#### The working directory is where you have/save files for an R session
#to check current working directory
getwd()
#to change working directory
setwd("INSERT_HERE_some_file_path_to_the_folder_of_your_choice")
#to check all files in current working directory
list.files()
##### Your working environment is where R saves the objects (variables, vectors, matrices, data frames , etc...) of your session
# to remove object from working environment
shining_list <- list("moviename" = "The Shining", "actors"= actors, "reviews"= reviews)
# 'last_actor'
last_actor <- shining_list$actors[5]
# 'second_review'
second_review <- shining_list[[3]][2,]
myname <- "TADDE"
myname
rm("myname")
myname
# you can remove multiple objects at the same time
myname <- "TADDE"
mybeard <- "growing"
rm(list=c("myname","mybeard"))
# to remove every object from your working environment
rm(list=ls()) # the function ls() returns the list of all objects in your working environment# An addition
5 + 5## [1] 10# A subtraction
5 - 5 ## [1] 0# A multiplication
3 * 5## [1] 15 # A division
(5 + 5)/2 ## [1] 5# Exponentiation
2^5## [1] 32# Modulo
28 %% 6## [1] 4# Assign the value 42 to 'x'
x <- 42
# Assign a value to the variables called 'my_apples' and 'my_oranges'
my_apples <- 5
my_oranges <- 6
# Add these two variables together and print the result
my_apples + my_oranges## [1] 11# Create the variable 'my_fruit'
my_fruit <- my_apples + my_oranges
my_fruit## [1] 11# integer
my_integer<- 42L
# Numeric
my_numeric<- 42L
# The quotation marks indicate that the variable is of type character
my_character <- "forty-two"
my_logical <- FALSE
# Check which type these variables have:
class(my_integer)## [1] "integer"class(my_numeric)## [1] "integer"class(my_character)## [1] "character"class(my_logical)## [1] "logical"#In R, you create a vector with the combine function c()
numeric_vector <- c(1, 10, 49)
character_vector <- c("a", "b", "c")
boolean_vector <- c(TRUE, FALSE, TRUE)
numeric_vector## [1] 1 10 49character_vector## [1] "a" "b" "c"boolean_vector## [1] TRUE FALSE TRUEsome_vector <- c("Johnny", "Poker Player")
names(some_vector) <- c("Name", "Profession")
some_vector## Name Profession
## "Johnny" "Poker Player"# Poker winnings from Monday to Friday
poker_vector <- c(140, -50, 20, -120, 240)
# Roulette winnings from Monday to Friday
roulette_vector <- c(-24, -50, 100, -350, 10)
# Give names to both 'poker_vector' and 'roulette_vector'
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(roulette_vector) <- days_vector
names(poker_vector) <- days_vector
# Define a new variable based on a selection
poker_wednesday_1 <- poker_vector["Wednesday"]
poker_wednesday_2 <- poker_vector[3]
poker_wednesday_1## Wednesday
## 20poker_wednesday_2## Wednesday
## 20# Construction of a matrix with 3 rows that contain the numbers 1 up to 9
mymatrix <-matrix(c(1:9), byrow= T, nrow =3) # byrow= T means the matrix is filled in one row at a time
mymatrix## [,1] [,2] [,3]
## [1,] 1 2 3
## [2,] 4 5 6
## [3,] 7 8 9colnames(mymatrix) <- c("firstCol", "secondCol", "thirdCol")
rownames(mymatrix) <- c("firRow","secondRow","thirdRow")
mymatrix## firstCol secondCol thirdCol
## firRow 1 2 3
## secondRow 4 5 6
## thirdRow 7 8 9mymatix <- cbind(mymatrix, c(11:13)) # we added a column that contains the numbers 11, 12, 13mymatix <- rbind(mymatrix, c(13:15)) # we added a row that contains the numbers 13, 14, 15# Just the first row
firstRow <- mymatrix[1,]
#mean of column 2 only
my_mean <- mean(mymatrix[,2])
my_mean## [1] 5# I only want column 1 and 3
columns1and3 <- mymatrix[,c(1,3)]
columns1and3## firstCol thirdCol
## firRow 1 3
## secondRow 4 6
## thirdRow 7 9# I only want the 2nd row of column 1 and 3
row2columns1and3 <- mymatrix[2,c(1,3)]
row2columns1and3## firstCol thirdCol
## 4 6#I want the element in row 2 and column 3
row2column3 <- mymatrix[2,3]
row2column3## [1] 6#I want the element in row 1,4 and columns 1,2,3
rows1.3columns2.3 <- mymatrix[c(1,3),1:3]
rows1.3columns2.3## firstCol secondCol thirdCol
## firRow 1 2 3
## thirdRow 7 8 9mymatrix^2## firstCol secondCol thirdCol
## firRow 1 4 9
## secondRow 16 25 36
## thirdRow 49 64 81mymatrix*5## firstCol secondCol thirdCol
## firRow 5 10 15
## secondRow 20 25 30
## thirdRow 35 40 45sqrt(mymatrix) ## firstCol secondCol thirdCol
## firRow 1.000000 1.414214 1.732051
## secondRow 2.000000 2.236068 2.449490
## thirdRow 2.645751 2.828427 3.000000mymatrix*5+(sqrt(mymatrix))/(x*my_apples-my_oranges)## firstCol secondCol thirdCol
## firRow 5.004902 10.00693 15.00849
## secondRow 20.009804 25.01096 30.01201
## thirdRow 35.012969 40.01386 45.01471gender_vector <- c("Male", "Female", "Female", "Male", "Male")
# Define factor_gender_vector using 'factor()'
factor_gender_vector <- factor(gender_vector)
factor_gender_vector## [1] Male Female Female Male Male
## Levels: Female MaleThe factor function is good for creating categorical variables such as colors and genders for example. Each level represents a class/case/type/instance of the categorical variable. The levels are unordered unless specified.
