inst/doc/getting-started-bigannoy.R

In bigANNOY: Approximate k-Nearest Neighbour Search for 'bigmemory' Matrices with Annoy

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

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

library(bigANNOY)
library(bigmemory)

ref_dense <- matrix(
  c(
    0.0, 0.1, 0.2, 0.3,
    0.1, 0.0, 0.1, 0.2,
    0.2, 0.1, 0.0, 0.1,
    1.0, 1.1, 1.2, 1.3,
    1.1, 1.0, 1.1, 1.2,
    1.2, 1.1, 1.0, 1.1,
    3.0, 3.1, 3.2, 3.3,
    3.1, 3.0, 3.1, 3.2
  ),
  ncol = 4,
  byrow = TRUE
)

ref_big <- as.big.matrix(ref_dense)
dim(ref_big)

index_path <- tempfile(fileext = ".ann")

index <- annoy_build_bigmatrix(
  ref_big,
  path = index_path,
  n_trees = 20L,
  metric = "euclidean",
  seed = 123L,
  load_mode = "lazy"
)

index

annoy_is_loaded(index)

self_result <- annoy_search_bigmatrix(
  index,
  k = 2L,
  search_k = 100L
)

self_result$index
round(self_result$distance, 3)

annoy_is_loaded(index)

str(self_result, max.level = 1)

query_dense <- matrix(
  c(
    0.05, 0.05, 0.15, 0.25,
    1.05, 1.05, 1.10, 1.25,
    3.05, 3.05, 3.15, 3.25
  ),
  ncol = 4,
  byrow = TRUE
)

query_result <- annoy_search_bigmatrix(
  index,
  query = query_dense,
  k = 3L,
  search_k = 100L
)

query_result$index
round(query_result$distance, 3)

index_out <- big.matrix(nrow(query_dense), 2L, type = "integer")
distance_out <- big.matrix(nrow(query_dense), 2L, type = "double")

streamed <- annoy_search_bigmatrix(
  index,
  query = query_dense,
  k = 2L,
  xpIndex = index_out,
  xpDistance = distance_out
)

bigmemory::as.matrix(index_out)
round(bigmemory::as.matrix(distance_out), 3)

annoy_close_index(index)
annoy_is_loaded(index)

reopened <- annoy_open_index(index$path, load_mode = "eager")
annoy_is_loaded(reopened)

validation <- annoy_validate_index(reopened, strict = TRUE, load = TRUE)

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