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 <- .data %>%
        
        # 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] 4

Adding arguments for details of operation

count_ncol_type <- function(.data, type_data = "numeric") {
    
     # if statement for type of variables
     if(type_data == "numeric") {
         # Body
         ncol_type <- .data %>%
            
            # Select a type of variables
            select(where(is.numeric)) %>%
            
            # Count columns
            ncol()
     } else if(type_data =="character") {
         # Body
         ncol_type <- .data %>%
            
            # Select a type of variables
            select(where(is.character)) %>%
            
            # Count columns
            ncol()
     }
    
        
     
     # Return the new variable
     return(ncol_type)
    
}

flights %>% count_ncol_type()
## [1] 14
flights %>% count_ncol_type(type_data = "character")
## [1] 4
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 <- .data %>%
        
        # 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 = "AA")
## [1] 2

Example 3: count rows

Create your own.

MKdata <- read_csv("../00_data/MKmyData1.csv")
## Rows: 101 Columns: 17
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (8): id.on.tag, animal.name, scientific.name, tag.deployment.start, tag....
## dbl (5): Column1, prey.per.month, hours.indoor.per.day, cats.in.house, age
## lgl (4): hunt, dry.food, wet.food, other.food
## 
## 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.
MKdata %>% skimr::skim()
Data summary
Name Piped data
Number of rows 101
Number of columns 17
_______________________
Column type frequency:
character 8
logical 4
numeric 5
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
id.on.tag 0 1.00 4 19 0 101 0
animal.name 0 1.00 2 15 0 101 0
scientific.name 0 1.00 11 11 0 1 0
tag.deployment.start 0 1.00 11 13 0 88 0
tag.deployment.end 0 1.00 11 14 0 101 0
reproductive.condition 3 0.97 6 9 0 3 0
sex 0 1.00 1 1 0 2 0
study.location 0 1.00 2 2 0 1 0

Variable type: logical

skim_variable n_missing complete_rate mean count
hunt 9 0.91 0.88 TRU: 81, FAL: 11
dry.food 0 1.00 0.96 TRU: 97, FAL: 4
wet.food 0 1.00 0.70 TRU: 71, FAL: 30
other.food 10 0.90 0.46 FAL: 49, TRU: 42

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
Column1 0 1.00 51.00 29.30 1.0 26.0 51.0 76.0 101.0 ▇▇▇▇▇
prey.per.month 0 1.00 3.74 4.83 0.0 0.5 3.0 3.0 17.5 ▇▁▁▁▁
hours.indoor.per.day 0 1.00 11.86 5.23 2.5 7.5 12.5 17.5 22.5 ▂▇▇▅▂
cats.in.house 0 1.00 2.08 1.00 1.0 1.0 2.0 3.0 4.0 ▆▇▁▃▂
age 1 0.99 5.42 3.38 0.0 3.0 5.0 8.0 16.0 ▇▇▅▂▁

code snippets

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

nrow_num <- MKdata %>%
    
    # Filter rows that meet a condition
    filter(reproductive.condition == "Spayed") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 41

Turn them into a function

count_num_spayed_by_condition <- function(.data, condition_name) {
    
    # Body
    nrow_num <- .data %>%
    
        # Filter rows that meet a condition
        filter(reproductive.condition == condition_name) %>%
        
        # Count rows
        nrow() 
    
    # Return the new variable
    return(nrow_num)
}

MKdata %>% .[1:10, "reproductive.condition"] %>%
count_num_spayed_by_condition(condition_name = "Spayed")
## [1] 4