# Load libraries and data
library(tidyverse)
## ── 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 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.1.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(scales)
##
## Attaching package: 'scales'
##
## The following object is masked from 'package:purrr':
##
## discard
##
## The following object is masked from 'package:readr':
##
## col_factor
library(viridis)
## Loading required package: viridisLite
##
## Attaching package: 'viridis'
##
## The following object is masked from 'package:scales':
##
## viridis_pal
library(ggrepel)
# Load the DataMart data
datamart <- read_csv("datamart_customer_analytics.csv")
## Rows: 2240 Columns: 29
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Education, Marital_Status, Dt_Customer
## dbl (26): ID, Year_Birth, Income, Kidhome, Teenhome, Recency, MntWines, MntF...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
# Clean & prep
datamart <- datamart %>%
filter(!is.na(Income)) %>%
mutate(
total_spending = rowSums(select(., starts_with("Mnt")), na.rm = TRUE),
total_purchases = NumWebPurchases + NumCatalogPurchases + NumStorePurchases,
recency = Recency,
Complain = factor(Complain, labels = c("No","Yes"))
)
cat("Dataset: ", nrow(datamart), "customers, ",
ncol(datamart), "variables\n")
## Dataset: 2216 customers, 32 variables
# Show relevant variables for our question
relevant_vars <- c("Education", "Income", "Marital_Status", "Kidhome", "Teenhome", "NumWebPurchases", "NumCatalogPurchases", "NumStorePurchases")
datamart %>% select(all_of(relevant_vars)) %>% head()
## # A tibble: 6 × 8
## Education Income Marital_Status Kidhome Teenhome NumWebPurchases
## <chr> <dbl> <chr> <dbl> <dbl> <dbl>
## 1 Graduation 58138 Single 0 0 8
## 2 Graduation 46344 Single 1 1 1
## 3 Graduation 71613 Together 0 0 8
## 4 Graduation 26646 Together 1 0 2
## 5 PhD 58293 Married 1 0 5
## 6 Master 62513 Together 0 1 6
## # ℹ 2 more variables: NumCatalogPurchases <dbl>, NumStorePurchases <dbl>
# Our first visualization attempt
# Calculate average purchases per channel
channel_means <- datamart %>%
summarise(
Store = mean(NumStorePurchases),
Web = mean(NumWebPurchases),
Catalog = mean(NumCatalogPurchases)
) %>%
pivot_longer(cols = everything(), names_to = "Channel", values_to = "AvgPurchases")
# Create the plot
plot_v1 <- ggplot(channel_means, aes(x = Channel, y = AvgPurchases, fill = Channel)) +
geom_col() +
labs(
title = "First Attempt: Average Purchases Across Channels",
subtitle = "Identifying issues with this approach",
x = "Purchase Channel",
y = "Average Number of Purchases"
) +
theme_minimal()
print(plot_v1)
# Improved version addressing the main issue
# Calculate average purchases by Education level
edu_channel <- datamart %>%
group_by(Education) %>%
summarise(
Store = mean(NumStorePurchases),
Web = mean(NumWebPurchases),
Catalog = mean(NumCatalogPurchases)
) %>%
pivot_longer(cols = c(Store, Web, Catalog), names_to = "Channel", values_to = "AvgPurchases")
# Create the plot
plot_v2 <- ggplot(edu_channel, aes(x = Education, y = AvgPurchases, group = Channel, color = Channel)) +
geom_line(size = 1.2, aes(linetype = Channel)) + # Added linetype for better distinction in B&W
geom_point(size = 2) +
labs(
title = "Iteration 1: Channel Preferences by Education Level",
subtitle = "How this addresses the problem of customer segmentation",
x = "Education Level",
y = "Average Number of Purchases",
color = "Channel",
linetype = "Channel"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
print(plot_v2)
# Further refinements
# Use the same data as Iteration 1
plot_v3 <- ggplot(edu_channel, aes(x = Education, y = AvgPurchases, group = 1, fill = Channel)) +
geom_col() + # Using bars for a different aesthetic within facets
facet_wrap(~ Channel, scales = "free_y", ncol = 1) + # This is the key change: separate facets with free y-scales
labs(
title = "Iteration 2: Channel Usage by Education (Faceted View)",
subtitle = "Separate scales for each channel reveal hidden patterns",
x = "Education Level",
y = "Average Number of Purchases",
fill = "Channel"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
print(plot_v3)
## Rows: 2240 Columns: 29
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Education, Marital_Status, Dt_Customer
## dbl (26): ID, Year_Birth, Income, Kidhome, Teenhome, Recency, MntWines, MntF...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## Dataset: 2216 customers, 32 variables
## # A tibble: 6 × 8
## Education Income Marital_Status Kidhome Teenhome NumWebPurchases
## <chr> <dbl> <chr> <dbl> <dbl> <dbl>
## 1 Graduation 58138 Single 0 0 8
## 2 Graduation 46344 Single 1 1 1
## 3 Graduation 71613 Together 0 0 8
## 4 Graduation 26646 Together 1 0 2
## 5 PhD 58293 Married 1 0 5
## 6 Master 62513 Together 0 1 6
## # ℹ 2 more variables: NumCatalogPurchases <dbl>, NumStorePurchases <dbl>