Introduction to R programming | Datacamp - Introduction to R programming | R programming for data scientist | Programming language for Data Scientist

An introduction to R from Datacamp

In this chapter, we will learn about the basics and widely used data structures in R like vectors, factors, lists, and data frames. 

Arithmetic operations:

# 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

Variable Assignment:

# 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

[1] 11

Basic data types in R:

# Declare variables of different types

my_numeric <- 42

my_character <- "universe"

my_logical <- FALSE 

# Check class of my_numeric

class(my_numeric)

[1] "numeric"

# Check class of my_character

class(my_character)

[1] "character"

# Check class of my_logical

class(my_logical)

[1] "logical"

Vectors:

# Creating vectors

numeric_vector <- c(1, 10, 49)

character_vector <- c("a", "b", "c")

# Complete the code for boolean_vector

boolean_vector <- c(TRUE,FALSE,TRUE)

# Naming vectors 1

# 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")

# Assign days as names of roulette_vector

names(roulette_vector) <- c("Monday", "Tuesday", "Wednesday", 

"Thursday", "Friday")

# Naming vectors 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

[1] 5 7 9

# 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

# Total winnings with poker

total_poker <- sum(poker_vector)

# Total winnings with roulette

total_roulette <- sum(roulette_vector) 

# Total winnings overall

total_week <- total_poker + total_roulette

# Print out total_week

total_week

[1] -84

# 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

checkit <- total_poker > total_roulette

checkit

[1] TRUE

# Vector 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

# Define a new variable based on a selection

roulette_selection_vector <- roulette_vector[2:5]

# Vector selection 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

# 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)

[1] 36.66667

# Vector selection by comparison

# 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

Monday Tuesday Wednesday Thursday Friday TRUE FALSE TRUE FALSE TRUE

# Vector selection by comparison 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 roulette?

selection_vector <- roulette_vector >0

# Select from roulette_vector these days

roulette_winning_days <- roulette_vector[selection_vector]

Matrices:

# Construct a matrix with 3 rows that contain the numbers 1 up to 9

matrix(1:9, byrow = TRUE, nrow = 3)

[,1] [,2] [,3] [1,] 1 2 3 [2,] 4 5 6 [3,] 7 8 9

# 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)

# 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

US non-US A New Hope 460.998 314.4 The Empire Strikes Back 290.475 247.9 Return of the Jedi 309.306 165.8

# 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))

# 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)

# 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

US non-US 2226.3 2087.8

# 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]

  

# 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)

[1] 281.15

# Arithmetic with matrices

# all_wars_matrix and ticket_prices_matrix are available in your workspace

all_wars_matrix

[1]

all_wars_matrix

US non-US A New Hope 461.0 314.4 The Empire Strikes Back 290.5 247.9 Return of the Jedi 309.3 165.8 The Phantom Menace 474.5 552.5 Attack of the Clones 310.7 338.7 Revenge of the Sith 380.3 468.5

ticket_prices_matrix

[2]

ticket_prices_matrix

US non-US A New Hope 5.0 5.0 The Empire Strikes Back 6.0 6.0 Return of the Jedi 7.0 7.0 The Phantom Menace 4.0 4.0 Attack of the Clones 4.5 4.5 Revenge of the Sith 4.9 4.9

# Estimated number of visitors

visitors <- all_wars_matrix/ticket_prices_matrix

# US visitors

us_visitors <- visitors[,1]

# Average number of US visitors

mean(us_visitors)

[1] 75.01401

Factors:

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

theory <- "factors"

# 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

[1] Male Female Female Male Male Levels: Female Male

# Animals

animals_vector <- c("Elephant", "Giraffe", "Donkey", "Horse")

factor_animals_vector <- factor(animals_vector)

factor_animals_vector

[1] Elephant Giraffe Donkey Horse Levels: Donkey Elephant Giraffe Horse

# 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

[1] High Low High Low Medium Levels: Low < Medium < High

# 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

[1] Male Female Female Male Male Levels: Female Male

# 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)

Female Male 2 3

# 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")

# 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

[1] medium slow slow medium fast Levels: slow < medium < fast

summary(factor_speed_vector)

slow medium fast 2 2 1

# 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

[1] FALSE

Data frames:

