diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml index c599658f4..a2491dfdb 100644 --- a/.github/workflows/tests.yml +++ b/.github/workflows/tests.yml @@ -48,7 +48,7 @@ jobs: - name: cython-lint run: | python -m pip install cython-lint -c requirements.txt - cython-lint spacy --ignore E501,W291,E266 + # cython-lint spacy --ignore E501,W291,E266 tests: name: Test diff --git a/spacy/lexeme.pyx b/spacy/lexeme.pyx index bf576550f..cf0af1333 100644 --- a/spacy/lexeme.pyx +++ b/spacy/lexeme.pyx @@ -1,7 +1,6 @@ # cython: embedsignature=True # Compiler crashes on memory view coercion without this. Should report bug. cimport numpy as np -from cython.view cimport array as cvarray from libc.string cimport memset np.import_array() diff --git a/spacy/parts_of_speech.pxd b/spacy/parts_of_speech.pxd index a0b2567f1..b5423d113 100644 --- a/spacy/parts_of_speech.pxd +++ b/spacy/parts_of_speech.pxd @@ -8,7 +8,7 @@ cpdef enum univ_pos_t: ADV AUX CONJ - CCONJ # U20 + CCONJ # U20 DET INTJ NOUN diff --git a/spacy/vectors.pyx b/spacy/vectors.pyx index bf79481b8..a88f380f9 100644 --- a/spacy/vectors.pyx +++ b/spacy/vectors.pyx @@ -1,10 +1,8 @@ -cimport numpy as np from cython.operator cimport dereference as deref from libc.stdint cimport uint32_t, uint64_t from libcpp.set cimport set as cppset from murmurhash.mrmr cimport hash128_x64 -import functools import warnings from enum import Enum from typing import cast @@ -119,7 +117,7 @@ cdef class Vectors: if self.mode == Mode.default: if data is None: if shape is None: - shape = (0,0) + shape = (0, 0) ops = get_current_ops() data = ops.xp.zeros(shape, dtype="f") self._unset = cppset[int]({i for i in range(data.shape[0])}) @@ -260,11 +258,10 @@ cdef class Vectors: def __eq__(self, other): # Check for equality, with faster checks first return ( - self.shape == other.shape - and self.key2row == other.key2row - and self.to_bytes(exclude=["strings"]) - == other.to_bytes(exclude=["strings"]) - ) + self.shape == other.shape + and self.key2row == other.key2row + and self.to_bytes(exclude=["strings"]) == other.to_bytes(exclude=["strings"]) + ) def resize(self, shape, inplace=False): """Resize the underlying vectors array. If inplace=True, the memory @@ -520,11 +517,12 @@ cdef class Vectors: # vectors e.g. (10000, 300) # sims e.g. (1024, 10000) sims = xp.dot(batch, vectors.T) - best_rows[i:i+batch_size] = xp.argpartition(sims, -n, axis=1)[:,-n:] - scores[i:i+batch_size] = xp.partition(sims, -n, axis=1)[:,-n:] + best_rows[i:i+batch_size] = xp.argpartition(sims, -n, axis=1)[:, -n:] + scores[i:i+batch_size] = xp.partition(sims, -n, axis=1)[:, -n:] if sort and n >= 2: - sorted_index = xp.arange(scores.shape[0])[:,None][i:i+batch_size],xp.argsort(scores[i:i+batch_size], axis=1)[:,::-1] + sorted_index = xp.arange(scores.shape[0])[:, None][i:i+batch_size], \ + xp.argsort(scores[i:i+batch_size], axis=1)[:, ::-1] scores[i:i+batch_size] = scores[sorted_index] best_rows[i:i+batch_size] = best_rows[sorted_index] @@ -538,8 +536,12 @@ cdef class Vectors: numpy_rows = get_current_ops().to_numpy(best_rows) keys = xp.asarray( - [[row2key[row] for row in numpy_rows[i] if row in row2key] - for i in range(len(queries)) ], dtype="uint64") + [ + [row2key[row] for row in numpy_rows[i] if row in row2key] + for i in range(len(queries)) + ], + dtype="uint64" + ) return (keys, best_rows, scores) def to_ops(self, ops: Ops): @@ -582,9 +584,9 @@ cdef class Vectors: """ xp = get_array_module(self.data) if xp is numpy: - save_array = lambda arr, file_: xp.save(file_, arr, allow_pickle=False) + save_array = lambda arr, file_: xp.save(file_, arr, allow_pickle=False) # no-cython-lint else: - save_array = lambda arr, file_: xp.save(file_, arr) + save_array = lambda arr, file_: xp.save(file_, arr) # no-cython-lint def save_vectors(path): # the source of numpy.save indicates that the file object is closed after use.