mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 17:06:29 +03:00
b71a11ff6d
* Add pos and morph scoring to Scorer Add pos, morph, and morph_per_type to `Scorer`. Report pos and morph accuracy in `spacy evaluate`. * Update morphologizer for v3 * switch to tagger-based morphologizer * use `spacy.HashCharEmbedCNN` for morphologizer defaults * add `Doc.is_morphed` flag * Add morphologizer to train CLI * Add basic morphologizer pipeline tests * Add simple morphologizer training example * Remove subword_features from CharEmbed models Remove `subword_features` argument from `spacy.HashCharEmbedCNN.v1` and `spacy.HashCharEmbedBiLSTM.v1` since in these cases `subword_features` is always `False`. * Rename setting in morphologizer example Use `with_pos_tags` instead of `without_pos_tags`. * Fix kwargs for spacy.HashCharEmbedBiLSTM.v1 * Remove defaults for spacy.HashCharEmbedBiLSTM.v1 Remove default `nM/nC` for `spacy.HashCharEmbedBiLSTM.v1`. * Set random seed for textcat overfitting test
75 lines
1.7 KiB
Cython
75 lines
1.7 KiB
Cython
from cymem.cymem cimport Pool
|
|
cimport numpy as np
|
|
|
|
from ..vocab cimport Vocab
|
|
from ..structs cimport TokenC, LexemeC
|
|
from ..typedefs cimport attr_t
|
|
from ..attrs cimport attr_id_t
|
|
|
|
|
|
cdef attr_t get_token_attr(const TokenC* token, attr_id_t feat_name) nogil
|
|
|
|
|
|
ctypedef const LexemeC* const_Lexeme_ptr
|
|
ctypedef const TokenC* const_TokenC_ptr
|
|
|
|
ctypedef fused LexemeOrToken:
|
|
const_Lexeme_ptr
|
|
const_TokenC_ptr
|
|
|
|
|
|
cdef int set_children_from_heads(TokenC* tokens, int length) except -1
|
|
|
|
|
|
cdef int _set_lr_kids_and_edges(TokenC* tokens, int length, int loop_count) except -1
|
|
|
|
|
|
cdef int token_by_start(const TokenC* tokens, int length, int start_char) except -2
|
|
|
|
|
|
cdef int token_by_end(const TokenC* tokens, int length, int end_char) except -2
|
|
|
|
|
|
cdef int set_children_from_heads(TokenC* tokens, int length) except -1
|
|
|
|
|
|
cdef int [:,:] _get_lca_matrix(Doc, int start, int end)
|
|
|
|
cdef class Doc:
|
|
cdef readonly Pool mem
|
|
cdef readonly Vocab vocab
|
|
|
|
cdef public object _vector
|
|
cdef public object _vector_norm
|
|
|
|
cdef public object tensor
|
|
cdef public object cats
|
|
cdef public object user_data
|
|
|
|
cdef TokenC* c
|
|
|
|
cdef public bint is_tagged
|
|
cdef public bint is_parsed
|
|
cdef public bint is_morphed
|
|
|
|
cdef public float sentiment
|
|
|
|
cdef public dict user_hooks
|
|
cdef public dict user_token_hooks
|
|
cdef public dict user_span_hooks
|
|
|
|
cdef public list _py_tokens
|
|
|
|
cdef int length
|
|
cdef int max_length
|
|
|
|
cdef public object noun_chunks_iterator
|
|
|
|
cdef object __weakref__
|
|
|
|
cdef int push_back(self, LexemeOrToken lex_or_tok, bint has_space) except -1
|
|
|
|
cpdef np.ndarray to_array(self, object features)
|
|
|
|
cdef void set_parse(self, const TokenC* parsed) nogil
|