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

Code:

suv <- filter(mpg, class == "suv") 
suv1 <- select(suv,hwy, cty, manufacturer, year)
arrange(suv1,desc( hwy), desc( cty))
## # A tibble: 62 × 4
##      hwy   cty manufacturer  year
##    <int> <int> <chr>        <int>
##  1    27    20 subaru        2008
##  2    26    20 subaru        2008
##  3    25    19 subaru        2008
##  4    25    18 subaru        1999
##  5    24    18 subaru        1999
##  6    23    18 subaru        2008
##  7    22    17 jeep          2008
##  8    20    16 toyota        1999
##  9    20    16 toyota        2008
## 10    20    15 jeep          1999
## # ℹ 52 more rows
ggplot(data = suv1) + 
    geom_col(mapping = aes(x = manufacturer, y = hwy))

Answer:

The most fuel economic SUVs are produced by Ford.

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

Code:

suv2 <- filter(suv1, between(year, 1999,2008))

ggplot(data = suv1) + 
    geom_col(mapping = aes(x = manufacturer, y = hwy, fill = year))

Answer:

Subaru is the SUV manufacturer that improved fuel economy most between 1999 and 2008

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

Code:

flights1 <- select(flights, sched_dep_time, dep_delay)
flights2 <- filter(flights1, !is.na(dep_delay))
ggplot(flights2) +
  geom_point(aes(sched_dep_time, dep_delay))

Answer:

Based on the plot, the data seems to be uniform, so that the schedule departure time doesn’t seem to be related to the delay reason. But actually, we can tell most of the early morning flight - 5 am or late night flight- 11pm both has a small amount of delay compare to the other.