1. In the mpg data set, which manufacturer produced the most fuel economic SUVs?

manufacturer_mpg <- select(mpg, manufacturer, cty, hwy, class)
filter(manufacturer_mpg, class == "suv")
## # A tibble: 62 × 4
##    manufacturer   cty   hwy class
##    <chr>        <int> <int> <chr>
##  1 chevrolet       14    20 suv  
##  2 chevrolet       11    15 suv  
##  3 chevrolet       14    20 suv  
##  4 chevrolet       13    17 suv  
##  5 chevrolet       12    17 suv  
##  6 chevrolet       14    19 suv  
##  7 chevrolet       11    14 suv  
##  8 chevrolet       11    15 suv  
##  9 chevrolet       14    17 suv  
## 10 dodge           13    17 suv  
## # ℹ 52 more rows
suv_mpg <- filter(manufacturer_mpg, class == "suv")
ggplot(data = suv_mpg, mapping = aes(x = manufacturer, y = (cty + hwy) / 2)) +
    stat_boxplot(geom = "errorbar", width = 0.5) + geom_boxplot() +
    labs(title = "SUV Fuel Economy by Manufacturers", x = "Manufacturer", y = "Average Combined MPG") +
    theme(plot.title = element_text(hjust = 0.5, size = rel(1.5), face = "bold"), axis.title = element_text(size = rel(1.2), face = "bold"))

Answer: Subaru produced the most fuel economic SUVs.

2. In the mpg data set, which SUV manufacturer improved fuel economy most between 1999 and 2008?

year_mpg <- select(mpg, manufacturer, cty, hwy, class, year)
filter(year_mpg, class == "suv")
## # A tibble: 62 × 5
##    manufacturer   cty   hwy class  year
##    <chr>        <int> <int> <chr> <int>
##  1 chevrolet       14    20 suv    2008
##  2 chevrolet       11    15 suv    2008
##  3 chevrolet       14    20 suv    2008
##  4 chevrolet       13    17 suv    1999
##  5 chevrolet       12    17 suv    2008
##  6 chevrolet       14    19 suv    2008
##  7 chevrolet       11    14 suv    2008
##  8 chevrolet       11    15 suv    1999
##  9 chevrolet       14    17 suv    1999
## 10 dodge           13    17 suv    1999
## # ℹ 52 more rows
year_suv_mpg <- filter(year_mpg, class == "suv")
ggplot(data = year_suv_mpg, mapping = aes(x = manufacturer, y = (cty + hwy) / 2, color = factor(year))) +
    stat_boxplot(geom = "errorbar", width = 0.5) + geom_boxplot() +
    labs(title = "Manufacturers SUV Fuel Economy by Year", x = "Manufacturer", y = "Average Combined MPG", color = "Year") +
    theme(plot.title = element_text(hjust = 0.5, size = rel(1.5), face = "bold"), axis.title = element_text(size = rel(1.2), face = "bold"))

Answer: Land Rover improved fuel economy the most between 1999 and 2008.

3. In the flights data set, pick up another variable other than carrier and analyze whether that variable correlates with long-delay flights or not. .

long_delay <- filter(flights, dep_delay >= 120 | arr_delay >= 120)
others <- filter(flights, dep_delay < 120 & arr_delay < 120)
ggplot(data = long_delay) + 
  geom_bar(aes(factor(month), y = after_stat(count/sum(count)))) + 
  labs(title = "Long Delay Flights", x = "Carrier", y = "Relative Frequency") + 
  theme(plot.title = element_text(hjust = 0.5, size = rel(1.5), margin = margin(15,15,15,15)), 
        axis.title = element_text(size = rel(1.4)), 
        axis.title.x = element_text(margin = margin(10,5,5,5)), 
        axis.title.y = element_text(margin = margin(5,10,5,5)), 
        axis.text = element_text(size = rel(1.4)))  

ggplot(data = others) + 
  geom_bar(aes(factor(month), y = after_stat(count/sum(count)))) +
  labs(title = "Short or No Delay Flights", x = "Carrier", y = "Relative Frequency") + 
  theme(plot.title = element_text(hjust = 0.5, size = rel(1.5), margin = margin(15,15,15,15)), 
        axis.title = element_text(size = rel(1.4)), 
        axis.title.x = element_text(margin = margin(10,5,5,5)), 
        axis.title.y = element_text(margin = margin(5,10,5,5)), 
        axis.text = element_text(size = rel(1.4)))

Answer: Different months also correlate with long-delay flights properly due to seasonal travel demand and weather. June and July have the most number of long delay flights, while short delay flights basically remain the same throughout the year.