uci-ml-to-r/readme-make.Rmd

63 lines
1.6 KiB
Plaintext
Raw Normal View History

---
title: "UCI Machine Learning datasets for R"
author: "Andrzej Wójtowicz"
output:
html_document:
keep_md: yes
number_sections: yes
toc: yes
---
```{r global-options, include=FALSE}
knitr::opts_chunk$set(comment="", echo=FALSE,
warning=FALSE, message=FALSE)
source('config.R')
```
Document generation date: `r Sys.time()`.
```{r show-datasets, results='asis'}
library(yaml)
for (dir.name in dir(PATH_DATASETS))
{
config.yaml.file.path = paste0(PATH_DATASETS, dir.name, "/", FILE_CONFIG_YAML)
config.yaml = yaml.load_file(config.yaml.file.path)
cat(paste("#", config.yaml$name, "\n\n"))
cat(paste("**Local directory**:", dir.name, "\n\n"))
cat(paste0("**Details**: [link](", config.yaml$info, ")\n\n"))
cat(paste("**Files**:\n\n"))
for (file.url in config.yaml$urls)
{
cat(paste0("* [", URLdecode(basename(file.url)), "](", file.url, ")\n"))
}
cat("\n")
cat(paste0("**Cite**:\n```nohighlight\n", config.yaml$cite, "\n```\n\n"))
cat(paste("**Dataset**:\n\n"))
preprocessed.dir = gsub("\\*", dir.name, PATH_DATASET_PREPROCESSED)
preprocessed.file.path = paste0(preprocessed.dir, FILE_PREPROCESSED_OUTPUT)
dataset = readRDS(preprocessed.file.path)
cat("```nohighlight\n")
cat(str(dataset))
cat("\n```\n\n")
perc.classes = sort(round(100*as.numeric(
table(dataset[, ncol(dataset)]))/nrow(dataset), 0))
cat(paste("**Class imbalance**:",
paste0(perc.classes[1], "% / ",
perc.classes[2], "%\n\n")))
cat("---\n\n")
}
```