diff options
| -rw-r--r-- | r_qtl/r_qtl2.py | 24 | ||||
| -rw-r--r-- | tests/r_qtl/test_files/test_geno.zip | bin | 0 -> 648 bytes | |||
| -rw-r--r-- | tests/r_qtl/test_files/test_geno_transposed.zip | bin | 0 -> 702 bytes | |||
| -rw-r--r-- | tests/r_qtl/test_r_qtl2_geno.py | 182 | ||||
| -rw-r--r-- | tests/r_qtl/test_r_qtl2_gmap.py (renamed from tests/r_qtl/test_r_qtl2.py) | 2 |
5 files changed, 196 insertions, 12 deletions
diff --git a/r_qtl/r_qtl2.py b/r_qtl/r_qtl2.py index a221f26..e019d99 100644 --- a/r_qtl/r_qtl2.py +++ b/r_qtl/r_qtl2.py @@ -50,17 +50,19 @@ def genotype_data(zfile: ZipFile, cdata: dict) -> Iterator[dict]: reader = csv.DictReader(filter(lambda line: not line.startswith("#"), io.TextIOWrapper(genofile)), delimiter=cdata.get("sep", ",")) - for row in reader: - yield { - key: thread_op( - value, - # replace genotype codes - lambda val: cdata["genotypes"].get(val, val), - # replace N/A strings - lambda val: (None if val in cdata["na.strings"] else val)) - for key,value - in row.items() - } + if not cdata.get("geno_transposed", False): + for row in reader: + yield { + key: thread_op( + value, + # replace genotype codes + lambda val: cdata["genotypes"].get(val, val), + # replace N/A strings + lambda val: ( + None if val in cdata["na.strings"] else val)) + for key,value + in row.items() + } def map_data(zfile: ZipFile, map_type: str, cdata: dict) -> dict: """Read gmap files to get the genome mapping data""" diff --git a/tests/r_qtl/test_files/test_geno.zip b/tests/r_qtl/test_files/test_geno.zip new file mode 100644 index 0000000..9cac5f9 --- /dev/null +++ b/tests/r_qtl/test_files/test_geno.zip Binary files differdiff --git a/tests/r_qtl/test_files/test_geno_transposed.zip b/tests/r_qtl/test_files/test_geno_transposed.zip new file mode 100644 index 0000000..6ce50f8 --- /dev/null +++ b/tests/r_qtl/test_files/test_geno_transposed.zip Binary files differdiff --git a/tests/r_qtl/test_r_qtl2_geno.py b/tests/r_qtl/test_r_qtl2_geno.py new file mode 100644 index 0000000..5ebb5a9 --- /dev/null +++ b/tests/r_qtl/test_r_qtl2_geno.py @@ -0,0 +1,182 @@ +"""Test the parsing of the R/qtl2 geno files.""" +from pathlib import Path + +import pytest +from zipfile import ZipFile + +from r_qtl import r_qtl2 as rqtl2 + +@pytest.mark.unit_test +@pytest.mark.parametrize( + "relpath,expected", + ( + ("tests/r_qtl/test_files/test_geno.zip", + ({ + "id": "1", + "PVV4": 1, + "AXR-1": 1, + "HH.335C-Col/PhyA": 1, + "EC.480C": 1, + "EC.66C": 1 + }, + { + "id": "2", + "PVV4": 1, + "AXR-1": 1, + "HH.335C-Col/PhyA": 1, + "EC.480C": 1, + "EC.66C": 1 + }, + { + "id": "3", + "PVV4": 2, + "AXR-1": 2, + "HH.335C-Col/PhyA": None, + "EC.480C": 1, + "EC.66C": 1 + }, + { + "id": "4", + "PVV4": 1, + "AXR-1": 1, + "HH.335C-Col/PhyA": 1, + "EC.480C": 1, + "EC.66C": 1 + }, + { + "id": "5", + "PVV4": 2, + "AXR-1": 2, + "HH.335C-Col/PhyA": 2, + "EC.480C": 2, + "EC.66C": 2 + }, + { + "id": "6", + "PVV4": 2, + "AXR-1": 2, + "HH.335C-Col/PhyA": 2, + "EC.480C": 2, + "EC.66C": 2 + }, + { + "id": "7", + "PVV4": 1, + "AXR-1": 1, + "HH.335C-Col/PhyA": 1, + "EC.480C": 1, + "EC.66C": 1 + }, + { + "id": "8", + "PVV4": 2, + "AXR-1": 2, + "HH.335C-Col/PhyA": 2, + "EC.480C": 1, + "EC.66C": 1 + }, + { + "id": "9", + "PVV4": None, + "AXR-1": 2, + "HH.335C-Col/PhyA": 2, + "EC.480C": 2, + "EC.66C": 2 + }, + { + "id": "10", + "PVV4": 2, + "AXR-1": 2, + "HH.335C-Col/PhyA": 2, + "EC.480C": 2, + "EC.66C": 2 + })), + ("tests/r_qtl/test_files/test_geno_transposed.zip", + ({ + "id": "1", + "PVV4": 1, + "AXR-1": 1, + "HH.335C-Col/PhyA": 1, + "EC.480C": 1, + "EC.66C": 1 + }, + { + "id": "2", + "PVV4": 1, + "AXR-1": 1, + "HH.335C-Col/PhyA": 1, + "EC.480C": 1, + "EC.66C": 1 + }, + { + "id": "3", + "PVV4": 2, + "AXR-1": 2, + "HH.335C-Col/PhyA": None, + "EC.480C": 1, + "EC.66C": 1 + }, + { + "id": "4", + "PVV4": 1, + "AXR-1": 1, + "HH.335C-Col/PhyA": 1, + "EC.480C": 1, + "EC.66C": 1 + }, + { + "id": "5", + "PVV4": 2, + "AXR-1": 2, + "HH.335C-Col/PhyA": 2, + "EC.480C": 2, + "EC.66C": 2 + }, + { + "id": "6", + "PVV4": 2, + "AXR-1": 2, + "HH.335C-Col/PhyA": 2, + "EC.480C": 2, + "EC.66C": 2 + }, + { + "id": "7", + "PVV4": 1, + "AXR-1": 1, + "HH.335C-Col/PhyA": 1, + "EC.480C": 1, + "EC.66C": 1 + }, + { + "id": "8", + "PVV4": 2, + "AXR-1": 2, + "HH.335C-Col/PhyA": 2, + "EC.480C": 1, + "EC.66C": 1 + }, + { + "id": "9", + "PVV4": None, + "AXR-1": 2, + "HH.335C-Col/PhyA": 2, + "EC.480C": 2, + "EC.66C": 2 + }, + { + "id": "10", + "PVV4": 2, + "AXR-1": 2, + "HH.335C-Col/PhyA": 2, + "EC.480C": 2, + "EC.66C": 2 + })))) +def test_parse_geno_files(relpath,expected): + """ + GIVEN: Path to a zip file with R/qtl2 data + WHEN: we parse the geno file + THEN: ensure that the data we get is as expected + """ + with ZipFile(Path(relpath).absolute(), "r") as zfile: + assert tuple(rqtl2.genotype_data(zfile, rqtl2.control_data(zfile))) == expected diff --git a/tests/r_qtl/test_r_qtl2.py b/tests/r_qtl/test_r_qtl2_gmap.py index 33ff5e5..64774c2 100644 --- a/tests/r_qtl/test_r_qtl2.py +++ b/tests/r_qtl/test_r_qtl2_gmap.py @@ -1,4 +1,4 @@ -"""Test the parsing of the R/qtl2 data files.""" +"""Test the parsing of the R/qtl2 gmap files.""" from pathlib import Path import pytest |