def test_makes_df(self):
from idiva.clf.df import v0_df
from idiva.io import ReadVCF
from idiva.utils import seek_then_rewind
for k in PATHS:
with PATHS[k].open(mode='r') as fd:
assert isinstance(fd, io.TextIOBase)
with seek_then_rewind(fd):
datalines = list(ReadVCF(fd))
with seek_then_rewind(fd):
df = v0_df(ReadVCF(fd))
self.assertEqual(len(datalines), len(df))
def maker_clinvar() -> pd.DataFrame:
"""
creates the clinvar dataframe
"""
from idiva.db import clinvar_open
from idiva.io import ReadVCF
from idiva.db.clinvar import clinvar_to_df
log.info('Making clinvar df.')
with clinvar_open(which=clinvar_file) as fd:
return clinvar_to_df(ReadVCF(fd))
def test_fisher_large_head(self):
from idiva.io import ReadVCF, open_maybe_gz
with open_maybe_gz(PATHS_LARGE_HEAD['case'], mode='r') as case:
with open_maybe_gz(PATHS_LARGE_HEAD['ctrl'], mode='r') as ctrl:
from idiva.stat.vcf_to_fisher import vcf_to_fisher
result = vcf_to_fisher(case=ReadVCF(case), ctrl=ReadVCF(ctrl))
df = result.df
from idiva.utils.testing import whatsmyname
out_dir = MY_SPACE / whatsmyname()
print(df)
def test_join_does_something(self):
from idiva.io import ReadVCF
from idiva.clf.df import v0_df, join
dfs = {}
for k in PATHS:
with PATHS[k].open(mode='r') as fd:
assert isinstance(fd, io.TextIOBase)
dfs[k] = v0_df(ReadVCF(fd))
df = join(case=dfs['case'], ctrl=dfs['ctrl'])
def test_poc_head(self):
"""
Proof-of-concept.
"""
from idiva.io import ReadVCF, open_maybe_gz
for (k, ref_file) in PATHS_LARGE_HEAD.items():
can_file = (MY_SPACE / F"{sys._getframe().f_code.co_name}__{k}").with_suffix(".log")
with open_maybe_gz(ref_file, mode='r') as fd_ref:
assert isinstance(fd_ref, io.TextIOBase)
vcf = ReadVCF(fd_ref).preload_all()
with open(can_file, mode='w') as fd_can:
with redirect_stdout(fd_can):
for (k, v) in vcf.meta.items():
if isinstance(v, str):
if (str(k).lower() == "filedate"):
from idiva.io.out import fileDate
v = fileDate
if (str(k).lower() == "source"):
from idiva.io.out import source
v = source
print(F"##{k}={v}")
elif isinstance(v, dict):
for (i, v) in v.items():
assert isinstance(v, dict)
assert v
p = ','.join(F"{k}={v if v is not None else '.'}" for (k, v) in v.items())
print(F"##{k}=<ID={i},{p}>")
print(F"#{SEP.join(vcf.header)}")
for dataline in vcf:
print(str(dataline))
from idiva.io import Oneliner
with open_maybe_gz(ref_file, mode='r') as fd_ref:
with open_maybe_gz(can_file, mode='r') as fd_can:
assert isinstance(fd_ref, io.TextIOBase)
assert isinstance(fd_can, io.TextIOBase)
lines_ref = list(Oneliner(fd_ref))
lines_can = list(Oneliner(fd_can))
for (ref, can) in zip(lines_ref, lines_can):
if not (ref.startswith("##fileDate") or ref.startswith("##source")):
self.assertEqual(can, ref)
self.assertEqual(len(lines_can), len(lines_ref))
def test_combine(self):
from idiva.io import ReadVCF
from idiva.io.vcf import SEP
from idiva.clf.df import v0_df, join, dtype_v0
dfs = {}
for k in PATHS:
with PATHS[k].open(mode='r') as fd:
assert isinstance(fd, io.TextIOBase)
dfs[k] = v0_df(ReadVCF(fd))
candidate = join(case=dfs['case'], ctrl=dfs['ctrl'])
def read_csv(file) -> pd.DataFrame:
return pd.read_csv(file, sep=SEP).astype(
{
'CHROM': str,
'POS': int,
'ID': str,
'ALT0_case': float, 'ALT1_case': float, 'ALT2_case': float,
'ALT0_ctrl': float, 'ALT1_ctrl': float, 'ALT2_ctrl': float,
}
)
ref_file = MY_SPACE / "reference.txt"
# Hack to create the reference
# candidate.to_csv(ref_file, sep=SEP, index=True)
reference = read_csv(ref_file)
# Write and read `candidate` to make comparable to `reference`
import tempfile
with tempfile.NamedTemporaryFile(mode='w') as tf:
candidate.to_csv(tf, sep=SEP, index=True)
tf.flush()
candidate = read_csv(tf.name)
self.assertTrue(reference.equals(candidate))