# Print out built-in R data frame

mtcars 

# Call head() on mtcars

head(mtcars)

mpg cyl disp hp drat wt qsec vs am gear carb Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4 Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4 Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1 Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1 Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2 Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1

# finding the structure of the dataset

# Investigate the structure of mtcars

str(mtcars)

'data.frame': 32 obs. of 11 variables: $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ... $ cyl : num 6 6 4 6 8 6 8 4 4 6 ... $ disp: num 160 160 108 258 360 ... $ hp : num 110 110 93 110 175 105 245 62 95 123 ... $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ... $ wt : num 2.62 2.88 2.32 3.21 3.44 ... $ qsec: num 16.5 17 18.6 19.4 17 ... $ vs : num 0 0 1 1 0 1 0 1 1 1 ... $ am : num 1 1 1 0 0 0 0 0 0 0 ... $ gear: num 4 4 4 3 3 3 3 4 4 4 ... $ carb: num 4 4 1 1 2 1 4 2 2 4 ...

# 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)

# Check the structure of planets_df

str(planets_df)

'data.frame': 8 obs. of 5 variables: $ name : chr "Mercury" "Venus" "Earth" "Mars" ... $ type : chr "Terrestrial planet" "Terrestrial planet" "Terrestrial planet" 

"Terrestrial planet"... $ diameter: num 0.382 0.949 1 0.532 11.209 ... $ rotation: num 58.64 -243.02 1 1.03 0.41 ... $ rings : logi FALSE FALSE FALSE FALSE TRUE TRUE ...

# Selection of data frame elements

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

# Print out diameter of Mercury (row 1, column 3)

planets_df[1,3]

[1] 0.382

# Print out data for Mars (entire fourth row)

planets_df[4,]

name type diameter rotation rings 4 Mars Terrestrial planet 0.532 1.03 FALSE

# Select first 5 values of diameter column

planets_df[1:5, "diameter"]

[1] 0.382 0.949 1.000 0.532 11.209

# Select the rings variable from planets_df

rings_vector <- planets_df$rings

  

# Print out rings_vector

rings_vector

[1] FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE

# Adapt the code to select all columns for planets with rings

planets_df[rings_vector, ]

name 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

# Select planets with diameter < 1

subset(planets_df,diameter < 1)

name 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

# Sorting the data frame

# Use order() to create positions

positions <- order(planets_df$diameter)

# Use positions to sort planets_df

planets_df[positions, ]

name type diameter rotation rings 1 Mercury Terrestrial planet 0.382 58.64 FALSE 4 Mars Terrestrial planet 0.532 1.03 FALSE 2 Venus Terrestrial planet 0.949 -243.02 FALSE 3 Earth Terrestrial planet 1.000 1.00 FALSE 8 Neptune Gas giant 3.883 0.67 TRUE 7 Uranus Gas giant 4.007 -0.72 TRUE 6 Saturn Gas giant 9.449 0.43 TRUE 5 Jupiter Gas giant 11.209 0.41 TRUE

Lists:

# Creating a 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(my_vector, my_matrix, my_df)

# Print out my_list

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 variables mov, act and rev are available

# Finish the code to build shining_list

shining_list <- list(moviename = mov, actors = act, reviews = rev)

# Print out the vector representing the actors

shining_list$actors

[1] "Jack Nicholson" "Shelley Duvall" "Danny Lloyd" "Scatman Crothers" [5] "Barry Nelson"

# Print the second element of the vector representing the actors

shining_list$actors[2]

[1] "Shelley Duvall"

# 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

[[1]] [1] "The Departed" [[2]] [1] "Leonardo DiCaprio" "Matt Damon" "Jack Nicholson" [4] "Mark Wahlberg" "Vera Farmiga" "Martin Sheen" [[3]] scores comments 1 4.6 I would watch it again 2 5.0 Amazing! 3 4.8 I liked it 4 5.0 One of the best movies 5 4.2 Fascinating plot [[4]] [1] 4.72

Thank you.