File size: 11,793 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 |
import numpy as np
from numpy.testing import assert_equal, assert_array_equal
import pytest
from scipy.conftest import skip_xp_invalid_arg
from scipy.stats import rankdata, tiecorrect
from scipy._lib._util import np_long
class TestTieCorrect:
def test_empty(self):
"""An empty array requires no correction, should return 1.0."""
ranks = np.array([], dtype=np.float64)
c = tiecorrect(ranks)
assert_equal(c, 1.0)
def test_one(self):
"""A single element requires no correction, should return 1.0."""
ranks = np.array([1.0], dtype=np.float64)
c = tiecorrect(ranks)
assert_equal(c, 1.0)
def test_no_correction(self):
"""Arrays with no ties require no correction."""
ranks = np.arange(2.0)
c = tiecorrect(ranks)
assert_equal(c, 1.0)
ranks = np.arange(3.0)
c = tiecorrect(ranks)
assert_equal(c, 1.0)
def test_basic(self):
"""Check a few basic examples of the tie correction factor."""
# One tie of two elements
ranks = np.array([1.0, 2.5, 2.5])
c = tiecorrect(ranks)
T = 2.0
N = ranks.size
expected = 1.0 - (T**3 - T) / (N**3 - N)
assert_equal(c, expected)
# One tie of two elements (same as above, but tie is not at the end)
ranks = np.array([1.5, 1.5, 3.0])
c = tiecorrect(ranks)
T = 2.0
N = ranks.size
expected = 1.0 - (T**3 - T) / (N**3 - N)
assert_equal(c, expected)
# One tie of three elements
ranks = np.array([1.0, 3.0, 3.0, 3.0])
c = tiecorrect(ranks)
T = 3.0
N = ranks.size
expected = 1.0 - (T**3 - T) / (N**3 - N)
assert_equal(c, expected)
# Two ties, lengths 2 and 3.
ranks = np.array([1.5, 1.5, 4.0, 4.0, 4.0])
c = tiecorrect(ranks)
T1 = 2.0
T2 = 3.0
N = ranks.size
expected = 1.0 - ((T1**3 - T1) + (T2**3 - T2)) / (N**3 - N)
assert_equal(c, expected)
def test_overflow(self):
ntie, k = 2000, 5
a = np.repeat(np.arange(k), ntie)
n = a.size # ntie * k
out = tiecorrect(rankdata(a))
assert_equal(out, 1.0 - k * (ntie**3 - ntie) / float(n**3 - n))
class TestRankData:
def test_empty(self):
"""stats.rankdata([]) should return an empty array."""
a = np.array([], dtype=int)
r = rankdata(a)
assert_array_equal(r, np.array([], dtype=np.float64))
r = rankdata([])
assert_array_equal(r, np.array([], dtype=np.float64))
@pytest.mark.parametrize("shape", [(0, 1, 2)])
@pytest.mark.parametrize("axis", [None, *range(3)])
def test_empty_multidim(self, shape, axis):
a = np.empty(shape, dtype=int)
r = rankdata(a, axis=axis)
expected_shape = (0,) if axis is None else shape
assert_equal(r.shape, expected_shape)
assert_equal(r.dtype, np.float64)
def test_one(self):
"""Check stats.rankdata with an array of length 1."""
data = [100]
a = np.array(data, dtype=int)
r = rankdata(a)
assert_array_equal(r, np.array([1.0], dtype=np.float64))
r = rankdata(data)
assert_array_equal(r, np.array([1.0], dtype=np.float64))
def test_basic(self):
"""Basic tests of stats.rankdata."""
data = [100, 10, 50]
expected = np.array([3.0, 1.0, 2.0], dtype=np.float64)
a = np.array(data, dtype=int)
r = rankdata(a)
assert_array_equal(r, expected)
r = rankdata(data)
assert_array_equal(r, expected)
data = [40, 10, 30, 10, 50]
expected = np.array([4.0, 1.5, 3.0, 1.5, 5.0], dtype=np.float64)
a = np.array(data, dtype=int)
r = rankdata(a)
assert_array_equal(r, expected)
r = rankdata(data)
assert_array_equal(r, expected)
data = [20, 20, 20, 10, 10, 10]
expected = np.array([5.0, 5.0, 5.0, 2.0, 2.0, 2.0], dtype=np.float64)
a = np.array(data, dtype=int)
r = rankdata(a)
assert_array_equal(r, expected)
r = rankdata(data)
assert_array_equal(r, expected)
