Import your data

data <- read_excel("myData.xlsx")
data
## # A tibble: 32,754 × 20
##         id original_title original_language overview tagline release_date       
##      <dbl> <chr>          <chr>             <chr>    <chr>   <dttm>             
##  1  760161 Orphan: First… en                After e… "There… 2022-07-27 00:00:00
##  2  760741 Beast          en                A recen… "Fight… 2022-08-11 00:00:00
##  3  882598 Smile          en                After w… "Once … 2022-09-23 00:00:00
##  4  717728 Jeepers Creep… en                Forced … "Evil … 2022-09-15 00:00:00
##  5  772450 Presencias     es                A man w…  <NA>   2022-09-07 00:00:00
##  6 1014226 Sonríe         es                <NA>      <NA>   2022-08-18 00:00:00
##  7  913290 Barbarian      en                In town… "Some … 2022-09-08 00:00:00
##  8  830788 The Invitation en                After t… "You a… 2022-08-24 00:00:00
##  9  927341 Hunting Ava B… en                Billion… "\"If … 2022-04-01 00:00:00
## 10  762504 Nope           en                Residen… "What’… 2022-07-20 00:00:00
## # ℹ 32,744 more rows
## # ℹ 14 more variables: title <chr>, popularity <dbl>, revenue <dbl>,
## #   budget <dbl>, poster_path <chr>, vote_count <dbl>, vote_average <dbl>,
## #   runtime <dbl>, status <chr>, adult <lgl>, backdrop_path <chr>,
## #   genre_names <chr>, collection <chr>, collection_name <chr>
small_data <- data %>%
  slice(1:5) %>%
  select(id, original_title, release_date, popularity, revenue,)

Chapter 14

Tools

Detect matches

small_data %>%
  mutate(has_Horror = str_detect(original_title, "Horror"))
## # A tibble: 5 × 6
##       id original_title        release_date        popularity revenue has_Horror
##    <dbl> <chr>                 <dttm>                   <dbl>   <dbl> <lgl>     
## 1 760161 Orphan: First Kill    2022-07-27 00:00:00      5089.  9.57e6 FALSE     
## 2 760741 Beast                 2022-08-11 00:00:00      2172.  5.6 e7 FALSE     
## 3 882598 Smile                 2022-09-23 00:00:00      1864.  4.50e7 FALSE     
## 4 717728 Jeepers Creepers: Re… 2022-09-15 00:00:00       822.  2.89e6 FALSE     
## 5 772450 Presencias            2022-09-07 00:00:00      1021.  0      FALSE

Extract matches

small_data %>%
  mutate(starting_digit = str_extract(revenue, "\\d"))
## # A tibble: 5 × 6
##       id original_title    release_date        popularity revenue starting_digit
##    <dbl> <chr>             <dttm>                   <dbl>   <dbl> <chr>         
## 1 760161 Orphan: First Ki… 2022-07-27 00:00:00      5089.  9.57e6 9             
## 2 760741 Beast             2022-08-11 00:00:00      2172.  5.6 e7 5             
## 3 882598 Smile             2022-09-23 00:00:00      1864.  4.50e7 4             
## 4 717728 Jeepers Creepers… 2022-09-15 00:00:00       822.  2.89e6 2             
## 5 772450 Presencias        2022-09-07 00:00:00      1021.  0      0

Replacing matches

small_data %>%
  mutate(clean_title = str_replace(original_title, ":", "-"))
## # A tibble: 5 × 6
##       id original_title       release_date        popularity revenue clean_title
##    <dbl> <chr>                <dttm>                   <dbl>   <dbl> <chr>      
## 1 760161 Orphan: First Kill   2022-07-27 00:00:00      5089.  9.57e6 Orphan- Fi…
## 2 760741 Beast                2022-08-11 00:00:00      2172.  5.6 e7 Beast      
## 3 882598 Smile                2022-09-23 00:00:00      1864.  4.50e7 Smile      
## 4 717728 Jeepers Creepers: R… 2022-09-15 00:00:00       822.  2.89e6 Jeepers Cr…
## 5 772450 Presencias           2022-09-07 00:00:00      1021.  0      Presencias