Welcome to Lab 2

data(nycflights)

ggplot(data = nycflights, aes(x = dep_delay)) +
  geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

  ggplot(data = nycflights, aes(x = dep_delay)) +
  geom_histogram(binwidth = 15)

  ggplot(data = nycflights, aes(x = dep_delay)) +
  geom_histogram(binwidth = 150)

Look carefully at these three histograms. How do they compare? Are features revealed in one that are obscured in another?

The lower the bindwith, the more specific the graph. A higher bindwith would potentially be useful for presenting data in simpiler models, but an appropriatly low bandwith creates the most accurate data.

data(nycflights)

lax_flights <- nycflights %>%
  filter(dest == "LAX")
ggplot(data = lax_flights, aes(x = dep_delay)) +
  geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

lax_flights %>%
  summarise(mean_dd   = mean(dep_delay), 
            median_dd = median(dep_delay), 
            n         = n())
## # A tibble: 1 × 3
##   mean_dd median_dd     n
##     <dbl>     <dbl> <int>
## 1    9.78        -1  1583
sfo_feb_flights <- nycflights %>%
  filter(dest == "SFO", month == 2)

sfo_feb_flights %>%
  summary(sfo_feb_flights)
##       year          month        day           dep_time      dep_delay    
##  Min.   :2013   Min.   :2   Min.   : 1.00   Min.   : 613   Min.   :-10.0  
##  1st Qu.:2013   1st Qu.:2   1st Qu.: 7.00   1st Qu.: 943   1st Qu.: -5.0  
##  Median :2013   Median :2   Median :16.00   Median :1268   Median : -2.0  
##  Mean   :2013   Mean   :2   Mean   :15.26   Mean   :1298   Mean   : 10.5  
##  3rd Qu.:2013   3rd Qu.:2   3rd Qu.:22.50   3rd Qu.:1742   3rd Qu.:  9.0  
##  Max.   :2013   Max.   :2   Max.   :28.00   Max.   :2159   Max.   :209.0  
##     arr_time      arr_delay        carrier            tailnum         
##  Min.   : 118   Min.   :-66.00   Length:68          Length:68         
##  1st Qu.:1233   1st Qu.:-21.25   Class :character   Class :character  
##  Median :1497   Median :-11.00   Mode  :character   Mode  :character  
##  Mean   :1607   Mean   : -4.50                                        
##  3rd Qu.:2062   3rd Qu.:  2.00                                        
##  Max.   :2256   Max.   :196.00                                        
##      flight          origin              dest              air_time    
##  Min.   :  11.0   Length:68          Length:68          Min.   :317.0  
##  1st Qu.:  85.0   Class :character   Class :character   1st Qu.:345.0  
##  Median : 641.0   Mode  :character   Mode  :character   Median :354.0  
##  Mean   : 795.1                                         Mean   :351.9  
##  3rd Qu.:1487.2                                         3rd Qu.:360.0  
##  Max.   :2126.0                                         Max.   :376.0  
##     distance         hour           minute     
##  Min.   :2565   Min.   : 6.00   Min.   : 1.00  
##  1st Qu.:2586   1st Qu.: 9.00   1st Qu.:25.00  
##  Median :2586   Median :12.50   Median :33.50  
##  Mean   :2584   Mean   :12.62   Mean   :36.35  
##  3rd Qu.:2586   3rd Qu.:17.00   3rd Qu.:54.00  
##  Max.   :2586   Max.   :21.00   Max.   :59.00
ggplot(data = sfo_feb_flights, aes(x = dep_delay)) +
  geom_histogram(binwidth = 2)

sfo_feb_flights %>%
  summarise(mean_dd = mean(dep_delay),
            median_dd = median(dep_delay))
## # A tibble: 1 × 2
##   mean_dd median_dd
##     <dbl>     <dbl>
## 1    10.5        -2

Create a new data frame that includes flights headed to SFO in February, and save this data frame as sfo_feb_flights. How many flights meet these criteria?

68 flights flew from NYC to San Franciso in Febuary

Describe the distribution of the arrival delays of these flights using a histogram and appropriate summary statistics. Hint: The summary statistics you use should depend on the shape of the distribution.

