Merge branch 'develop' into refactor/simplify-warnings

spacy/gold.pxd

@@ -1,9 +1,10 @@
 from cymem.cymem cimport Pool
 
-from .tokens import Doc
 from .typedefs cimport attr_t
 from .syntax.transition_system cimport Transition
 
+from .tokens import Doc
+
 
 cdef struct GoldParseC:
     int* tags

spacy/kb.pxd

@@ -1,15 +1,15 @@
 """Knowledge-base for entity or concept linking."""
 from cymem.cymem cimport Pool
 from preshed.maps cimport PreshMap
-
 from libcpp.vector cimport vector
 from libc.stdint cimport int32_t, int64_t
 from libc.stdio cimport FILE
 
 from .vocab cimport Vocab
 from .typedefs cimport hash_t
-
 from .structs cimport KBEntryC, AliasC
+
+
 ctypedef vector[KBEntryC] entry_vec
 ctypedef vector[AliasC] alias_vec
 ctypedef vector[float] float_vec

spacy/kb.pyx

@@ -1,5 +1,4 @@
-# cython: infer_types=True
+# cython: infer_types=True, profile=True
-# cython: profile=True
 from cymem.cymem cimport Pool
 from preshed.maps cimport PreshMap
 from cpython.exc cimport PyErr_SetFromErrno

spacy/lexeme.pxd

@@ -1,13 +1,12 @@
+from numpy cimport ndarray
+
 from .typedefs cimport attr_t, hash_t, flags_t, len_t, tag_t
 from .attrs cimport attr_id_t
 from .attrs cimport ID, ORTH, LOWER, NORM, SHAPE, PREFIX, SUFFIX, LENGTH, CLUSTER, LANG
-
 from .structs cimport LexemeC, SerializedLexemeC
 from .strings cimport StringStore
 from .vocab cimport Vocab
 
-from numpy cimport ndarray
-
 
 cdef LexemeC EMPTY_LEXEME
 

spacy/matcher/dependencymatcher.pyx

@@ -1,7 +1,9 @@
-# cython: infer_types=True
+# cython: infer_types=True, profile=True
-# cython: profile=True
 from cymem.cymem cimport Pool
 from preshed.maps cimport PreshMap
+from libcpp cimport bool
+
+import numpy
 
 from .matcher cimport Matcher
 from ..vocab cimport Vocab
@@ -10,8 +12,6 @@ from ..tokens.doc cimport Doc
 from .matcher import unpickle_matcher
 from ..errors import Errors
 
-from libcpp cimport bool
-import numpy
 
 DELIMITER = "||"
 INDEX_HEAD = 1

spacy/matcher/matcher.pyx

@@ -1,5 +1,4 @@
-# cython: infer_types=True
+# cython: infer_types=True, cython: profile=True
-# cython: profile=True
 from libcpp.vector cimport vector
 from libc.stdint cimport int32_t
 from cymem.cymem cimport Pool

spacy/matcher/phrasematcher.pxd

@@ -1,5 +1,4 @@
 from libcpp.vector cimport vector
-
 from cymem.cymem cimport Pool
 from preshed.maps cimport key_t, MapStruct
 

spacy/matcher/phrasematcher.pyx

@@ -1,5 +1,4 @@
-# cython: infer_types=True
+# cython: infer_types=True, profile=True
-# cython: profile=True
 from libc.stdint cimport uintptr_t
 from preshed.maps cimport map_init, map_set, map_get, map_clear, map_iter
 

spacy/morphology.pxd

@@ -8,14 +8,14 @@ from .structs cimport TokenC, MorphAnalysisC
 from .strings cimport StringStore
 from .typedefs cimport hash_t, attr_t, flags_t
 from .parts_of_speech cimport univ_pos_t
-
 from . cimport symbols
 
