This document is on purpose in one big block
exampleString<-'hello world'
class(exampleString)## [1] "character"number=15
class(number)## [1] "numeric"anotherNumber=2000
number+anotherNumber## [1] 2015conference <- 'AMIA'
#error
#conference + number
paste(conference,number+anotherNumber)## [1] "AMIA 2015"ls()## [1] "anotherNumber" "conference" "exampleString" "number"#load some data into R
#load a library (also can use require())
library(devtools)
#get a package (more like files in this case)
devtools::install_github('vojtechhuser/rcdisc')## Downloading GitHub repo vojtechhuser/rcdisc@master
## Installing rcdisc
## "C:/PROGRA~1/R/R-32~1.2/bin/x64/R" --no-site-file --no-environ --no-save \
## --no-restore CMD INSTALL \
## "C:/Users/huserv.NIH/AppData/Local/Temp/1/RtmpsJXNeK/devtools21583262d38/vojtechhuser-rcdisc-e868e07" \
## --library="C:/d/R/win-library/3.2" --install-tests library(rcdisc)
fileName<-system.file('extdata','cm.xpt.csv',package = 'rcdisc')
fileName## [1] "C:/d/R/win-library/3.2/rcdisc/extdata/cm.xpt.csv" studyData<-read.csv(fileName)
#exploring r functions
#how many rows
nrow(studyData)## [1] 36#ncol(studyData)
#dim(studyData)
#getting help
#?nrow()
str(studyData)## 'data.frame': 36 obs. of 21 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ STUDYID : Factor w/ 1 level "CDISC01": 1 1 1 1 1 1 1 1 1 1 ...
## $ DOMAIN : Factor w/ 1 level "CM": 1 1 1 1 1 1 1 1 1 1 ...
## $ USUBJID : Factor w/ 5 levels "CDISC01.100008",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ CMSEQ : int 1 2 3 4 5 6 7 8 9 10 ...
## $ CMTRT : Factor w/ 28 levels "ACCUPRIL","ALKA SELTZER PLUS",..: 23 11 1 4 10 10 17 19 22 3 ...
## $ CMMODIFY: Factor w/ 6 levels "","DONEPEZIL HYDROCHLORIDE",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ CMDECOD : Factor w/ 27 levels "ACETYLSALICYLIC ACID",..: 19 10 22 3 16 16 15 18 13 1 ...
## $ CMCAT : Factor w/ 2 levels "CONCOMITANT MEDICATIONS",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ CMINDC : Factor w/ 17 levels "ALZHEIMER'S DISEASE",..: 7 5 7 15 5 5 15 15 9 13 ...
## $ CMCLAS : Factor w/ 15 levels "AGENTS ACTING ON THE RENIN-ANGIOTENSIN SYSTEM",..: 6 9 1 10 9 9 10 15 8 3 ...
## $ CMCLASCD: Factor w/ 15 levels "A02","A04","A10",..: 6 3 7 5 3 3 5 4 1 11 ...
## $ CMDOSTXT: Factor w/ 18 levels ".125","1","10",..: 15 12 7 16 4 14 11 2 9 17 ...
## $ CMDOSU : Factor w/ 4 levels "IU","mg","TABLET",..: 2 2 2 2 2 2 2 3 2 2 ...
## $ CMDOSFRQ: Factor w/ 4 levels "BID","ONCE","PRN",..: 4 1 4 4 4 4 4 4 4 4 ...
## $ CMROUTE : Factor w/ 3 levels "INTRAVENOUS",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ CMSTDTC : Factor w/ 21 levels "1960","1986",..: 2 3 4 4 4 4 4 4 5 6 ...
## $ CMENDTC : Factor w/ 15 levels "","2001-09-15",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ CMSTDY : int -5963 -5598 -2676 -2676 -2676 -2676 -2676 -2676 -1580 -910 ...
## $ CMENDY : int NA NA NA NA NA NA NA NA NA NA ...
## $ CMENRF : Factor w/ 2 levels "","AFTER": 2 2 2 2 2 2 2 2 2 2 ...studyData<-read.csv(fileName,stringsAsFactors = FALSE)
str(studyData)## 'data.frame': 36 obs. of 21 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ STUDYID : chr "CDISC01" "CDISC01" "CDISC01" "CDISC01" ...
## $ DOMAIN : chr "CM" "CM" "CM" "CM" ...
## $ USUBJID : chr "CDISC01.100008" "CDISC01.100008" "CDISC01.100008" "CDISC01.100008" ...
## $ CMSEQ : int 1 2 3 4 5 6 7 8 9 10 ...
## $ CMTRT : chr "PROCARDIA XL" "GLYBURIDE" "ACCUPRIL" "CALCIUM" ...
## $ CMMODIFY: chr "" "" "" "" ...
## $ CMDECOD : chr "NIFEDIPINE" "GLIBENCLAMIDE" "QUINAPRIL HYDROCHLORIDE" "CALCIUM" ...
## $ CMCAT : chr "CONCOMITANT MEDICATIONS" "CONCOMITANT MEDICATIONS" "CONCOMITANT MEDICATIONS" "CONCOMITANT MEDICATIONS" ...