temperature_vector <- c("High", "Low", "High","Low", "Medium")
#Specifying the order of the levels
factor_temperature_vector <- factor(temperature_vector, order = TRUE, levels = c("Low", "Medium", "High"))
factor_temperature_vector## [1] High Low High Low Medium
## Levels: Low < Medium < Highsummary(factor_gender_vector)## Female Male
## 2 3A data frame is a matrix that can have variables (columns) of different types (integer, numeric, logical, factor, character) A matrix can only have columns of type integer OR numeric
#There are many ways to do this,...but this is the very basic way
planets <- c("Mercury", "Venus", "Earth", "Mars", "Jupiter", "Saturn", "Uranus", "Neptune");
type <- c("Terrestrial planet", "Terrestrial planet", "Terrestrial planet", "Terrestrial planet", "Gas giant", "Gas giant", "Gas giant", "Gas giant")
diameter <- c(0.382, 0.949, 1, 0.532, 11.209, 9.449, 4.007, 3.883);
rotation <- c(58.64, -243.02, 1, 1.03, 0.41, 0.43, -0.72, 0.67);
rings <- c(FALSE, FALSE, FALSE, FALSE, TRUE, TRUE, TRUE, TRUE);
# Create the data frame:
planets_df <- data.frame(planets, type, diameter, rotation, rings)
planets_df## planets type diameter rotation rings
## 1 Mercury Terrestrial planet 0.382 58.64 FALSE
## 2 Venus Terrestrial planet 0.949 -243.02 FALSE
## 3 Earth Terrestrial planet 1.000 1.00 FALSE
## 4 Mars Terrestrial planet 0.532 1.03 FALSE
## 5 Jupiter Gas giant 11.209 0.41 TRUE
## 6 Saturn Gas giant 9.449 0.43 TRUE
## 7 Uranus Gas giant 4.007 -0.72 TRUE
## 8 Neptune Gas giant 3.883 0.67 TRUE# All data from the first three planets
closest_planets_df <- planets_df[1:3,]
# All data from the last three planets
furthest_planets_df <- planets_df[6:8,]
# Have a look:
closest_planets_df## planets type diameter rotation rings
## 1 Mercury Terrestrial planet 0.382 58.64 FALSE
## 2 Venus Terrestrial planet 0.949 -243.02 FALSE
## 3 Earth Terrestrial planet 1.000 1.00 FALSEfurthest_planets_df## planets type diameter rotation rings
## 6 Saturn Gas giant 9.449 0.43 TRUE
## 7 Uranus Gas giant 4.007 -0.72 TRUE
## 8 Neptune Gas giant 3.883 0.67 TRUE#Select for the last six rows only the diameter
furthest_planets_diameter <- planets_df[3:8, "diameter"]
furthest_planets_df## planets type diameter rotation rings
## 6 Saturn Gas giant 9.449 0.43 TRUE
## 7 Uranus Gas giant 4.007 -0.72 TRUE
## 8 Neptune Gas giant 3.883 0.67 TRUE#Select the "rings" variable/column
rings_vector <- planets_df$rings
rings_vector## [1] FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE# Planets that are smaller than planet Earth:
small_planets_df <- subset(planets_df, subset = planets_df$diameter<1)
small_planets_df## planets type diameter rotation rings
## 1 Mercury Terrestrial planet 0.382 58.64 FALSE
## 2 Venus Terrestrial planet 0.949 -243.02 FALSE
## 4 Mars Terrestrial planet 0.532 1.03 FALSE#Example of sorting
x <- c(15, 18, 293, 67, 85, 197, 65, 32)
order(x)## [1] 1 2 8 7 4 5 6 3x[order(x)]## [1] 15 18 32 65 67 85 197 293# What is the correct ordering based on the planets_df$diameter variable?
