# R programs consist of creating or reading in a dataset
# R is also case-sensitive 

# 1st way to read in data using the c() command

name=c("Hamb","Chsbrg","Delxbg","Fish","Chix")
size=c(107,121,216,156,223)
totfat=c(9,13,31,25,20)
burgers=data.frame(name,size,totfat)
# look at it by either calling the object (dataset) or use View()
burgers
View(burgers)

# 2nd way using read.csv() or read.table()
burgers=read.table("S:/webpages/~renaes/Data/burgs1.txt",sep='',header=T)
burgers=read.csv("S:/webpages/~renaes/Data/burgs1.csv",header=T)

# In RStudio, you can use the Import Dataset option in the Environment window
# (which cannot really be shown here)

# this dataset was a bit picky and I had to change the variable types
# it coded most of the numeric variables as character and I changed them back to integer

students=read.csv("S:/webpages/~renaes/Data/STUDENT.csv",header=T)
View(students)

with(students,mean(Sys1,na.rm=T)) #na.rm=T removes missing values for calculation
with(students,mean(Dias1,na.rm=T))

with(students,plot(Dias1,Sys1))

# table with counts
with(students,table(Eye))
# Contingency table with cross-calssifying factors
with(students,xtabs(~Eye+Thumb))

# sorting data
# sorted by eye color (Eye)
# sorting is ascending by default
students2=students[order(students$Eye),] # the comma means all columns
# sort by eye color (ascending) and Thumb (descending) (for thumb descending use a - sign)
students3=students[order(students$Eye,-students$Thumb),]

# means of Sys1, Dias1 by eye color
with(students,tapply(Sys1,Eye,mean,na.rm=T))
with(students,tapply(Dias1,Eye,mean,na.rm=T))
# we would have been able to do both variables at once if there were no missing values
# example that won't work here but will if dataset had no missing values
with(students,tapply(c(Sys1,Dias1),Eye,mean,na.rm=T))