Context

The dataset contains two tables:

• df_movies.csv
• df_names.csv

df_movies table

The table consists some of the important information about the movie titles. The table is the merged and trimmed version of the following IMDb original tables:

• title_basics (tconst a.k.a. ID_title, primaryTitle, originalTitle, startYear, runtimeMinutes, genres, averageRating, numVotes,)
• title_principals (nconst a.k.a. ID_crew, category, job, characters)
• title_crew (director, writer)

The table is sorted by ID_title, missing titles are the ones which are not either movie or tv_movie.

• Each title have its number of crew times rows
• Also note that the above number multiplies by number of directors and writers (due to merging tables, therefore groupby function need to be used for single entries for each film)

df_names table

The table is the trimmed version of "names_basics" table of IMDb's. It contains only the names which are involved in the movies.