Justin Kaplan

Assignment 5

library (nycflights13) 
library (tidyverse)
library (dplyr)

Create the code makes a table for each of the below questions.

1. join + filter - Which airplanes fly LGA to XNA (1 POINT)

Question_1 <- flights %>%
select(tailnum, origin, dest) %>%
filter(origin == "LGA") %>%
filter(dest == "XNA")
print(Question_1)
## # A tibble: 745 × 3
##    tailnum origin dest 
##    <chr>   <chr>  <chr>
##  1 N722MQ  LGA    XNA  
##  2 N719MQ  LGA    XNA  
##  3 N739MQ  LGA    XNA  
##  4 N719MQ  LGA    XNA  
##  5 N711MQ  LGA    XNA  
##  6 N723MQ  LGA    XNA  
##  7 N711MQ  LGA    XNA  
##  8 N730MQ  LGA    XNA  
##  9 N722MQ  LGA    XNA  
## 10 N719MQ  LGA    XNA  
## # ℹ 735 more rows

2. join - Add the airline name to the flights table (1 POINT)

Question_2 <- right_join(flights, airlines)
## Joining with `by = join_by(carrier)`
print(Question_2)
## # A tibble: 336,776 × 20
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013     1     1      517            515         2      830            819
##  2  2013     1     1      533            529         4      850            830
##  3  2013     1     1      542            540         2      923            850
##  4  2013     1     1      544            545        -1     1004           1022
##  5  2013     1     1      554            600        -6      812            837
##  6  2013     1     1      554            558        -4      740            728
##  7  2013     1     1      555            600        -5      913            854
##  8  2013     1     1      557            600        -3      709            723
##  9  2013     1     1      557            600        -3      838            846
## 10  2013     1     1      558            600        -2      753            745
## # ℹ 336,766 more rows
## # ℹ 12 more variables: arr_delay <dbl>, carrier <chr>, flight <int>,
## #   tailnum <chr>, origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>,
## #   hour <dbl>, minute <dbl>, time_hour <dttm>, name <chr>

3. join + select + distinct() - Which airports have no commercial flights (1 POINT)

4. EXTRA CREDIT - (2 POINT2) - NO HELP - NO PARTIAL CREDIT

Create a table with the names of the airports with the most winds (wind_speed > 30).The table must contain only the airport name (airports$name) and no duplicate rows

 full_join(weather, flights) %>%
  select(wind_speed, origin)
## Joining with `by = join_by(origin, year, month, day, hour, time_hour)`
## # A tibble: 343,513 × 2
##    wind_speed origin
##         <dbl> <chr> 
##  1      10.4  EWR   
##  2       8.06 EWR   
##  3      11.5  EWR   
##  4      12.7  EWR   
##  5      12.7  EWR   
##  6      12.7  EWR   
##  7      11.5  EWR   
##  8      11.5  EWR   
##  9      11.5  EWR   
## 10      11.5  EWR   
## # ℹ 343,503 more rows