The distrubuiton of delay times of flights headed to San Francisco is strange; a majority of the flights actually left early, (the median is -2), but the average delay time is actually 10 minutes over because of extreme outliers.

data(nycflights)

sfo_feb_flights <- nycflights %>%
  filter(dest == "SFO", month == 2)

sfo_feb_flights %>%
  group_by(origin) %>%
  summarise(median_dd = median(dep_delay), iqr_dd = IQR(dep_delay), n_flights = n())
## # A tibble: 2 × 4
##   origin median_dd iqr_dd n_flights
##   <chr>      <dbl>  <dbl>     <int>
## 1 EWR          0.5   5.75         8
## 2 JFK         -2.5  15.2         60
sfo_feb_flights %>%
  group_by(carrier) %>%
  summarise(median_dd = median(dep_delay), iqr_dd = IQR(dep_delay), n_flights = n())
## # A tibble: 5 × 4
##   carrier median_dd iqr_dd n_flights
##   <chr>       <dbl>  <dbl>     <int>
## 1 AA           13     32.8        10
## 2 B6           -2      3.5         6
## 3 DL           -3      6.5        19
## 4 UA           -2     13          21
## 5 VX           -3.5   16.8        12

Calculate the median and interquartile range for arr_delays of flights in in the sfo_feb_flights data frame, grouped by carrier. Which carrier has the most variable arrival delays?

The carrier AA has the highest median delay and highest Inter quartile range

nycflights %>%
  group_by(month) %>%
  summarise(mean_dd = mean(dep_delay)) %>%
  arrange(desc(mean_dd))
## # A tibble: 12 × 2
##    month mean_dd
##    <int>   <dbl>
##  1     7   20.8 
##  2     6   20.4 
##  3    12   17.4 
##  4     4   14.6 
##  5     3   13.5 
##  6     5   13.3 
##  7     8   12.6 
##  8     2   10.7 
##  9     1   10.2 
## 10     9    6.87
## 11    11    6.10
## 12    10    5.88

Suppose you really dislike departure delays and you want to schedule your travel in a month that minimizes your potential departure delay leaving NYC. One option is to choose the month with the lowest mean departure delay. Another option is to choose the month with the lowest median departure delay. What are the pros and cons of these two choices?

A lower median depature could potentially mean your more likely to get a flight with a higher delay time compared to a lower mean, but if a month tends to run the risk of having an extremely long depature delay then that risk would be modeled in the average.

nycflights <- nycflights %>%
  mutate(dep_type = ifelse(dep_delay < 5, "on time", "delayed"))

nycflights %>%
  group_by(origin) %>%
  summarise(ot_dep_rate = sum(dep_type == "on time") / n()) %>%
  arrange(desc(ot_dep_rate))
## # A tibble: 3 × 2
##   origin ot_dep_rate
##   <chr>        <dbl>
## 1 LGA          0.728
## 2 JFK          0.694
## 3 EWR          0.637
ggplot(data = nycflights, aes(x = origin, fill = dep_type)) +
  geom_bar()

If you were selecting an airport simply based on on time departure percentage, which NYC airport would you choose to fly out of?

LGA is the least likely to be delayed.

nycflights <- nycflights %>%
  mutate(air_speed = distance / (air_time / 60))
nycflights %>% 
  group_by(origin) %>%
  summarise(distance = sum(dep_type == "on time") / n()) %>%
  arrange(desc(distance))
## # A tibble: 3 × 2
##   origin distance
##   <chr>     <dbl>
## 1 LGA       0.728
## 2 JFK       0.694
## 3 EWR       0.637
ggplot(data = nycflights, aes(x = distance, y = air_speed)) +
  geom_point()

library(ggplot2)
colors <- c('AA' = 'red', 'DL' = 'green', 'UA' = 'blue')
nycflights_carry <- nycflights %>%
  filter(carrier %in% c("AA", "DL", "UA"))
ggplot(data = nycflights_carry, aes(x = dep_delay, y = arr_delay, color = carrier)) +
  geom_point(size = 3) +
  scale_color_manual(values = colors) +
  labs(
    x = 'dep_delay',
    y = 'arr_delay',
    title = 'Dot Plot with Colors based on Carrier'
  )