Merge branch 'master' of https://github.com/honnibal/spaCy into attrs

setup.py

@@ -92,6 +92,7 @@ def cython_setup(mod_names, language, includes, compile_args, link_args):
         package_data={"spacy": ["*.pxd"],
                       "spacy.en": ["*.pxd", "data/pos/*",
                                    "data/wordnet/*", "data/tokenizer/*",
+                                   "data/vocab/tag_map.json",
                                    "data/vocab/lexemes.bin",
                                    "data/vocab/strings.txt"],
                       "spacy.syntax": ["*.pxd"]},
@@ -134,7 +135,7 @@ def run_setup(exts):
     headers_workaround.install_headers('numpy')
 
 
-VERSION = '0.94'
+VERSION = '0.95'
 def main(modules, is_pypy):
     language = "cpp"
     includes = ['.', path.join(sys.prefix, 'include')]

spacy/en/download.py

@@ -7,7 +7,7 @@ import wget
 import plac
 
 # TODO: Read this from the same source as the setup
-VERSION = '0.9.1'
+VERSION = '0.9.5'
 
 AWS_STORE = 'https://s3-us-west-1.amazonaws.com/media.spacynlp.com'
 

tests/test_basic_create.py

@@ -0,0 +1,89 @@
+"""Some quick tests that don't depend on data files or on pytest, for debugging the
+MS windows build issues."""
+from __future__ import print_function, unicode_literals
+
+import unittest
+import re
+
+from spacy.lemmatizer import Lemmatizer
+from spacy.morphology import Morphology
+from spacy.strings import StringStore
+from spacy.vocab import Vocab
+from spacy.tokenizer import Tokenizer
+from spacy.syntax.arc_eager import ArcEager
+from spacy._ml import Model
+from spacy.tagger import Tagger
+from spacy.syntax.parser import Parser
+from spacy.matcher import Matcher
+
+
+class TestStringStore(unittest.TestCase):
+    def test_encode_decode(self):
+        strings = StringStore()
+        hello_id = strings[u'Hello']
+        world_id = strings[u'World']
+
+        self.assertNotEqual(hello_id, world_id)
+        
+        self.assertEqual(strings[hello_id], u'Hello')
+        self.assertEqual(strings[world_id], u'World')
+
+        self.assertEqual(strings[u'Hello'], hello_id)
+        self.assertEqual(strings[u'World'], world_id)
+
+
+class TestMorphology(unittest.TestCase):
+    def test_create(self):
+        lemmatizer = Lemmatizer({}, {}, {})
+        strings = StringStore()
+        lemmatizer = Lemmatizer({}, {}, {})
+        morphology = Morphology(strings, {}, lemmatizer)
+
+
+class TestVocab(unittest.TestCase):
+    def test_create(self):
+        vocab = Vocab()
+
+    def test_get_lexeme(self):
+        vocab = Vocab()
+        lexeme = vocab[u'Hello']
+        self.assertEqual(lexeme.orth_, u'Hello')
+
+
+class TestTokenizer(unittest.TestCase):
+    def test_create(self):
+        vocab = Vocab()
+        dummy_re = re.compile(r'sklfb;s')
+        tokenizer = Tokenizer(vocab, {}, dummy_re, dummy_re, dummy_re)
+        doc = tokenizer(u'I am a document.')
+        
+        self.assertEqual(len(doc), 4)
+
+
+class TestTagger(unittest.TestCase):
+    def test_create(self):
+        vocab = Vocab()
+        templates = ((1,),)
+        model = Model(vocab.morphology.n_tags, templates, model_loc=None)
+        tagger = Tagger(vocab, model)
+
+
+class TestParser(unittest.TestCase):
+    def test_create(self):
+        vocab = Vocab()
+        templates = ((1,),)
+        labels_by_action = {0: ['One', 'Two'], 1: ['Two', 'Three']}
+        transition_system = ArcEager(vocab.strings, labels_by_action)
+        model = Model(vocab.morphology.n_tags, templates, model_loc=None)
+        
+        parser = Parser(vocab.strings, transition_system, model)
+
+
+class TestMatcher(unittest.TestCase):
+    def test_create(self):
+        vocab = Vocab()
+        matcher = Matcher(vocab, {})
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/test_basic_load.py