# The docstring states explicitly that the argument is flattened.
a2d = a.reshape(2, 3)
r = rankdata(a2d)
assert_array_equal(r, expected)
@skip_xp_invalid_arg
def test_rankdata_object_string(self):
def min_rank(a):
return [1 + sum(i < j for i in a) for j in a]
def max_rank(a):
return [sum(i <= j for i in a) for j in a]
def ordinal_rank(a):
return min_rank([(x, i) for i, x in enumerate(a)])
def average_rank(a):
return [(i + j) / 2.0 for i, j in zip(min_rank(a), max_rank(a))]
def dense_rank(a):
b = np.unique(a)
return [1 + sum(i < j for i in b) for j in a]
rankf = dict(min=min_rank, max=max_rank, ordinal=ordinal_rank,
average=average_rank, dense=dense_rank)
def check_ranks(a):
for method in 'min', 'max', 'dense', 'ordinal', 'average':
out = rankdata(a, method=method)
assert_array_equal(out, rankf[method](a))
val = ['foo', 'bar', 'qux', 'xyz', 'abc', 'efg', 'ace', 'qwe', 'qaz']
check_ranks(np.random.choice(val, 200))
check_ranks(np.random.choice(val, 200).astype('object'))
val = np.array([0, 1, 2, 2.718, 3, 3.141], dtype='object')
check_ranks(np.random.choice(val, 200).astype('object'))
def test_large_int(self):
data = np.array([2**60, 2**60+1], dtype=np.uint64)
r = rankdata(data)
assert_array_equal(r, [1.0, 2.0])
data = np.array([2**60, 2**60+1], dtype=np.int64)
r = rankdata(data)
assert_array_equal(r, [1.0, 2.0])
data = np.array([2**60, -2**60+1], dtype=np.int64)
r = rankdata(data)
assert_array_equal(r, [2.0, 1.0])
def test_big_tie(self):
for n in [10000, 100000, 1000000]:
data = np.ones(n, dtype=int)
r = rankdata(data)
expected_rank = 0.5 * (n + 1)
assert_array_equal(r, expected_rank * data,
"test failed with n=%d" % n)
def test_axis(self):
data = [[0, 2, 1],
[4, 2, 2]]
expected0 = [[1., 1.5, 1.],
[2., 1.5, 2.]]
r0 = rankdata(data, axis=0)
assert_array_equal(r0, expected0)
expected1 = [[1., 3., 2.],
[3., 1.5, 1.5]]
r1 = rankdata(data, axis=1)
assert_array_equal(r1, expected1)
methods = ["average", "min", "max", "dense", "ordinal"]
dtypes = [np.float64] + [np_long]*4
@pytest.mark.parametrize("axis", [0, 1])
@pytest.mark.parametrize("method, dtype", zip(methods, dtypes))
def test_size_0_axis(self, axis, method, dtype):
shape = (3, 0)
data = np.zeros(shape)
r = rankdata(data, method=method, axis=axis)
assert_equal(r.shape, shape)
assert_equal(r.dtype, dtype)
@pytest.mark.parametrize('axis', range(3))
@pytest.mark.parametrize('method', methods)
def test_nan_policy_omit_3d(self, axis, method):
shape = (20, 21, 22)
rng = np.random.RandomState(23983242)
a = rng.random(size=shape)
i = rng.random(size=shape) < 0.4
j = rng.random(size=shape) < 0.1
k = rng.random(size=shape) < 0.1
a[i] = np.nan
a[j] = -np.inf
a[k] - np.inf
def rank_1d_omit(a, method):
out = np.zeros_like(a)
i = np.isnan(a)
a_compressed = a[~i]
res = rankdata(a_compressed, method)
out[~i] = res
out[i] = np.nan
return out
def rank_omit(a, method, axis):
return np.apply_along_axis(lambda a: rank_1d_omit(a, method),
axis, a)
res = rankdata(a, method, axis=axis, nan_policy='omit')
res0 = rank_omit(a, method, axis=axis)
assert_array_equal(res, res0)
def test_nan_policy_2d_axis_none(self):
# 2 2d-array test with axis=None
data = [[0, np.nan, 3],
[4, 2, np.nan],
[1, 2, 2]]
assert_array_equal(rankdata(data, axis=None, nan_policy='omit'),
[1., np.nan, 6., 7., 4., np.nan, 2., 4., 4.])