## $ CMINDC : chr "HYPERTENSION" "DIABETES" "HYPERTENSION" "SUPPLEMENT" ...
## $ CMCLAS : chr "CALCIUM CHANNEL BLOCKERS" "DRUGS USED IN DIABETES" "AGENTS ACTING ON THE RENIN-ANGIOTENSIN SYSTEM" "MINERAL SUPPLEMENTS" ...
## $ CMCLASCD: chr "C08" "A10" "C09" "A12" ...
## $ CMDOSTXT: chr "60" "5" "20" "600" ...
## $ CMDOSU : chr "mg" "mg" "mg" "mg" ...
## $ CMDOSFRQ: chr "Q24H" "BID" "Q24H" "Q24H" ...
## $ CMROUTE : chr "ORAL" "ORAL" "ORAL" "ORAL" ...
## $ CMSTDTC : chr "1986" "1987" "1995" "1995" ...
## $ CMENDTC : chr "" "" "" "" ...
## $ CMSTDY : int -5963 -5598 -2676 -2676 -2676 -2676 -2676 -2676 -1580 -910 ...
## $ CMENDY : int NA NA NA NA NA NA NA NA NA NA ...
## $ CMENRF : chr "AFTER" "AFTER" "AFTER" "AFTER" ...#just one column
studyData$CMDOSU## [1] "mg" "mg" "mg" "mg" "mg" "mg" "mg"
## [8] "TABLET" "mg" "mg" "mg" "mg" "mg" "mg"
## [15] "mg" "mg" "TABLET" "TABLET" "TABLET" "TABLET" "IU"
## [22] "mg" "mg" "mg" "mg" "mg" "mg" "VIAL"
## [29] "TABLET" "mg" "mg" "TABLET" "VIAL" "mg" "TABLET"
## [36] "mg"#indexing in data.frame [row,column]
studyData[1,6]## [1] "PROCARDIA XL"studyData[1,'CMTRT']## [1] "PROCARDIA XL"studyData$CMTRT[1]## [1] "PROCARDIA XL"studyData$CMTRT[2:12]## [1] "GLYBURIDE" "ACCUPRIL" "CALCIUM" "GLUCOPHAGE"
## [5] "GLUCOPHAGE" "MAGNESIUM" "MULTIVITAMIN" "PREVACID"
## [9] "ASPIRIN" "LEVOXYL" "LANSOPRAZOLE"studyData$CMROUTE## [1] "ORAL" "ORAL" "ORAL" "ORAL"
## [5] "ORAL" "ORAL" "ORAL" "ORAL"
## [9] "ORAL" "ORAL" "ORAL" "ORAL"
## [13] "INTRAVENOUS" "ORAL" "ORAL" "ORAL"
## [17] "ORAL" "ORAL" "ORAL" "ORAL"
## [21] "ORAL" "ORAL" "ORAL" "ORAL"
## [25] "ORAL" "ORAL" "ORAL" "SUBCUTANEOUS"
## [29] "ORAL" "ORAL" "ORAL" "ORAL"
## [33] "SUBCUTANEOUS" "ORAL" "ORAL" "ORAL"#make it lower case
tolower(studyData$CMROUTE)## [1] "oral" "oral" "oral" "oral"
## [5] "oral" "oral" "oral" "oral"
## [9] "oral" "oral" "oral" "oral"
## [13] "intravenous" "oral" "oral" "oral"
## [17] "oral" "oral" "oral" "oral"
## [21] "oral" "oral" "oral" "oral"
## [25] "oral" "oral" "oral" "subcutaneous"
## [29] "oral" "oral" "oral" "oral"
## [33] "subcutaneous" "oral" "oral" "oral"# "write it to the database"
studyData$route<-'something'
studyData$route<-paste('route was',tolower(studyData$CMROUTE))
#overwriting it
studyData$CMROUTE<-tolower(studyData$CMROUTE)
str(studyData)## 'data.frame': 36 obs. of 22 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ STUDYID : chr "CDISC01" "CDISC01" "CDISC01" "CDISC01" ...
## $ DOMAIN : chr "CM" "CM" "CM" "CM" ...
## $ USUBJID : chr "CDISC01.100008" "CDISC01.100008" "CDISC01.100008" "CDISC01.100008" ...
## $ CMSEQ : int 1 2 3 4 5 6 7 8 9 10 ...
## $ CMTRT : chr "PROCARDIA XL" "GLYBURIDE" "ACCUPRIL" "CALCIUM" ...
## $ CMMODIFY: chr "" "" "" "" ...
## $ CMDECOD : chr "NIFEDIPINE" "GLIBENCLAMIDE" "QUINAPRIL HYDROCHLORIDE" "CALCIUM" ...
## $ CMCAT : chr "CONCOMITANT MEDICATIONS" "CONCOMITANT MEDICATIONS" "CONCOMITANT MEDICATIONS" "CONCOMITANT MEDICATIONS" ...
## $ CMINDC : chr "HYPERTENSION" "DIABETES" "HYPERTENSION" "SUPPLEMENT" ...
## $ CMCLAS : chr "CALCIUM CHANNEL BLOCKERS" "DRUGS USED IN DIABETES" "AGENTS ACTING ON THE RENIN-ANGIOTENSIN SYSTEM" "MINERAL SUPPLEMENTS" ...
