All chapters together

Chapter 1 - Intro to basics
How it works
# Calculate 3 + 4
3 + 4

# Calculate 6 + 12
6+12

Arithmetic with R
# An addition
5 + 5 

# A subtraction
5 - 5 

# A multiplication
3 * 5

 # A division
(5 + 5) / 2 

# Exponentiation
2^5
#python pow(2,5) 2**5

# Modulo
28 %% 6
#python 28%6

Variable assignment
# Assign the value 42 to x
x <- 42
#python x=42
# Print out the value of the variable x
x


Variable assignment (2)
# Assign the value 5 to the variable my_apples
my_apples <- 5

# Print out the value of the variable my_apples
my_apples

Variable assignment (3)
# Assign a value to the variables my_apples and my_oranges
my_apples <- 5
my_oranges <- 6

# Add these two variables together
my_apples + my_oranges

# Create the variable my_fruit
my_fruit=my_apples + my_oranges

Apples and oranges
# Assign a value to the variable my_apples
my_apples <- 5 

# Fix the assignment of my_oranges
my_oranges <- 6

# Create the variable my_fruit and print it out
my_fruit <- my_apples + my_oranges 
my_fruit

Basic data types in R
# Change my_numeric to be 42
my_numeric <- 42

# Change my_character to be "universe"
my_character <- "universe"

# Change my_logical to be FALSE
my_logical <- FALSE

What's that data type?
# Declare variables of different types
my_numeric <- 42
my_character <- "universe"
my_logical <- FALSE 

# Check class of my_numeric
class(my_numeric)

# Check class of my_character
class(my_character)

# Check class of my_logical
class(my_logical)

Chapter 2- Vectors
Create a vector



# Define the variable vegas
vegas <- "Go!"


Create a vector (2)

numeric_vector <- c(1, 10, 49)
character_vector <- c("a", "b", "c")

# Complete the code for boolean_vector
boolean_vector <- c(TRUE,FALSE,TRUE)

Create a vector (3)
# 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)

Naming a vector
# 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)

# Assign days as names of poker_vector
names(poker_vector) <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
poker_vector
# Assign days as names of roulette_vector
names(roulette_vector) <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
roulette_vector


Naming a vector (2)
# 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)

# The variable days_vector
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
 
# Assign the names of the day to roulette_vector and poker_vector
names(poker_vector) <-  days_vector 
names(roulette_vector) <- days_vector

Calculating total winnings
A_vector <- c(1, 2, 3)
B_vector <- c(4, 5, 6)

# Take the sum of A_vector and B_vector
total_vector <- A_vector + B_vector
  
# Print out total_vector
total_vector

Calculating total winnings (2)
# Poker and roulette winnings from Monday to Friday:
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Assign to total_daily how much you won/lost on each day
total_daily <- poker_vector + roulette_vector
#total_daily
# the names of two vectors are the same


Calculating total winnings (3)
# Poker and roulette winnings from Monday to Friday:
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Total winnings with poker
total_poker <- sum(poker_vector)

# Total winnings with roulette
total_roulette <-  sum(roulette_vector)

# Total winnings overall
total_week <- sum(poker_vector) + sum(roulette_vector)

# Print out total_week
total_week

Comparing total winnings
# Poker and roulette winnings from Monday to Friday:
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Calculate total gains for poker and roulette
total_poker <- sum(poker_vector)
total_roulette <- sum(roulette_vector)

# Check if you realized higher total gains in poker than in roulette
total_poker > total_roulette

Vector selection: the good times
# Poker and roulette winnings from Monday to Friday:
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Define a new variable based on a selection
poker_wednesday <- poker_vector[3]
#poker_wednesday

Vector selection: the good times (2)
# Poker and roulette winnings from Monday to Friday:
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Define a new variable based on a selection
poker_midweek <- poker_vector[c(2,3,4)]

Vector selection: the good times (3)
# Poker and roulette winnings from Monday to Friday:
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Define a new variable based on a selection
roulette_selection_vector <- roulette_vector[2:5]


