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 
myData <-read_csv ("../00_data/myData.csv")
## Rows: 27 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (2): film, film_rating
## dbl  (2): number, run_time
## date (1): release_date
## 
## 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.

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_num <- function(.data){
    
    ncol_num <- .data %>%
    
    # Select a type of variables
    select(where(is.numeric)) %>%
    
    # Count columns
    ncol()
    
    return(ncol_num)
    
}

flights%>% count_ncol_num()
## [1] 14
flights %>% .[1:10, -1:-13] %>% count_ncol_num()
## [1] 4

Adding arguments for details of operation

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

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

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){
    
    nrow_num <- .data %>%
    
    # filter rows that meet a condition
    filter(carrier == carrier_name) %>%
    
    # Count rows
    nrow()
    
    return(nrow_num)
    
}
flights%>% .[1:10, "carrier"]%>% count_num_flights_by_carrier(carrier_name = "AA")
## [1] 2

Example 3: count colums

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()

frcol_num<- myData%>%
    
    select(where(is.numeric))%>%
    
    ncol()
frcol_num
## [1] 2

Turn them into a function

count_frcol_num <- function(.idk){
    
    frcol_num <- .idk %>%
    
    select(where(is.numeric)) %>%
   
    ncol()
    
    return(frcol_num)
    
}

myData%>% count_frcol_num()
## [1] 2
myData %>% .[6:16,2:5] %>% count_frcol_num()
## [1] 1

Adding arguments for details of operation

count_frcol_type <- function(.idk, type_data= "numeric"){
    
    if(type_data== "numeric"){
    frcol_type <- .idk %>%
        
            select(where(is.numeric)) %>%
        
            ncol()
    }else if(type_data== "character"){
        frcol_type <- .idk %>%
        
            select(where(is.character)) %>%
        
            ncol()
    }
    
    return(frcol_num)
}
myData%>% count_frcol_type()
## [1] 2
myData%>% count_frcol_type(type_data = "character")
## [1] 2
myData%>% .[6:16,2:5]%>% count_frcol_type(type_data = "character")
## [1] 2

Count rows

code snippets

frrow_num<- myData %>%
    
    filter(film_rating == "G") %>%
   
    nrow()

frrow_num
## [1] 13

Turn them into a function

count_num_myData_by_film_rating<- function(.idk, film_rating){
    
    frrow_num <- .idk %>%
    
    # filter rows that meet a condition
    filter(film_rating == film_rating) %>%
    
    # Count rows
    nrow()
    
    return(frrow_num)
    
}
myData%>% .[2:5, "film_rating"]%>% count_num_myData_by_film_rating(film_rating = "G")
## [1] 4