Module 12: Apply it to your data 11

Chapter 19 Functions

Import your data

powerrangers <- read_csv("../00_data/PowerRangers.csv")

## Rows: 922 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): season, title, air.date, description
## dbl (3): episode, imdb.rating, total.votes
## 
## 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 <- powerrangers %>%
    
    # Select a type of variables
    select(where(is.numeric)) %>%
    
    # Count columns
    ncol()

ncol_num

## [1] 3

Turn them into a function

count_ncol_numeric <- function(.powerrangers) {
    
    # body
    ncol_num <- .powerrangers %>%
    
        # Select a type of variables
        select(where(is.numeric)) %>%
    
        # Count columns
        ncol()
    
    # return the new variable
    return(ncol_num)
}

powerrangers %>% count_ncol_numeric()

## [1] 3

powerrangers %>% .[1:7] %>% count_ncol_numeric

## [1] 3

Adding arguments for details of operation

count_ncol_type <- function(.powerrangers, type_data = "numeric") {
    # Determine the type of variable to count
    if (type_data == "numeric") {
        ncol_type <- .powerrangers %>%
            select(where(is.numeric)) %>%
            ncol()
    } else if (type_data == "character") {
        ncol_type <- .powerrangers %>%
            select(where(is.character)) %>%
            ncol()
    } else {
        stop("Invalid type_data specified. Use 'numeric' or 'character'.")
    }
    
    # Return the count
    return(ncol_type)
}

powerrangers %>% count_ncol_type()

## [1] 3

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

## [1] 4

powerrangers %>%
    .[1:10, 1:5] %>%  # Subset the first 10 rows and first 5 columns
    count_ncol_type(type_data = "character")

## [1] 3

Example 2: count rows

code snippets

nrow_num <- powerrangers %>%
    
    # filter rows that meet a condition
    filter(season == "UA") %>%
    
    # Count rows
    nrow()

nrow_num

## [1] 0

Turn them into a function

count_num_flights_by_carrier <- function(.powerrangers, season_name) {
  # Check if the season column exists
    if (!"season" %in% colnames(.powerrangers)) {
        stop("The column 'season' does not exist in the dataset.")
    }

    # Count rows matching the season
    nrow_num <- .powerrangers %>%
        filter(season == season_name) %>%
        nrow()

    # Return the count
    return(nrow_num)
}

powerrangers %>% filter(season == "Ninja Steel") %>% count_num_flights_by_carrier(season_name = "Ninja Steel")

## [1] 22

Example 3: count rows

Create your own.

powerrangers <- data.frame(
    season = c("Ninja Steel", "Dino Charge", "Dino Charge", "Ninja Steel", "Beast Morphers"),
    carrier = c("UA", "Delta", "UA", "Southwest", "Delta"),
    episodes = c(20, 22, 22, 20, 19)
)

# Preview the dataset
print(powerrangers)

##           season   carrier episodes
## 1    Ninja Steel        UA       20
## 2    Dino Charge     Delta       22
## 3    Dino Charge        UA       22
## 4    Ninja Steel Southwest       20
## 5 Beast Morphers     Delta       19

# Count rows where season is "Ninja Steel"
ninja_steel_count <- powerrangers %>%
    filter(season == "Ninja Steel") %>%
    nrow()

# Print the result
print(ninja_steel_count)

## [1] 2

code snippets

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

Turn them into a function