Module 12: Apply it to your data 11

Chapter 19 Functions

Import your data

nhl_rosters <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2024/2024-01-09/nhl_rosters.csv')

## Rows: 54883 Columns: 18
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (10): team_code, position_type, headshot, first_name, last_name, positi...
## dbl   (7): season, player_id, sweater_number, height_in_inches, weight_in_po...
## date  (1): birth_date
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

Create Data frame functions

Example 1: count columns

code snippets

ncol_num <- nhl_rosters %>%
    
    # Select a type of variables
    select(where(is.numeric)) %>%
    
    # Count columns
    ncol()

ncol_num

## [1] 7

Turn them into a function

count_ncol_num <- function(.data){
    
    ncol_num <- .data %>%
    
    # Select a type of variables
    select(where(is.numeric)) %>%
    
    # Count columns
    ncol()
 
    return(ncol_num)   
}

nhl_rosters %>% count_ncol_num

## [1] 7

Adding arguments for details of operation

count_ncol_type <- function(.data, type_data = "numeric"){
    
    #if statement
    if(type_data == "numeric") {
    
        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(ncol_type)  }

nhl_rosters %>% count_ncol_type(type_data = "character")

## [1] 10

Example 2: count rows

code snippets

nrow_num <- nhl_rosters %>%
    
    filter(team_code == "ATL") %>%
    nrow()

nrow_num

## [1] 410

Turn them into a function

count_nrow_num <- function(.data, team_code_input) {
    
    nrow_num <- .data %>%
        filter(team_code == team_code_input) %>%
        nrow()
    
    nrow_num
}

nhl_rosters %>% count_nrow_num(team_code_input = "ATL")

## [1] 410

nhl_rosters %>% count_nrow_num(team_code_input = "TOR")

## [1] 2944

Example 3: count rows

Create your own.

code snippets

nrow_num <- nhl_rosters %>%
    
    filter(birth_state_province == "Alberta") %>%
    nrow()

nrow_num

## [1] 4201

Turn them into a function

count_nrow_num <- function(.data, birth_prov_input) {
    
    nrow_num <- .data %>%
        filter(birth_state_province == birth_prov_input) %>%
        nrow()
    
    nrow_num
}

nhl_rosters %>% count_nrow_num(birth_prov_input = "Ontario")

## [1] 16378

nhl_rosters %>% count_nrow_num(birth_prov_input = "British Columbia")

## [1] 2724