===== Presentation ===== This dataset has been extracted from IMDb (http://www.imdb.org) to have two data matrices descibing the same movies. It has been used in co-clustering tasks, the main goal was to find the genre of the movies, combining the information from the two matrices (keywords and actors). author: Clément Grimal http://membres-lig.imag.fr/grimal/ Questions, suggestions or comments are appreciated! date: April, 2010 ===== Description ===== 617 movies of 17 genres 1878 keywords and 1398 actors A movie stars at least 2 actors and is described by at least 2 keywords. A keyword is used for at least 3 movies. An actor appears in at least 2 movies. ===== Files ===== All the files are encoded in UTF8. M1.txt -- the movies-keywords matrix M2.txt -- the movies-actors matrix movies-mapping.txt -- movie_id||movie_title ... The mapping between the rows of M1 and M2 and the movies title. keywords-mapping.txt -- keyword_id||actor_name ... The mapping between the columns of M1 and the keywords. actors-mapping.txt -- actor_id||actor_name ... The mapping between the columns of M2 and the actors name. genre-list.txt -- genre_id|genre_name ... The list of all the genres. movies_genre_act.txt -- genre_id ... The actual genre of each movie. The order is the one of the movies-mapping.txt file. ===== Statistics ===== Short - 21 - 3.4035656401944894% Drama - 37 - 5.996758508914101% Comedy - 45 - 7.293354943273906% Documentary - 7 - 1.1345218800648298% Romance - 36 - 5.834683954619125% Action - 46 - 7.455429497568882% Animation - 41 - 6.645056726094003% Thriller - 35 - 5.672609400324149% Crime - 44 - 7.13128038897893% Family - 39 - 6.3209076175040515% Adventure - 36 - 5.834683954619125% Horror - 35 - 5.672609400324149% Fantasy - 39 - 6.3209076175040515% Mystery - 42 - 6.807131280388979% Western - 40 - 6.482982171799027% Sci-Fi - 33 - 5.348460291734198% Biography - 41 - 6.645056726094003% Average number of keywords describing a movie : 33 Average number of actors in a movie : 9 Average number of movies a keyword is used for : 11 Average number of movies an actor appears in : 4