explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-11 08:42:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Make small changes to Doc.to_array

Browse Source 
* Change type-check logic to 'hasattr' (Python type-checking is brittle)
* Small 'house style' edits, mostly making code more terse.
This commit is contained in:
Matthew Honnibal 2017-10-20 11:17:00 +02:00 committed by GitHub
parent fbccc8c87d
commit c0799430a7
1 changed files with 17 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
spacy/tokens/doc.pyx
View File

@ -499,28 +499,25 @@ cdef class Doc:
""" """
cdef int i, j cdef int i, j
cdef attr_id_t feature cdef attr_id_t feature
cdef np.ndarray[attr_t, ndim=1] attr_ids, output_1D
cdef np.ndarray[attr_t, ndim=2] output cdef np.ndarray[attr_t, ndim=2] output
cdef np.ndarray[attr_t, ndim=1] output_1D
# Handle scalar/list inputs of strings/ints for py_attr_ids # Handle scalar/list inputs of strings/ints for py_attr_ids
if( type(py_attr_ids) is not list and type(py_attr_ids) is not tuple ): if not hasattr(py_attr_ids, '__iter__'):
py_attr_ids = [py_attr_ids] py_attr_ids = [py_attr_ids]
py_attr_ids_input = []
for py_attr_id in py_attr_ids: # Allow strings, e.g. 'lemma' or 'LEMMA'
if( type(py_attr_id) is int ): convert_id = lambda id_: IDS[id_.upper()] if hasattr(id_, 'upper') else id_
py_attr_ids_input.append(py_attr_id) # Make an array from the attributes --- otherwise inner loop would be Python
else:
py_attr_ids_input.append(IDS[py_attr_id.upper()])
# Make an array from the attributes --- otherwise our inner loop is Python
# dict iteration. # dict iteration.
cdef np.ndarray[attr_t, ndim=1] attr_ids = numpy.asarray(py_attr_ids_input, dtype=numpy.int32) attr_ids = numpy.asarray((convert_id(id_) for id_ in py_attr_ids),
dtype=numpy.int32)
output = numpy.ndarray(shape=(self.length, len(attr_ids)), dtype=numpy.int32) output = numpy.ndarray(shape=(self.length, len(attr_ids)), dtype=numpy.int32)
for i in range(self.length): for i in range(self.length):
for j, feature in enumerate(attr_ids): for j, feature in enumerate(attr_ids):
output[i, j] = get_token_attr(&self.c[i], feature) output[i, j] = get_token_attr(&self.c[i], feature)
if( len(attr_ids) == 1 ): # Handle 1d case
output_1D = output.reshape((self.length)) return output if len(attr_ids) >= 2 else output.reshape((self.length,))
return output_1D
return output
def count_by(self, attr_id_t attr_id, exclude=None, PreshCounter counts=None): def count_by(self, attr_id_t attr_id, exclude=None, PreshCounter counts=None):
""" """