DataWhispers Recommender System for Data Exploration DHBW course

Github Link

Our Goal

Our goal is to develop a content-based recommender system that makes recommendations for other similar films based on one or more films watched. In addition, the system is to be presented in a user-friendly interface.

Team Members

👤 German Paul

👤 Michael Greif

👤 Nico Dobberkau

Our tech stack

Our structure

📦root directory
 ┣ 📂app
 ┃ ┣ 📜Streamlit App
 ┣ 📂data
 ┃ ┣ 📜Logos and movie image placeholder
 ┃ ┣ 📜Pretrained model files
 ┃ ┣ 📜Report
 ┃ ┣ 📜Presentation
 ┃ ┣ 📜Our datasets and preprocessed datasets
 ┣ 📂EDA
 ┃ ┣ 📜Explanatory Data Analysis Notebook
 ┣ 📂model
 ┃ ┣ 📜Model creation files
 ┃ ┣ 📜Creation of preprocessed datasets scripts
 ┣ 📜README
 ┣ 📜dependencies
 ┗ 📜files to be ignored by github

Download and view our report on this project here

Download and view our PowerPoint for the project here

Prerequisites for the local setup

ℹ️ Should work with all python 3 versions >= , but if you don't have python 3 installed on your machine we recommend to install the same version as we have

🐍 Click here to get to the download page of our python version:

💻 Also you need a RAM space capacity of at least 8GB, since models will be saved in memory ;-)

Setup project locally on your machine from scratch

1. clone the repository

   git clone https://github.com/GermanPaul12/DataWhispers-Recommender-System-DHBW.git

2. Change directory to the project

   cd DataWhispers-Recommender-System-DHBW/

3. Create a virtual environment:

   Linux or mac OS

   python3 -m venv venv/

   Windows

   python -m venv venv/

4. Activate the virtual environment

   Linux or mac OS

   source venv/bin/activate

   Windows

   .\venv\Scripts\Activate

5. Install the dependencies

   pip install -r requirements.txt

6. Start the application

   streamlit run app/app.py 

7. View the web-app at http://localhost:8501/