##Tried to install packages when they failed to load while coding
library(dplyr) # Load the dplyr package
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
library(RColorBrewer)
library(ggplot2)
library(dplyr)
library(completejourney)
## Welcome to the completejourney package! Learn more about these data
## sets at http://bit.ly/completejourney.
library(scales)
library(reshape2)
library(ggcorrplot)
library(gganimate)
library(gifski)
# Loading the datasets from the completejourney package
data("transactions_sample")
data("demographics")
data("products")
data("campaigns")
data("coupon_redemptions")
##Identifying Customer Segmentation by Age and Coupon Redemption Impact
# Join the datasets and calculate average sales by age group and coupon usage
coupon_analysis <- transactions_sample %>%
inner_join(demographics, by = "household_id") %>%
left_join(coupon_redemptions, by = "household_id", relationship = "many-to-many") %>%
mutate(coupon_used = !is.na(coupon_upc)) %>%
group_by(age, coupon_used) %>%
summarise(total_sales = sum(sales_value, na.rm = TRUE),
household_count = n()) %>%
mutate(avg_sales = total_sales / household_count)
## `summarise()` has grouped output by 'age'. You can override using the `.groups`
## argument.
# Basic plot for Coupon Usage Impact on Sales by Age Group
ggplot(coupon_analysis, aes(x = age, y = avg_sales, fill = coupon_used)) +
geom_bar(stat = "identity", position = "dodge") +
scale_fill_manual(values = c("#FF9999", "#66B2FF")) +
labs(title = "Coupon Usage Impact by Age", x = "Age Group", y = "Avg Sales") +
theme_minimal() +
scale_y_continuous(labels = scales::dollar_format()) +
theme(axis.text.x = element_text(angle = 0), plot.title = element_text(hjust = 0.5))
# 2nd Plot
# Summarizing the sales data by product category and filter top 10 categories
category_sales <- transactions_sample %>%
inner_join(products, by = "product_id") %>%
group_by(department) %>%
summarise(total_sales = sum(sales_value, na.rm = TRUE)) %>%
top_n(10, total_sales) # Select top 10 categories by sales
# Creating a clearer pie chart with larger labels and better sorting
ggplot(category_sales, aes(x = "", y = total_sales, fill = reorder(department, total_sales))) +
geom_bar(stat = "identity", width = 1, color = "white") +
coord_polar(theta = "y") +
labs(title = "Top 10 Sales Distribution by Product Category") +
theme_void() + # Removes unnecessary elements for clarity
scale_fill_brewer(palette = "Set3") + # Use a color palette for better contrast
theme(legend.position = "right", legend.title = element_blank()) # Position and simplify the legend
####PLOT 3
# Aggregating total spending by income and marital status
bar_chart_data <- transactions_sample %>%
inner_join(demographics, by = "household_id") %>%
group_by(income, marital_status) %>%
summarise(total_spent = sum(sales_value, na.rm = TRUE), .groups = "drop") # Aggregating total spending
# This is used to define colors || Using retro palette
retro_metro_palette <- c("#ea5545", "#f46a9b", "#ef9b20", "#edbf33", "#ede15b",
"#bdcf32", "#87bc45", "#27aef7", "#b33dc6")
# Create the stacked bar chart with the new color palette
ggplot(bar_chart_data, aes(x = income, y = total_spent, fill = marital_status)) +
geom_bar(stat = "identity", position = "stack") +
labs(title = "Total Spending by Income and Marital Status",
x = "Household Income", y = "Total Spending (USD)") +
theme_minimal() +
scale_fill_manual(values = retro_metro_palette[1:length(unique(bar_chart_data$marital_status))]) + # Apply the Retro Metro palette
theme(plot.title = element_text(face = "bold", size = 14, hjust = 0.5),
axis.text = element_text(size = 12),
axis.text.x = element_text(angle = 45, hjust = 1), # Rotate the x-axis labels
plot.margin = margin(10, 10, 10, 10)) # Adjust the margin for better spacing