+
 cdef class Morphology:
     cdef readonly Pool mem
     cdef readonly StringStore strings
     cdef PreshMap tags # Keyed by hash, value is pointer to tag
- 
+
     cdef public object lemmatizer
     cdef readonly object tag_map
     cdef readonly object tag_names
@@ -26,7 +26,7 @@ cdef class Morphology:
 
     cdef MorphAnalysisC create_morph_tag(self, field_feature_pairs) except *
     cdef int insert(self, MorphAnalysisC tag) except -1
-    
+
     cdef int assign_untagged(self, TokenC* token) except -1
     cdef int assign_tag(self, TokenC* token, tag) except -1
     cdef int assign_tag_id(self, TokenC* token, int tag_id) except -1

spacy/morphology.pyx

@@ -1,19 +1,21 @@
 # cython: infer_types
 from libc.string cimport memset
+
 import srsly
 from collections import Counter
 import numpy
 import warnings
 
-from .strings import get_string_id
-from . import symbols
 from .attrs cimport POS, IS_SPACE
-from .attrs import LEMMA, intify_attrs
 from .parts_of_speech cimport SPACE
-from .parts_of_speech import IDS as POS_IDS
 from .lexeme cimport Lexeme
+
+from .strings import get_string_id
+from .attrs import LEMMA, intify_attrs
+from .parts_of_speech import IDS as POS_IDS
 from .errors import Errors, Warnings
 from .util import ensure_path
+from . import symbols
 
 
 def _normalize_props(props):

spacy/pipeline/morphologizer.pyx

@@ -1,20 +1,20 @@
-from collections import defaultdict
-
-import numpy
 cimport numpy as np
 
+import numpy
+from collections import defaultdict
 from thinc.api import chain, list2array, to_categorical, get_array_module
 from thinc.util import copy_array
 
-from .. import util
-from .pipes import Pipe
-from ..language import component
-from ..util import link_vectors_to_models, create_default_optimizer
-from ..errors import Errors, TempErrors
 from ..tokens.doc cimport Doc
 from ..vocab cimport Vocab
 from ..morphology cimport Morphology
 
+from .. import util
+from ..language import component
+from ..util import link_vectors_to_models, create_default_optimizer
+from ..errors import Errors, TempErrors
+from .pipes import Pipe
+
 
 @component("morphologizer", assigns=["token.morph", "token.pos"])
 class Morphologizer(Pipe):

spacy/pipeline/pipes.pyx

@@ -1,5 +1,4 @@
-# cython: infer_types=True
+# cython: infer_types=True, profile=True
-# cython: profile=True
 import numpy
 import srsly
 import random

spacy/strings.pxd

@@ -1,7 +1,6 @@
 from libc.stdint cimport int64_t
 from libcpp.vector cimport vector
 from libcpp.set cimport set
-
 from cymem.cymem cimport Pool
 from preshed.maps cimport PreshMap
 from murmurhash.mrmr cimport hash64

spacy/strings.pyx

@@ -4,11 +4,13 @@ from libc.string cimport memcpy
 from libcpp.set cimport set
 from libc.stdint cimport uint32_t
 from murmurhash.mrmr cimport hash64, hash32
+
 import srsly
 
+from .typedefs cimport hash_t
+
 from .symbols import IDS as SYMBOLS_BY_STR
 from .symbols import NAMES as SYMBOLS_BY_INT
-from .typedefs cimport hash_t
 from .errors import Errors
 from . import util
 

spacy/structs.pxd

@@ -1,11 +1,9 @@
 from libc.stdint cimport uint8_t, uint32_t, int32_t, uint64_t
-
-from .typedefs cimport flags_t, attr_t, hash_t
-from .parts_of_speech cimport univ_pos_t
-
 from libcpp.vector cimport vector
 from libc.stdint cimport int32_t, int64_t
 
