rhilfi

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console

rhilfi

https://mycolor.space 

rhilfi

# adapted from: https://stackoverflow.com/questions/44077122/r-select-rows-with-non-na-values-in-at-least-one-of-the-four-columns 

a<-c(NA,NA,NA,NA,2,5,4,3,NA,NA)
b<-c(NA,NA,NA,NA,2,3,4,5,NA,NA)
c<-c(NA,NA,NA,NA,NA,NA,NA,NA,NA,NA)
d<-c(1,4,3,1,2,4,3,2,1,NA)
df<-cbind(a,b,c,d)
df_atLeastOneNonMissingValue <- df[rowSums(is.na(df)) != ncol(df),] ## just to keep rows with at least one non-missing value 
nrow(df)
nrow(df_atLeastOneNonMissingValue)

rhilfi

## adapted from: https://stackoverflow.com/questions/22286419/move-a-column-to-first-position-in-a-data-frame
## see also: https://stackoverflow.com/questions/37171891/how-does-dplyrs-select-helper-function-everything-differ-from-copying 

# create data.frame to illustrate
 a<-1:5
 b<-a
 c<-as.character(b)
 df<-as.data.frame(cbind(a,b,c))
 # end create data.frame to illustrate
 df

rhilfi

## AUC expected versus AUC minimal 

## sample size calculatino AUC
## we use formula 7.5 in http://dx.doi.org/10.1016/j.jbi.2014.02.013 
## Variance of AUC, following Appendix A (nonparametric AUC)

minimalAcceptableAUC<-0.7
expectedAUC<-0.8
ratioControlToCases<-2

rhilfi

#####################################################################################################
###     This exercise should illustrate perfect agreement, random error and systematic error      ###
#####################################################################################################
library(rio)
library(tidyverse)
library(ggplot2)
library(BlandAltmanLeh)
library(psych)

rnorm2 <- function(n,mean,sd) { mean+sd*scale(rnorm(n)) } # this function is just to make it possible to fix the values or rnorm https://stackoverflow.com/questions/18919091/generate-random-numbers-with-fixed-mean-and-sd?lq=1

rhilfi

#########################################
###   Example comments and labels     ###
#########################################
## Hier lassen wir R nachschauen, ob die benötigten Packages installiert sind, falls nein: installieren wir sie. 
list.of.packages <- c("Hmisc","janitor", "tidyverse", "rio")
new.packages <- list.of.packages[!(list.of.packages %in% installed.packages()[,"Package"])]
if(length(new.packages)) install.packages(new.packages)
# update.packages(ask=TRUE)

## If you have a csv with variable labels on the second row and you want label the variables 

rhilfi

####  Remove all non-number ####
library(tidyverse)
library(readr)

numbers<-c(1,2,3,4,5,6,7,8,9,10,11)
numbers_with_some_characters<-c("1","2zwei","3","4vier","5","6 sechs","7","8 ", " 9", "1 0", " 1 1 ")


data_to_show_remove_nonnumbers<-data.frame(numbers, numbers_with_some_characters)

rhilfi

list.of.packages <- c("summarytools")
new.packages <- list.of.packages[!(list.of.packages %in% installed.packages()[,"Package"])] # https://stackoverflow.com/questions/4090169/elegant-way-to-check-for-missing-packages-and-install-them
if(length(new.packages)) install.packages(new.packages)


summarytools::freq(models$significant) # https://cran.r-project.org/web/packages/summarytools/vignettes/Introduction.html


gender<-c(rep("men",10), rep("women", 20), rep(NA,5))

rhilfi

# see http://theautomatic.net/2018/07/11/manipulate-files-r/#:~:text=Files%20can%20be%20deleted%20with,add%20the%20parameter%20recursive%20%3D%20TRUE.