Mini TidyTuesday - Programming Languages.

# Load necessary packages
library(ggplot2)
library(ggrepel)
library(scales) # For formatting numbers

tuesdata <- tidytuesdayR::tt_load(2023, week = 12)

data <- tuesdata$languages

# Subset the data to include only the points of interest
top_languages <- data[data$number_of_users > 500000,]

# Create the plot
ggplot(top_languages, aes(x = number_of_users, y = number_of_jobs)) +
  geom_smooth(method = "lm", se = FALSE, linetype = "solid", color = "steelblue", size = 1) +
  geom_point(color = "darkorange", size = 3, alpha = 0.8) +
  geom_label_repel(data = top_languages, aes(label = title),
                   force = 20,
                   fontface = "bold",
                   color = "black",
                   size = 4,
                   box.padding = 0.5,
                   point.padding = 0.5) +
  labs(title = "The Relationship Between Users and Job Openings",
       subtitle = "An analysis of top programming languages with over 500,000 users",
       x = "Number of Users",
       y = "Number of Job Openings",
       caption = "Data source: PLDB.com") +
  theme_minimal() +
  theme(text = element_text(family = "Helvetica", size = 12),
        plot.title = element_text(size = 18, hjust = 0.5, face = "bold"),
        plot.subtitle = element_text(size = 14, hjust = 0.5),
        plot.caption = element_text(size = 10, hjust = 1, margin = margin(t = 5)),
        axis.title = element_text(size = 14, face = "bold"),
        panel.grid.minor = element_blank(),
        panel.background = element_rect(fill='#FAF9F0', color=NA),
        plot.background = element_rect(fill='#FAF9F0', color=NA)) +
  scale_x_continuous(labels = comma) + # Format x-axis numbers
  scale_y_continuous(labels = comma)   # Format y-axis numbers