category_spend <- completejourney::transactions_sample %>%
inner_join(products) %>%
group_by(product_category) %>%
mutate(product_category = fct_lump(product_category, 10)) %>%
summarise(total_spend = sum(sales_value), .groups = "drop")%>%
arrange(desc(total_spend))%>%
slice(2:11)
category_spend = category_spend %>%
mutate(product_category = recode(product_category,
"FRZN MEAT/MEAT DINNERS" = "FROZEN MEALS",
"BAKED BREAD/BUNS/ROLLS" = "BAKED GOODS",
"FLUID MILK PRODUCTS" = "MILK PRODUCTS",
"BEERS/ALES" = "BEERS & ALES"))
ggplot(category_spend, aes(x = reorder(product_category, -total_spend), y = total_spend)) +
geom_bar(stat = "identity", aes(fill = total_spend), show.legend = FALSE) +
scale_fill_gradient(high = "orchid", low = "#BF94E4") +
geom_text(aes(label = scales::label_dollar(accuracy = 1)(total_spend)), hjust = 1.2, color = "white", size = 3) +
labs(title = "Revenue by Product Categories",
subtitle = "Total Revenue for the Top 10 product categories sold.",
caption = "Data Source: CompleteJourney\nAnalysis by Kaitlyn Straight",
x = "Product Category", y = "Total Revenue (USD)") +
theme_classic() +
theme(axis.text.x = element_text(hjust = 1),
plot.title = element_text(hjust = 0, size = 16, face = "bold"),
axis.title = element_text(size = 12, face = "bold"),
panel.grid.major.x = element_line(color = "gray90"),
panel.grid.minor.y = element_line(color = "gray40", linetype = "dotted")) +
scale_y_continuous(labels = scales::label_dollar(),
expand = c(-.1, max(category_spend$total_spend) * 0.1)) +
coord_flip()
product_cat_months <- transactions_sample %>%
inner_join(products) %>%
mutate(month = floor_date(transaction_timestamp, "month")) %>%
group_by(month, product_category) %>%
summarise(total_spend = sum(sales_value, na.rm = TRUE), .groups = "drop") %>%
mutate(product_category = fct_reorder(product_category, total_spend))
top_5_categories <- product_cat_months %>%
group_by(product_category) %>%
summarise(total_spend = sum(total_spend), .groups = "drop") %>%
arrange(desc(total_spend))%>%
slice(2:6) %>%
pull(product_category)
product_cat_months_top5 <- product_cat_months %>%
filter(product_category %in% top_5_categories)
product_cat_months_top5 = product_cat_months_top5 %>%
mutate(product_category = recode(product_category,
"FRZN MEAT/MEAT DINNERS" = "FROZEN MEALS",
"FLUID MILK PRODUCTS" = "MILK PRODUCTS",
"BEERS/ALES" = "BEERS & ALES"))
chosen_palette = wes_palette("Zissou1", n = 5)
product_cat_months_top5 %>%
ggplot(aes(x = month, y = total_spend, color = product_category)) +
geom_line(size = 2, alpha = 0.5) +
geom_point(size = 3, alpha = 0.5) +
geom_smooth(method = "lm", se = FALSE, aes(group = product_category), linetype = "dashed", size = 1) +
labs(title = "Revenue Over Time for Product Categories",
subtitle = "Revenue by month for Top 5 product categories sold.",
caption = "Data Source: CompleteJourney\nAnalysis by Kaitlyn Straight",
x = "Month", y = "Total Revenue (USD)") +
scale_color_manual(values = chosen_palette) +
scale_x_date(labels = scales::date_format("%b %Y"), breaks = "1 month") +
scale_y_continuous(labels = scales::label_dollar()) +
theme_classic() +
theme(
plot.title = element_text(hjust = 0.5, size = 16, face = "bold"),
axis.title = element_text(size = 12, face = "bold"),
axis.text.x = element_text(angle = 45, hjust = 1),
legend.title = element_text(size = 12),
legend.text = element_text(size = 10),
panel.grid.major = element_line(color = "gray90", size = 0.5),
panel.grid.minor = element_line(color = "gray95", size = 0.5),
plot.caption = element_text(face = "italic")
)
## 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.
## Warning: The `size` argument of `element_line()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
income_kids_coupons <- transactions_sample %>%
inner_join(demographics) %>%
mutate(Kid_Status = ifelse(kids_count > 0, TRUE, FALSE)) %>%
group_by(Kid_Status, income) %>%
summarise(total_coupons = sum(retail_disc, na.rm = TRUE) +
sum(coupon_disc, na.rm = TRUE) +
sum(coupon_match_disc, na.rm = TRUE), .groups = "drop")
palette_colors = c("darkgreen", "palegreen3")
ggplot(income_kids_coupons, aes(x = income, y = total_coupons, fill = Kid_Status)) +
geom_bar(stat = "identity", show.legend = TRUE, position = "dodge", color = "palegreen4") +
scale_fill_manual(values = palette_colors,
labels = c("No Kids", "Kids")) +
geom_text(aes(label = scales::label_dollar(accuracy = 1)(total_coupons)),
position = position_dodge(0.9),
hjust = -0.1, vjust = 0.4,
color = "grey20", size = 2.5, fontface = "bold") +
labs(title = "Coupons Used by Income Level",
subtitle = "USD used in coupons by income level, faceted by kid status.",
caption = "Data Source: CompleteJourney\nAnalysis by Kaitlyn Straight",
x = "Income", y = "Total Coupons Used (USD)") +
theme_bw() +
theme(
axis.text.x = element_text(hjust = 1, angle = 45),
plot.title = element_text(hjust = 0, size = 16, face = "bold"),
axis.title = element_text(size = 12, face = "bold"),
panel.grid.major.x = element_line(color = "gray90"),
panel.grid.minor.y = element_line(color = "gray40", linetype = "dotted"),
plot.caption = element_text(face = "italic")
) +
scale_y_continuous(labels = scales::label_dollar(),
expand = expansion(mult = c(0, 0.1)),
n.breaks = 10) +
coord_flip()
