randomize samples per run

Author: Zachary Foster

publication/scratch/performance_vs_sample_count/prepare_test_data.R

@@ -1,3 +1,4 @@
 metadata <- read.csv('https://raw.githubusercontent.com/nf-core/test-datasets/refs/heads/pathogensurveillance/samplesheets/klebsiella.csv')
 metadata <- metadata[metadata$sequence_type == "ILLUMINA" & metadata$Organism == "Klebsiella pneumoniae", ]
+metadata <- metadata[sample(nrow(metadata)), ]
 write.csv(metadata, file = 'input_data_subset.csv', row.names = FALSE)

publication/scratch/performance_vs_sample_count/run_test_data.sh

@@ -4,6 +4,9 @@
 SAMPLE_COUNTS=(1 3 5 10 25 50 75 100 150 200)
 OUTPUT_DIR='run_results'
 
+# Create input data (randomizes samples used each time)
+Rscript prepare_test_data.R
+
 # Run pipeline for each sample count
 for NUM in "${SAMPLE_COUNTS[@]}"; do
     echo "=================================================================================================="