## $ CMCLASCD: chr "C08" "A10" "C09" "A12" ...
## $ CMDOSTXT: chr "60" "5" "20" "600" ...
## $ CMDOSU : chr "mg" "mg" "mg" "mg" ...
## $ CMDOSFRQ: chr "Q24H" "BID" "Q24H" "Q24H" ...
## $ CMROUTE : chr "oral" "oral" "oral" "oral" ...
## $ CMSTDTC : chr "1986" "1987" "1995" "1995" ...
## $ CMENDTC : chr "" "" "" "" ...
## $ CMSTDY : int -5963 -5598 -2676 -2676 -2676 -2676 -2676 -2676 -1580 -910 ...
## $ CMENDY : int NA NA NA NA NA NA NA NA NA NA ...
## $ CMENRF : chr "AFTER" "AFTER" "AFTER" "AFTER" ...
## $ route : chr "route was oral" "route was oral" "route was oral" "route was oral" ...#delete a column
studyData$route <- NULL
str(studyData)## 'data.frame': 36 obs. of 21 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ STUDYID : chr "CDISC01" "CDISC01" "CDISC01" "CDISC01" ...
## $ DOMAIN : chr "CM" "CM" "CM" "CM" ...
## $ USUBJID : chr "CDISC01.100008" "CDISC01.100008" "CDISC01.100008" "CDISC01.100008" ...
## $ CMSEQ : int 1 2 3 4 5 6 7 8 9 10 ...
## $ CMTRT : chr "PROCARDIA XL" "GLYBURIDE" "ACCUPRIL" "CALCIUM" ...
## $ CMMODIFY: chr "" "" "" "" ...
## $ CMDECOD : chr "NIFEDIPINE" "GLIBENCLAMIDE" "QUINAPRIL HYDROCHLORIDE" "CALCIUM" ...
## $ CMCAT : chr "CONCOMITANT MEDICATIONS" "CONCOMITANT MEDICATIONS" "CONCOMITANT MEDICATIONS" "CONCOMITANT MEDICATIONS" ...
## $ CMINDC : chr "HYPERTENSION" "DIABETES" "HYPERTENSION" "SUPPLEMENT" ...
## $ CMCLAS : chr "CALCIUM CHANNEL BLOCKERS" "DRUGS USED IN DIABETES" "AGENTS ACTING ON THE RENIN-ANGIOTENSIN SYSTEM" "MINERAL SUPPLEMENTS" ...
## $ CMCLASCD: chr "C08" "A10" "C09" "A12" ...
## $ CMDOSTXT: chr "60" "5" "20" "600" ...
## $ CMDOSU : chr "mg" "mg" "mg" "mg" ...
## $ CMDOSFRQ: chr "Q24H" "BID" "Q24H" "Q24H" ...
## $ CMROUTE : chr "oral" "oral" "oral" "oral" ...
## $ CMSTDTC : chr "1986" "1987" "1995" "1995" ...
## $ CMENDTC : chr "" "" "" "" ...
## $ CMSTDY : int -5963 -5598 -2676 -2676 -2676 -2676 -2676 -2676 -1580 -910 ...
## $ CMENDY : int NA NA NA NA NA NA NA NA NA NA ...
## $ CMENRF : chr "AFTER" "AFTER" "AFTER" "AFTER" ...temp<-readr::read_file('introToR-A.Rmd')
cat(temp)---
title: "Intro"
author: "Vojtech Huser"
output: html_document
---
This document is on purpose in one big block
```{r}
exampleString<-'hello world'
class(exampleString)
number=15
class(number)
anotherNumber=2000
number+anotherNumber
conference <- 'AMIA'
#error
#conference + number
paste(conference,number+anotherNumber)
ls()
#load some data into R
#load a library (also can use require())
library(devtools)
#get a package (more like files in this case)
devtools::install_github('vojtechhuser/rcdisc')
library(rcdisc)
fileName<-system.file('extdata','cm.xpt.csv',package = 'rcdisc')
fileName
studyData<-read.csv(fileName)
#exploring r functions
#how many rows
nrow(studyData)
#ncol(studyData)
#dim(studyData)
#getting help
#?nrow()
str(studyData)
studyData<-read.csv(fileName,stringsAsFactors = FALSE)
str(studyData)
#just one column
studyData$CMDOSU
#indexing in data.frame [row,column]
studyData[1,6]
studyData[1,'CMTRT']
studyData$CMTRT[1]
studyData$CMTRT[2:12]
studyData$CMROUTE
#make it lower case
tolower(studyData$CMROUTE)
# "write it to the database"
studyData$route<-'something'
studyData$route<-paste('route was',tolower(studyData$CMROUTE))
#overwriting it
studyData$CMROUTE<-tolower(studyData$CMROUTE)
str(studyData)
#delete a column
studyData$route <- NULL
str(studyData)
```
#code export
```{r comment=''}
temp<-readr::read_file('introToR-A.Rmd')
cat(temp)
```
``````