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
|
import pytest
import pyranges as pr
import numpy as np
import pandas as pd
from io import StringIO
def string_to_df(c):
return pd.read_csv(StringIO(c), sep=r"\s+", dtype={"Chromosome": "category", "Start": np.int32, "End": np.int32, "Start_b": np.int32, "End_b": np.int32})
@pytest.fixture
def gr():
return pr.PyRanges(chromosomes="chr1", starts=[1, 15, 200], ends=[10, 20, 2000])
@pytest.fixture
def gr2():
return pr.PyRanges(chromosomes="chr1", starts=[11, 11, 20, 20, 50], ends=[16, 20, 21, 22, 100])
@pytest.fixture
def result_k_nearest_different():
c = """Chromosome Start End Start_b End_b Distance
chr1 1 10 11 16 2
chr1 1 10 11 20 2
chr1 1 10 20 21 11
chr1 1 10 20 22 11
chr1 1 10 50 100 41
chr1 15 20 11 20 0
chr1 15 20 11 16 0
chr1 15 20 20 21 1
chr1 15 20 20 22 1
chr1 200 2000 50 100 -101"""
df = string_to_df(c)
return df
@pytest.fixture
def result_k_nearest_different2():
c = """Chromosome Start End Start_b End_b Distance
0 chr1 11 16 15 20 0
1 chr1 11 20 15 20 0
2 chr1 11 20 1 10 -2
3 chr1 20 21 15 20 1
4 chr1 20 21 1 10 -11
5 chr1 20 21 200 2000 180
6 chr1 20 22 15 20 1
7 chr1 20 22 1 10 -11
8 chr1 20 22 200 2000 179
9 chr1 50 100 15 20 -31
10 chr1 50 100 1 10 -41"""
df = string_to_df(c)
return df
def test_k_nearest_different(result_k_nearest_different, result_k_nearest_different2, gr, gr2):
k = [3, 2, 1]
r = gr.k_nearest(gr2, ties="different", k=k).df
print(r)
print(result_k_nearest_different)
pd.testing.assert_frame_equal(r, result_k_nearest_different)
ks = [1, 2, 3, 4, 2]
r2 = gr2.k_nearest(gr, ties="different", k=ks).df
# gr2.k = ks
print(gr2)
print(gr)
print("actual")
print(r2)
print("expected")
print(result_k_nearest_different2)
pd.testing.assert_frame_equal(r2, result_k_nearest_different2)
@pytest.fixture
def result_k_nearest_first():
c = """Chromosome Start End Start_b End_b Distance
0 chr1 1 10 11 16 2
1 chr1 1 10 20 21 11
2 chr1 1 10 50 100 41
3 chr1 15 20 11 20 0
4 chr1 15 20 20 21 1
5 chr1 200 2000 50 100 -101"""
df = string_to_df(c)
return df
@pytest.fixture
def result_k_nearest_first2():
c = """Chromosome Start End Start_b End_b Distance
0 chr1 11 16 15 20 0
1 chr1 11 20 15 20 0
2 chr1 11 20 1 10 -2
3 chr1 20 21 15 20 1
4 chr1 20 21 1 10 -11
5 chr1 20 21 200 2000 180
6 chr1 20 22 15 20 1
7 chr1 20 22 1 10 -11
8 chr1 20 22 200 2000 179
9 chr1 50 100 15 20 -31
10 chr1 50 100 1 10 -41
11 chr1 50 100 200 2000 101"""
df = string_to_df(c)
return df
def test_k_nearest_first(result_k_nearest_first, result_k_nearest_first2, gr, gr2): # result_k_nearest_first,
print(gr)
print(gr2)
k = [3, 2, 1]
r = gr.k_nearest(gr2, ties="first", k=k).df
# print(r)
# print(result_k_nearest_first)
# assert 0
pd.testing.assert_frame_equal(r, result_k_nearest_first)
r2 = gr2.k_nearest(gr, ties="first", k=list(range(1, 5 + 1))).df
# print(r2)
# print(result_k_nearest_first2)
# raise
pd.testing.assert_frame_equal(r2, result_k_nearest_first2)
@pytest.fixture
def result_k_nearest_last():
c = """Chromosome Start End Start_b End_b Distance
0 chr1 1 10 11 20 2
1 chr1 1 10 20 22 11
2 chr1 1 10 50 100 41
3 chr1 15 20 11 20 0
4 chr1 15 20 20 22 1
5 chr1 200 2000 50 100 -101"""
df = string_to_df(c)
return df
@pytest.fixture
def result_k_nearest_last2():
c = """Chromosome Start End Start_b End_b Distance
0 chr1 11 16 15 20 0
1 chr1 11 20 15 20 0
2 chr1 11 20 1 10 -2
3 chr1 20 21 15 20 1
4 chr1 20 21 1 10 -11
5 chr1 20 21 200 2000 180
6 chr1 20 22 15 20 1
7 chr1 20 22 1 10 -11
8 chr1 20 22 200 2000 179
9 chr1 50 100 15 20 -31
10 chr1 50 100 1 10 -41
11 chr1 50 100 200 2000 101"""
df = string_to_df(c)
return df
def test_k_nearest_last(result_k_nearest_last, result_k_nearest_last2, gr, gr2): # result_k_nearest_last,
# print(gr)
# print(gr2)
k = [3, 2, 1]
r = gr.k_nearest(gr2, ties="last", k=k).df
print(gr)
print(gr2)
print(r)
print(result_k_nearest_last)
pd.testing.assert_frame_equal(r, result_k_nearest_last)
r2 = gr2.k_nearest(gr, ties="last", k=[1, 2, 3, 4, 5]).df
# print("results")
print(gr2)
print(gr)
print(r2)
print(result_k_nearest_last2)
pd.testing.assert_frame_equal(r2, result_k_nearest_last2)
# assert 0
|