@@ -0,0 +1,75 @@
+"""Some quick tests that don't depend on data files or on pytest, for debugging the
+MS windows build issues."""
+from __future__ import print_function, unicode_literals
+
+import unittest
+import re
+from os import path
+
+from spacy.lemmatizer import Lemmatizer
+from spacy.morphology import Morphology
+from spacy.strings import StringStore
+from spacy.vocab import Vocab
+from spacy.tokenizer import Tokenizer
+from spacy.syntax.arc_eager import ArcEager
+from spacy._ml import Model
+from spacy.tagger import Tagger
+from spacy.syntax.parser import Parser
+from spacy.matcher import Matcher
+from spacy.syntax.parser import get_templates
+
+from spacy.en import English
+
+from thinc.learner import LinearModel
+
+
+class TestLoadVocab(unittest.TestCase):
+    def test_load(self):
+        vocab = Vocab.from_dir(path.join(English.default_data_dir(), 'vocab'))
+
+
+class TestLoadTokenizer(unittest.TestCase):
+    def test_load(self):
+        data_dir = English.default_data_dir()
+        vocab = Vocab.from_dir(path.join(data_dir, 'vocab'))
+        tokenizer = Tokenizer.from_dir(vocab, path.join(data_dir, 'tokenizer'))
+
+
+class TestLoadTagger(unittest.TestCase):
+    def test_load(self):
+        data_dir = English.default_data_dir()
+        vocab = Vocab.from_dir(path.join(data_dir, 'vocab'))
+        tagger = Tagger.from_dir(path.join(data_dir, 'tagger'), vocab)
+
+
+class TestLoadParser(unittest.TestCase):
+    def test_load(self):
+        data_dir = English.default_data_dir()
+        vocab = Vocab.from_dir(path.join(data_dir, 'vocab'))
+        parser = Parser.from_dir(path.join(data_dir, 'deps'), vocab.strings, ArcEager)
+
+    def test_load_careful(self):
+        config_data = {"labels": {"0": {"": True}, "1": {"": True}, "2": {"cc": True, "agent": True, "ccomp": True, "prt": True, "meta": True, "nsubjpass": True, "csubj": True, "conj": True, "dobj": True, "neg": True, "csubjpass": True, "mark": True, "auxpass": True, "advcl": True, "aux": True, "ROOT": True, "prep": True, "parataxis": True, "xcomp": True, "nsubj": True, "nummod": True, "advmod": True, "punct": True, "relcl": True, "quantmod": True, "acomp": True, "compound": True, "pcomp": True, "intj": True, "poss": True, "npadvmod": True, "case": True, "attr": True, "dep": True, "appos": True, "det": True, "nmod": True, "amod": True, "dative": True, "pobj": True, "expl": True, "predet": True, "preconj": True, "oprd": True, "acl": True}, "3": {"cc": True, "agent": True, "ccomp": True, "prt": True, "meta": True, "nsubjpass": True, "csubj": True, "conj": True, "acl": True, "poss": True, "neg": True, "mark": True, "auxpass": True, "advcl": True, "aux": True, "amod": True, "ROOT": True, "prep": True, "parataxis": True, "xcomp": True, "nsubj": True, "nummod": True, "advmod": True, "punct": True, "quantmod": True, "acomp": True, "pcomp": True, "intj": True, "relcl": True, "npadvmod": True, "case": True, "attr": True, "dep": True, "appos": True, "det": True, "nmod": True, "dobj": True, "dative": True, "pobj": True, "iobj": True, "expl": True, "predet": True, "preconj": True, "oprd": True}, "4": {"ROOT": True}}, "seed": 0, "features": "basic", "beam_width": 1}
+
+        data_dir = English.default_data_dir()
+        vocab = Vocab.from_dir(path.join(data_dir, 'vocab'))
+
+        moves = ArcEager(vocab.strings, config_data['labels'])
+        templates = get_templates(config_data['features'])
+
+        model = Model(moves.n_moves, templates, path.join(data_dir, 'deps'))
+
+        parser = Parser(vocab.strings, moves, model)
+
+    def test_thinc_load(self):
+        data_dir = English.default_data_dir()
+        model_loc = path.join(data_dir, 'deps', 'model')
+
+        # n classes. moves.n_moves above
+        # n features. len(templates) + 1 above
+        model = LinearModel(92, 116)
+        model.load(model_loc)
+
+
+if __name__ == '__main__':
+    unittest.main()