explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 02:06:31 +03:00
Code Issues Packages Projects Releases Wiki Activity

Defer some attributes to Doc via getters_for_spans

Browse Source
This commit is contained in:
Matthew Honnibal 2016-10-17 02:43:35 +02:00
parent 62230dd13a
commit d15a88c66a
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/tokens/span.pyx
View File

@ -81,6 +81,8 @@ cdef class Span:
self.doc.merge(self.start_char, self.end_char, tag, lemma, ent_type) self.doc.merge(self.start_char, self.end_char, tag, lemma, ent_type)
def similarity(self, other): def similarity(self, other):
if 'similarity' in self.doc.getters_for_spans:
self.doc.getters_for_spans['similarity'](self, other)
if self.vector_norm == 0.0 or other.vector_norm == 0.0: if self.vector_norm == 0.0 or other.vector_norm == 0.0:
return 0.0 return 0.0
return numpy.dot(self.vector, other.vector) / (self.vector_norm * other.vector_norm) return numpy.dot(self.vector, other.vector) / (self.vector_norm * other.vector_norm)
@ -102,6 +104,8 @@ cdef class Span:
property sent: property sent:
'''Get the sentence span that this span is a part of.''' '''Get the sentence span that this span is a part of.'''
def __get__(self): def __get__(self):
if 'sent' in self.doc.getters_for_spans:
return self.doc.getters_for_spans['sent'](self)
# This should raise if we're not parsed. # This should raise if we're not parsed.
self.doc.sents self.doc.sents
cdef int n = 0 cdef int n = 0
@ -115,16 +119,22 @@ cdef class Span:
property has_vector: property has_vector:
def __get__(self): def __get__(self):
if 'has_vector' in self.doc.getters_for_spans:
return self.doc.getters_for_spans['has_vector'](self)
return any(token.has_vector for token in self) return any(token.has_vector for token in self)
property vector: property vector:
def __get__(self): def __get__(self):
if 'vector' in self.doc.getters_for_spans:
return self.doc.getters_for_spans['vector'](self)
if self._vector is None: if self._vector is None:
self._vector = sum(t.vector for t in self) / len(self) self._vector = sum(t.vector for t in self) / len(self)
return self._vector return self._vector
property vector_norm: property vector_norm:
def __get__(self): def __get__(self):
if 'vector_norm' in self.doc.getters_for_spans:
return self.doc.getters_for_spans['vector'](self)
cdef float value cdef float value
if self._vector_norm is None: if self._vector_norm is None:
self._vector_norm = 1e-20 self._vector_norm = 1e-20
@ -187,6 +197,8 @@ cdef class Span:
""" """
def __get__(self): def __get__(self):
self._recalculate_indices() self._recalculate_indices()
if 'root' in self.doc.getters_for_spans:
return self.doc.getters_for_spans['root'](self)
# This should probably be called 'head', and the other one called # This should probably be called 'head', and the other one called
# 'gov'. But we went with 'head' elsehwhere, and now we're stuck =/ # 'gov'. But we went with 'head' elsehwhere, and now we're stuck =/
cdef int i cdef int i