- π About the Project
- π» Getting Started
- π₯ Authors
- π€ Contributing
- βοΈ Show your support
- π Acknowledgements
The purpose of this project is to build a machine learning model from a non existing database to predict the popularity of a movie based on several features. The database is collected using web scrapping technique. In this project the website named Sens Critique has been used for scrapping to collect necessary data.
N.B. The author does not support web scrapping for piracy or any sort of unauthorized use of data from any website. This project is for education purpose only.
Python3
,Pandas
,NumPy
, andSQLLite3
- 500 pages of the website containing 16 movies each is scrapped and about page of each movie is also scrapped to collect necessary data.
- This project is a great example of scrapping dynamically loaded data on a website.
- Several features are considered in order to build the machine learning model for the prediction of a movie popularity.
- The project uses
selenium
package to simulate a browser experience in order to load every page smoothly. Pandas
is used to generate a dataframe.
To clone the repository in local environment try following steps.
- A web browser like Google Chrome.
- A code editor like Visual Studio Code with
Git
,Python3
,Pandas
,Selenium
.
You can check if Git is installed by running the following command in the terminal.
$ git --version
Likewise for python
and pip
for package installation.
$ python --version
$ pip show pandas
$ pip show numpy
$ pip show selenium
N.B. If any required package is missing, they must be installed using pip install {package_name}
to ensure the proper use of the notebook.
Clone the repository using this link.
In the terminal, go to your file directory and run this command.
$ git clone https://github.com/PrangonGhose/movie-popularity-prediction-model.git
In the terminal, run these commands to get into development.
$ cd movie-popularity-prediction-model
π€ Prangon Ghose
- GitHub: @PrangonGhose
- LinkedIn: Prangon Ghose
Contributions, issues, and feature requests are welcome! Add suggestions by opening new issues.
Feel free to check the issues page.
Give a βοΈ if you like this project!
Authors would like to thank: