Import your data

data(flights)

flights %>% skimr::skim()
Data summary
Name Piped data
Number of rows 336776
Number of columns 19
_______________________
Column type frequency:
character 4
numeric 14
POSIXct 1
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
carrier 0 1.00 2 2 0 16 0
tailnum 2512 0.99 5 6 0 4043 0
origin 0 1.00 3 3 0 3 0
dest 0 1.00 3 3 0 105 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
year 0 1.00 2013.00 0.00 2013 2013 2013 2013 2013 ▁▁▇▁▁
month 0 1.00 6.55 3.41 1 4 7 10 12 ▇▆▆▆▇
day 0 1.00 15.71 8.77 1 8 16 23 31 ▇▇▇▇▆
dep_time 8255 0.98 1349.11 488.28 1 907 1401 1744 2400 ▁▇▆▇▃
sched_dep_time 0 1.00 1344.25 467.34 106 906 1359 1729 2359 ▁▇▇▇▃
dep_delay 8255 0.98 12.64 40.21 -43 -5 -2 11 1301 ▇▁▁▁▁
arr_time 8713 0.97 1502.05 533.26 1 1104 1535 1940 2400 ▁▃▇▇▇
sched_arr_time 0 1.00 1536.38 497.46 1 1124 1556 1945 2359 ▁▃▇▇▇
arr_delay 9430 0.97 6.90 44.63 -86 -17 -5 14 1272 ▇▁▁▁▁
flight 0 1.00 1971.92 1632.47 1 553 1496 3465 8500 ▇▃▃▁▁
air_time 9430 0.97 150.69 93.69 20 82 129 192 695 ▇▂▂▁▁
distance 0 1.00 1039.91 733.23 17 502 872 1389 4983 ▇▃▂▁▁
hour 0 1.00 13.18 4.66 1 9 13 17 23 ▁▇▇▇▅
minute 0 1.00 26.23 19.30 0 8 29 44 59 ▇▃▆▃▅

Variable type: POSIXct

skim_variable n_missing complete_rate min max median n_unique
time_hour 0 1 2013-01-01 05:00:00 2013-12-31 23:00:00 2013-07-03 10:00:00 6936

Create Data frame functions

Example 1: count columns

code snippets

ncol_num <- flights %>%
    
    # Select a type of variables
    select(where(is.numeric)) %>%
    
    # Count columns
    ncol()

ncol_num
## [1] 14

Turn them into a function

count_ncol_numeric <- function(.data) {
    
    # Body
    ncol_num <- flights %>%
    
    # Select a type of variables
    select(where(is.numeric)) %>%
    
    # Count columns
    ncol()
    
    # Return the new variable
    return(ncol_num)
}

flights %>% count_ncol_numeric()
## [1] 14
flights %>% .[1:10, -1:-13] %>% count_ncol_numeric()
## [1] 14

Adding arguments for details of operation

count_ncol_type <- function(.data, type_data = "numeric") {
  
  if (type_data == "numeric") {
    
    ncol_type <- .data %>%
      select(where(is.numeric)) %>%
      ncol()
    
  } else if (type_data == "character") {
    
    ncol_type <- .data %>%
      select(where(is.character)) %>%
      ncol()
    
  }
  
  return(ncol_type)
}

flights %>% count_ncol_type(type_data = "character")
## [1] 4
flights %>% count_ncol_type()
## [1] 14
flights %>% .[1:10, 1:5] %>% count_ncol_type(type_data = "character")
## [1] 0

Example 2: count rows

code snippets

nrow_num <- flights %>%
    
    # filter rows that meet a condition
    filter(carrier == "DL") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 48110

Turn them into a function

count_num_flights_by_carrier <- function(.data, carrier_name) {
    
    # Body
    nrow_num <- flights %>%
    
    # filter rows that meet a condition
    filter(carrier == carrier_name) %>%
    
    # Count rows
    nrow()
    
    # Return the new variable
    return(nrow_num)
}

flights %>% .[1:10, "carrier"] %>% count_num_flights_by_carrier(carrier_name = "UA")
## [1] 58665

Example 3: count rows

Create your own.

code snippets

Use the filter() function to select rows that meet a condition. Refer to Chapter 5.2 Filter rows with filter()

data <- read_csv("C:/Users/ejp14/OneDrive/Desktop/PSU_DAT3000_IntroToDA/01_module4/Data/myData.csv")
## Rows: 81525 Columns: 24
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (3): name, team, position
## dbl (21): game_year, game_week, rush_att, rush_yds, rush_avg, rush_tds, rush...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
data
## # A tibble: 81,525 × 24
##    name            team  game_year game_week rush_att rush_yds rush_avg rush_tds
##    <chr>           <chr>     <dbl>     <dbl>    <dbl>    <dbl>    <dbl>    <dbl>
##  1 Duce Staley     PHI        2000         1       26      201      7.7        1
##  2 Lamar Smith     MIA        2000         1       27      145      5.4        1
##  3 Tiki Barber     NYG        2000         1       13      144     11.1        2
##  4 Stephen Davis   WAS        2000         1       23      133      5.8        1
##  5 Edgerrin James  IND        2000         1       28      124      4.4        1
##  6 Priest Holmes   BAL        2000         1       27      119      4.4        0
##  7 Curtis Martin   NYJ        2000         1       30      110      3.7        1
##  8 Robert Smith    MIN        2000         1       14      109      7.8        0
##  9 Tim Biakabutuka CAR        2000         1       15       88      5.9        0
## 10 Cade McNown     CHI        2000         1       10       87      8.7        1
## # ℹ 81,515 more rows
## # ℹ 16 more variables: rush_fumbles <dbl>, rec <dbl>, rec_yds <dbl>,
## #   rec_avg <dbl>, rec_tds <dbl>, rec_fumbles <dbl>, pass_att <dbl>,
## #   pass_yds <dbl>, pass_tds <dbl>, int <dbl>, sck <dbl>, pass_fumbles <dbl>,
## #   rate <dbl>, position <chr>, total_yards <dbl>, `total tds` <dbl>
nrow_number <- data %>%
    
    # filter rows that meet a condition
    filter(position == "QB") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 48110

Turn them into a function

count_num_by_position <- function(.data, position_name) {
  
  nrow_number <- .data %>%
    # filter rows that meet a condition
    filter(position == position_name) %>%
    # count rows
    nrow()
  
  return(nrow_number)
}