Python - Applying machine learning to predict the gross and movie trends
The project was developed via Python language using the list of packages as below:
-
For scraping:
- requests
- csv
- BeautifulSoup
-
For building up models:
- tkinter
- pandas
- numpy
- seaborn
- matplotlib
- sklearn
Summary: Using history data of movies (genre, budget and gross) to predict the gross for a given genre and budget. In that:
-
The scripts include two parts. The first part is to scrape the information from https://www.the-numbers.com/movie/budgets/all and write them into a csv file. The second part is to develop a program building up a Linear Regression model based on the budget, gross and genre in that past. Following that, with a chosen genre, a model would base on the given budget to predict the gross and show the trend in future (up or down).
-
Along with the scripts, a pdf file were provided for general information about this project and should be used as a guidelines.