Data Visualization with ggplot2

library(ggplot2)
library(dplyr)

# ggplot2 FORMULA:
# ggplot(data, aes(x, y, color, fill, size)) +
#   geom_*() +
#   scale_*() +
#   labs() +
#   theme_*()

# Aesthetics (aes) map data to visual properties:
#   x, y       → position
#   color      → outline/line color
#   fill       → area fill color
#   size       → point/line size
#   shape      → point shape
#   alpha      → transparency (0=transparent, 1=opaque)
#   linetype   → solid, dashed, dotted

# Sample data
set.seed(42)
sales_df <- data.frame(
  month   = rep(month.abb, 2),
  year    = rep(c(2023, 2024), each=12),
  revenue = c(round(runif(12, 40000, 90000), -3),
              round(runif(12, 50000, 100000), -3)),
  region  = rep(c("North","South","East","West","North","North",
                   "South","East","West","North","East","South"), 2)
)

# ─── SCATTER PLOT ────────────────────────────────────
ggplot(mtcars, aes(x=hp, y=mpg, color=factor(cyl), size=wt)) +
  geom_point(alpha=0.7) +
  geom_smooth(method="lm", se=TRUE, aes(group=1), color="black", linetype="dashed") +
  scale_color_manual(values=c("4"="#1565C0","6"="#E65100","8"="#B71C1C"),
                     name="Cylinders") +
  labs(title="Horsepower vs Fuel Efficiency",
       subtitle="Color = cylinders, Size = weight",
       x="Horsepower", y="Miles per Gallon",
       caption="Source: mtcars dataset") +
  theme_bw() +
  theme(plot.title=element_text(size=14, face="bold"),
        legend.position="bottom")

# ─── BAR CHART ───────────────────────────────────────
region_revenue <- sales_df %>%
  group_by(region) %>%
  summarise(total=sum(revenue), .groups="drop") %>%
  arrange(desc(total))

ggplot(region_revenue, aes(x=reorder(region, total), y=total, fill=region)) +
  geom_col(show.legend=FALSE, width=0.7) +
  geom_text(aes(label=paste0("$", formatC(total/1000, format="f", digits=0),"K")),
             hjust=-0.1, fontface="bold") +
  coord_flip() +
  scale_fill_manual(values=c("#1565C0","#2E7D32","#E65100","#6A1B9A")) +
  scale_y_continuous(limits=c(0, max(region_revenue$total)*1.15),
                     labels=function(x) paste0("$",x/1000,"K")) +
  labs(title="Total Revenue by Region", x=NULL, y="Revenue") +
  theme_minimal(base_size=12) +
  theme(panel.grid.major.y=element_blank(),
        plot.title=element_text(face="bold"))

# ─── LINE CHART ──────────────────────────────────────
monthly_rev <- sales_df %>%
  mutate(month_order = match(month, month.abb)) %>%
  arrange(year, month_order)

ggplot(monthly_rev, aes(x=month_order, y=revenue, color=factor(year), group=year)) +
  geom_line(size=1.5) +
  geom_point(size=3) +
  scale_x_continuous(breaks=1:12, labels=month.abb) +
  scale_y_continuous(labels=function(x) paste0("$",x/1000,"K")) +
  scale_color_manual(values=c("2023"="#90CAF9","2024"="#1565C0"), name="Year") +
  labs(title="Monthly Revenue: 2023 vs 2024", x="Month", y="Revenue") +
  theme_minimal() + theme(legend.position="top")

# ─── HISTOGRAM ───────────────────────────────────────
ggplot(mtcars, aes(x=mpg)) +
  geom_histogram(bins=15, fill="#1565C0", color="white", alpha=0.8) +
  geom_vline(xintercept=mean(mtcars$mpg), color="red", linetype="dashed", size=1) +
  labs(title="Distribution of Fuel Efficiency", x="MPG", y="Count") +
  theme_minimal()

# ─── BOX PLOT ────────────────────────────────────────
ggplot(mtcars, aes(x=factor(cyl), y=mpg, fill=factor(cyl))) +
  geom_boxplot(alpha=0.7, outlier.color="red") +
  geom_jitter(width=0.1, alpha=0.4) +
  scale_fill_manual(values=c("#42A5F5","#1565C0","#0D47A1")) +
  labs(title="Fuel Efficiency by Number of Cylinders",
       x="Cylinders", y="Miles per Gallon") +
  theme_minimal() + theme(legend.position="none")

# Facet wrap — small multiples
ggplot(sales_df, aes(x=match(month, month.abb), y=revenue)) +
  geom_col(fill="#1565C0", alpha=0.8) +
  facet_wrap(~region, nrow=2) +
  scale_x_continuous(breaks=1:12, labels=month.abb) +
  labs(title="Monthly Revenue by Region", x="Month", y="Revenue") +
  theme_minimal() +
  theme(axis.text.x=element_text(angle=45, hjust=1))

# Custom theme function
my_theme <- theme_minimal(base_size=12) +
  theme(
    plot.title       = element_text(face="bold", size=14, color="#1565C0"),
    plot.subtitle    = element_text(color="#666666"),
    axis.title       = element_text(face="bold"),
    panel.grid.minor = element_blank(),
    panel.grid.major = element_line(color="#EEEEEE"),
    strip.background = element_rect(fill="#F5F5F5"),
    strip.text       = element_text(face="bold")
  )

# Save plot
ggsave("revenue_chart.png", width=10, height=6, dpi=300)
ggsave("revenue_chart.pdf", width=10, height=6)  # Vector format