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 
soccer <- read_csv("../00_data/myData.csv")
## Rows: 900 Columns: 15
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (11): country, city, stage, home_team, away_team, outcome, win_conditio...
## dbl   (3): year, home_score, away_score
## date  (1): 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.
soccer %>% skimr::skim()
Data summary
Name Piped data
Number of rows 900
Number of columns 15
_______________________
Column type frequency:
character 11
Date 1
numeric 3
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
country 0 1.00 5 13 0 17 0
city 0 1.00 4 17 0 161 0
stage 0 1.00 5 13 0 20 0
home_team 0 1.00 4 22 0 81 0
away_team 0 1.00 4 22 0 82 0
outcome 0 1.00 1 1 0 3 0
win_conditions 838 0.07 16 44 0 48 0
winning_team 169 0.81 4 22 0 66 0
losing_team 169 0.81 4 22 0 85 0
month 0 1.00 3 3 0 3 0
dayofweek 0 1.00 6 9 0 7 0

Variable type: Date

skim_variable n_missing complete_rate min max median n_unique
date 0 1 1930-07-13 2018-07-15 1990-06-23 355

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
year 0 1 1986.92 23.15 1930 1970 1990 2006 2018 ▁▃▅▆▇
home_score 0 1 1.57 1.49 0 0 1 2 10 ▇▂▁▁▁
away_score 0 1 1.26 1.31 0 0 1 2 8 ▇▃▁▁▁

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

flights %>% count_ncol_types()
## [1] 14
flights %>% count_ncol_types(type_data = "character")
## [1] 14
flights %>% .[1:10, 1:5] %>% count_ncol_types(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) {
    
    # 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 = "UA")
## [1] 3

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()

nrow_num <- soccer %>%
    
    # filter rows that meet a condition
    filter(year == "2018") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 64

Turn them into a function

count_num_soccer_by_year <- function(.data ,year_name) {
    
    # body 
    nrow_num <- .data %>%
    
    # filter rows that meet a condition
    filter(year == year_name) %>%
    
    # Count rows
    nrow()
    
    # return the new variable
    return(nrow_num)
}

soccer %>% .[1:10, "year"] %>% count_num_soccer_by_year(year_name = "2018")
## [1] 0