rhilfi

library(dplyr)
# see https://www.tidyverse.org/blog/2020/04/dplyr-1-0-0-colwise/
# see https://vbaliga.github.io/replace-text-in-specific-column/

ID<-1:3
Names<-c("Peter", "Paul", "Marhy")
FamilyNames<-c("Lennon", "McCartney", "Jagger")
Age<-rnorm(3, 80, 12)
data<-data.frame(Names, FamilyNames, ID, Age)

rhilfi

# http://www.cookbook-r.com/Manipulating_data/Summarizing_data/
library(tidyverse)

id<-1:100
group<-sample(c("Men", "Women"), 100, replace =TRUE)
age=rnorm(100, 50, 12)

data<-data.frame(id, group, age)

rhilfi

numeric<-sample(c(0,1), 100, replace=TRUE)

factor<-factor(numeric, levels=c(0,1), labels=c("nein", "Ja"))

mean(numeric)
mean(factor)
mean(as.numeric(factor))

rhilfi

library(tidyverse)
library(lubridate)

# you can find more information here: 
  # https://r4ds.had.co.nz/dates-and-times.html
  # https://cran.r-project.org/web/packages/lubridate/vignettes/lubridate.html
  # https://lubridate.tidyverse.org


data<-read.table(text="id	Tag_Monat_Jahr	Monat_Tag_Jahr	dmy_hms	dob	dod	date_event	date_release_white_album	start_rooftop_concert	end_rooftop_concert

rhilfi

# example to illustrate scientific notation 
# https://stackoverflow.com/questions/5352099/how-to-disable-scientific-notation
scientificNotation=format(c(1000,100,10,1,0.1,0.01, 0.001, 0.0001, 0.00001, 0.000001, 0.0000001), scientific=TRUE)
nonScientificNotation=format(c(1000,100,10,1,0.1,0.01, 0.001, 0.0001, 0.00001, 0.000001, 0.0000001), scientific=FALSE)

data<-data.frame(nonScientificNotation, scientificNotation)

rhilfi

library(rio)
library(tidyverse)

# the two lines with str_replace just show that the author of this code does not know how to correctly format date_time. Sorry for that. 
st=format(Sys.time(), "%a %b %d %X %Y")
st=str_replace_all(st, ":","_")
st=str_replace_all(st, " ","_")
rio::export(check_error_start_intervention,paste("../02_data_checks/start_intervention_before_eval_initiale",st,".xlsx", sep="_"))

rhilfi

library(rio)
library(tidyverse)
library(summarytools)

size=100000

  age_years<-rnorm(size, mean=50, sd=12)

gender<-sample(c("1", "2"), size=size,prob=c(0.51, 0.49), replace=TRUE)

rhilfi

library(tidyverse)
# thanks for the help: 
# https://community.rstudio.com/t/pivot-longer-on-multiple-column-sets-pairs/43958/9 
# https://cran.r-project.org/web/packages/stringr/vignettes/regular-expressions.html 

walking_speed_1<-c(0.3,0.5,0.7)
balance_four_balance_test_1<-c(1,2,1)
tug_1<-c(10,20,12)

walking_speed_2<-c(0.4,0.6,0.8)

rhilfi

mutate(across(Age_mean:woman_perc, as.numeric))

rhilfi

library(summarytools)
library(dplyr)
first_name=c("Hans", "Peter", "", "Fritz", "Susi")

family_name=c("Meier", "Muller", "Zgraggen", "", "Zurcher")
age=c(43,43,23,55,40)

data<-data.frame(first_name, family_name, age)

summarytools::freq(data$first_name)