CompleteJourney Data Visualization

library(completejourney)
library(dplyr)
library(ggplot2)

# Load the sample datasets provided by completejourney
data("transactions_sample")
data("products")
data("demographics")
income_products <- transactions_sample %>%
  left_join(products, by = "product_id") %>%
  left_join(demographics, by = "household_id") %>%
  group_by(income, product_category) %>%
  summarise(total_sales_value = sum(sales_value, na.rm = TRUE)) %>%
  arrange(desc(total_sales_value)) %>%
  group_by(income) %>%
  top_n(5, total_sales_value)

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

ggplot(income_products, aes(x = reorder(product_category, total_sales_value), y = total_sales_value, fill = income)) +
  geom_bar(stat = "identity", position = position_dodge(width = 0.8)) +  # Dodge for side-by-side bars
  labs(title = "Top 5 Products Purchased by Income Level",
       subtitle = "Total sales value comparison across income groups",
       x = "Product Category", y = "Total Sales Value") +
  theme_minimal() +
  theme(
    plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 12, hjust = 0.5),
    axis.text.x = element_text(angle = 45, hjust = 1, size = 10),  # Adjust rotation for x-axis labels
    axis.text.y = element_text(size = 10),
    axis.title.x = element_text(size = 12),
    axis.title.y = element_text(size = 12),
    legend.position = "right"
  )

# Plot 2: Customer Loyalty vs. Purchase Frequency
ggplot(loyalty_data, aes(x = as.factor(loyalty), y = purchase_frequency, fill = as.factor(loyalty))) +
  geom_boxplot() +
  labs(title = "Customer Loyalty vs. Purchase Frequency",
       subtitle = "Distribution of purchase frequency by household size",
       x = "Household Size (Loyalty)", y = "Purchase Frequency") +
  theme_minimal() +
  theme(
    plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 12, hjust = 0.5),
    axis.text.x = element_text(size = 10),
    axis.text.y = element_text(size = 10),
    axis.title.x = element_text(size = 12),
    axis.title.y = element_text(size = 12),
    legend.position = "none"
  )

# Ensure that the transaction_timestamp is in POSIXct format
transactions_sample <- transactions_sample %>%
  mutate(transaction_timestamp = as.POSIXct(transaction_timestamp, format = "%Y-%m-%d %H:%M:%S"))

# If the format only has the date part, use this:
# transactions_sample <- transactions_sample %>%
#   mutate(transaction_timestamp = as.POSIXct(transaction_timestamp, format = "%Y-%m-%d"))
# Aggregate spending by month and region
monthly_spending <- transactions_sample %>%
  left_join(demographics, by = "household_id") %>%
  mutate(month = format(transaction_timestamp, "%Y-%m")) %>%  # Extract month directly as a string
  group_by(month, region = home_ownership) %>%
  summarise(total_spending = sum(sales_value, na.rm = TRUE)) %>%
  ungroup()

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

# Convert month back to date format (if necessary) for plotting
monthly_spending$month <- as.Date(paste0(monthly_spending$month, "-01"), format = "%Y-%m-%d")
# Plot the monthly spending pattern
ggplot(monthly_spending, aes(x = month, y = total_spending, color = region)) +
  geom_line(size = 1.2) +
  labs(title = "Monthly Spending Patterns Across Regions",
       subtitle = "Analysis of spending patterns by region over time",
       x = "Month", y = "Total Spending") +
  theme_light() +
  theme(
    plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 12, hjust = 0.5),
    axis.text.x = element_text(angle = 45, hjust = 1),
    panel.grid.major = element_line(color = "grey80")
  )

Warning: Removed 12 rows containing missing values or values outside the scale range (`geom_line()`).