Import an experimental file-backed weighted graph — massive_weighted

Imports prefix.indices.u32 and prefix.weights.f32 without copying them. Each row must have k distinct non-self neighbors and float32 weights between 0 and 1. This is a directed, externally supplied graph; import does not construct or verify a symmetric UMAP fuzzy graph.

Usage

massive_weighted_graph(prefix, n_vertices, k, access = c("stream", "mmap"))

Arguments

prefix: Prefix of the existing KNN file pair.
n_vertices: Number of vertices; currently at most 2^31 - 1.
k: Number of non-self neighbors per vertex; at most 65,536.
access: Sequential file reads or memory-mapped access.

Value

A lightweight fastEmbedR_massive_graph descriptor with edge_value = "weight".