Merge branch 'master' into fix-entity-recognizer-docs

.github/contributors/nikhilsaldanha.md

@@ -98,9 +98,9 @@ mark both statements:
 
 | Field                          | Entry                |
 |------------------------------- | -------------------- |
-| Name                           |   Nikhil Saldanha    |
+| Name                           | Nikhil Saldanha      |
 | Company name (if applicable)   |                      |
 | Title or role (if applicable)  |                      |
-| Date                           |     2020/03/28       |
-| GitHub username                |    nikhilsaldanha    |
+| Date                           | 2020-03-17           |
+| GitHub username                | nikhilsaldanha       |
 | Website (optional)             |                      |

.github/contributors/tommilligan.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 GmbH](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                          | Tom Milligan |
+| Company name (if applicable)  |              |
+| Title or role (if applicable) |              |
+| Date                          | 2020-03-24   |
+| GitHub username               | tommilligan  |
+| Website (optional)            |              |

setup.cfg

@@ -61,17 +61,17 @@ install_requires =
 lookups =
     spacy_lookups_data>=0.0.5,<0.2.0
 cuda =
-    cupy>=5.0.0b4
+    cupy>=5.0.0b4,<9.0.0
 cuda80 =
-    cupy-cuda80>=5.0.0b4
+    cupy-cuda80>=5.0.0b4,<9.0.0
 cuda90 =
-    cupy-cuda90>=5.0.0b4
+    cupy-cuda90>=5.0.0b4,<9.0.0
 cuda91 =
-    cupy-cuda91>=5.0.0b4
+    cupy-cuda91>=5.0.0b4,<9.0.0
 cuda92 =
-    cupy-cuda92>=5.0.0b4
+    cupy-cuda92>=5.0.0b4,<9.0.0
 cuda100 =
-    cupy-cuda100>=5.0.0b4
+    cupy-cuda100>=5.0.0b4,<9.0.0
 # Language tokenizers with external dependencies
 ja =
     fugashi>=0.1.3

spacy/_ml.py

@@ -693,9 +693,11 @@ def build_text_classifier(nr_class, width=64, **cfg):
         )
 
         linear_model = build_bow_text_classifier(
-            nr_class, ngram_size=cfg.get("ngram_size", 1), exclusive_classes=False
+            nr_class,
+            ngram_size=cfg.get("ngram_size", 1),
+            exclusive_classes=cfg.get("exclusive_classes", False),
         )
-        if cfg.get("exclusive_classes"):
+        if cfg.get("exclusive_classes", False):
             output_layer = Softmax(nr_class, nr_class * 2)
         else:
             output_layer = (

spacy/errors.py

@@ -551,6 +551,7 @@ class Errors(object):
             "array.")
     E191 = ("Invalid head: the head token must be from the same doc as the "
             "token itself.")
+    E192 = ("Unable to resize vectors in place with cupy.")
 
 
 @add_codes

spacy/lang/kn/examples.py

@@ -0,0 +1,22 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+
+"""
+Example sentences to test spaCy and its language models.
+
+>>> from spacy.lang.en.examples import sentences
+>>> docs = nlp.pipe(sentences)
+"""
+
+
+sentences = [
+    "ಆಪಲ್ ಒಂದು ಯು.ಕೆ. ಸ್ಟಾರ್ಟ್ಅಪ್ ಅನ್ನು ೧ ಶತಕೋಟಿ ಡಾಲರ್ಗಳಿಗೆ ಖರೀದಿಸಲು ನೋಡುತ್ತಿದೆ.",
+    "ಸ್ವಾಯತ್ತ ಕಾರುಗಳು ವಿಮಾ ಹೊಣೆಗಾರಿಕೆಯನ್ನು ತಯಾರಕರ ಕಡೆಗೆ ಬದಲಾಯಿಸುತ್ತವೆ.",
+    "ಕಾಲುದಾರಿ ವಿತರಣಾ ರೋಬೋಟ್‌ಗಳನ್ನು ನಿಷೇಧಿಸುವುದನ್ನು ಸ್ಯಾನ್ ಫ್ರಾನ್ಸಿಸ್ಕೊ ​​ಪರಿಗಣಿಸುತ್ತದೆ.",
+    "ಲಂಡನ್ ಯುನೈಟೆಡ್ ಕಿಂಗ್‌ಡಂನ ದೊಡ್ಡ ನಗರ.",
+    "ನೀನು ಎಲ್ಲಿದಿಯಾ?",
+    "ಫ್ರಾನ್ಸಾದ ಅಧ್ಯಕ್ಷರು ಯಾರು?",
+    "ಯುನೈಟೆಡ್ ಸ್ಟೇಟ್ಸ್ನ ರಾಜಧಾನಿ ಯಾವುದು?",
+    "ಬರಾಕ್ ಒಬಾಮ ಯಾವಾಗ ಜನಿಸಿದರು?",
+]

spacy/tests/vocab_vectors/test_vectors.py

@@ -89,17 +89,28 @@ def test_init_vectors_with_resize_data(data, resize_data):
     assert v.shape != data.shape
 
 
-def test_get_vector_resize(strings, data, resize_data):
-    v = Vectors(data=data)
-    v.resize(shape=resize_data.shape)
+def test_get_vector_resize(strings, data):
     strings = [hash_string(s) for s in strings]
+
+    # decrease vector dimension (truncate)
+    v = Vectors(data=data)
+    resized_dim = v.shape[1] - 1
+    v.resize(shape=(v.shape[0], resized_dim))
     for i, string in enumerate(strings):
         v.add(string, row=i)
 
-    assert list(v[strings[0]]) == list(resize_data[0])
-    assert list(v[strings[0]]) != list(resize_data[1])
-    assert list(v[strings[1]]) != list(resize_data[0])
-    assert list(v[strings[1]]) == list(resize_data[1])
+    assert list(v[strings[0]]) == list(data[0, :resized_dim])
+    assert list(v[strings[1]]) == list(data[1, :resized_dim])
+
+    # increase vector dimension (pad with zeros)
+    v = Vectors(data=data)
+    resized_dim = v.shape[1] + 1
+    v.resize(shape=(v.shape[0], resized_dim))
+    for i, string in enumerate(strings):
+        v.add(string, row=i)
+
+    assert list(v[strings[0]]) == list(data[0]) + [0]
+    assert list(v[strings[1]]) == list(data[1]) + [0]
 
 
 def test_init_vectors_with_data(strings, data):

spacy/vectors.pyx

@@ -198,11 +198,17 @@ cdef class Vectors:
 
         DOCS: https://spacy.io/api/vectors#resize
         """
+        xp = get_array_module(self.data)
         if inplace:
-            self.data.resize(shape, refcheck=False)
+            if xp == numpy:
+                self.data.resize(shape, refcheck=False)
+            else:
+                raise ValueError(Errors.E192)
         else:
-            xp = get_array_module(self.data)
-            self.data = xp.resize(self.data, shape)
+            resized_array = xp.zeros(shape, dtype=self.data.dtype)
+            copy_shape = (min(shape[0], self.data.shape[0]), min(shape[1], self.data.shape[1]))
+            resized_array[:copy_shape[0], :copy_shape[1]] = self.data[:copy_shape[0], :copy_shape[1]]
+            self.data = resized_array
         filled = {row for row in self.key2row.values()}
         self._unset = cppset[int]({row for row in range(shape[0]) if row not in filled})
         removed_items = []