Import your data

# My dataset
data(flights)
data <- read_excel("myData_charts.xlsx")
data %>% skimr::skim()
Data summary
Name Piped data
Number of rows 45090
Number of columns 10
_______________________
Column type frequency:
character 1
logical 1
numeric 7
POSIXct 1
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
stock_symbol 2 1 3 5 0 14 0

Variable type: logical

skim_variable n_missing complete_rate mean count
Column1 45090 0 NaN :

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
open 2 1 89.27 101.63 1.08 25.67 47.93 128.66 6.962800e+02 ▇▂▁▁▁
high 2 1 90.37 103.00 1.11 25.93 48.46 129.85 7.009900e+02 ▇▂▁▁▁
low 2 1 88.11 100.12 1.00 25.36 47.47 127.25 6.860900e+02 ▇▂▁▁▁
close 2 1 89.27 101.59 1.05 25.66 47.97 128.64 6.916900e+02 ▇▂▁▁▁
adj_close 2 1 85.21 101.00 1.05 22.08 45.38 113.67 6.916900e+02 ▇▁▁▁▁
volume 2 1 52978130.54 93247295.87 589200.00 9629425.00 26463150.00 58397675.00 1.880998e+09 ▇▁▁▁▁
HPR 1 1 0.00 0.02 -0.20 -0.01 0.00 0.01 2.000000e-01 ▁▁▇▁▁

Variable type: POSIXct

skim_variable n_missing complete_rate min max median n_unique
date 2 1 2010-01-04 2023-01-24 2016-08-09 3287 
# Selecting stocks and their closing prices
selected_stocks <- c("AAPL", "ADBE", "AMZN", "CRM", "CSCO", "GOOGL", "IBM", "INTC", "META", "MSFT", "NFLX", "NVDA", "ORCL", "TSLA")

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 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(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 == "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 = "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 <- data %>%
  filter(stock_symbol == "AAPL") %>%
  nrow()

nrow_num
## [1] 3271
# Count numeric columns
ncol_num_numeric <- data %>%
  select(where(is.numeric)) %>%
  ncol()

ncol_num_numeric
## [1] 7

Turn them into a function

count_ncol_closes_by_stock_symbol <- function(.data, symbol) {
    
    # body
    nrow_num <- .data %>%
        
        # Select a type of variables
        filter(stock_symbol == symbol) %>%
        
        # Count columns
        nrow()
    
    # return the new variable
    return(nrow_num)
}

data %>% count_ncol_closes_by_stock_symbol(symbol = "AAPL")
## [1] 3271
data %>% count_ncol_closes_by_stock_symbol(symbol = "TSLA")
## [1] 3148
data %>% .[1:10, "stock_symbol"] %>% count_ncol_closes_by_stock_symbol(symbol = "AAPL")
## [1] 10
count_ncol_numeric <- function(.data) {
  # Count numeric columns in the data
  ncol_num_numeric <- .data %>%
    select(where(is.numeric)) %>%
    ncol()
  
  # Return the number of numeric columns
  return(ncol_num_numeric)
}

# Example usage of the function
data %>% count_ncol_numeric()
## [1] 7