aboutsummaryrefslogtreecommitdiff
path: root/gn3/computations/parsers.py
diff options
context:
space:
mode:
authorFrederick Muriuki Muriithi2021-09-27 04:48:53 +0300
committerFrederick Muriuki Muriithi2021-09-27 04:48:53 +0300
commit19783a18c2bc7941fc5980e593f19fb1d18c3623 (patch)
treef3a6e241be3c6224b9647c8258c516a7b741a28c /gn3/computations/parsers.py
parent8d9bc0f29ce9208306915b079818e6f0c31785e2 (diff)
downloadgenenetwork3-19783a18c2bc7941fc5980e593f19fb1d18c3623.tar.gz
Update terminology: `strain` to `sample`
Issue: https://github.com/genenetwork/gn-gemtext-threads/blob/main/topics/gn1-migration-to-gn2/clustering.gmi * Update the terminology used: use `sample` in place of `strain` according to Zachary's direction at https://github.com/genenetwork/genenetwork3/pull/37#issuecomment-926043306
Diffstat (limited to 'gn3/computations/parsers.py')
-rw-r--r--gn3/computations/parsers.py10
1 files changed, 5 insertions, 5 deletions
diff --git a/gn3/computations/parsers.py b/gn3/computations/parsers.py
index 94387ff..1af35d6 100644
--- a/gn3/computations/parsers.py
+++ b/gn3/computations/parsers.py
@@ -14,7 +14,7 @@ def parse_genofile(file_path: str) -> Tuple[List[str],
'h': 0,
'u': None,
}
- genotypes, strains = [], []
+ genotypes, samples = [], []
with open(file_path, "r") as _genofile:
for line in _genofile:
line = line.strip()
@@ -22,8 +22,8 @@ def parse_genofile(file_path: str) -> Tuple[List[str],
continue
cells = line.split()
if line.startswith("Chr"):
- strains = cells[4:]
- strains = [strain.lower() for strain in strains]
+ samples = cells[4:]
+ samples = [sample.lower() for sample in samples]
continue
values = [__map.get(value.lower(), None) for value in cells[4:]]
genotype = {
@@ -32,7 +32,7 @@ def parse_genofile(file_path: str) -> Tuple[List[str],
"cm": cells[2],
"mb": cells[3],
"values": values,
- "dicvalues": dict(zip(strains, values)),
+ "dicvalues": dict(zip(samples, values)),
}
genotypes.append(genotype)
- return strains, genotypes
+ return samples, genotypes