+from .typedefs cimport flags_t, attr_t, hash_t
+from .parts_of_speech cimport univ_pos_t
 
 
 cdef struct LexemeC:

spacy/syntax/_beam_utils.pyx

@@ -1,18 +1,19 @@
-# cython: infer_types=True
+# cython: infer_types=True, profile=True
-# cython: profile=True
 cimport numpy as np
-import numpy
 from cpython.ref cimport PyObject, Py_XDECREF
 from thinc.extra.search cimport Beam
-from thinc.extra.search import MaxViolation
 from thinc.extra.search cimport MaxViolation
 
+from thinc.extra.search import MaxViolation
+import numpy
+
 from ..typedefs cimport hash_t, class_t
 from .transition_system cimport TransitionSystem, Transition
 from ..gold cimport GoldParse
-from ..errors import Errors
 from .stateclass cimport StateC, StateClass
 
+from ..errors import Errors
+
 
 # These are passed as callbacks to thinc.search.Beam
 cdef int transition_state(void* _dest, void* _src, class_t clas, void* _moves) except -1:
@@ -326,5 +327,3 @@ def cleanup_beam(Beam beam):
             seen.add(addr)
         else:
             raise ValueError(Errors.E023.format(addr=addr, i=i))
-
-

spacy/syntax/_parser_model.pyx

@@ -1,9 +1,5 @@
-# cython: infer_types=True
+# cython: infer_types=True, cdivision=True, boundscheck=False
-# cython: cdivision=True
-# cython: boundscheck=False
-import numpy
 cimport cython.parallel
-import numpy.random
 cimport numpy as np
 from libc.math cimport exp
 from libcpp.vector cimport vector
@@ -11,21 +7,25 @@ from libc.string cimport memset, memcpy
 from libc.stdlib cimport calloc, free, realloc
 from cymem.cymem cimport Pool
 from thinc.extra.search cimport Beam
-from thinc.api import Linear, Model, CupyOps, NumpyOps, use_ops
 from thinc.backends.linalg cimport Vec, VecVec
 cimport blis.cy
 
+import numpy
+import numpy.random
+from thinc.api import Linear, Model, CupyOps, NumpyOps, use_ops
+
 from ..typedefs cimport weight_t, class_t, hash_t
-from ..compat import copy_array
 from ..tokens.doc cimport Doc
 from ..gold cimport GoldParse
-from ..errors import Errors, TempErrors
-from .. import util
 from .stateclass cimport StateClass
 from .transition_system cimport Transition
+
+from ..compat import copy_array
+from ..errors import Errors, TempErrors
+from ..util import link_vectors_to_models, create_default_optimizer
+from .. import util
 from . import _beam_utils
 from . import nonproj
-from ..util import link_vectors_to_models, create_default_optimizer
 
 
 cdef WeightsC get_c_weights(model) except *:

spacy/syntax/_state.pxd

@@ -1,9 +1,7 @@
 from libc.string cimport memcpy, memset, memmove
 from libc.stdlib cimport malloc, calloc, free
 from libc.stdint cimport uint32_t, uint64_t
-
 from cpython.exc cimport PyErr_CheckSignals, PyErr_SetFromErrno
-
 from murmurhash.mrmr cimport hash64
 
 from ..vocab cimport EMPTY_LEXEME

spacy/syntax/arc_eager.pxd

@@ -1,10 +1,7 @@
 from cymem.cymem cimport Pool
 
-from ..typedefs cimport weight_t
-
 from .stateclass cimport StateClass
-from ..typedefs cimport attr_t
+from ..typedefs cimport weight_t, attr_t
-
 from .transition_system cimport TransitionSystem, Transition
 from ..gold cimport GoldParseC
 
@@ -15,4 +12,3 @@ cdef class ArcEager(TransitionSystem):
 
 cdef weight_t push_cost(StateClass stcls, const GoldParseC* gold, int target) nogil
 cdef weight_t arc_cost(StateClass stcls, const GoldParseC* gold, int head, int child) nogil
-

spacy/syntax/arc_eager.pyx

@@ -1,23 +1,24 @@
-# cython: profile=True
+# cython: profile=True, cdivision=True, infer_types=True
-# cython: cdivision=True
-# cython: infer_types=True
 from cpython.ref cimport Py_INCREF
 from cymem.cymem cimport Pool
-from collections import defaultdict, Counter
 from thinc.extra.search cimport Beam
+
+from collections import defaultdict, Counter
 import json
 
