def f():
s = SNPs("tests/input/generic.csv")
s.sort_snps()
def test_merging_files_discrepant_snps(self):
df = pd.read_csv(
"tests/input/discrepant_snps.csv",
skiprows=1,
na_values="--",
names=[
"rsid",
"chrom",
"pos_file1",
"pos_file2",
"genotype_file1",
"genotype_file2",
"discrepant_position",
"discrepant_genotype",
"expected_position",
"expected_genotype",
],
index_col=0,
dtype={
"chrom": object,
"pos_file1": np.int64,
"pos_file2": np.int64,
"discrepant_position": bool,
"discrepant_genotype": bool,
},
)
df1 = df[["chrom", "pos_file1", "genotype_file1"]]
df2 = df[["chrom", "pos_file2", "genotype_file2"]]
df1.to_csv(
"tests/input/discrepant_snps1.csv",
na_rep="--",
header=["chromosome", "position", "genotype"],
)
df2.to_csv(
"tests/input/discrepant_snps2.csv",
na_rep="--",
header=["chromosome", "position", "genotype"],
)
sc = SNPsCollection([
"tests/input/discrepant_snps1.csv",
"tests/input/discrepant_snps2.csv"
])
expected = df[[
"chrom",
"discrepant_position",
"discrepant_genotype",
"expected_position",
"expected_genotype",
]]
expected = expected.rename(columns={
"expected_position": "pos",
"expected_genotype": "genotype"
})
expected_snps = SNPs()
expected_snps._snps = expected
expected_snps.sort_snps()
expected = expected_snps.snps
pd.testing.assert_index_equal(
sc.discrepant_positions.index,
expected.loc[expected["discrepant_position"] == True].index,
)
pd.testing.assert_index_equal(
sc.discrepant_genotypes.index,
expected.loc[expected["discrepant_genotype"] == True].index,
)
pd.testing.assert_series_equal(sc.snps["pos"], expected["pos"])
pd.testing.assert_series_equal(sc.snps["genotype"],
expected["genotype"])