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) {
    
    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 types 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") {
        
        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 == "AA") %>%
    
    # Count rows
    nrow()

nrow_num
## [1] 32729

Turn them into a function

count_num_flight_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_flight_by_carrier(carrier_name = "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()

getwd()
## [1] "/Users/marlenesophiekrohn/Library/Mobile Documents/com~apple~CloudDocs/PSU❤️/F26 Financial Analytics/PSU_FIN3100_FinancialAnalytics"
file.exists("portfolio_returns_tbl.rds")
## [1] TRUE
list.files(pattern = "portfolio_returns_tbl")
## [1] "portfolio_returns_tbl.rds"
portfolio_returns_tbl <- readRDS("portfolio_returns_tbl.rds")
portfolio_returns_tbl
## # A tibble: 70 × 2
##    date       returns
##    <date>       <dbl>
##  1 2021-01-29  0.127 
##  2 2021-02-26 -0.0768
##  3 2021-03-31 -0.0370
##  4 2021-04-30 -0.0170
##  5 2021-05-28 -0.0150
##  6 2021-06-30  0.112 
##  7 2021-07-30 -0.0438
##  8 2021-08-31  0.0689
##  9 2021-09-30 -0.0484
## 10 2021-10-29  0.0685
## # ℹ 60 more rows
nreturns_num <- portfolio_returns_tbl %>%
    
    # filter rows that meet a condition
    filter(returns > 0) %>%
    
    # Count rows
    nrow()

nreturns_num
## [1] 37

Turn them into a function

Only Positive Returns
count_returns_by_sign <- function(.data) {
    
    # body
   nreturns_num <- .data %>%
    
    # filter rows that meet a condition
    filter(returns > 0) %>%
    
    # Count rows
    nrow()

    # Return the new variable
return(nreturns_num)

}

portfolio_returns_tbl %>% count_returns_by_sign
## [1] 37
Flexible Returns
count_returns_by_sign <- function(.data) {
    
    # Count positive returns
    positive_returns <- .data %>%
        filter(returns > 0) %>%
        nrow()
    

    # Count negative returns
negative_returns <- .data %>%
    filter(returns < 0 ) %>%
    nrow()

return(tibble(
    positive_returns = positive_returns,
    negative_returns = negative_returns))
}

portfolio_returns_tbl %>% count_returns_by_sign()
## # A tibble: 1 × 2
##   positive_returns negative_returns
##              <int>            <int>
## 1               37               33