# simple base R and simple dplyr operations 

# 0. determine your current working directory. Set your working directory to another directory

getwd()
# setwd("/Path/To/Dir...")

# 1. investigate the functions c, data.frame, and setwd with the help function, for example ?c

?c
?data.frame
?setwd

# 2. create  a numeric vector named object consisting of the values
#1,NA,3,4,67,98,43,NA,NA






# 3. create another numberic vector named object2 consisting of the values 1,NA,3,4,67,98,43,NA,13

object <- c(1, NA, 3, 4, 67, 98, 43, NA, NA)

object2 <- c(1, NA, 3, 4, 67, 98, 43, NA, 13)
# 4. Investigate NA, the mode and the length of the 2 vectors, create a factor variable containing the following levels "small", "medium", "large"

?NA
mode(object)
mode(object2)

length(object)
length(object2)
facvar <- factor(level = c("small", "medium", "large"))

# 5. combine the 2 numeric vectors into a data frame named frame
ob <- c(object,object2)


# 6. install the tidyverse packages using install.packages






install.packages("tidyverse")
library(tidyverse)
tidyverse_update()
# 7. access the dataset mpg read about the data
mpg




#8. determine the average number of city miles per gallon for the data
mean(unlist(mpg['cty']))

# 9. use the is.na function to find/locate NAs in object and object2
is.na(object)
is.na(object2)
# 10. use the na.omit function to remove the NAs from object and object2






object <- na.omit(object)
object2 <- na.omit(object2)

# 11. use the logical function to create a logical vector named tt of length 5

tt <- logical(5)

# 12. calculate the sum of object
sum(object)

# 13. use the seq function to create the following sequence 5, 10, 15, 20
num5 <- seq(5,20,by=5)

# 14. learn about the diamonds dataset using the help facility


?diamonds
# 15. determine the number of columns and rows in the diamonds data set

dim(diamonds)

# 16 select the carat and price variables from diamonds 
carprice <- select(diamonds, carat, price)

#17 select all columns but the x, y, z, and price columns 
select(diamonds, -x, -y, -z, -price)

#18 find all diamonds with carat > .5
filter(diamonds, carat > .5)

# 19. Create at least 2 other filter expressions for diamonds dataset use %in% 
filter(diamonds, cut %in% c('Ideal', 'Good'))


head(diamonds)
head(object)