Vector selection: the good times (4)
# Poker and roulette winnings from Monday to Friday:
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Select poker results for Monday, Tuesday and Wednesday
poker_start <- poker_vector[c("Monday",'Tuesday','Wednesday')]
  
# Calculate the average of the elements in poker_start
mean(poker_start)


Selection by comparison - Step 1
# Poker and roulette winnings from Monday to Friday:
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Which days did you make money on poker?
selection_vector <- (poker_vector >0)
  
# Print out selection_vector
selection_vector

Selection by comparison - Step 2
# Poker and roulette winnings from Monday to Friday:
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Which days did you make money on poker?
selection_vector <- poker_vector > 0

# Select from poker_vector these days
poker_winning_days <- poker_vector[selection_vector]

Advanced selection
# Poker and roulette winnings from Monday to Friday:
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Which days did you make money on roulette?
selection_vector <- (roulette_vector>0)

# Select from roulette_vector these days
roulette_winning_days <- roulette_vector[selection_vector]



Chapter 3 - Matrices
What's a matrix?
# Construct a matrix with 3 rows that contain the numbers 1 up to 9
matrix(1:9, byrow = TRUE, nrow = 3)

Analyze matrices, you shall
# Box office Star Wars (in millions!)
new_hope <- c(460.998, 314.4)
empire_strikes <- c(290.475, 247.900)
return_jedi <- c(309.306, 165.8)

# Create box_office
box_office <- c(new_hope, empire_strikes, return_jedi)

# Construct star_wars_matrix
star_wars_matrix <- matrix(box_office, byrow = TRUE, nrow = 3)

Naming a matrix
# Box office Star Wars (in millions!)
new_hope <- c(460.998, 314.4)
empire_strikes <- c(290.475, 247.900)
return_jedi <- c(309.306, 165.8)

# Construct matrix
star_wars_matrix <- matrix(c(new_hope, empire_strikes, return_jedi), nrow = 3, byrow = TRUE)

# Vectors region and titles, used for naming
region <- c("US", "non-US")
titles <- c("A New Hope", "The Empire Strikes Back", "Return of the Jedi")

# Name the columns with region
colnames(star_wars_matrix) <- region

# Name the rows with titles
rownames(star_wars_matrix) <- titles


# Print out star_wars_matrix
star_wars_matrix

Calculating the worldwide box office
# Construct star_wars_matrix
box_office <- c(460.998, 314.4, 290.475, 247.900, 309.306, 165.8)
region <- c("US", "non-US")
titles <- c("A New Hope", 
                 "The Empire Strikes Back", 
                 "Return of the Jedi")
               
star_wars_matrix <- matrix(box_office, 
                      nrow = 3, byrow = TRUE,
                      dimnames = list(titles, region))
#star_wars_matrix
# Calculate worldwide box office figures
worldwide_vector <- rowSums(star_wars_matrix)

Adding a column for the Worldwide box office
# Construct star_wars_matrix
box_office <- c(460.998, 314.4, 290.475, 247.900, 309.306, 165.8)
region <- c("US", "non-US")
titles <- c("A New Hope", 
            "The Empire Strikes Back", 
            "Return of the Jedi")
               
star_wars_matrix <- matrix(box_office, 
                      nrow = 3, byrow = TRUE,
                      dimnames = list(titles, region))

# The worldwide box office figures
worldwide_vector <- rowSums(star_wars_matrix)

# Bind the new variable worldwide_vector as a column to star_wars_matrix
all_wars_matrix <- cbind(star_wars_matrix ,worldwide_vector )

Adding a row
# star_wars_matrix and star_wars_matrix2 are available in your workspace
star_wars_matrix  
star_wars_matrix2 

# Combine both Star Wars trilogies in one matrix
all_wars_matrix <- rbind(star_wars_matrix  ,star_wars_matrix2)
all_wars_matrix
#all_wars_matrixp <- cbind(star_wars_matrix  ,star_wars_matrix2)
#all_wars_matrixp

