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
|
from io import StringIO
import pandas as pd
import numpy as np
import pytest
from bioframe.core.construction import from_any
from bioframe.core import construction
def test_add_ucsc_name_column():
df = pd.DataFrame(
{"chrom": [f"chr{i}" for i in range(3)], "start": [1, 2, 3], "end": [4, 5, 6]}
)
pd.testing.assert_series_equal(
construction.add_ucsc_name_column(df)["name"],
pd.Series(
data=["chr0:1-4", "chr1:2-5", "chr2:3-6"], index=[0, 1, 2], name="name"
),
)
def test_any():
### tests copied from old parse_regions
# main functionality: convert to dataframe and create name
df = pd.DataFrame(
{"chrom": [f"chr{i}" for i in range(3)], "start": [1, 2, 3], "end": [4, 5, 6]}
)
parsed = from_any(df)
assert not "name" in parsed.columns
assert parsed.iloc[0]["chrom"] == "chr0"
# re-create dataframe from UCSC name alone
df2 = pd.DataFrame(
{
"regions": construction.add_ucsc_name_column(parsed, name_col="regions")[
"regions"
].values
}
)
assert (
(from_any(df2, name_col="regions")[["chrom", "start", "end"]] == parsed)
.all()
.all()
)
# re-parsing results yields the same
assert (from_any(parsed) == parsed).all().all()
# extra columns don't get overwritten
df["name"] = "test-value"
assert (from_any(df)["name"] == df["name"]).all()
# None or False will be parsed
assert from_any([("chr1", None, 5)], fill_null={"chr1": 10})["start"].values[0] == 0
# pull end from chromsizes
p2 = from_any([("chr1", 5, None)], fill_null={"chr1": 40})
assert list(p2.values[0]) == ["chr1", 5, 40]
# We could keep things as None if chromsizes were not proviced
p3 = from_any(["chr1", "chr2"], fill_null=False)
assert list(p3.values[0]) == ["chr1", None, None]
# parse the strange name
p8 = from_any(["chr1:1,000,000-4M"])
assert list(p8.values[0]) == ["chr1", 1000000, 4000000]
p9 = from_any(["chr1"])
assert list(p9.values[0]) == ["chr1", None, None]
with pytest.raises(ValueError):
from_any([("ch1", 1, 2, "chr1:1-2", "puppies")]) # puppies are not allowed
with pytest.raises(ValueError):
from_any([("chr1", 5, None)], fill_null={"chr2": 40})
# input tuple of tuples
p2 = from_any((("chr1", 5, 10), ("chrX", 10, 20)))
assert list(p2.values[0]) == ["chr1", 5, 10]
# input tuple of lists
p2 = from_any((["chr1", 5, 10], ["chrX", 10, 20]))
assert list(p2.values[0]) == ["chr1", 5, 10]
# input tuple of ucsc strings
p2 = from_any(("chr1:5-10",))
assert list(p2.values[0]) == ["chr1", 5, 10]
# input single tuple
p2 = from_any(("chr1", 5, 10))
assert list(p2.values[0]) == ["chr1", 5, 10]
def test_sanitize_bedframe():
df1 = pd.DataFrame(
[
["chr1", 10, 20],
["chr1", 10, 20],
["chr1", 15, np.nan],
["chr1", pd.NA, 25],
],
columns=["chrom", "start", "end"],
)
# drop rows with null values
sanitized_df1 = pd.DataFrame(
[["chr1", 10, 20], ["chr1", 10, 20]], columns=["chrom", "start", "end"]
)
sanitized_df1 = sanitized_df1.astype(
{"chrom": str, "start": pd.Int64Dtype(), "end": pd.Int64Dtype()}
)
pd.testing.assert_frame_equal(
sanitized_df1, construction.sanitize_bedframe(df1, drop_null=True)
)
# keep rows with null, but recast
sanitized_df1 = pd.DataFrame(
[
["chr1", 10, 20],
["chr1", 10, 20],
