Nowadays, there are almost unlimited number of TV shows available across all the platforms. If you have to pick up what's the next show you want to watch, how would you choose? Can you detect what TV shows will potentially dissapoint you before you start watching it?
We will analyse the data to identify similar patterns among them, but also explain their differences. For example, are older shows better than the latest ones? Which TV shows are particularly good during the first seasons but then they become bad and boring? Or is there a clear trend when TV shows start to receive worse ratings?
The main goal is to obtain data about the top 50 TV shows based on the IMDb paltform. They are selected based on the number of votes their episodes get over time. Since the dataset is not publicly available, we will have to scrape that data from its website.
- Import necessary libraries
- Scrape data
- Clean data
- Exploratory data analysis