def test_count(assembly, tmp_path):
out = tmp_path / "kmers.tsv"
size = 5
force = False
df = kmers.count(assembly=assembly, size=size, out=out, force=force)
assert df.shape[1] == 4**size / 2
assert df.index.name == "contig"
assert out.exists()
def test_count_out_exists(assembly, counts, force, tmp_path):
out = tmp_path / "kmers.tsv"
counts.to_csv(out, sep="\t", index=True, header=True)
size = 5
df = kmers.count(assembly=assembly, size=size, out=out, force=force)
assert df.shape[1] == 4**size / 2
assert df.index.name == "contig"
assert out.exists()
def get_kmers(self, num_records: int = 5):
if num_records < 5:
raise ValueError(
f"At least 5 records are required for embedding tests! provided: {num_records}"
)
logger.info("Preparing kmer counts test data...")
# kmer size is 5 (b/c this is the default).
counts = kmers.count(assembly=self.metagenome, size=5)
# subset counts to `num_records`
counts = counts.sample(n=num_records, random_state=42)
# method is am_clr (b/c this is the default).
am_clr_normalized_counts = kmers.normalize(df=counts, method="am_clr")
for df in [counts, am_clr_normalized_counts]:
df.reset_index(inplace=True)
self.data["kmers"] = {
"counts": counts.to_json(),
"am_clr_normalized_counts": am_clr_normalized_counts.to_json(),
}
def test_count_wrong_size(assembly):
size = 5.5
with pytest.raises(TypeError):
kmers.count(assembly=assembly, size=size)