Introduces support for batched MPHF lookups, chunked data handling via `SlottedKmers`, and a comprehensive benchmarking suite to measure performance across the indexing and querying pipeline. This includes new layer functionality for batch operations, chunking logic in the query layer, and scripts to measure wall time and resource usage for various commands. Documentation related to specific implementation details has also been cleaned up.
15 lines
755 B
Python
15 lines
755 B
Python
#!/usr/bin/env python3
|
|
"""Usage: summarize_bench.py LABEL [LABEL...] — median wall per step, side by side."""
|
|
import csv, statistics, sys, os
|
|
base = os.path.join(os.path.dirname(os.path.abspath(__file__)), "run", "bench_mphf")
|
|
data = {}
|
|
for lab in sys.argv[1:]:
|
|
for r in csv.DictReader(open(f"{base}/{lab}/results.csv")):
|
|
data.setdefault(r["step"], {}).setdefault(lab, []).append(float(r["wall_s"]))
|
|
print(f"{'step':32}" + "".join(f"{l:>14}" for l in sys.argv[1:]) + (" ratio" if len(sys.argv) > 2 else ""))
|
|
for step, d in data.items():
|
|
med = [statistics.median(d[l]) for l in sys.argv[1:]]
|
|
line = f"{step:32}" + "".join(f"{m:14.2f}" for m in med)
|
|
if len(med) > 1 and med[0]: line += f" {med[-1]/med[0]:.3f}"
|
|
print(line)
|