The total box office revenue for the entire saga
# all_wars_matrix is available in your workspace
all_wars_matrix

# Total revenue for US and non-US
total_revenue_vector <- (colSums(all_wars_matrix))
  
# Print out total_revenue_vector
total_revenue_vector

Selection of matrix elements
# all_wars_matrix is available in your workspace
all_wars_matrix

# Select the non-US revenue for all movies
non_us_all <- (all_wars_matrix[,2])
non_us_all
# Average non-US revenue
mean(non_us_all)
  
# Select the non-US revenue for first two movies
non_us_some <- (all_wars_matrix[1:2,2])
  
# Average non-US revenue for first two movies
mean(non_us_some)

A little arithmetic with matrices
# all_wars_matrix is available in your workspace
all_wars_matrix

# Estimate the visitors
visitors <- all_wars_matrix/5
  
# Print the estimate to the console
visitors

A little arithmetic with matrices (2)
# all_wars_matrix and ticket_prices_matrix are available in your workspace
all_wars_matrix
ticket_prices_matrix

# Estimated number of visitors
visitors <- all_wars_matrix/ticket_prices_matrix
visitors
# US visitors
us_visitors <- visitors[,1]

# Average number of US visitors
mean(us_visitors)



Chapter 4 - Factors
What's a factor and why would you use it?

# Assign to the variable theory what this chapter is about!
theory="factors"

What's a factor and why would you use it? (2)

# Sex vector
sex_vector <- c("Male", "Female", "Female", "Male", "Male")

# Convert sex_vector to a factor
factor_sex_vector <- factor(sex_vector)

# Print out factor_sex_vector
factor_sex_vector

What's a factor and why would you use it? (3)

# Animals
animals_vector <- c("Elephant", "Giraffe", "Donkey", "Horse")
factor_animals_vector <- factor(animals_vector)
factor_animals_vector

# Temperature
temperature_vector <- c("High", "Low", "High","Low", "Medium")
factor_temperature_vector <- factor(temperature_vector, order = TRUE, levels = c("Low", "Medium", "High"))
factor_temperature_vector

Factor levels
# Code to build factor_survey_vector
survey_vector <- c("M", "F", "F", "M", "M")
factor_survey_vector <- factor(survey_vector)

# Specify the levels of factor_survey_vector
levels(factor_survey_vector) <- c("Male","Female")

factor_survey_vector


Factor levels

# Code to build factor_survey_vector
survey_vector <- c("M", "F", "F", "M", "M")
factor_survey_vector <- factor(survey_vector)

# Specify the levels of factor_survey_vector
levels(factor_survey_vector) <- c("Female", "Male")

factor_survey_vector

Summarizing a factor

# Build factor_survey_vector with clean levels
survey_vector <- c("M", "F", "F", "M", "M")
factor_survey_vector <- factor(survey_vector)
levels(factor_survey_vector) <- c("Female", "Male")
factor_survey_vector

# Generate summary for survey_vector
summary(survey_vector)

# Generate summary for factor_survey_vector
summary(factor_survey_vector)


Battle of the sexes

# Build factor_survey_vector with clean levels
survey_vector <- c("M", "F", "F", "M", "M")
factor_survey_vector <- factor(survey_vector)
levels(factor_survey_vector) <- c("Female", "Male")

# Male
male <- factor_survey_vector[1]

# Female
female <- factor_survey_vector[2]

# Battle of the sexes: Male 'larger' than female?
male > female


Ordered factors

# Create speed_vector
speed_vector <- c('medium','slow','slow','medium','fast')
speed_vector

Ordered factors (2)

# Create speed_vector
speed_vector <- c("medium", "slow", "slow", "medium", "fast")

# Convert speed_vector to ordered factor vector
factor_speed_vector <- factor(speed_vector,ordered = TRUE,levels=c("slow", "medium", "fast"))

# Print factor_speed_vector
factor_speed_vector
summary(factor_speed_vector)


Comparing ordered factors

# Create factor_speed_vector
speed_vector <- c("medium", "slow", "slow", "medium", "fast")
factor_speed_vector <- factor(speed_vector, ordered = TRUE, levels = c("slow", "medium", "fast"))

# Factor value for second data analyst
da2 <- factor_speed_vector[2]

# Factor value for fifth data analyst
da5 <- factor_speed_vector[5]

# Is data analyst 2 faster than data analyst 5?
da2>da5



Chapter 5- Data frames
What's a data frame?

