mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 19:06:33 +03:00
efdbb722c5
* Store activations in Doc when `store_activations` is enabled This change adds the new `activations` attribute to `Doc`. This attribute can be used by trainable pipes to store their activations, probabilities, and guesses for downstream users. As an example, this change modifies the `tagger` and `senter` pipes to add an `store_activations` option. When this option is enabled, the probabilities and guesses are stored in `set_annotations`. * Change type of `store_activations` to `Union[bool, List[str]]` When the value is: - A bool: all activations are stored when set to `True`. - A List[str]: the activations named in the list are stored * Formatting fixes in Tagger * Support store_activations in spancat and morphologizer * Make Doc.activations type visible to MyPy * textcat/textcat_multilabel: add store_activations option * trainable_lemmatizer/entity_linker: add store_activations option * parser/ner: do not currently support returning activations * Extend tagger and senter tests So that they, like the other tests, also check that we get no activations if no activations were requested. * Document `Doc.activations` and `store_activations` in the relevant pipes * Start errors/warnings at higher numbers to avoid merge conflicts Between the master and v4 branches. * Add `store_activations` to docstrings. * Replace store_activations setter by set_store_activations method Setters that take a different type than what the getter returns are still problematic for MyPy. Replace the setter by a method, so that type inference works everywhere. * Use dict comprehension suggested by @svlandeg * Revert "Use dict comprehension suggested by @svlandeg" This reverts commit6e7b958f70. * EntityLinker: add type annotations to _add_activations * _store_activations: make kwarg-only, remove doc_scores_lens arg * set_annotations: add type annotations * Apply suggestions from code review Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * TextCat.predict: return dict * Make the `TrainablePipe.store_activations` property a bool This means that we can also bring back `store_activations` setter. * Remove `TrainablePipe.activations` We do not need to enumerate the activations anymore since `store_activations` is `bool`. * Add type annotations for activations in predict/set_annotations * Rename `TrainablePipe.store_activations` to `save_activations` * Error E1400 is not used anymore This error was used when activations were still `Union[bool, List[str]]`. * Change wording in API docs after store -> save change * docs: tag (save_)activations as new in spaCy 4.0 * Fix copied line in morphologizer activations test * Don't train in any test_save_activations test * Rename activations - "probs" -> "probabilities" - "guesses" -> "label_ids", except in the edit tree lemmatizer, where "guesses" -> "tree_ids". * Remove unused W400 warning. This warning was used when we still allowed the user to specify which activations to save. * Formatting fixes Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Replace "kb_ids" by a constant * spancat: replace a cast by an assertion * Fix EOF spacing * Fix comments in test_save_activations tests * Do not set RNG seed in activation saving tests * Revert "spancat: replace a cast by an assertion" This reverts commit0bd5730d16. Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
74 lines
1.7 KiB
Cython
74 lines
1.7 KiB
Cython
from cymem.cymem cimport Pool
|
|
cimport numpy as np
|
|
|
|
from ..vocab cimport Vocab
|
|
from ..structs cimport TokenC, LexemeC, SpanC
|
|
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
|
|
cdef attr_t get_token_attr_for_matcher(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 start, int end) except -1
|
|
|
|
|
|
cdef int _set_lr_kids_and_edges(TokenC* tokens, int start, int end, 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 [:,:] _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 readonly object spans
|
|
|
|
cdef TokenC* c
|
|
|
|
cdef public float sentiment
|
|
|
|
cdef public dict activations
|
|
|
|
cdef public dict user_hooks
|
|
cdef public dict user_token_hooks
|
|
cdef public dict user_span_hooks
|
|
|
|
cdef public bint has_unknown_spaces
|
|
|
|
cdef public object _context
|
|
|
|
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)
|