You can start Rstudio either from terminal or among installed softwares.
These are a few R packages we will use along the tutorial:
# Enter commands in R (or R studio, if installed)
# install.packages()
install.packages('tidyverse')
library(tidyverse)
We are going to start with the basics of coding, Rstudio, and R language.
1 + 2
## [1] 3
x <- 1
x
## [1] 1
Functions take arguments in paranthesis and process the output. Here the function ‘c’ returns the values as a vector.
c(1, 2, 3)
## [1] 1 2 3
a <- 2
b <- 9.5
a > b
## [1] FALSE
z <- a > b
z
## [1] FALSE
class(a)
## [1] "numeric"
class(b)
## [1] "numeric"
class(z)
## [1] "logical"
Reverse the logic:
!z
## [1] TRUE
x <- as.character(3.14)
x
## [1] "3.14"
fname = "John"; lname ="Doe";
paste(fname, lname)
## [1] "John Doe"
?paste
my_vec1 <- c("aa", "bb", "cc", "dd", "ee")
my_vec2 <- c(1, 2, 3, 4, 5)
length(my_vec2)
## [1] 5
#Combining vectors:
c(my_vec1, my_vec2)
## [1] "aa" "bb" "cc" "dd" "ee" "1" "2" "3" "4" "5"
my_vec2
## [1] 1 2 3 4 5
2 * my_vec2 # Mutliply by 2
## [1] 2 4 6 8 10
my_vec2 - 2
## [1] -1 0 1 2 3
my_vec3 <- c(10, 20, 30, 40, 50)
my_vec2 + my_vec3
## [1] 11 22 33 44 55
3 * (my_vec2 + my_vec3) / 5
## [1] 6.6 13.2 19.8 26.4 33.0
Indexing starts with 1
unlike python.
s <- c("aa", "bb", "cc", "dd", "ee")
s[3]
## [1] "cc"
s[3:5]
## [1] "cc" "dd" "ee"
s[-4] #Now 'dd' is gone!
## [1] "aa" "bb" "cc" "ee"
s[c(2, 3, 3)]
## [1] "bb" "cc" "cc"
s[c(2, 1, 3)]
## [1] "bb" "aa" "cc"
s[c(FALSE, TRUE, FALSE, TRUE, FALSE)] #Logical indexing
## [1] "bb" "dd"
Naming the vector members:
v <- c("Mary", "Sue")
v
## [1] "Mary" "Sue"
names(v) <- c("First", "Last")
v
## First Last
## "Mary" "Sue"
v["First"]
## First
## "Mary"
“A matrix is a collection of data elements arranged in a two-dimensional rectangular layout.”
A <- matrix(
c(2, 4, 3, 1, 5, 7), # the data elements
nrow=2, # number of rows
ncol=3, # number of columns
byrow = TRUE) # fill matrix by rows
A
## [,1] [,2] [,3]
## [1,] 2 4 3
## [2,] 1 5 7
A[2, 3] # A[row, column]
## [1] 7
A[2, ] # The entire 2nd row
## [1] 1 5 7
A[, 3] # The entire 3rd column
## [1] 3 7
A[, c(1,3)] # the 1st and 3rd columns
## [,1] [,2]
## [1,] 2 3
## [2,] 1 7
Transpose the matrix
B <- matrix(
c(2, 4, 3, 1, 5, 7),
nrow=3,
ncol=2)
B
## [,1] [,2]
## [1,] 2 1
## [2,] 4 5
## [3,] 3 7
t(B)
## [,1] [,2] [,3]
## [1,] 2 4 3
## [2,] 1 5 7
Combine matrices
cbind(A, t(B)) # combine row-wise
## [,1] [,2] [,3] [,4] [,5] [,6]
## [1,] 2 4 3 2 4 3
## [2,] 1 5 7 1 5 7
rbind(A, t(B)) # combine column-wise
## [,1] [,2] [,3]
## [1,] 2 4 3
## [2,] 1 5 7
## [3,] 2 4 3
## [4,] 1 5 7
“A data frame is used for storing data tables. It is a list of vectors of equal length.”
