[R-Package] mulset - generate dataset intersections in sparse data

Share and discuss new tools, frameworks and packages!
Post Reply
User avatar
LogIN
Admin
Posts: 5
Joined: Wed Feb 13, 2019 7:47 pm
Location: Palo Alto, CA
Contact:

Mon May 06, 2019 5:39 pm

Description

If you have missing values in your data, but you dont want to impute those values or mess with them in any other artificial way,
you can use mulset and generate multiple datasets of those data that you can use latter on in autoML or some other analysis.

Image

Download links
  • https://cran.r-project.org/web/packages/mulset/index.html
  • https://github.com/LogIN-/mulset
Installation

Code: Select all

install.packages("devtools")
devtools::install_github("LogIN-/mulset", subdir = 'R-package')
Usage Example

Code: Select all

library("mulset")
## Using provided demo data
data(mulsetDemo)
resamples <- mulset(mulsetDemo, exclude = c("outcome", "age", "gender"), 250)

## or from CSV file
## mulsetDemo <-fread("./data/mulsetDemo.csv", header = T, sep = ',', stringsAsFactors = FALSE, data.table = FALSE)
## exclude <- c("come_column")
## resamples <- mulset(mulsetDemo, exclude = exclude, include = c("samples_count", "datapoints"), maxIntersections = 250, hashMethod = "sha1")
Attachments
mulset.zip
(86.85 KiB) Downloaded 14 times
“We can not solve our problems with the same level of thinking that created them” A.E.
Post Reply