File size: 9,603 Bytes
7885a28 |
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 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 |
import pickle
import numpy as np
import pytest
from numpy.testing import assert_array_equal
from sklearn.utils._encode import _check_unknown, _encode, _get_counts, _unique
@pytest.mark.parametrize(
"values, expected",
[
(np.array([2, 1, 3, 1, 3], dtype="int64"), np.array([1, 2, 3], dtype="int64")),
(
np.array([2, 1, np.nan, 1, np.nan], dtype="float32"),
np.array([1, 2, np.nan], dtype="float32"),
),
(
np.array(["b", "a", "c", "a", "c"], dtype=object),
np.array(["a", "b", "c"], dtype=object),
),
(
np.array(["b", "a", None, "a", None], dtype=object),
np.array(["a", "b", None], dtype=object),
),
(np.array(["b", "a", "c", "a", "c"]), np.array(["a", "b", "c"])),
],
ids=["int64", "float32-nan", "object", "object-None", "str"],
)
def test_encode_util(values, expected):
uniques = _unique(values)
assert_array_equal(uniques, expected)
result, encoded = _unique(values, return_inverse=True)
assert_array_equal(result, expected)
assert_array_equal(encoded, np.array([1, 0, 2, 0, 2]))
encoded = _encode(values, uniques=uniques)
assert_array_equal(encoded, np.array([1, 0, 2, 0, 2]))
result, counts = _unique(values, return_counts=True)
assert_array_equal(result, expected)
assert_array_equal(counts, np.array([2, 1, 2]))
result, encoded, counts = _unique(values, return_inverse=True, return_counts=True)
assert_array_equal(result, expected)
assert_array_equal(encoded, np.array([1, 0, 2, 0, 2]))
assert_array_equal(counts, np.array([2, 1, 2]))
def test_encode_with_check_unknown():
# test for the check_unknown parameter of _encode()
uniques = np.array([1, 2, 3])
values = np.array([1, 2, 3, 4])
# Default is True, raise error
with pytest.raises(ValueError, match="y contains previously unseen labels"):
_encode(values, uniques=uniques, check_unknown=True)
# dont raise error if False
_encode(values, uniques=uniques, check_unknown=False)
# parameter is ignored for object dtype
uniques = np.array(["a", "b", "c"], dtype=object)
values = np.array(["a", "b", "c", "d"], dtype=object)
with pytest.raises(ValueError, match="y contains previously unseen labels"):
_encode(values, uniques=uniques, check_unknown=False)
def _assert_check_unknown(values, uniques, expected_diff, expected_mask):
diff = _check_unknown(values, uniques)
assert_array_equal(diff, expected_diff)
diff, valid_mask = _check_unknown(values, uniques, return_mask=True)
assert_array_equal(diff, expected_diff)
assert_array_equal(valid_mask, expected_mask)
@pytest.mark.parametrize(
"values, uniques, expected_diff, expected_mask",
[
(np.array([1, 2, 3, 4]), np.array([1, 2, 3]), [4], [True, True, True, False]),
(np.array([2, 1, 4, 5]), np.array([2, 5, 1]), [4], [True, True, False, True]),
(np.array([2, 1, np.nan]), np.array([2, 5, 1]), [np.nan], [True, True, False]),
(
np.array([2, 1, 4, np.nan]),
np.array([2, 5, 1, np.nan]),
[4],
[True, True, False, True],
),
(
np.array([2, 1, 4, np.nan]),
np.array([2, 5, 1]),
[4, np.nan],
[True, True, False, False],
),
(
np.array([2, 1, 4, 5]),
np.array([2, 5, 1, np.nan]),
[4],
[True, True, False, True],
),
(
np.array(["a", "b", "c", "d"], dtype=object),
np.array(["a", "b", "c"], dtype=object),
np.array(["d"], dtype=object),
[True, True, True, False],
),
(
np.array(["d", "c", "a", "b"], dtype=object),
np.array(["a", "c", "b"], dtype=object),
np.array(["d"], dtype=object),
[False, True, True, True],
),
(
np.array(["a", "b", "c", "d"]),
np.array(["a", "b", "c"]),
np.array(["d"]),
[True, True, True, False],
),
(
np.array(["d", "c", "a", "b"]),
np.array(["a", "c", "b"]),
np.array(["d"]),
[False, True, True, True],
),
],
)
def test_check_unknown(values, uniques, expected_diff, expected_mask):
_assert_check_unknown(values, uniques, expected_diff, expected_mask)
@pytest.mark.parametrize("missing_value", [None, np.nan, float("nan")])
@pytest.mark.parametrize("pickle_uniques", [True, False])
def test_check_unknown_missing_values(missing_value, pickle_uniques):
# check for check_unknown with missing values with object dtypes
values = np.array(["d", "c", "a", "b", missing_value], dtype=object)