-from .nonproj import is_nonproj_tree
 from ..typedefs cimport hash_t, attr_t
 from ..strings cimport hash_string
-from .stateclass cimport StateClass
-from ._state cimport StateC
-from . import nonproj
-from .transition_system cimport move_cost_func_t, label_cost_func_t
 from ..gold cimport GoldParse, GoldParseC
 from ..structs cimport TokenC
-from ..errors import Errors
 from ..tokens.doc cimport Doc, set_children_from_heads
+from .stateclass cimport StateClass
+from ._state cimport StateC
+from .transition_system cimport move_cost_func_t, label_cost_func_t
+
+from ..errors import Errors
+from .nonproj import is_nonproj_tree
+from . import nonproj
+
 
 # Calculate cost as gold/not gold. We don't use scalar value anyway.
 cdef int BINARY_COSTS = 1

spacy/syntax/ner.pyx

@@ -1,4 +1,5 @@
 from thinc.extra.search cimport Beam
+
 from collections import Counter
 
 from ..typedefs cimport weight_t
@@ -9,6 +10,7 @@ from .transition_system cimport do_func_t
 from ..gold cimport GoldParseC, GoldParse
 from ..lexeme cimport Lexeme
 from ..attrs cimport IS_SPACE
+
 from ..errors import Errors
 
 

spacy/syntax/nn_parser.pyx

@@ -1,6 +1,4 @@
-# cython: infer_types=True
+# cython: infer_types=True, cdivision=True, boundscheck=False
-# cython: cdivision=True
-# cython: boundscheck=False
 cimport cython.parallel
 cimport numpy as np
 from cpython.ref cimport PyObject, Py_XDECREF
@@ -21,23 +19,24 @@ import numpy.random
 import numpy
 import warnings
 
-from ..gold import Example
+from ..tokens.doc cimport Doc
+from ..gold cimport GoldParse
 from ..typedefs cimport weight_t, class_t, hash_t
 from ._parser_model cimport alloc_activations, free_activations
 from ._parser_model cimport predict_states, arg_max_if_valid
 from ._parser_model cimport WeightsC, ActivationsC, SizesC, cpu_log_loss
 from ._parser_model cimport get_c_weights, get_c_sizes
-from ._parser_model import ParserModel
-from ..util import link_vectors_to_models, create_default_optimizer, registry
-from ..compat import copy_array
-from ..tokens.doc cimport Doc
-from ..gold cimport GoldParse
-from ..errors import Errors, Warnings
-from .. import util
 from .stateclass cimport StateClass
 from ._state cimport StateC
 from .transition_system cimport Transition
 from . cimport _beam_utils
+
+from ..gold import Example
+from ..util import link_vectors_to_models, create_default_optimizer, registry
+from ..compat import copy_array
+from ..errors import Errors, Warnings
+from .. import util
+from ._parser_model import ParserModel
 from . import _beam_utils
 from . import nonproj
 

spacy/syntax/nonproj.pyx

@@ -1,13 +1,13 @@
-# cython: profile=True
+# cython: profile=True, infer_types=True
-# cython: infer_types=True
 """Implements the projectivize/deprojectivize mechanism in Nivre & Nilsson 2005
 for doing pseudo-projective parsing implementation uses the HEAD decoration
 scheme.
 """
 from copy import copy
 
-from ..gold import Example
 from ..tokens.doc cimport Doc, set_children_from_heads
+
+from ..gold import Example
 from ..errors import Errors
 
