[R] EDA: Motorcycle parts (Competition)

knitr::opts_chunk$set(echo = TRUE)
knitr::opts_chunk$set(class.output = "code-background")

.code-background {
  background-color: lightgreen;
  border: 3px solid brown;
  font-weight: bold;
}

library(tidyverse)
library(viridisLite)

theme_set(theme_bw())
theme_update(plot.title = element_text(hjust = 0.5, size = 20),
             plot.subtitle = element_text(hjust = 0.5, size = 15),
             axis.text = element_text(size = 18),
             axis.title = element_text(size = 18),
             legend.position = "bottom")

df <- readr::read_csv('./data/sales_data.csv')

head(df)

sales_per_payment <- df %>% 
  group_by(payment) %>% 
  summarize(transactions = n(),
            total_sales_usd = sum(total)) %>% 
  arrange(desc(total_sales_usd))

sales_per_payment

unit_price_per_line <- df %>% 
  group_by(product_line) %>% 
  summarize(mean_price = mean(unit_price)) %>% 
  arrange(desc(mean_price))

unit_price_per_line

ggplot(sales_per_payment, aes(payment, total_sales_usd)) +
  geom_segment(aes(xend = payment, yend = total_sales_usd, col = payment), y = 0, lwd = 1.5) +
  geom_point(pch = 21, aes(size = transactions, fill = payment)) +
  coord_flip() + 
  geom_text(aes(label = round(total_sales_usd, -3)), size = 5) +
  scale_size(range = c(18, 40), name = "Number of\ntransactions") +
  scale_y_continuous(limits = c(10000, 170000)) +
  guides(fill = "none", color = "none") +
  theme(legend.key.size = unit(0.1, 'cm')) +
  labs(x = "Payment method", y = "Total purchase value ($)")
 

ggplot(df, aes(fct_reorder(product_line, unit_price), unit_price, fill = product_line)) +
  geom_point(pch = 21, col = "black", alpha = 0.5,
             position = position_jitter(0.2, 0)) +
  stat_summary(fun = mean, geom = "point", col = "red", size = 3) +
  scale_fill_viridis_d() +
  labs(x = "Product line", y = "Unit price ($)") +
  theme(legend.position = "none",
        axis.text.x = element_text(angle = 45, hjust = 1))