def genotypearray_df():
DATA_DIR = Path(__file__).parent.parent / "data" / "plink"
input = DATA_DIR / "plink_test_small"
df = io.from_plink(input, max_variants=20, swap_alleles=True)
df["num"] = [1.0 for n in range(len(df))]
df["bool"] = [True if n % 3 == 0 else False for n in range(len(df))]
return df
def test_round_trip_sim(tmp_path):
"""Simulate data, save it, and load it again"""
d = tmp_path / "test"
d.mkdir()
output = str(d / "test")
data = sim.BAMS().generate_case_control()
original = data.copy()
io.to_plink(
data,
output,
phenotype_name="Outcome",
phenotype_case="Case",
phenotype_control="Control",
)
# Load data and reset index to extract phenotype and get original data format back
loaded_data = (
io.from_plink(output, categorical_phenotype=True)
.reset_index(level=-1)
.reset_index(drop=True)
)
loaded_data.columns = data.columns # Correct column names
assert_frame_equal(
data, loaded_data, check_categorical=False
) # Categorical order may be different
# Ensure there were no side effects
assert_array_equal(
original["SNP1"].array.allele_idxs, data["SNP1"].array.allele_idxs
)
def test_round_trip_real(tmp_path):
"""Load real data, save it, and load it again"""
d = tmp_path / "test"
d.mkdir()
output = str(d / "test")
# Load data
input = DATA_DIR / "plink_test_small"
loaded = io.from_plink(str(input), categorical_phenotype=True, max_variants=100)
# Save data
io.to_plink(loaded, output)
# Reload data
reloaded = io.from_plink(str(output), categorical_phenotype=True)
# Compare
assert_frame_equal(
loaded.reset_index(), reloaded.reset_index(), check_categorical=False
)
def plink_small_20_swap():
input = DATA_DIR / "plink" / "plink_test_small"
result = io.from_plink(input, max_variants=20, swap_alleles=True)
return result
def plink_small_20():
input = DATA_DIR / "plink" / "plink_test_small"
result = io.from_plink(input, max_variants=20)
return result
def test_loaded_medium():
"""Validate the medium dataset"""
input = DATA_DIR / "plink_test_medium"
result = io.from_plink(input)
assert result.shape == (600, 45100)
def test_small():
"""Validate the small dataset"""
input = DATA_DIR / "plink_test_small"
result = io.from_plink(input, categorical_phenotype=True)
assert result.shape == (150, 3020)