mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
98c59027ed
* Use max(uint64) for OOV lexeme rank * Add test for default OOV rank * Revert back to thinc==7.4.0 Requiring the updated version of thinc was unnecessary. * Define OOV_RANK in one place Define OOV_RANK in one place in `util`. * Fix formatting [ci skip] * Switch to external definitions of max(uint64) Switch to external defintions of max(uint64) and confirm that they are equal.
81 lines
2.6 KiB
Python
81 lines
2.6 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
import numpy
|
|
from spacy.attrs import IS_ALPHA, IS_DIGIT
|
|
from spacy.util import OOV_RANK
|
|
|
|
|
|
@pytest.mark.parametrize("text1,prob1,text2,prob2", [("NOUN", -1, "opera", -2)])
|
|
def test_vocab_lexeme_lt(en_vocab, text1, text2, prob1, prob2):
|
|
"""More frequent is l.t. less frequent"""
|
|
lex1 = en_vocab[text1]
|
|
lex1.prob = prob1
|
|
lex2 = en_vocab[text2]
|
|
lex2.prob = prob2
|
|
|
|
assert lex1 < lex2
|
|
assert lex2 > lex1
|
|
|
|
|
|
@pytest.mark.parametrize("text1,text2", [("phantom", "opera")])
|
|
def test_vocab_lexeme_hash(en_vocab, text1, text2):
|
|
"""Test that lexemes are hashable."""
|
|
lex1 = en_vocab[text1]
|
|
lex2 = en_vocab[text2]
|
|
lexes = {lex1: lex1, lex2: lex2}
|
|
assert lexes[lex1].orth_ == text1
|
|
assert lexes[lex2].orth_ == text2
|
|
|
|
|
|
def test_vocab_lexeme_is_alpha(en_vocab):
|
|
assert en_vocab["the"].flags & (1 << IS_ALPHA)
|
|
assert not en_vocab["1999"].flags & (1 << IS_ALPHA)
|
|
assert not en_vocab["hello1"].flags & (1 << IS_ALPHA)
|
|
|
|
|
|
def test_vocab_lexeme_is_digit(en_vocab):
|
|
assert not en_vocab["the"].flags & (1 << IS_DIGIT)
|
|
assert en_vocab["1999"].flags & (1 << IS_DIGIT)
|
|
assert not en_vocab["hello1"].flags & (1 << IS_DIGIT)
|
|
|
|
|
|
def test_vocab_lexeme_add_flag_auto_id(en_vocab):
|
|
is_len4 = en_vocab.add_flag(lambda string: len(string) == 4)
|
|
assert en_vocab["1999"].check_flag(is_len4) is True
|
|
assert en_vocab["1999"].check_flag(IS_DIGIT) is True
|
|
assert en_vocab["199"].check_flag(is_len4) is False
|
|
assert en_vocab["199"].check_flag(IS_DIGIT) is True
|
|
assert en_vocab["the"].check_flag(is_len4) is False
|
|
assert en_vocab["dogs"].check_flag(is_len4) is True
|
|
|
|
|
|
def test_vocab_lexeme_add_flag_provided_id(en_vocab):
|
|
is_len4 = en_vocab.add_flag(lambda string: len(string) == 4, flag_id=IS_DIGIT)
|
|
assert en_vocab["1999"].check_flag(is_len4) is True
|
|
assert en_vocab["199"].check_flag(is_len4) is False
|
|
assert en_vocab["199"].check_flag(IS_DIGIT) is False
|
|
assert en_vocab["the"].check_flag(is_len4) is False
|
|
assert en_vocab["dogs"].check_flag(is_len4) is True
|
|
|
|
|
|
def test_lexeme_bytes_roundtrip(en_vocab):
|
|
one = en_vocab["one"]
|
|
alpha = en_vocab["alpha"]
|
|
assert one.orth != alpha.orth
|
|
assert one.lower != alpha.lower
|
|
alpha.from_bytes(one.to_bytes())
|
|
|
|
assert one.orth_ == alpha.orth_
|
|
assert one.orth == alpha.orth
|
|
assert one.lower == alpha.lower
|
|
assert one.lower_ == alpha.lower_
|
|
|
|
|
|
def test_vocab_lexeme_oov_rank(en_vocab):
|
|
"""Test that default rank is OOV_RANK."""
|
|
lex = en_vocab["word"]
|
|
assert OOV_RANK == numpy.iinfo(numpy.uint64).max
|
|
assert lex.rank == OOV_RANK
|