# Name First R Program
# Purpose is to install and show basic R commands
# Author Sunil Gupta, SASSavvy.com/R-Guru
# Date Oct 25 2021
# Copyright - 2021, This macro has copyright protection by the author.
Application of this program for its intended use only in its original form is authorized by the author.  All other applications are at users risk.
R program is not to be used in commercial software product without the written approval by the author.
Any reference to the R program must include reference to SASSavvy.com/R-Guru.
No support or guarantee is provided with the R program or results.
User takes responsibility for R program and results and is encouraged to test the program.

# 1. install R windows (32 or 64 bit)
# https://cran.rstudio.com

# 2. download R studio
# https://www.rstudio.com/products/rstudio/download  

# 3. Double click on R icon

# 4. Please select a CRAN mirror for use in this session
# Select US option for internal setting. 

setwd("C:/study/analysis/output")
# change default working folder
getwd() 
# confirm working folder

# option b
install.packages('tidyverse')
library(tidyverse) # load popular data management package
library(dplyr) # load common data management and sql package
library(sqldf) # load sql package

library() # display loaded libraries

.libPaths() # display path of each package

lsf.str("package:dplyr") # display dplyr functions
lsf.str("package:tidyverse") # display tidyverse functions

t <- c("Sun","Mon","Tue","Wed","Thurs","Fri","Sat")
view(t)

x= c(2, 4, 6)
mean(x) 
y=c(1, 1, 1)
z = x + y 
view(z)

mydata <- data.frame(
  class = c("1st", "2nd", "3rd", "Crew"),
  n = c(325, 285, 706, 885),
  prop = c(14.8, 12.9, 32.1, 40.2)
)
mydata

tg <- ToothGrowth # save sample data frame to tg data frame
View(tg) # browse tg
str(tg)  # display tg attributes and sample records
attributes(tg) # display tg attributes, names (tg) is alternative to display variable names
head(tg) # display tg sample records
print(tg) # display tg all records, similar to proc print
summary(tg) # display stats object of continuous variables
table(tg) # display freq of categorical variables

objects() # to display all objects in workspace (data frames, vectors, etc.)

library(readxl) # read excel files
dm_specs <- read_excel("D:/Sunil/GP/Business/ACL Digital/r programming/DM_Specs.xlsx")
View(dm_specs)

dm <- read.csv("D:/Sunil/GP/Business/ACL Digital/r programming/input.csv")
dm1 <- read.table("D:/Sunil/GP/Business/ACL Digital/r programming/input.csv")
dm
dm1

write.csv(dm, "C:/study/analysis/output/mydm.csv", row.names = FALSE)
# save permanent csv

sdtm <- "D:/Sunil/GP/Business/ACL Digital/r programming" # assign libname to object named sdtm
list.files
dir

library(haven) # read SAS datasets
asl1 <- read_sas(file.path(sdtm, 'adsl.sas7bdat'))  #  read_sas from haven package within tidyverse to read DM dataset in sdtm library
asl1

asl2 <- read_sas("D:/Sunil/GP/Business/ACL Digital/r programming/adsl.sas7bdat") # read DM dataset directly
asl2
View(asl2)

saveRDS(asl2, file = "asl2.RDS") 
# save permanent R data frame

myasl <- readRDS("asl2.RDS")
# load permanent R data frame
myasl

# enter data values into data frame
vs <- read.table(header = TRUE,
 stringsAsFactors = FALSE,
 text = "
 SUBJID HT WT PERIOD
001 180 NA 1
001 181 77 2
002 173 85 1
002 173 83 2");
View(vs)

test_df <- data.frame(
  class = c("1st", "2nd", "3rd", "Crew"),
  n = c(325, 285, 706, 885),
  prop = c(14.8, 12.9, 32.1, 40.2)
)
View(test_df)

patient <- 1  # assign number patient = 1
is(patient)
patient

Right Variable Assignment
1 ->  patient  # right assign number patient = 1
is(patient)
patient

# Variable Assignment Options
assign('ae', 'Headache') # assign char ae = 'Headache' 
ae = 'Headache' # assign char ae = 'Headache'
ae

# Keeping Variables
test_df2=test_df[c('class', 'n')]
View(test_df2)

# Dropping Variables
test_df3= subset(test_df, select = -c(class))
View(test_df3)
test_df4= test_df[-c(3)]
View(test_df4)

df1 <- subset(test_df, class == '1st')
df1 <- filter(test_df, class == '1st')
df1

# sorting examples using the mtcars dataset
attach(mtcars)

# sort by mpg
newdata <- mtcars[order(mpg),]

# sort by mpg and cyl
newdata <- mtcars[order(mpg, cyl),]
newdata

# pipe example
query1 <- ToothGrowth %>% 
select(len, supp, dose) %>% 
mutate(dose2 = (dose*2)) %>% 
filter(supp == 'VC') %>% 
arrange(supp, dose)
View(query1)

# intermediate objects
query1 <- ToothGrowth  

query2 <- select(query1, len, supp, dose)  
View(query2)

query3 <- mutate(query2, dose2 = (dose*2))  
View(query3)

query4 <- filter(query3, supp == 'VC') 
View(query4)

query5 <- arrange(query4, supp, dose)
View(query5)

objects()

ASL_mean <- asl1 %>% 
 group_by(SEX) %>% 
 summarise(avg_age = mean(AGE))
asl1
ASL_mean

table(asl1$SEX)
# proc freq data=asl1; tables sex; run;

table(asl1$SEX, asl1$SAFFL)
# proc freq data=asl1; tables sex*saffl; run;