tlevine/filesurvey: Sample statistics about directories of files

Apply sampling methods to a directory files, including cluster sampling, stratified sampling, systematic sampling, and multistage sampling. Run arbitrary statistics with the selected files (perhaps file size, word count, file format) to estimate the population averages. You may specify various approaches to selecting strata; you may use each directory as a stratum, or you may use heuristics based on file names.

install.packages("remotes")
remotes::install_github("tlevine/filesurvey")