# We first order the "diameter" column
positions <- order(planets_df$diameter, decreasing = TRUE)
positions## [1] 5 6 7 8 3 2 4 1# Then we can use it to sort our data frame like this
largest_first_df <- planets_df[positions, ]
largest_first_df## planets type diameter rotation rings
## 5 Jupiter Gas giant 11.209 0.41 TRUE
## 6 Saturn Gas giant 9.449 0.43 TRUE
## 7 Uranus Gas giant 4.007 -0.72 TRUE
## 8 Neptune Gas giant 3.883 0.67 TRUE
## 3 Earth Terrestrial planet 1.000 1.00 FALSE
## 2 Venus Terrestrial planet 0.949 -243.02 FALSE
## 4 Mars Terrestrial planet 0.532 1.03 FALSE
## 1 Mercury Terrestrial planet 0.382 58.64 FALSE# Vector with numerics from 1 up to 10
my_vector <- 1:10
# Matrix with numerics from 1 up to 9
my_matrix <- matrix(1:9, ncol = 3)
# First 10 elements of the built-in data frame 'mtcars'
my_df <- mtcars[1:10,]
# Construct 'my_list' with these different elements:
my_list <- list("vec" =my_vector, "mat"=my_matrix, "df"=my_df)
my_list## $vec
## [1] 1 2 3 4 5 6 7 8 9 10
##
## $mat
## [,1] [,2] [,3]
## [1,] 1 4 7
## [2,] 2 5 8
## [3,] 3 6 9
##
## $df
## 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# The list 'shining_list'
actors <- c("Jack Nicholson","Shelley Duvall","Danny Lloyd","Scatman Crothers","Barry Nelson")
reviews <- data.frame(
scores= c(4.5,4.0,5.0),
sources= c("IMDb1","IMDb2","IMDb3"),
comments=c("Best Horror Film I Have Ever Seen",
"truly brilliant and scary film from Stanley Kubrick",
"A masterpiece of psychological horror"
)
)
shining_list <- list("moviename" = "The Shining", "actors"= actors, "reviews"= reviews)
shining_list## $moviename
## [1] "The Shining"
##
## $actors
## [1] "Jack Nicholson" "Shelley Duvall" "Danny Lloyd"
## [4] "Scatman Crothers" "Barry Nelson"
##
## $reviews
## scores sources comments
## 1 4.5 IMDb1 Best Horror Film I Have Ever Seen
## 2 4.0 IMDb2 truly brilliant and scary film from Stanley Kubrick
## 3 5.0 IMDb3 A masterpiece of psychological horror# 'last_actor'
last_actor <- shining_list$actors[5]
last_actor## [1] "Barry Nelson"# 'second_review'
second_review <- shining_list[[3]][2,]
second_review## scores sources comments
## 2 4 IMDb2 truly brilliant and scary film from Stanley Kubrick# We forgot something; add the year to shining_list
shining_list_full <- c(shining_list, "year" = c(1980))
shining_list_full## $moviename
## [1] "The Shining"
##
## $actors
## [1] "Jack Nicholson" "Shelley Duvall" "Danny Lloyd"
## [4] "Scatman Crothers" "Barry Nelson"
##
## $reviews
## scores sources comments
## 1 4.5 IMDb1 Best Horror Film I Have Ever Seen
## 2 4.0 IMDb2 truly brilliant and scary film from Stanley Kubrick
## 3 5.0 IMDb3 A masterpiece of psychological horror
##
## $year
## [1] 1980# a look at shining_list
str(shining_list_full)## List of 4
## $ moviename: chr "The Shining"
## $ actors : chr [1:5] "Jack Nicholson" "Shelley Duvall" "Danny Lloyd" "Scatman Crothers" ...
## $ reviews :'data.frame': 3 obs. of 3 variables:
## ..$ scores : num [1:3] 4.5 4 5
## ..$ sources : Factor w/ 3 levels "IMDb1","IMDb2",..: 1 2 3
## ..$ comments: Factor w/ 3 levels "A masterpiece of psychological horror",..: 2 3 1
## $ year : num 1980