assert_array_equal(rankdata(data, axis=None, nan_policy='propagate'),
[np.nan, np.nan, np.nan, np.nan, np.nan, np.nan,
np.nan, np.nan, np.nan])
def test_nan_policy_raise(self):
# 1 1d-array test
data = [0, 2, 3, -2, np.nan, np.nan]
with pytest.raises(ValueError, match="The input contains nan"):
rankdata(data, nan_policy='raise')
# 2 2d-array test
data = [[0, np.nan, 3],
[4, 2, np.nan],
[np.nan, 2, 2]]
with pytest.raises(ValueError, match="The input contains nan"):
rankdata(data, axis=0, nan_policy="raise")
with pytest.raises(ValueError, match="The input contains nan"):
rankdata(data, axis=1, nan_policy="raise")
def test_nan_policy_propagate(self):
# 1 1d-array test
data = [0, 2, 3, -2, np.nan, np.nan]
assert_array_equal(rankdata(data, nan_policy='propagate'),
[np.nan, np.nan, np.nan, np.nan, np.nan, np.nan])
# 2 2d-array test
data = [[0, np.nan, 3],
[4, 2, np.nan],
[1, 2, 2]]
assert_array_equal(rankdata(data, axis=0, nan_policy='propagate'),
[[1, np.nan, np.nan],
[3, np.nan, np.nan],
[2, np.nan, np.nan]])
assert_array_equal(rankdata(data, axis=1, nan_policy='propagate'),
[[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan],
[1, 2.5, 2.5]])
_cases = (
# values, method, expected
([], 'average', []),
([], 'min', []),
([], 'max', []),
([], 'dense', []),
([], 'ordinal', []),
#
([100], 'average', [1.0]),
([100], 'min', [1.0]),
([100], 'max', [1.0]),
([100], 'dense', [1.0]),
([100], 'ordinal', [1.0]),
#
([100, 100, 100], 'average', [2.0, 2.0, 2.0]),
([100, 100, 100], 'min', [1.0, 1.0, 1.0]),
([100, 100, 100], 'max', [3.0, 3.0, 3.0]),
([100, 100, 100], 'dense', [1.0, 1.0, 1.0]),
([100, 100, 100], 'ordinal', [1.0, 2.0, 3.0]),
#
([100, 300, 200], 'average', [1.0, 3.0, 2.0]),
([100, 300, 200], 'min', [1.0, 3.0, 2.0]),
([100, 300, 200], 'max', [1.0, 3.0, 2.0]),
([100, 300, 200], 'dense', [1.0, 3.0, 2.0]),
([100, 300, 200], 'ordinal', [1.0, 3.0, 2.0]),
#
([100, 200, 300, 200], 'average', [1.0, 2.5, 4.0, 2.5]),
([100, 200, 300, 200], 'min', [1.0, 2.0, 4.0, 2.0]),
([100, 200, 300, 200], 'max', [1.0, 3.0, 4.0, 3.0]),
([100, 200, 300, 200], 'dense', [1.0, 2.0, 3.0, 2.0]),
([100, 200, 300, 200], 'ordinal', [1.0, 2.0, 4.0, 3.0]),
#
([100, 200, 300, 200, 100], 'average', [1.5, 3.5, 5.0, 3.5, 1.5]),
([100, 200, 300, 200, 100], 'min', [1.0, 3.0, 5.0, 3.0, 1.0]),
([100, 200, 300, 200, 100], 'max', [2.0, 4.0, 5.0, 4.0, 2.0]),
([100, 200, 300, 200, 100], 'dense', [1.0, 2.0, 3.0, 2.0, 1.0]),
([100, 200, 300, 200, 100], 'ordinal', [1.0, 3.0, 5.0, 4.0, 2.0]),
#
([10] * 30, 'ordinal', np.arange(1.0, 31.0)),
)
def test_cases():
for values, method, expected in _cases:
r = rankdata(values, method=method)
assert_array_equal(r, expected)
|