1. Let's recreate the result from the final step of the Selecting the smallest from the largest recipe:

>>> movie = pd.read_csv('data/movie.csv')
>>> movie2 = movie[['movie_title', 'imdb_score', 'budget']]
>>> movie_smallest_largest = movie2.nlargest(100, 'imdb_score') 
                                   .nsmallest(5, 'budget')
>>> movie_smallest_largest

2. Use sort_values to replicate the first part of the expression and grab the first 100 rows with the head method:

>>> movie2.sort_values('imdb_score', ascending=False).head(100)

3. Now that we have the top 100 scoring movies, we can use sort_values with head again to grab the lowest five by budget:

>>> movie2.sort_values('imdb_score', ascending=False).head(100) 
          .sort_values('budget').head()