3 ways to relabel data

label_cleaning.R

library(tidyverse)
big_tech_companies <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2023/2023-02-07/big_tech_companies.csv')
big_tech_companies
# # A tibble: 14 × 2
#    stock_symbol company                                  
#    <chr>        <chr>                                    
#  1 AAPL         Apple Inc.                               
#  2 ADBE         Adobe Inc.                               
#  3 AMZN         Amazon.com, Inc.                         
#  4 CRM          Salesforce, Inc.                         
#  5 CSCO         Cisco Systems, Inc.                      
#  6 GOOGL        Alphabet Inc.                            
#  7 IBM          International Business Machines Corporat…
#  8 INTC         Intel Corporation                        
#  9 META         Meta Platforms, Inc.                     
# 10 MSFT         Microsoft Corporation                    
# 11 NFLX         Netflix, Inc.                            
# 12 NVDA         NVIDIA Corporation                       
# 13 ORCL         Oracle Corporation                       
# 14 TSLA         Tesla, Inc. 


## METHOD 1: case_when()
big_tech_companies |> 
  mutate(
    company = case_when(
      stock_symbol == 'AAPL' ~ "Apple",
      stock_symbol == 'ADBE' ~ "Adobe",
      stock_symbol == 'AMZN' ~ "Amazon",
      stock_symbol == 'CRM' ~ "Salesforce",
      stock_symbol == 'CSCO' ~ "Cisco Systems",
      stock_symbol == 'GOOGL' ~ "Alphabet",
      stock_symbol == 'IBM' ~ "IBM",
      stock_symbol == 'INTC' ~ "Intel",
      stock_symbol == 'META' ~ "Meta",
      stock_symbol == 'MSFT' ~ "Microsoft",
      stock_symbol == 'NFLX' ~ "Netflix",
      stock_symbol == 'NVDA' ~ "NVIDIA",
      stock_symbol == 'ORCL' ~ "Oracle",
      stock_symbol == 'TSLA' ~ "Tesla",
    )
  )
# # A tibble: 14 × 2
# stock_symbol company      
# <chr>        <chr>        
# 1 AAPL         Apple        
# 2 ADBE         Adobe        
# 3 AMZN         Amazon       
# 4 CRM          Salesforce   
# 5 CSCO         Cisco Systems
# 6 GOOGL        Alphabet     
# 7 IBM          IBM          
# 8 INTC         Intel        
# 9 META         Meta         
# 10 MSFT         Microsoft    
# 11 NFLX         Netflix      
# 12 NVDA         NVIDIA       
# 13 ORCL         Oracle       
# 14 TSLA         Tesla   



## METHOD 2: case_match() saves a little bit of typing
big_tech_companies |> 
  mutate(
    company = case_match(stock_symbol,
      'AAPL' ~ "Apple",
      'ADBE' ~ "Adobe",
      'AMZN' ~ "Amazon",
      'CRM' ~ "Salesforce",
      'CSCO' ~ "Cisco Systems",
      'GOOGL' ~ "Alphabet",
      'IBM' ~ "IBM",
      'INTC' ~ "Intel",
      'META' ~ "Meta",
      'MSFT' ~ "Microsoft",
      'NFLX' ~ "Netflix",
      'NVDA' ~ "NVIDIA",
      'ORCL' ~ "Oracle",
      'TSLA' ~ "Tesla",
    )
  )

## METHOD 3: if_else() + str_remove_all() + regex
big_tech_companies |> 
  mutate(
    company = if_else(
      stock_symbol == 'IBM',
      'IBM',
      company
    ),
    company = str_remove_all(
      company,
      '( Platforms| Corporation| Inc\\.|\\.com|,)'
    )
  )