diff --git a/spacy/language.py b/spacy/language.py index 881df7d1a..f32756a4d 100644 --- a/spacy/language.py +++ b/spacy/language.py @@ -1,4 +1,5 @@ from os import path +from warnings import warn try: import ujson as json @@ -184,7 +185,10 @@ class Language(object): return None def __init__(self, data_dir=None, vocab=None, tokenizer=None, tagger=None, - parser=None, entity=None, matcher=None, serializer=None): + parser=None, entity=None, matcher=None, serializer=None, + load_vectors=True): + if load_vectors is not True: + warn("load_vectors is deprecated", DeprecationWarning) if data_dir is None: data_dir = self.default_data_dir() if vocab is None: diff --git a/spacy/lexeme.pyx b/spacy/lexeme.pyx index 8ec238e32..e0fa854cb 100644 --- a/spacy/lexeme.pyx +++ b/spacy/lexeme.pyx @@ -60,19 +60,19 @@ cdef class Lexeme: def __set__(self, int x): self.c.suffix = x property cluster: - def __get__(self): return self.c.suffix - def __set__(self, int x): self.c.suffix = x + def __get__(self): return self.c.cluster + def __set__(self, int x): self.c.cluster = x property prob: - def __get__(self): return self.c.suffix - def __set__(self, int x): self.c.suffix = x + def __get__(self): return self.c.prob + def __set__(self, float x): self.c.prob = x property lower_: def __get__(self): return self.vocab.strings[self.c.lower] def __set__(self, unicode x): self.c.lower = self.vocab.strings[x] property norm_: - def __get__(self): return self.c.norm + def __get__(self): return self.vocab.strings[self.c.norm] def __set__(self, unicode x): self.c.norm = self.vocab.strings[x] property shape_: @@ -80,11 +80,11 @@ cdef class Lexeme: def __set__(self, unicode x): self.c.shape = self.vocab.strings[x] property prefix_: - def __get__(self): return self.c.prefix + def __get__(self): return self.vocab.strings[self.c.prefix] def __set__(self, unicode x): self.c.prefix = self.vocab.strings[x] property suffix_: - def __get__(self): return self.c.suffix + def __get__(self): return self.vocab.strings[self.c.suffix] def __set__(self, unicode x): self.c.suffix = self.vocab.strings[x] property flags: diff --git a/spacy/morphology.pyx b/spacy/morphology.pyx index 77d7bd2df..2cc5552f9 100644 --- a/spacy/morphology.pyx +++ b/spacy/morphology.pyx @@ -24,6 +24,7 @@ cdef class Morphology: self.rich_tags[i].id = i self.rich_tags[i].name = self.strings[tag_str] self.rich_tags[i].morph = 0 + self.rich_tags[i].pos = UNIV_POS_NAMES[props['pos'].upper()] self.reverse_index[self.rich_tags[i].name] = i self._cache = PreshMapArray(self.n_tags) diff --git a/spacy/tokens/doc.pyx b/spacy/tokens/doc.pyx index ccde5d599..d878f97eb 100644 --- a/spacy/tokens/doc.pyx +++ b/spacy/tokens/doc.pyx @@ -188,7 +188,7 @@ cdef class Doc: def noun_chunks(self): """Yield spans for base noun phrases.""" cdef const TokenC* word - labels = ['nsubj', 'dobj', 'nsubjpass', 'pcomp', 'pobj', 'attr'] + labels = ['nsubj', 'dobj', 'nsubjpass', 'pcomp', 'pobj', 'attr', 'conj'] np_deps = [self.vocab.strings[label] for label in labels] np_label = self.vocab.strings['NP'] for i in range(self.length):