From 5f40229397f8ed283386f8422432dfdbecfcdc07 Mon Sep 17 00:00:00 2001 From: Daniel King <43149077+danielkingai2@users.noreply.github.com> Date: Wed, 6 Mar 2019 14:58:38 -0800 Subject: [PATCH] Don't use numpy directly for similarity (#3362) * Don't use numpy directly for similarity * Contributor agreement --- .github/contributors/danielkingai2.md | 106 ++++++++++++++++++++++++++ spacy/lexeme.pyx | 6 +- spacy/tokens/doc.pyx | 10 +-- spacy/tokens/span.pyx | 6 +- spacy/tokens/token.pyx | 6 +- 5 files changed, 126 insertions(+), 8 deletions(-) create mode 100644 .github/contributors/danielkingai2.md diff --git a/.github/contributors/danielkingai2.md b/.github/contributors/danielkingai2.md new file mode 100644 index 000000000..dd2f6006d --- /dev/null +++ b/.github/contributors/danielkingai2.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 | Daniel King | +| Company name (if applicable) | Allen Institute for Artificial Intelligence | +| Title or role (if applicable) | Predoctoral Young Investigator | +| Date | 03/06/2019 | +| GitHub username | danielkingai2 | +| Website (optional) | | \ No newline at end of file diff --git a/spacy/lexeme.pyx b/spacy/lexeme.pyx index ca93df9bd..0a9698682 100644 --- a/spacy/lexeme.pyx +++ b/spacy/lexeme.pyx @@ -8,6 +8,7 @@ cimport numpy as np np.import_array() from libc.string cimport memset import numpy +from thinc.neural.util import get_array_module from .typedefs cimport attr_t, flags_t from .attrs cimport IS_ALPHA, IS_ASCII, IS_DIGIT, IS_LOWER, IS_PUNCT, IS_SPACE @@ -123,7 +124,10 @@ cdef class Lexeme: return 1.0 if self.vector_norm == 0 or other.vector_norm == 0: return 0.0 - return (numpy.dot(self.vector, other.vector) / + + vector = self.vector + xp = get_array_module(vector) + return (xp.dot(self.vector, other.vector) / (self.vector_norm * other.vector_norm)) def to_bytes(self): diff --git a/spacy/tokens/doc.pyx b/spacy/tokens/doc.pyx index ba39ac304..f8320bb74 100644 --- a/spacy/tokens/doc.pyx +++ b/spacy/tokens/doc.pyx @@ -321,7 +321,10 @@ cdef class Doc: if self.vector_norm == 0 or other.vector_norm == 0: return 0.0 - return numpy.dot(self.vector, other.vector) / (self.vector_norm * other.vector_norm) + + vector = self.vector + xp = get_array_module(vector) + return xp.dot(self.vector, other.vector) / (self.vector_norm * other.vector_norm) property has_vector: """A boolean value indicating whether a word vector is associated with @@ -356,10 +359,7 @@ cdef class Doc: dtype='f') return self._vector elif self.vocab.vectors.data.size > 0: - vector = numpy.zeros((self.vocab.vectors_length,), dtype='f') - for token in self.c[:self.length]: - vector += self.vocab.get_vector(token.lex.orth) - self._vector = vector / len(self) + self._vector = sum(t.vector for t in self) / len(self) return self._vector elif self.tensor.size > 0: self._vector = self.tensor.mean(axis=0) diff --git a/spacy/tokens/span.pyx b/spacy/tokens/span.pyx index 0ddb509c2..639aac30e 100644 --- a/spacy/tokens/span.pyx +++ b/spacy/tokens/span.pyx @@ -6,6 +6,7 @@ cimport numpy as np import numpy import numpy.linalg from libc.math cimport sqrt +from thinc.neural.util import get_array_module from .doc cimport token_by_start, token_by_end, get_token_attr, _get_lca_matrix from .token cimport TokenC @@ -214,7 +215,10 @@ cdef class Span: return 1.0 if self.vector_norm == 0.0 or other.vector_norm == 0.0: return 0.0 - return numpy.dot(self.vector, other.vector) / (self.vector_norm * other.vector_norm) + + vector = self.vector + xp = get_array_module(vector) + return xp.dot(self.vector, other.vector) / (self.vector_norm * other.vector_norm) cpdef np.ndarray to_array(self, object py_attr_ids): """Given a list of M attribute IDs, export the tokens to a numpy diff --git a/spacy/tokens/token.pyx b/spacy/tokens/token.pyx index 38a34bbec..753a94b90 100644 --- a/spacy/tokens/token.pyx +++ b/spacy/tokens/token.pyx @@ -9,6 +9,7 @@ from cython.view cimport array as cvarray cimport numpy as np np.import_array() import numpy +from thinc.neural.util import get_array_module from ..typedefs cimport hash_t from ..lexeme cimport Lexeme @@ -165,7 +166,10 @@ cdef class Token: other_norm = other.vector_norm if self_norm == 0 or other_norm == 0: return 0.0 - return (numpy.dot(self.vector, other.vector) / + + vector = self.vector + xp = get_array_module(self.vector) + return (xp.dot(self.vector, other.vector) / (self_norm * other_norm)) property lex_id: