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
|
import pytest
from natsort import natsorted
from hypothesis import given, settings, HealthCheck #, assume
from hypothesis import reproduce_failure # pylint: disable=unused-import
import tempfile
import subprocess # nosec
from io import StringIO
import numpy as np
import pandas as pd
from tests.helpers import assert_df_equal
from tests.hypothesis_helper import dfs_min, df_data, selector, dfs_min_with_id, max_examples, deadline
import pyranges as pr
# if environ.get("TRAVIS"):
# max_examples = 100
# deadline = None
# else:
# max_examples = 1000
# deadline = None
merge_command = "bedtools merge -o first,count -c 6,1 {} -i <(sort -k1,1 -k2,2n {})"
@pytest.mark.bedtools
@pytest.mark.parametrize("strand", [True, False])
@settings(
max_examples=max_examples,
deadline=deadline,
suppress_health_check=HealthCheck.all())
@given(gr=dfs_min()) # pylint: disable=no-value-for-parameter
def test_merge(gr, strand):
bedtools_strand = {True: "-s", False: ""}[strand]
print(gr)
with tempfile.TemporaryDirectory() as temp_dir:
f1 = "{}/f1.bed".format(temp_dir)
gr.df.to_csv(f1, sep="\t", header=False, index=False)
cmd = merge_command.format(bedtools_strand, f1)
print(cmd)
# ignoring bandit security warning. All strings created by test suite
result = subprocess.check_output( # nosec
cmd, shell=True, executable="/bin/bash").decode() # nosec
print("result" * 10)
print(result)
if not strand:
print("if not " * 10)
bedtools_df = pd.read_csv(
StringIO(result),
sep="\t",
header=None,
usecols=[0, 1, 2, 4],
names="Chromosome Start End Count".split(),
dtype={"Chromosome": "category"})
else:
bedtools_df = pd.read_csv(
StringIO(result),
sep="\t",
header=None,
names="Chromosome Start End Strand Count".split(),
dtype={"Chromosome": "category"})
print("bedtools_df\n", bedtools_df)
result = gr.merge(strand=strand, count=True)
print("result\n", result.df)
if not bedtools_df.empty:
# need to sort because bedtools sometimes gives the result in non-natsorted chromosome order!
if result.stranded:
assert_df_equal(
result.df.sort_values("Chromosome Start Strand".split()),
bedtools_df.sort_values("Chromosome Start Strand".split()))
else:
assert_df_equal(
result.df.sort_values("Chromosome Start".split()),
bedtools_df.sort_values("Chromosome Start".split()))
else:
assert bedtools_df.empty == result.df.empty
cluster_command = "bedtools cluster {} -i <(sort -k1,1 -k2,2n {})"
@pytest.mark.bedtools
@pytest.mark.parametrize("strand", [True, False])
@settings(
max_examples=max_examples,
deadline=deadline,
suppress_health_check=HealthCheck.all())
@given(gr=dfs_min()) # pylint: disable=no-value-for-parameter
def test_cluster(gr, strand):
bedtools_strand = {True: "-s", False: ""}[strand]
print(gr)
with tempfile.TemporaryDirectory() as temp_dir:
f1 = "{}/f1.bed".format(temp_dir)
gr.df.to_csv(f1, sep="\t", header=False, index=False)
cmd = cluster_command.format(bedtools_strand, f1)
print(cmd)
# ignoring bandit security warning. All strings created by test suite
result = subprocess.check_output( # nosec
cmd, shell=True, executable="/bin/bash").decode() # nosec
bedtools_df = pd.read_csv(
StringIO(result),
sep="\t",
header=None,
names="Chromosome Start End Name Score Strand Cluster".split(),
dtype={"Chromosome": "category"}).squeeze('columns')
print("bedtools_df\n", bedtools_df)
# from pydbg import dbg
# dbg(gr.cluster(strand=strand))
print("gr\n", gr)
result = gr.cluster(strand=strand)
print("result\n", result[["Cluster"]])
print("result\n", result.df)
if not bedtools_df.empty:
# need to sort because bedtools sometimes gives the result in non-natsorted chromosome order!
if result.stranded:
sort_values = "Chromosome Start Strand".split()
else:
sort_values = "Chromosome Start".split()
result_df = result.df.sort_values(sort_values)
bedtools_df = bedtools_df.sort_values(sort_values)
cluster_ids = {
k: v
for k, v in zip(result_df.Cluster.drop_duplicates(),
bedtools_df.Cluster.drop_duplicates())
}
# bedtools gives different cluster ids than pyranges
result_df.Cluster.replace(cluster_ids, inplace=True)
assert_df_equal(result_df, bedtools_df)
else:
assert bedtools_df.empty == result.df.empty
@pytest.mark.parametrize("strand", [True, False])
@settings(
max_examples=max_examples,
deadline=deadline,
suppress_health_check=HealthCheck.all())
@given(gr=dfs_min_with_id()) # pylint: disable=no-value-for-parameter
def test_cluster_by(gr, strand):
result = gr.cluster(by="ID", strand=strand).df
print(result)
df = gr.df
if strand:
groupby = ["Chromosome", "Strand", "ID"]
else:
groupby = ["Chromosome", "ID"]
grs = []
for _, gdf in natsorted(df.groupby(groupby)):
grs.append(pr.PyRanges(gdf))
clusters = [gr.cluster(strand=strand) for gr in grs]
i = 1
new_clusters = []
for c in clusters:
print("c")
print(c)
c.Cluster = i
i += 1
new_clusters.append(c)
expected = pr.concat(new_clusters).df
expected.Cluster = expected.Cluster.astype(np.int32)
# expected = expected.drop_duplicates()
print(expected)
print(result)
assert_df_equal(result, expected)
@pytest.mark.parametrize("strand", [True, False])
@settings(
max_examples=max_examples,
deadline=deadline,
suppress_health_check=HealthCheck.all())
@given(gr=dfs_min_with_id()) # pylint: disable=no-value-for-parameter
def test_merge_by(gr, strand):
print(gr)
result = gr.merge(by="ID").df.drop("ID", axis=1)
df = gr.df
grs = []
for _, gdf in df.groupby("ID"):
grs.append(pr.PyRanges(gdf))
expected = pr.concat([gr.merge() for gr in grs]).df
print(expected)
print(result)
assert_df_equal(result, expected)
makewindows_command = "bedtools makewindows -w 10 -b <(sort -k1,1 -k2,2n {})"
@pytest.mark.bedtools
@settings(
max_examples=max_examples,
print_blob=True,
deadline=deadline,
suppress_health_check=HealthCheck.all())
@given(gr=dfs_min()) # pylint: disable=no-value-for-parameter
# @reproduce_failure('5.5.4', b'AXicY2RgYGAEIzgAsRkBAFsABg==')
def test_windows(gr):
with tempfile.TemporaryDirectory() as temp_dir:
f1 = "{}/f1.bed".format(temp_dir)
gr.df.to_csv(f1, sep="\t", header=False, index=False)
cmd = makewindows_command.format(f1)
print(cmd)
# ignoring bandit security warning. All strings created by test suite
result = subprocess.check_output( # nosec
cmd, shell=True, executable="/bin/bash").decode() # nosec
bedtools_df = pd.read_csv(
StringIO(result),
sep="\t",
header=None,
names="Chromosome Start End".split(),
dtype={"Chromosome": "category"}).squeeze('columns')
print("bedtools_df\n", bedtools_df)
result = gr.window(10)["Chromosome Start End".split()].unstrand()
print("result\n", result.df)
if not bedtools_df.empty:
assert_df_equal(result.df, bedtools_df)
else:
assert bedtools_df.empty == result.df.empty
@pytest.mark.parametrize("strand", [True, False])
@settings(
max_examples=max_examples,
deadline=deadline,
suppress_health_check=HealthCheck.all())
@given(gr=df_data()) # pylint: disable=no-value-for-parameter
def test_init(gr, strand):
c, s, e, strands = gr
if strand:
pr.PyRanges(chromosomes=c, starts=s, ends=e, strands=strands)
else:
pr.PyRanges(chromosomes=c, starts=s, ends=e)
chipseq = pr.data.chipseq()
@settings(
max_examples=max_examples,
deadline=deadline,
suppress_health_check=[HealthCheck.return_value])
@given(selector=selector()) # pylint: disable=no-value-for-parameter
def test_getitem(selector):
# have these weird returns to avoid being flagged as unused code
if len(selector) == 3:
a, b, c = selector
return chipseq[a, b, c]
elif len(selector) == 2:
a, b = selector
return chipseq[a, b]
elif len(selector) == 1:
a = selector[0]
return chipseq[a]
elif len(selector) == 0:
pass
else:
raise Exception("Should never happen")
@pytest.mark.bedtools
@settings(
max_examples=max_examples,
deadline=deadline,
print_blob=True,
suppress_health_check=HealthCheck.all())
@given(gr=dfs_min()) # pylint: disable=no-value-for-parameter
def test_summary(gr):
print(gr.to_example())
# merely testing that it does not error
# contents are just (pandas) dataframe.describe()
gr.summary()
|
