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 snippers

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, 1:5] %>% count_ncol_numeric()
## [1] 5

Adding arguments for details of operation

count_ncol_type <- function(.data, type_data = "numeric") {
  
  if (type_data == "numeric") {
    result <- .data %>%
      select(where(is.numeric)) %>%
      ncol()
    
  } else if (type_data == "character") {
    result <- .data %>%
      select(where(is.character)) %>%
      ncol()
    
  } else {
    stop("Unsupported type_data: use 'numeric' or 'character'")
  }
  
  return(result)
}

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 == "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 <- flights %>%
        
        #filter rows that meet a condition
        filter(carrier == carrier_name) %>%
        # Count rows
        nrow()
    
    # return the new variable 
}
flights %>% .[1:10, "carrier"] %>% count_num_flights_by_carrier(carrier_name = "UA")

Example 3: count rows

Create your own

# Load packages

# Core
library(tidyverse)
library(tidyquant)
## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo
## ── Attaching core tidyquant packages ─────────────────────── tidyquant 1.0.11 ──
## ✔ PerformanceAnalytics 2.0.8      ✔ TTR                  0.24.4
## ✔ quantmod             0.4.27     ✔ xts                  0.14.1
## ── Conflicts ────────────────────────────────────────── tidyquant_conflicts() ──
## ✖ zoo::as.Date()                 masks base::as.Date()
## ✖ zoo::as.Date.numeric()         masks base::as.Date.numeric()
## ✖ dplyr::filter()                masks stats::filter()
## ✖ xts::first()                   masks dplyr::first()
## ✖ dplyr::lag()                   masks stats::lag()
## ✖ xts::last()                    masks dplyr::last()
## ✖ PerformanceAnalytics::legend() masks graphics::legend()
## ✖ quantmod::summary()            masks base::summary()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

1 Import stock prices

symbols <- c("LULU", "NKE","UA") 
prices <- tq_get(x    = symbols, 
                 get = "stock.prices",
                 from = "2012-12-31",
                 to   = "2017-12-31")
data(prices)

prices %>% skimr::skim()
Data summary
Name Piped data
Number of rows 2011
Number of columns 1
_______________________
Column type frequency:
numeric 1
________________________
Group variables None

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
AdjClose 0 1 86.54 13.17 50.51 77.06 83.77 96.02 124.29 ▁▇▇▅▂