R Notebook

R Objects Demonstration

Scalar

A scalar in R is a single value, such as a number or a string.

# Numeric scalar
num_scalar <- 42

# Character scalar
char_scalar <- "Hello, world!"

num_scalar

[1] 42

char_scalar

[1] "Hello, world!"

Vector

Vectors store a collection of elements of the same type.

# Numeric vector
num_vec <- c(1, 2, 3, 4)

# Character vector
char_vec <- c("A", "B", "C")

num_vec

[1] 1 2 3 4

char_vec

[1] "A" "B" "C"

List

Lists can store elements of different types.

my_list <- list(name = "Alice", age = 30, scores = c(85, 90, 88))
my_list

$name
[1] "Alice"

$age
[1] 30

$scores
[1] 85 90 88

Matrix

A matrix is a two-dimensional structure where all elements are of the same type.

mat <- matrix(1:6, nrow = 2, ncol = 3)
mat

     [,1] [,2] [,3]
[1,]    1    3    5
[2,]    2    4    6

Array

An array can have more than two dimensions.

arr <- array(1:12, dim = c(3, 2, 2))
arr

, , 1

     [,1] [,2]
[1,]    1    4
[2,]    2    5
[3,]    3    6

, , 2

     [,1] [,2]
[1,]    7   10
[2,]    8   11
[3,]    9   12

Data Frame

A data frame is a table-like structure where columns can have different types.

df <- data.frame(Name = c("Alice", "Bob"), Age = c(25, 30))
df

Factor

Factors handle categorical data.

gender <- factor(c("Male", "Female", "Female"))
gender

[1] Male   Female Female
Levels: Female Male

Function

Functions are objects that perform specific tasks.

add <- function(a, b) {
  return(a + b)
}

add(5, 7)

[1] 12

Checking Object Types

You can inspect the type or structure of an object using built-in functions.

class(num_vec)  # Class of the vector

[1] "numeric"

str(my_list)    # Structure of the list

List of 3
 $ name  : chr "Alice"
 $ age   : num 30
 $ scores: num [1:3] 85 90 88

typeof(mat)     # Type of the matrix

[1] "integer"

email_data %>% group_by(EmailID) %>% summarise(email_count = n()) %>%
summarise(email_count > 1)

G1;H1;Errorh in email_data %>% group_by(EmailID) %>% summarise(email_count = n()) %>%  : 
  could not find function "%>%"
Error during wrapup: not that many frames on the stack
Error: no more error handlers available (recursive errors?); invoking 'abort' restart
g

if (!require("tidyverse")) install.packages("tidyverse")

G3;Loading required package: tidyverse
g── Attaching core tidyverse packages ────────────────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.2     ✔ tibble    3.2.1
✔ lubridate 1.9.4     ✔ tidyr     1.3.1
✔ purrr     1.0.4     
── Conflicts ──────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors

library(tidyverse)

load("HW1_Retail_Transactions_Data.RData")

head(retail_transaction_records)

head(retail_transaction_details)

# Method 1: Using dplyr's left_join
retail_data <- left_join(retail_transaction_records, retail_transaction_details, by = "TransactionID")

# Method 2: Using base R's merge function
retail_data2 <- merge(retail_transaction_records, retail_transaction_details, by = "TransactionID")

mean(retail_data$Price)

[1] 16.75

retail_data <- retail_data %>%
  mutate(Revenue = Price * Quantity)

retail_data <- retail_data %>%
  mutate(ProductCategory = ifelse(ProductID %in% c("P0", "P1", "P2"), "CategoryA", "CategoryB"))

units_per_category <- retail_data %>%
  group_by(ProductCategory) %>%
  summarise(TotalUnits = sum(Quantity))
units_per_category

top_product <- retail_data %>%
  group_by(ProductID) %>%
  summarise(TotalRevenue = sum(Revenue)) %>%
  arrange(desc(TotalRevenue)) %>%
  slice(1)
top_product

transactions_per_payment <- retail_data %>%
  group_by(PaymentMethod) %>%
  summarise(NumTransactions = n())
transactions_per_payment

discount_proportion <- retail_data %>%
  group_by(ProductID, Channel) %>%
  summarise(ProportionDiscounted = mean(DiscountApplied))

`summarise()` has grouped output by 'ProductID'. You can override using the `.groups`
argument.

discount_proportion

most_recent_date <- max(retail_data$TransactionDate)
most_recent_date

[1] "2024-04-09 UTC"

discounted_cash_purchases <- retail_data %>%
  filter(DiscountApplied == 1, PaymentMethod == "Cash") %>%
  nrow()
discounted_cash_purchases

[1] 4