Visualization with ggplot2

Visualization with ggplot2

Installation and the Core Pattern

install.packages("ggplot2")  # once
library(ggplot2)

Every ggplot2 chart follows the same pattern:

ggplot(data = your_data, aes(x = col1, y = col2)) +  # setup
  geom_point() +         # draw points
  labs(title = "Title") + # labels
  theme_minimal()          # appearance

---

Scatter Plot

# Built-in mtcars dataset: fuel efficiency vs weight
ggplot(mtcars, aes(x = wt, y = mpg, color = factor(cyl), size = hp)) +
  geom_point(alpha = 0.8) +
  scale_color_manual(values = c("4" = "#2196F3", "6" = "#FF9800", "8" = "#F44336")) +
  labs(
    title    = "Fuel Efficiency vs. Weight",
    subtitle = "Colored by cylinders, sized by horsepower",
    x        = "Weight (1000 lbs)",
    y        = "Miles per Gallon",
    color    = "Cylinders",
    size     = "Horsepower"
  ) +
  theme_minimal(base_size = 13)

---

Histogram

# Distribution of mpg values
ggplot(mtcars, aes(x = mpg)) +
  geom_histogram(bins = 10, fill = "#2196F3", color = "white", alpha = 0.8) +
  geom_vline(aes(xintercept = mean(mpg)), color = "red", linetype = "dashed", linewidth = 1) +
  annotate("text", x = mean(mtcars$mpg) + 1, y = 7,
           label = paste("Mean:", round(mean(mtcars$mpg), 1)),
           color = "red", hjust = 0) +
  labs(title = "Distribution of Fuel Efficiency", x = "MPG", y = "Count") +
  theme_classic()

---

Bar Chart

library(dplyr)

# Count cars by cylinder
cyl_counts <- mtcars %>%
  count(cyl) %>%
  mutate(cyl = factor(cyl))

ggplot(cyl_counts, aes(x = cyl, y = n, fill = cyl)) +
  geom_col(show.legend = FALSE) +
  geom_text(aes(label = n), vjust = -0.5, fontface = "bold") +
  scale_fill_brewer(palette = "Blues") +
  labs(title = "Cars by Number of Cylinders", x = "Cylinders", y = "Count") +
  theme_minimal()

---

Box Plot

ggplot(mtcars, aes(x = factor(cyl), y = mpg, fill = factor(cyl))) +
  geom_boxplot(outlier.shape = 21, outlier.size = 3, alpha = 0.8) +
  geom_jitter(width = 0.15, alpha = 0.5, size = 2) +  # show individual points
  scale_fill_brewer(palette = "Set2", guide = "none") +
  labs(
    title = "MPG Distribution by Cylinder Count",
    x     = "Number of Cylinders",
    y     = "Miles per Gallon"
  ) +
  theme_bw()

---

Line Chart with Multiple Series

# Simulated time series
set.seed(42)
time_data <- data.frame(
  week     = rep(1:12, 3),
  revenue  = c(
    cumsum(rnorm(12, 100, 15)),
    cumsum(rnorm(12, 90, 20)),
    cumsum(rnorm(12, 110, 10))
  ),
  product  = rep(c("Laptop", "Phone", "Monitor"), each = 12)
)

ggplot(time_data, aes(x = week, y = revenue, color = product, group = product)) +
  geom_line(linewidth = 1.2) +
  geom_point(size = 2.5) +
  scale_color_brewer(palette = "Dark2") +
  labs(title = "Weekly Revenue by Product", x = "Week", y = "Cumulative Revenue ($)") +
  theme_minimal() +
  theme(legend.position = "bottom")

---

facet_wrap() — Small Multiples

# Separate scatter plot per cylinder count
ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point(color = "#2196F3", size = 2.5, alpha = 0.7) +
  geom_smooth(method = "lm", se = TRUE, color = "#F44336") +
  facet_wrap(~cyl, labeller = label_both) +
  labs(title = "MPG vs Weight: Faceted by Cylinders") +
  theme_bw()

---

Saving Plots

# Save the last plot
ggsave("mpg_analysis.png", width = 8, height = 6, dpi = 300)

# Save a specific plot object
p <- ggplot(mtcars, aes(x = mpg)) + geom_histogram(bins = 10)
ggsave("histogram.pdf", plot = p, width = 6, height = 4)

---

Customizing Themes

# A fully custom theme
my_theme <- theme_minimal(base_size = 12) +
  theme(
    plot.title       = element_text(face = "bold", size = 14, hjust = 0),
    plot.subtitle    = element_text(color = "grey50"),
    panel.grid.minor = element_blank(),
    axis.line        = element_line(color = "grey70"),
    legend.position  = "bottom"
  )

ggplot(mtcars, aes(x = wt, y = mpg)) +
  geom_point(color = "#2196F3") +
  labs(title = "Custom Theme Example", subtitle = "Clean, minimal style") +
  my_theme