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 
library(readxl)
# excel file
mydata <- read_excel("../00_data/data/myData.xlsx")
mydata
## # A tibble: 9,355 × 12
##    work_year job_title    job_category      salary_currency salary salary_in_usd
##        <dbl> <chr>        <chr>             <chr>            <dbl>         <dbl>
##  1      2023 AI Architect Machine Learning… USD             305100        305100
##  2      2023 AI Architect Machine Learning… USD             146900        146900
##  3      2023 AI Architect Machine Learning… USD             330000        330000
##  4      2023 AI Architect Machine Learning… USD             204000        204000
##  5      2023 AI Architect Machine Learning… USD             330000        330000
##  6      2023 AI Architect Machine Learning… USD             204000        204000
##  7      2023 AI Architect Machine Learning… EUR             200000        215936
##  8      2023 AI Architect Machine Learning… USD             330000        330000
##  9      2023 AI Architect Machine Learning… USD             204000        204000
## 10      2023 AI Architect Machine Learning… USD             200000        200000
## # ℹ 9,345 more rows
## # ℹ 6 more variables: employee_residence <chr>, experience_level <chr>,
## #   employment_type <chr>, work_setting <chr>, company_location <chr>,
## #   company_size <chr>

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) {
    
    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("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 == "UA") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 58665

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("AA")
## [1] 2

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 <- mydata %>%
    
    # filter rows that meet a condition
    filter(employee_residence == "United States") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 8086

Turn them into a function

count_num_employers_by_residence<- function(.data,residence) {
    
    #body
    nrow_num <- .data %>%
        
        # filter rows that meet a condition
        filter(employee_residence == residence) %>%
        
        # Count rows
        nrow()
    
    # return the new variable
    return(nrow_num)
}
mydata %>% .[1:10, "employee_residence"]
## # A tibble: 10 × 1
##    employee_residence
##    <chr>             
##  1 United States     
##  2 United States     
##  3 United States     
##  4 United States     
##  5 United States     
##  6 United States     
##  7 Belgium           
##  8 United States     
##  9 United States     
## 10 United States
mydata %>% .[1:10, "employee_residence"] %>% count_num_employers_by_residence("United States")
## [1] 9
mydata %>% count_num_employers_by_residence("Germany")
## [1] 66