uniques = np.array(["c", "a", "b", missing_value], dtype=object)
if pickle_uniques:
uniques = pickle.loads(pickle.dumps(uniques))
expected_diff = ["d"]
expected_mask = [False, True, True, True, True]
_assert_check_unknown(values, uniques, expected_diff, expected_mask)
values = np.array(["d", "c", "a", "b", missing_value], dtype=object)
uniques = np.array(["c", "a", "b"], dtype=object)
if pickle_uniques:
uniques = pickle.loads(pickle.dumps(uniques))
expected_diff = ["d", missing_value]
expected_mask = [False, True, True, True, False]
_assert_check_unknown(values, uniques, expected_diff, expected_mask)
values = np.array(["a", missing_value], dtype=object)
uniques = np.array(["a", "b", "z"], dtype=object)
if pickle_uniques:
uniques = pickle.loads(pickle.dumps(uniques))
expected_diff = [missing_value]
expected_mask = [True, False]
_assert_check_unknown(values, uniques, expected_diff, expected_mask)
@pytest.mark.parametrize("missing_value", [np.nan, None, float("nan")])
@pytest.mark.parametrize("pickle_uniques", [True, False])
def test_unique_util_missing_values_objects(missing_value, pickle_uniques):
# check for _unique and _encode with missing values with object dtypes
values = np.array(["a", "c", "c", missing_value, "b"], dtype=object)
expected_uniques = np.array(["a", "b", "c", missing_value], dtype=object)
uniques = _unique(values)
if missing_value is None:
assert_array_equal(uniques, expected_uniques)
else: # missing_value == np.nan
assert_array_equal(uniques[:-1], expected_uniques[:-1])
assert np.isnan(uniques[-1])
if pickle_uniques:
uniques = pickle.loads(pickle.dumps(uniques))
encoded = _encode(values, uniques=uniques)
assert_array_equal(encoded, np.array([0, 2, 2, 3, 1]))
def test_unique_util_missing_values_numeric():
# Check missing values in numerical values
values = np.array([3, 1, np.nan, 5, 3, np.nan], dtype=float)
expected_uniques = np.array([1, 3, 5, np.nan], dtype=float)
expected_inverse = np.array([1, 0, 3, 2, 1, 3])
uniques = _unique(values)
assert_array_equal(uniques, expected_uniques)
uniques, inverse = _unique(values, return_inverse=True)
assert_array_equal(uniques, expected_uniques)
assert_array_equal(inverse, expected_inverse)
encoded = _encode(values, uniques=uniques)
assert_array_equal(encoded, expected_inverse)
def test_unique_util_with_all_missing_values():
# test for all types of missing values for object dtype
values = np.array([np.nan, "a", "c", "c", None, float("nan"), None], dtype=object)
uniques = _unique(values)
assert_array_equal(uniques[:-1], ["a", "c", None])
# last value is nan
assert np.isnan(uniques[-1])
expected_inverse = [3, 0, 1, 1, 2, 3, 2]
_, inverse = _unique(values, return_inverse=True)
assert_array_equal(inverse, expected_inverse)
def test_check_unknown_with_both_missing_values():
# test for both types of missing values for object dtype
values = np.array([np.nan, "a", "c", "c", None, np.nan, None], dtype=object)
diff = _check_unknown(values, known_values=np.array(["a", "c"], dtype=object))
assert diff[0] is None
assert np.isnan(diff[1])
diff, valid_mask = _check_unknown(
values, known_values=np.array(["a", "c"], dtype=object), return_mask=True
)
assert diff[0] is None
assert np.isnan(diff[1])
assert_array_equal(valid_mask, [False, True, True, True, False, False, False])
@pytest.mark.parametrize(
"values, uniques, expected_counts",
[
(np.array([1] * 10 + [2] * 4 + [3] * 15), np.array([1, 2, 3]), [10, 4, 15]),
(
np.array([1] * 10 + [2] * 4 + [3] * 15),
np.array([1, 2, 3, 5]),
[10, 4, 15, 0],
),
(
np.array([np.nan] * 10 + [2] * 4 + [3] * 15),
np.array([2, 3, np.nan]),
[4, 15, 10],
),
(
np.array(["b"] * 4 + ["a"] * 16 + ["c"] * 20, dtype=object),
["a", "b", "c"],
[16, 4, 20],
),
(
np.array(["b"] * 4 + ["a"] * 16 + ["c"] * 20, dtype=object),
["c", "b", "a"],
[20, 4, 16],
),
(
np.array([np.nan] * 4 + ["a"] * 16 + ["c"] * 20, dtype=object),
["c", np.nan, "a"],
[20, 4, 16],
),
(
np.array(["b"] * 4 + ["a"] * 16 + ["c"] * 20, dtype=object),
["a", "b", "c", "e"],
[16, 4, 20, 0],
),
],
)
def test_get_counts(values, uniques, expected_counts):
counts = _get_counts(values, uniques)
assert_array_equal(counts, expected_counts)
|