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

Import stock prices

symbols <- c("Asker.st", "Atco-B.st", "Axfo.st", "Bahn-b.st", "BRK-B", "Cers", "LLY", "Embrac-b.st", "Indu-c.st", "Inve-b.st", "Inwi.st", "Novo-b.co", "NVDA", "Yubico.st")

prices <- tq_get(x    = symbols, 
                 get  = "stock.prices", 
                 from = "2020-04-01",
                 to   = "2025-06-01")
## Warning: There was 1 warning in `dplyr::mutate()`.
## ℹ In argument: `data.. = purrr::map(...)`.
## Caused by warning:
## ! x = 'Inwi.st', get = 'stock.prices': Error in getSymbols.yahoo(Symbols = "Inwi.st", env = <environment>, verbose = FALSE, : Unable to import "Inwi.st".
## cannot open the connection
##  Removing Inwi.st.
prices
## # A tibble: 15,373 × 8
##    symbol   date        open  high   low close   volume adjusted
##    <chr>    <date>     <dbl> <dbl> <dbl> <dbl>    <dbl>    <dbl>
##  1 Asker.st 2025-03-27  83    87.2  80.2  83.7 16441271     83.7
##  2 Asker.st 2025-03-28  83    84.0  81.7  82    1262083     82  
##  3 Asker.st 2025-03-31  81.3  81.9  80.1  80.5   626988     80.5
##  4 Asker.st 2025-04-01  80.8  82.2  80.6  81.9   356628     81.9
##  5 Asker.st 2025-04-02  81.9  82.1  80.9  82.1   576561     82.1
##  6 Asker.st 2025-04-03  81    81.8  80.1  80.7   235131     80.7
##  7 Asker.st 2025-04-04  80.5  81.2  77.3  78.6   780928     78.6
##  8 Asker.st 2025-04-07  74.8  80.1  71.4  77.8   377461     77.8
##  9 Asker.st 2025-04-08  79.2  79.9  75    77     371563     77  
## 10 Asker.st 2025-04-09  76.1  78.7  72.8  74.2  1171607     74.2
## # ℹ 15,363 more rows

Convert prices to returns (monthly)

asset_returns_tbl <- prices %>% 
    
    group_by(symbol) %>%  
    
    tq_transmute(select     = adjusted, 
                 mutate_fun = periodReturn, 
                 period     = "monthly", 
                 type      = "log") %>% 
    
    slice(-1) %>% 
    
    ungroup() %>% 
    
    set_names(c("asset", "date", "returns"))

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 variable 
    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_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 == "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(carrier_name = "AA") 
## [1] 2

Example 3: count rows

code snippets

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

nrow_num <- asset_returns_tbl %>%
    
    # Filter rows that meet a condition
    filter(returns > "0") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 409

Turn them into a function

count_num_positive_stock_returns <- function(.data, x) {
    # Body 
    nrow_num <- .data %>%
    
        # Filter rows that meet a condition
        filter(returns > 0) %>%
        
        # Count rows
        nrow()
    
    # Return the new variable 
    return(nrow_num)
}
asset_returns_tbl %>% count_num_positive_stock_returns(returns > "0")
## [1] 409