aircraft

library(tidyverse)
library(ggimage)
library(viridis)


setwd("~/DATA110")
aircraft <- read_csv("aircraft_wildlife_strikes_faa (2).csv")
data(aircraft)

cln1 <- aircraft |>
  filter(SPECIES %in% c("Mourning dove", "Barn swallow", "Killdeer")) |>
  filter(!is.na(INCIDENT_YEAR)) |>
  filter(INCIDENT_YEAR >= 2000) |>
  group_by(INCIDENT_YEAR, SPECIES) |>
  summarise(nb_incidents = n(), .groups = "drop")

ggplot(cln1, aes(x = factor(INCIDENT_YEAR), y = nb_incidents, fill = SPECIES)) +
  geom_bar(stat = "identity", position = "stack") +
  scale_fill_manual(values = c("Mourning dove" = "pink", 
                               "Barn swallow" = "violet", 
                               "Killdeer" = "blue")) +
  labs(
    title = "Number of Incidents per Year for the 3 Species",
    x = "Year",
    y = "Number of Incidents",
    fill = "Species"
  ) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

summary_operator <- aircraft |>
  filter(!is.na(OPERATOR)) |>
  group_by(OPERATOR) |>
  summarise(
    nb_incidents = n(),
    avg_cost = mean(COST_REPAIRS, na.rm = TRUE)
  ) |>
  arrange(desc(nb_incidents)) |>
  filter(!OPERATOR %in% c("UNKNOWN", "BUSINESS"))|>
 
  slice_head(n = 10)

ggplot(summary_operator, aes(x = reorder(OPERATOR, nb_incidents), y = nb_incidents, fill = OPERATOR)) +
  geom_col() +
  coord_flip() +
  scale_fill_viridis_d(option ="rocket") +
  labs(
    title = "Top 10 Operators by Number of Incidents",
    x = "Operator",
    y = "Number of Incidents",
    fill = "Operator"
  ) +
  theme_minimal()