This repository download and analyse IMDb movie dataset in order to predict movie ratings.
Dataset: https://www.imdb.com/interfaces/
Data set gets downloaded automatically.
dataset_downloader is in charge of downloading and extracting dataset files.
Number of total rows: 984,914
Raw features used: Directors, titleType, isAdult, startYear, runtime, genres.
Number of features after cleaning and transforming to numerical values: 100
For more insights and analysis report download and read the documentation and powerpoint presentation.