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
|
from __future__ import division, print_function, absolute_import
import numpy as np
from numpy.testing import TestCase, run_module_suite, assert_equal, \
assert_array_equal, dec
from scipy.stats import rankdata, tiecorrect
class TestTieCorrect(TestCase):
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(TestCase):
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))
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)
def test_rankdata_object_string(self):
min_rank = lambda a: [1 + sum(i < j for i in a) for j in a]
max_rank = lambda a: [sum(i <= j for i in a) for j in a]
ordinal_rank = lambda a: 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)
_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():
def check_case(values, method, expected):
r = rankdata(values, method=method)
assert_array_equal(r, expected)
for values, method, expected in _cases:
yield check_case, values, method, expected
if __name__ == "__main__":
run_module_suite()
|
