I hereby claim:
- I am alexpawlowski on github.
- I am alexpawlowski (https://keybase.io/alexpawlowski) on keybase.
- I have a public key whose fingerprint is 29E4 84AB 9DDD 0286 933D 542C 72EB 4CC2 2DD8 5222
To claim this, I am signing this object:
#' @title PRESS | |
#' @author Thomas Hopper | |
#' @description Returns the PRESS statistic (predictive residual sum of squares). | |
#' Useful for evaluating predictive power of regression models. | |
#' @param linear.model A linear regression model (class 'lm'). Required. | |
#' | |
PRESS <- function(linear.model) { | |
#' calculate the predictive residuals | |
pr <- residuals(linear.model)/(1-lm.influence(linear.model)$hat) | |
#' calculate the PRESS |
I hereby claim:
To claim this, I am signing this object:
LastUpdated | versions | |||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2017-11-14 |
|
While Jupyter Lab
is still in alpha
and subject to change often (beta
coming soon), it's interface is incredibly useful over the standard notebook interface.
Typically this happens when you're on a work machine with McAfee with zero power to 'disable it'. The issue of course, is when you update your `R` packages, McAfee (and probably others) lock the temporary file that R uses in unzipping the downloaded folder of the package you are installing. | |
The first method is to just keep trying the install command (I find this handy for large lists of packages, like when you update `tidyverse`) some packages will fail to be moved, but some will get through! | |
When you get down to `Rcpp` and the last stragglers, you'll need to slow your roll, son. | |
To do so, use this command: [Source](http://r.789695.n4.nabble.com/unable-to-move-temporary-installation-td4521714.html#a4529846) | |
```R | |
debug(utils:::unpackPkgZip) | |
``` |
While Anaconda has made it much simpler to get python running on Windows, I think Windows Sublayer for Linux is a really good platform to do coding, especially if you later merge the code you're working on to a container online. Conda (Anaconda's product) is a package manager that takes care of most of the weird things you may encounter programming with windows when you're interfacing with Unix users. Python's built-ins like pathlib
do even better.