[pd.NA, pd.NA, pd.NA],
[pd.NA, pd.NA, pd.NA],
],
columns=["chrom", "start", "end"],
)
sanitized_df1 = sanitized_df1.astype(
{"chrom": object, "start": pd.Int64Dtype(), "end": pd.Int64Dtype()}
)
pd.testing.assert_frame_equal(
sanitized_df1.fillna(-1), construction.sanitize_bedframe(df1).fillna(-1)
)
# flip intervals as well as drop NA
df1 = pd.DataFrame(
[
["chr1", 20, 10],
["chr1", pd.NA, 25],
],
columns=["chrom", "start", "end"],
)
sanitized_df1 = pd.DataFrame([["chr1", 10, 20]], columns=["chrom", "start", "end"])
sanitized_df1 = sanitized_df1.astype(
{"chrom": str, "start": pd.Int64Dtype(), "end": pd.Int64Dtype()}
)
pd.testing.assert_frame_equal(
sanitized_df1,
construction.sanitize_bedframe(
df1, start_exceed_end_action="fLiP", drop_null=True
),
)
# flip intervals as well as drop NA
df1 = pd.DataFrame(
[
["chr1", 20, 10],
["chr1", pd.NA, 25],
],
columns=["chrom", "start", "end"],
)
sanitized_df1 = pd.DataFrame([["chr1", 10, 20]], columns=["chrom", "start", "end"])
sanitized_df1 = sanitized_df1.astype(
{"chrom": str, "start": pd.Int64Dtype(), "end": pd.Int64Dtype()}
)
assert construction.sanitize_bedframe(
df1, start_exceed_end_action="drop", drop_null=True
).empty
def test_make_viewframe():
# test dict input
view_df = pd.DataFrame(
[
["chrTESTX", 0, 10, "chrTESTX:0-10"],
["chrTESTX_p", 0, 12, "chrTESTX_p:0-12"],
],
columns=["chrom", "start", "end", "name"],
)
pd.testing.assert_frame_equal(
view_df.copy(),
construction.make_viewframe(
{"chrTESTX": 10, "chrTESTX_p": 12}, name_style="ucsc"
),
)
# test list input
region_list = [("chrTESTX", 0, 10), ("chrTESTX_p", 0, 12)]
pd.testing.assert_frame_equal(
view_df.copy(),
construction.make_viewframe(region_list, name_style="ucsc"),
)
# test pd.Series input
chromsizes = pd.Series(data=[5, 8], index=["chrTESTXq", "chrTEST_2p"])
d = """ chrom start end name
0 chrTESTXq 0 5 chrTESTXq
1 chrTEST_2p 0 8 chrTEST_2p"""
view_df = pd.read_csv(StringIO(d), sep=r"\s+")
pd.testing.assert_frame_equal(
view_df.copy(), construction.make_viewframe(chromsizes, name_style=None)
)
d = """ chrom start end name
0 chrTESTXq 0 5 chrTESTXq:0-5
1 chrTEST_2p 0 8 chrTEST_2p:0-8"""
view_df = pd.read_csv(StringIO(d), sep=r"\s+")
pd.testing.assert_frame_equal(
view_df.copy(),
construction.make_viewframe(chromsizes, name_style="UCSC"),
)
# test pd.DataFrame input
pd.testing.assert_frame_equal(view_df.copy(), construction.make_viewframe(view_df))
# if you provide unique names, this is accepted unchanged by make_viewframe
view_df = pd.DataFrame(
[["chrTESTX", 0, 10, "chrTEST_1"], ["chrTESTY", 0, 12, "chrTEST_2"]],
columns=["chrom", "start", "end", "name"],
)
region_list = [("chrTESTX", 0, 10, "chrTEST_1"), ("chrTESTY", 0, 12, "chrTEST_2")]
pd.testing.assert_frame_equal(
view_df.copy(), construction.make_viewframe(region_list)
)
pd.testing.assert_frame_equal(view_df.copy(), construction.make_viewframe(view_df))
pd.testing.assert_frame_equal(
view_df.copy(),
construction.make_viewframe(
view_df, check_bounds={"chrTESTX": 11, "chrTESTY": 13}
),
)
with pytest.raises(ValueError):
construction.make_viewframe(
view_df, check_bounds={"chrTESTX": 9, "chrTESTY": 13}
)
|
