Assignment 3 link

Q1

q1  <- movies %>%  
  rename(movie_title = Film , release_year = Year)

print(head(q1))

Q2

selected_movies <- q1 %>%
  select(movie_title, release_year, Genre, Profitability)

print(selected_movies)

Q3

filtered_movies <- movies %>%
  filter(Year > 2000, `Rotten Tomatoes %` > 80)

print(filtered_movies)

Q4

movies_with_profitability <- movies %>%
  mutate(Profitability_millions = Profitability * 1000000)

print(movies_with_profitability)

Q5

sorted_movies <- movies_with_profitability %>%
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))

print(sorted_movies)

Q6

final_dataframe <- movies %>%
  rename(
    movie_title = Film,
    release_year = Year
  ) %>%
  filter(release_year > 2000, `Rotten Tomatoes %` > 80) %>%
  mutate(Profitability_millions = Profitability * 1000000) %>%
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))

print(final_dataframe)

Q7

# while some of the movies with high rotten tomatoes % have high audience score %, 
# there are also movies with low rotten tomatoes % and high audience score (like twilight)
# some also have high rotten tomatoes % and low audience score % (rachel getting married)

Extra Credit

summary_dataframe <- movies %>%
  rename(
    movie_title = Film,
    release_year = Year
  ) %>%
  mutate(Profitability_millions = Profitability * 1000000) %>%
  group_by(Genre) %>%
  summarize(
    average_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
    average_profitability = mean(Profitability_millions, na.rm = TRUE)
  )

  print(summary_dataframe)