 

spacy/syntax/transition_system.pxd

@@ -5,7 +5,6 @@ from ..structs cimport TokenC
 from ..gold cimport GoldParse
 from ..gold cimport GoldParseC
 from ..strings cimport StringStore
-
 from .stateclass cimport StateClass
 from ._state cimport StateC
 

spacy/syntax/transition_system.pyx

@@ -1,16 +1,18 @@
 # cython: infer_types=True
 from cpython.ref cimport Py_INCREF
 from cymem.cymem cimport Pool
-from ..typedefs cimport weight_t
 from thinc.extra.search cimport Beam
+
 from collections import Counter
 import srsly
 
+from ..typedefs cimport weight_t
 from . cimport _beam_utils
 from ..tokens.doc cimport Doc
 from ..structs cimport TokenC
 from .stateclass cimport StateClass
 from ..typedefs cimport attr_t
+
 from ..errors import Errors
 from .. import util
 

spacy/tokenizer.pxd

@@ -1,5 +1,4 @@
 from libcpp.vector cimport vector
-
 from preshed.maps cimport PreshMap
 from cymem.cymem cimport Pool
 

spacy/tokenizer.pyx

@@ -1,5 +1,4 @@
-# cython: embedsignature=True
+# cython: embedsignature=True, profile=True
-# cython: profile=True
 from __future__ import unicode_literals
 
 from cython.operator cimport dereference as deref
@@ -15,13 +14,13 @@ import warnings
 
 from .tokens.doc cimport Doc
 from .strings cimport hash_string
+from .lexeme cimport EMPTY_LEXEME
+
 from .attrs import intify_attrs
 from .symbols import ORTH
-
 from .errors import Errors, Warnings
 from . import util
 from .attrs import intify_attrs
-from .lexeme cimport EMPTY_LEXEME
 from .symbols import ORTH
 
 

spacy/tokens/_retokenize.pyx

@@ -1,6 +1,4 @@
-# cython: infer_types=True
+# cython: infer_types=True, bounds_check=False, profile=True
-# cython: bounds_check=False
-# cython: profile=True
 from libc.string cimport memcpy, memset
 from libc.stdlib cimport malloc, free
 from cymem.cymem cimport Pool

spacy/tokens/doc.pyx

@@ -1,12 +1,10 @@
-# cython: infer_types=True
+# cython: infer_types=True, bounds_check=False, profile=True
-# cython: bounds_check=False
-# cython: profile=True
 cimport cython
 cimport numpy as np
 from libc.string cimport memcpy, memset
 from libc.math cimport sqrt
-from collections import Counter
 
+from collections import Counter
 import numpy
 import numpy.linalg
 import struct

spacy/tokens/span.pyx

@@ -1,4 +1,5 @@
 from __future__ import unicode_literals
+
 cimport numpy as np
 from libc.math cimport sqrt
 

spacy/tokens/token.pxd

@@ -6,6 +6,7 @@ from ..typedefs cimport attr_t, flags_t
 from ..parts_of_speech cimport univ_pos_t
 from .doc cimport Doc
 from ..lexeme cimport Lexeme
+
 from ..errors import Errors
 
 

spacy/tokens/token.pyx

@@ -18,12 +18,12 @@ from ..attrs cimport IS_OOV, IS_TITLE, IS_UPPER, IS_CURRENCY, LIKE_URL, LIKE_NUM
 from ..attrs cimport IS_STOP, ID, ORTH, NORM, LOWER, SHAPE, PREFIX, SUFFIX
 from ..attrs cimport LENGTH, CLUSTER, LEMMA, POS, TAG, DEP
 from ..symbols cimport conj
+from .morphanalysis cimport MorphAnalysis
 
 from .. import parts_of_speech
 from .. import util
 from ..errors import Errors, Warnings
 from .underscore import Underscore, get_ext_args
-from .morphanalysis cimport MorphAnalysis
 
 
 cdef class Token:

spacy/vocab.pxd

@@ -1,5 +1,4 @@
 from libcpp.vector cimport vector
-
 from preshed.maps cimport PreshMap
 from cymem.cymem cimport Pool
 from murmurhash.mrmr cimport hash64