knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

options(bigANNOY.progress = FALSE)
set.seed(20260326)

library(bigANNOY)

bench_dir <- tempfile("bigannoy-benchmark-")
dir.create(bench_dir, recursive = TRUE, showWarnings = FALSE)
bench_dir

single_csv <- file.path(bench_dir, "single.csv")

single <- benchmark_annoy_bigmatrix(
  n_ref = 200L,
  n_query = 20L,
  n_dim = 6L,
  k = 3L,
  n_trees = 10L,
  search_k = 50L,
  exact = FALSE,
  path_dir = bench_dir,
  output_path = single_csv,
  load_mode = "eager"
)

single$summary

names(single)
single$params
single$exact_available

single$validation$valid
single$validation$checks[, c("check", "passed", "severity")]

read.csv(single_csv, stringsAsFactors = FALSE)

external_run <- benchmark_annoy_bigmatrix(
  n_ref = 120L,
  n_query = 12L,
  n_dim = 5L,
  k = 3L,
  n_trees = 8L,
  exact = FALSE,
  path_dir = bench_dir
)

self_run <- benchmark_annoy_bigmatrix(
  n_ref = 120L,
  query = NULL,
  n_dim = 5L,
  k = 3L,
  n_trees = 8L,
  exact = FALSE,
  path_dir = bench_dir
)

shape_cols <- c("self_search", "n_ref", "n_query", "k")

rbind(
  external = external_run[["summary"]][, shape_cols],
  self = self_run[["summary"]][, shape_cols]
)

suite_csv <- file.path(bench_dir, "suite.csv")

suite <- benchmark_annoy_recall_suite(
  n_ref = 200L,
  n_query = 20L,
  n_dim = 6L,
  k = 3L,
  n_trees = c(5L, 10L),
  search_k = c(-1L, 50L),
  exact = FALSE,
  path_dir = bench_dir,
  output_path = suite_csv,
  load_mode = "eager"
)

suite$summary

read.csv(suite_csv, stringsAsFactors = FALSE)

if (length(find.package("bigKNN", quiet = TRUE)) > 0L) {
  exact_run <- benchmark_annoy_bigmatrix(
    n_ref = 150L,
    n_query = 15L,
    n_dim = 5L,
    k = 3L,
    n_trees = 10L,
    search_k = 50L,
    metric = "euclidean",
    exact = TRUE,
    path_dir = bench_dir
  )

  exact_run$exact_available
  exact_run$summary[, c("build_elapsed", "search_elapsed", "exact_elapsed", "recall_at_k")]
} else {
  "Exact baseline example skipped because bigKNN is not installed."
}

ref <- matrix(rnorm(80 * 4), nrow = 80, ncol = 4)
query <- matrix(rnorm(12 * 4), nrow = 12, ncol = 4)

user_run <- benchmark_annoy_bigmatrix(
  x = ref,
  query = query,
  k = 3L,
  n_trees = 12L,
  search_k = 40L,
  exact = FALSE,
  filebacked = TRUE,
  path_dir = bench_dir,
  load_mode = "eager"
)

user_run$summary[, c(
  "filebacked",
  "self_search",
  "n_ref",
  "n_query",
  "n_dim",
  "build_elapsed",
  "search_elapsed"
)]

compare_csv <- file.path(bench_dir, "compare.csv")

compare_run <- benchmark_annoy_vs_rcppannoy(
  n_ref = 200L,
  n_query = 20L,
  n_dim = 6L,
  k = 3L,
  n_trees = 10L,
  search_k = 50L,
  exact = FALSE,
  path_dir = bench_dir,
  output_path = compare_csv,
  load_mode = "eager"
)

compare_run$summary[, c(
  "implementation",
  "reference_storage",
  "n_ref",
  "n_query",
  "n_dim",
  "total_data_bytes",
  "index_bytes",
  "build_elapsed",
  "search_elapsed"
)]

read.csv(compare_csv, stringsAsFactors = FALSE)[, c(
  "implementation",
  "ref_bytes",
  "query_bytes",
  "index_bytes",
  "metadata_bytes",
  "artifact_bytes"
)]

volume_csv <- file.path(bench_dir, "volume.csv")

volume_run <- benchmark_annoy_volume_suite(
  n_ref = c(200L, 500L),
  n_query = 20L,
  n_dim = c(6L, 12L),
  k = 3L,
  n_trees = 10L,
  search_k = 50L,
  exact = FALSE,
  path_dir = bench_dir,
  output_path = volume_csv,
  load_mode = "eager"
)

volume_run$summary[, c(
  "implementation",
  "n_ref",
  "n_dim",
  "total_data_bytes",
  "index_bytes",
  "build_elapsed",
  "search_elapsed"
)]

system.file("benchmarks", "benchmark_annoy.R", package = "bigANNOY")