rm(list=ls(all=TRUE))

#define vectors
age<- c(40, 50, 60)
wt<- c(100, 130, 150)

#create a data frame
MyDF <- data.frame(age, wt, NewName = c(2, 3, 4))
View(MyDF)

MyDF   #observations are rows and variables are columns or called attributes

age <-age+3

age
MyDF   #note that age in data frame didn't change because it was created before the change
age[2]

MyDF[1,2]   #reference elements in brackets, row number 1 and column number 2
MyDF[2,2]   #reference elements in brackets, row number 2 and column number 2

MyDF[1,] 
MyDF[,2] 

MyDF[1,1] <- MyDF[2,2]


MyNewFrame <- MyDF[,2] 

mean(MyDF$age)

#use $ to reference one column
mean(MyDF$age)
age #this is different than what I am calculating

#add the new age to the DF that I already have in a new attribute
MyDF$NewAge <- age
MyDF

MyDF$newAge <-age

#ANOTHER WAY IS
#MyDF$age <- age
MyDF$newAge <-NULL

MyDF <- rbind(MyDF, c(5, 6))
MyDF

MyDF[order(MyDF$age),] #sort ascending

MyDF <- MyDF[order(MyDF$age),] 

rownames(MyDF) <- NULL

#change column names
colnames(MyDF) <- c("Name", "name2", "name3")

#change the name of one column
colnames(MyDF)[3] <- "myName"

#___________
#Install a package in R and use a funtion on it to rename rows 
install.packages("data.table")
library(data.table)

?data.table

setattr(MyDF, "row.names", 1:4)

setnames(MyDF, 2, "wt")

#___________
#view the data set
View(MyDF)

#mtcars is a data set that is within R
#to get the list of available data use data()
data()
#seek info about the data set
?mtcars
#list the data
mtcars
#This is a data frame that has observations and variables. row values is not a variable in the data set. 
#structure command to get an idea about the meta data (structure)
str(mtcars)
# Summary
summary(mtcars)

MyCars <- mtcars

MyCars[1,]
MyCars[1,3]
MyCars[,3]

mean(MyCars$mpg)

MySortedCars <- MyCars[order(MyCars$mpg, -MyCars$cyl),]

head(MySortedCars)
tail(MySortedCars)
tail(MySortedCars, 1)

#descending with the negative - high to low
MySortedCars <- MyCars[order(-MyCars$mpg),]

MeanMPG <- mean(MyCars$mpg)
MySortedCars$mpg>MeanMPG

MyCars[MyCars$mpg>=21 & MyCars$mpg<=24,]

mtcars[mtcars$mpg>30,]

MyCars[MyCars$mpg>MeanMPG,1]

max(MyCars$mpg)    #the actual value
which.max(MyCars$mpg)  #which position includes the maximum value

#store them in new vectors
MaxMPG <- max(MyCars$mpg)
MaxIndex <- which.max(MyCars$mpg)
MyCars[MaxIndex,]

MyCars[which.min(MyCars$mpg),] #show the minimum

row.names(MyCars[MaxIndex,])

CarName <- row.names(MyCars[MaxIndex,])
#assign the row names to a new column
MyCars$CarName <- row.names(MyCars)

setattr(MyCars, "row.names", c(1:32))

cat("Max mpg & car name:", MaxMPG, CarName)

#which.max when there is more than one value with the max
MyCars[cyl==max(cyl),]