# Print out built-in R data frame
mtcars 

Quick, have a look at your dataset
# Call head() on mtcars
head(mtcars)

Have a look at the structure

# Investigate the structure of mtcars
str(mtcars)


Creating a data frame

# Definition of vectors
name <- 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 a data frame from the vectors
planets_df <- data.frame(name, type, diameter, rotation, rings)
#planets_df


Creating a data frame (2)

# Check the structure of planets_df
str(planets_df)


Selection of data frame elements

# The planets_df data frame from the previous exercise is pre-loaded
planets_df
# Print out diameter of Mercury (row 1, column 3)
planets_df[1,3]

# Print out data for Mars (entire fourth row)
planets_df[4,]

Selection of data frame elements (2)

# The planets_df data frame from the previous exercise is pre-loaded

# Select first 5 values of diameter column
planets_df[1:5,"diameter"]


Only planets with rings

# planets_df is pre-loaded in your workspace

# Select the rings variable from planets_df
rings_vector <- planets_df[,"rings"]
  
# Print out rings_vector
rings_vector


Only planets with rings (2)

# planets_df and rings_vector are pre-loaded in your workspace

# Adapt the code to select all columns for planets with rings
planets_df[rings_vector, ]


Only planets with rings but shorter

# planets_df is pre-loaded in your workspace

# Select planets with diameter < 1
subset(planets_df, diameter < 1)


Sorting


# Play around with the order function in the console
a <- c(134567, 1567890, 3456)
order(a)
a[order(a)]


Sorting your data frame

# planets_df is pre-loaded in your workspace

# Use order() to create positions
positions <- order(planets_df$diameter)
positions
# Use positions to sort planets_df
planets_df[positions, ]



Chapter 6- Lists
Lists, why would you need them?

# Just submit the answer

Lists, why would you need them? (2)

# Just submit the answer to start the first exercise on lists.

Creating a list

# Vector with numerics from 1 up to 10
my_vector <- 1:10 
my_vector
# Matrix with numerics from 1 up to 9
my_matrix <- matrix(1:9, ncol = 3)
my_matrix
# First 10 elements of the built-in data frame mtcars
my_df <- mtcars[1:10,]
my_df
# Construct list with these different elements:
my_list <- list(my_vector, my_matrix,my_df)


Creating a named list

# 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,]

# Adapt list() call to give the components names
my_list <- list(vec=my_vector, mat=my_matrix, df=my_df)
#Alternative way
#my_list <- list(my_vector, my_matrix, my_df)
#names(my_list) <- c("vec", "mat","df")
# Print out my_list
my_list

Creating a named list (2)

# The variables mov, act and rev are available

# Finish the code to build shining_list
shining_list <- list(moviename = mov, actors=act, reviews=rev)
shining_list

Selecting elements from a list

# shining_list is already pre-loaded in the workspace
shining_list
# Print out the vector representing the actors
shining_list[[2]]

# Print the second element of the vector representing the actors
shining_list[[2]][2]

Creating a new list for another movie

# Use the table from the exercise to define the comments and scores vectors
scores <- c(4.6, 5, 4.8, 5, 4.2)
comments <- c("I would watch it again", "Amazing!", "I liked it", "One of the best movies", 'Fascinating plot') 

# Save the average of the scores vector as avg_review
avg_review=mean(scores)

# Combine scores and comments into the reviews_df data frame
reviews_df=data.frame(scores,comments)

# Create and print out a list, called departed_list
departed_list<- list(movie_title, movie_actors, reviews_df, avg_review)
departed_list