Spaces:
Sleeping
Sleeping
File size: 1,888 Bytes
d916065 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 |
import pytest
from nltk.util import everygrams
@pytest.fixture
def everygram_input():
"""Form test data for tests."""
return iter(["a", "b", "c"])
def test_everygrams_without_padding(everygram_input):
expected_output = [
("a",),
("a", "b"),
("a", "b", "c"),
("b",),
("b", "c"),
("c",),
]
output = list(everygrams(everygram_input))
assert output == expected_output
def test_everygrams_max_len(everygram_input):
expected_output = [
("a",),
("a", "b"),
("b",),
("b", "c"),
("c",),
]
output = list(everygrams(everygram_input, max_len=2))
assert output == expected_output
def test_everygrams_min_len(everygram_input):
expected_output = [
("a", "b"),
("a", "b", "c"),
("b", "c"),
]
output = list(everygrams(everygram_input, min_len=2))
assert output == expected_output
def test_everygrams_pad_right(everygram_input):
expected_output = [
("a",),
("a", "b"),
("a", "b", "c"),
("b",),
("b", "c"),
("b", "c", None),
("c",),
("c", None),
("c", None, None),
(None,),
(None, None),
(None,),
]
output = list(everygrams(everygram_input, max_len=3, pad_right=True))
assert output == expected_output
def test_everygrams_pad_left(everygram_input):
expected_output = [
(None,),
(None, None),
(None, None, "a"),
(None,),
(None, "a"),
(None, "a", "b"),
("a",),
("a", "b"),
("a", "b", "c"),
("b",),
("b", "c"),
("c",),
]
output = list(everygrams(everygram_input, max_len=3, pad_left=True))
assert output == expected_output
|