explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-21 17:41:59 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix kb.

Browse Source
This commit is contained in:
Raphael Mitsch 2023-07-03 11:28:58 +02:00
parent a0bf50661b
commit 77e9e4ddad
2 changed files with 45 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
spacy/kb/candidate.pxd
View File

@ -4,7 +4,8 @@ from ..typedefs cimport hash_t
from .kb cimport KnowledgeBase
# Object used by the Entity Linker that summarizes one entity-alias candidate combination.
# Object used by the Entity Linker that summarizes one entity-alias candidate
# combination.
cdef class Candidate:
cdef readonly KnowledgeBase kb
cdef hash_t entity_hash

62
spacy/kb/kb_in_memory.pxd
View File

@ -55,23 +55,28 @@ cdef class InMemoryLookupKB(KnowledgeBase):
# optional data, we can let users configure a DB as the backend for this.
cdef object _features_table
cdef inline int64_t c_add_vector(self, vector[float] entity_vector) nogil:
"""Add an entity vector to the vectors table."""
cdef int64_t new_index = self._vectors_table.size()
self._vectors_table.push_back(entity_vector)
return new_index
cdef inline int64_t c_add_entity(self, hash_t entity_hash, float freq,
int32_t vector_index, int feats_row) nogil:
cdef inline int64_t c_add_entity(
self,
hash_t entity_hash,
float freq,
int32_t vector_index,
int feats_row
) nogil:
"""Add an entry to the vector of entries.
After calling this method, make sure to update also the _entry_index using the return value"""
After calling this method, make sure to update also the _entry_index
using the return value"""
# This is what we'll map the entity hash key to. It's where the entry will sit
# in the vector of entries, so we can get it later.
cdef int64_t new_index = self._entries.size()
# Avoid struct initializer to enable nogil, cf https://github.com/cython/cython/issues/1642
# Avoid struct initializer to enable nogil, cf.
# https://github.com/cython/cython/issues/1642
cdef KBEntryC entry
entry.entity_hash = entity_hash
entry.vector_index = vector_index
@ -81,11 +86,17 @@ cdef class InMemoryLookupKB(KnowledgeBase):
self._entries.push_back(entry)
return new_index
cdef inline int64_t c_add_aliases(self, hash_t alias_hash, vector[int64_t] entry_indices, vector[float] probs) nogil:
"""Connect a mention to a list of potential entities with their prior probabilities .
After calling this method, make sure to update also the _alias_index using the return value"""
# This is what we'll map the alias hash key to. It's where the alias will be defined
# in the vector of aliases.
cdef inline int64_t c_add_aliases(
self,
hash_t alias_hash,
vector[int64_t] entry_indices,
vector[float] probs
) nogil:
"""Connect a mention to a list of potential entities with their prior
probabilities. After calling this method, make sure to update also the
_alias_index using the return value"""
# This is what we'll map the alias hash key to. It's where the alias will be
# defined in the vector of aliases.
cdef int64_t new_index = self._aliases_table.size()
# Avoid struct initializer to enable nogil
@ -98,8 +109,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
cdef inline void _create_empty_vectors(self, hash_t dummy_hash) nogil:
"""
Initializing the vectors and making sure the first element of each vector is a dummy,
because the PreshMap maps pointing to indices in these vectors can not contain 0 as value
Initializing the vectors and making sure the first element of each vector is a
dummy, because the PreshMap maps pointing to indices in these vectors can not
contain 0 as value.
cf. https://github.com/explosion/preshed/issues/17
"""
cdef int32_t dummy_value = 0
@ -130,12 +142,18 @@ cdef class InMemoryLookupKB(KnowledgeBase):
cdef class Writer:
cdef FILE* _fp
cdef int write_header(self, int64_t nr_entries, int64_t entity_vector_length) except -1
cdef int write_header(
self, int64_t nr_entries, int64_t entity_vector_length
) except -1
cdef int write_vector_element(self, float element) except -1
cdef int write_entry(self, hash_t entry_hash, float entry_freq, int32_t vector_index) except -1
cdef int write_entry(
self, hash_t entry_hash, float entry_freq, int32_t vector_index
) except -1
cdef int write_alias_length(self, int64_t alias_length) except -1
cdef int write_alias_header(self, hash_t alias_hash, int64_t candidate_length) except -1
cdef int write_alias_header(
self, hash_t alias_hash, int64_t candidate_length
) except -1
cdef int write_alias(self, int64_t entry_index, float prob) except -1
cdef int _write(self, void* value, size_t size) except -1
@ -143,12 +161,18 @@ cdef class Writer:
cdef class Reader:
cdef FILE* _fp
cdef int read_header(self, int64_t* nr_entries, int64_t* entity_vector_length) except -1
cdef int read_header(
self, int64_t* nr_entries, int64_t* entity_vector_length
) except -1
cdef int read_vector_element(self, float* element) except -1
cdef int read_entry(self, hash_t* entity_hash, float* freq, int32_t* vector_index) except -1
cdef int read_entry(
self, hash_t* entity_hash, float* freq, int32_t* vector_index
) except -1
cdef int read_alias_length(self, int64_t* alias_length) except -1
cdef int read_alias_header(self, hash_t* alias_hash, int64_t* candidate_length) except -1
cdef int read_alias_header(
self, hash_t* alias_hash, int64_t* candidate_length
) except -1
cdef int read_alias(self, int64_t* entry_index, float* prob) except -1
cdef int _read(self, void* value, size_t size) except -1