pradeep Kumar Tippa Date: Wed, 7 Feb 2018 14:55:12 +0530 Subject: [PATCH 1/6] Fixing vocab doc Replacing "like" with "love", coffee suffix should be "fee" but not "ffe" --- website/usage/_spacy-101/_vocab.jade | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/website/usage/_spacy-101/_vocab.jade b/website/usage/_spacy-101/_vocab.jade index 185e634fe..b81e0f33c 100644 --- a/website/usage/_spacy-101/_vocab.jade +++ b/website/usage/_spacy-101/_vocab.jade @@ -32,7 +32,7 @@ p | string to get its hash, or a hash to get its string: +code. - doc = nlp(u'I like coffee') + doc = nlp(u'I love coffee') assert doc.vocab.strings[u'coffee'] == 3197928453018144401 assert doc.vocab.strings[3197928453018144401] == u'coffee' @@ -70,7 +70,7 @@ p - var style = [0, 1, 1, 0, 0, 1, 1] +annotation-row(["I", "4690420944186131903", "X", "I", "I", true, false], style) +annotation-row(["love", "3702023516439754181", "xxxx", "l", "ove", true, false], style) - +annotation-row(["coffee", "3197928453018144401", "xxxx", "c", "ffe", true, false], style) + +annotation-row(["coffee", "3197928453018144401", "xxxx", "c", "fee", true, false], style) p | The mapping of words to hashes doesn't depend on any state. To make sure From f1911ef73a627900638793eced4d210ff0d592f1 Mon Sep 17 00:00:00 2001 From: Pradeep Kumar Tippa Date: Wed, 7 Feb 2018 15:37:28 +0530 Subject: [PATCH 2/6] Added pktippa contributor agreement --- .github/contributors/pktippa.md | 106 ++++++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/pktippa.md diff --git a/.github/contributors/pktippa.md b/.github/contributors/pktippa.md new file mode 100644 index 000000000..740944a72 --- /dev/null +++ b/.github/contributors/pktippa.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. + + * [x] 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 | Pradeep Kumar Tippa | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 07-02-2018 | +| GitHub username | pktippa | +| Website (optional) | | From da9d687e75e9fbf7e5779634151491b660559ac6 Mon Sep 17 00:00:00 2001 From: Pradeep Kumar Tippa Date: Wed, 7 Feb 2018 16:49:25 +0530 Subject: [PATCH 3/6] Fixing typo from taining to training --- website/usage/_v2/_migrating.jade | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/usage/_v2/_migrating.jade b/website/usage/_v2/_migrating.jade index 5ed0fb13e..f313d1ce3 100644 --- a/website/usage/_v2/_migrating.jade +++ b/website/usage/_v2/_migrating.jade @@ -127,7 +127,7 @@ p | #[+api("pipe") #[code Pipe]], fully trainable and serializable, | and follow the same API. Instead of updating the model and telling | spaCy when to #[em stop], you can now explicitly call - | #[+api("language#begin_training") #[code begin_taining]], which + | #[+api("language#begin_training") #[code begin_training]], which | returns an optimizer you can pass into the | #[+api("language#update") #[code update]] function. While #[code update] | still accepts sequences of #[code Doc] and #[code GoldParse] objects, From 26bc75134db09b87dbc77a0afd40506b0b2b6059 Mon Sep 17 00:00:00 2001 From: ines Date: Thu, 8 Feb 2018 11:28:44 +0100 Subject: [PATCH 4/6] Fix typo --- website/api/matcher.jade | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/api/matcher.jade b/website/api/matcher.jade index 95a51a1d6..2418dd2fa 100644 --- a/website/api/matcher.jade +++ b/website/api/matcher.jade @@ -89,7 +89,7 @@ p Match a stream of documents, yielding them in turn. +aside-code("Example"). from spacy.matcher import Matcher matcher = Matcher(nlp.vocab) - for doc in matcher.pipe(texts, batch_size=50, n_threads=4): + for doc in matcher.pipe(docs, batch_size=50, n_threads=4): pass +table(["Name", "Type", "Description"]) From 696ae87b477c6f7424c432947ec83ba1f14ce8fe Mon Sep 17 00:00:00 2001 From: ines Date: Thu, 8 Feb 2018 11:28:54 +0100 Subject: [PATCH 5/6] Fix whitespace --- website/usage/_linguistic-features/_rule-based-matching.jade | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/usage/_linguistic-features/_rule-based-matching.jade b/website/usage/_linguistic-features/_rule-based-matching.jade index 794b6595c..ea50ec7b3 100644 --- a/website/usage/_linguistic-features/_rule-based-matching.jade +++ b/website/usage/_linguistic-features/_rule-based-matching.jade @@ -161,7 +161,7 @@ p p | The #[code +] and #[code *] operators are usually interpretted - | "greedily", i.e. longer matches are returned where possible. + | "greedily", i.e. longer matches are returned where possible. +h(3, "adding-phrase-patterns") Adding phrase patterns From a3b965b29d56fe9b2cd64d11f65db93ab7b2f988 Mon Sep 17 00:00:00 2001 From: ines Date: Thu, 8 Feb 2018 11:29:27 +0100 Subject: [PATCH 6/6] Remove UPPER from Matcher attributes docs (resolves #1949) --- .../usage/_linguistic-features/_rule-based-matching.jade | 8 ++++---- website/usage/_spacy-101/_lightning-tour.jade | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/website/usage/_linguistic-features/_rule-based-matching.jade b/website/usage/_linguistic-features/_rule-based-matching.jade index ea50ec7b3..7872b668f 100644 --- a/website/usage/_linguistic-features/_rule-based-matching.jade +++ b/website/usage/_linguistic-features/_rule-based-matching.jade @@ -88,8 +88,8 @@ p +cell The exact verbatim text of a token. +row - +cell.u-nowrap #[code LOWER], #[code UPPER] - +cell The lowercase, uppercase form of the token text. + +cell.u-nowrap #[code LOWER] + +cell The lowercase form of the token text. +row +cell.u-nowrap #[code IS_ALPHA], #[code IS_ASCII], #[code IS_DIGIT] @@ -222,8 +222,8 @@ p doc.ents += ((EVENT, start, end),) matcher.add('GoogleIO', add_event_ent, - [{'ORTH': 'Google'}, {'UPPER': 'I'}, {'ORTH': '/'}, {'UPPER': 'O'}], - [{'ORTH': 'Google'}, {'UPPER': 'I'}, {'ORTH': '/'}, {'UPPER': 'O'}, {'IS_DIGIT': True}]) + [{'ORTH': 'Google'}, {'ORTH': 'I'}, {'ORTH': '/'}, {'ORTH': 'O'}], + [{'ORTH': 'Google'}, {'ORTH': 'I'}, {'ORTH': '/'}, {'ORTH': 'O'}, {'IS_DIGIT': True}]) p | In addition to mentions of "Google I/O", your data also contains some diff --git a/website/usage/_spacy-101/_lightning-tour.jade b/website/usage/_spacy-101/_lightning-tour.jade index 96f274002..dc0808eea 100644 --- a/website/usage/_spacy-101/_lightning-tour.jade +++ b/website/usage/_spacy-101/_lightning-tour.jade @@ -231,7 +231,7 @@ p def set_sentiment(matcher, doc, i, matches): doc.sentiment += 0.1 - pattern1 = [{'ORTH': 'Google'}, {'UPPER': 'I'}, {'ORTH': '/'}, {'UPPER': 'O'}] + pattern1 = [{'ORTH': 'Google'}, {'ORTH': 'I'}, {'ORTH': '/'}, {'ORTH': 'O'}] pattern2 = [[{'ORTH': emoji, 'OP': '+'}] for emoji in ['😀', '😂', '🤣', '😍']] matcher.add('GoogleIO', None, pattern1) # match "Google I/O" or "Google i/o" matcher.add('HAPPY', set_sentiment, *pattern2) # match one or more happy emoji