Eric Coissac
89ea077456
Introduces a complete query benchmark track to evaluate performance and verify consistency between dense and sparse index formats. Adds scripts to simulate fixed-size paired-end reads, pack a sparse presence index, execute queries in both modes, and capture wall time and RSS metrics. Includes a verification step that compares outputs by read ID to ensure content identity across parallel processing. Updates build configuration, documentation, and ignore patterns to support the new pipeline for two microbial specimens.
60 lines
2.4 KiB
Bash
Executable File
60 lines
2.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Usage: aggregate_stats.sh TYPE
|
|
# TYPE = indexing_presence | indexing_count | verify_presence | verify_count
|
|
#
|
|
# Reads all stats/TYPE/*.stats files (one CSV data row each, no header).
|
|
# Creates a new stats/TYPE/run_NNN.csv only if any .stats file is newer than
|
|
# the most recent run CSV (idempotent when nothing changed).
|
|
set -euo pipefail
|
|
|
|
TYPE="$1"
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
STATS_DIR="${SCRIPT_DIR}/stats/${TYPE}"
|
|
|
|
case "${TYPE}" in
|
|
indexing_presence|indexing_count)
|
|
HEADER="run,species,strain,scatter_wall_s,scatter_rss_b,dereplicate_wall_s,dereplicate_rss_b,count_kmer_wall_s,count_kmer_rss_b,index_wall_s,index_rss_b,total_wall_s,total_rss_b"
|
|
;;
|
|
verify_presence)
|
|
HEADER="run,species,strain,ref_kmers,idx_kmers,false_neg,false_pos,fn_pct,fp_pct"
|
|
;;
|
|
verify_count)
|
|
HEADER="run,species,strain,ref_kmers,idx_kmers,false_neg,false_pos,count_mismatch,fn_pct,fp_pct,cm_pct"
|
|
;;
|
|
specific_kmer_presence|specific_kmer_count)
|
|
HEADER="run,species,rebuild_wall_s,rebuild_rss_b,pack_wall_s,pack_rss_b,filter_total_wall_s,filter_total_rss_b,select_wall_s,select_rss_b,select_total_wall_s,select_total_rss_b"
|
|
;;
|
|
query_dense|query_sparse)
|
|
HEADER="run,species,strain,query_wall_s,query_rss_b,total_wall_s,total_rss_b"
|
|
;;
|
|
verify_query)
|
|
HEADER="run,species,strain,n_reads,n_common,missing_in_dense,missing_in_sparse,mismatched,mismatch_pct"
|
|
;;
|
|
*)
|
|
echo "ERROR: unknown stats type '${TYPE}'" >&2
|
|
exit 1
|
|
;;
|
|
esac
|
|
|
|
# Find most recent existing run CSV (empty string if none).
|
|
latest_csv=$(find "${STATS_DIR}" -maxdepth 1 -name 'run_*.csv' 2>/dev/null | sort | tail -1)
|
|
|
|
# Check if any .stats file is newer than the latest run CSV.
|
|
if [[ -n "${latest_csv}" ]] && \
|
|
[[ -z "$(find "${STATS_DIR}" -maxdepth 1 -name '*.stats' -newer "${latest_csv}" 2>/dev/null)" ]]; then
|
|
echo "[${TYPE}] stats up to date (${latest_csv})"
|
|
exit 0
|
|
fi
|
|
|
|
run_n=$(printf '%03d' "$(find "${STATS_DIR}" -maxdepth 1 -name 'run_*.csv' 2>/dev/null | wc -l | tr -d ' ')")
|
|
CSV="${STATS_DIR}/run_${run_n}.csv"
|
|
|
|
echo "${HEADER}" >"${CSV}"
|
|
|
|
# Sort .stats files by name for reproducible row order.
|
|
while IFS= read -r stats_file; do
|
|
sed "s/^/${run_n},/" "${stats_file}"
|
|
done < <(find "${STATS_DIR}" -maxdepth 1 -name '*.stats' | sort) >>"${CSV}"
|
|
|
|
echo "[${TYPE}] run ${run_n} → ${CSV}"
|