n <- c(2, 3, 5)
s <- c("aa", "bb", "cc")
b <- c(TRUE, FALSE, TRUE)
df <- data.frame(n, s, b) # df is a data frame
df
## n s b
## 1 2 aa TRUE
## 2 3 bb FALSE
## 3 5 cc TRUE
mtcars
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
## Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
## Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3
## Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3
## Cadillac Fleetwood 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4
## Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4
## Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4
## Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
## Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
## Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
## Dodge Challenger 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2
## AMC Javelin 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2
## Camaro Z28 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4
## Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2
## Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
## Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2
## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4
## Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6
## Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8
## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2
mtcars[10, 4]
## [1] 123
mtcars['Merc 280', 'hp']
## [1] 123
mtcars["Merc 280", ]
## mpg cyl disp hp drat wt qsec vs am gear carb
## Merc 280 19.2 6 167.6 123 3.92 3.44 18.3 1 0 4 4
mtcars[["hp"]]
## [1] 110 110 93 110 175 105 245 62 95 123 123 180 180 180 205 215 230 66 52
## [20] 65 97 150 150 245 175 66 91 113 264 175 335 109
mtcars$hp
## [1] 110 110 93 110 175 105 245 62 95 123 123 180 180 180 205 215 230 66 52
## [20] 65 97 150 150 245 175 66 91 113 264 175 335 109
nrow(mtcars)
## [1] 32
ncol(mtcars)
## [1] 11
mtcars[, c("mpg", "hp")]
## mpg hp
## Mazda RX4 21.0 110
## Mazda RX4 Wag 21.0 110
## Datsun 710 22.8 93
## Hornet 4 Drive 21.4 110
## Hornet Sportabout 18.7 175
## Valiant 18.1 105
## Duster 360 14.3 245
## Merc 240D 24.4 62
## Merc 230 22.8 95
## Merc 280 19.2 123
## Merc 280C 17.8 123
## Merc 450SE 16.4 180
## Merc 450SL 17.3 180
## Merc 450SLC 15.2 180
## Cadillac Fleetwood 10.4 205
## Lincoln Continental 10.4 215
## Chrysler Imperial 14.7 230
## Fiat 128 32.4 66
## Honda Civic 30.4 52
## Toyota Corolla 33.9 65
## Toyota Corona 21.5 97
## Dodge Challenger 15.5 150
## AMC Javelin 15.2 150
## Camaro Z28 13.3 245
## Pontiac Firebird 19.2 175
## Fiat X1-9 27.3 66
## Porsche 914-2 26.0 91
## Lotus Europa 30.4 113
## Ford Pantera L 15.8 264
## Ferrari Dino 19.7 175
## Maserati Bora 15.0 335
## Volvo 142E 21.4 109
getwd()
setwd("your target directory")
Disclaimer: This tutorial has been originated from: http://www.r-tutor.com/r-introduction
sessionInfo()
## R version 4.1.0 (2021-05-18)
## Platform: x86_64-apple-darwin17.0 (64-bit)
## Running under: macOS Big Sur 10.16
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.1/Resources/lib/libRblas.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.1/Resources/lib/libRlapack.dylib
##
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## loaded via a namespace (and not attached):
## [1] digest_0.6.29 R6_2.5.1 jsonlite_1.8.0 magrittr_2.0.3
## [5] evaluate_0.16 stringi_1.7.8 cachem_1.0.6 rlang_1.0.4
## [9] cli_3.3.0 rstudioapi_0.13 jquerylib_0.1.4 bslib_0.4.0
## [13] rmarkdown_2.15 tools_4.1.0 stringr_1.4.0 xfun_0.32
## [17] yaml_2.3.5 fastmap_1.1.0 compiler_4.1.0 htmltools_0.5.3
## [21] knitr_1.39 sass_0.4.2
Comments
Everything that follows a ‘#’ is considered as command.