DataPrism team has been hired as data science consultants for an anime streaming platform. Our task is to create personalized anime recommender models using Python and deploy them as a user-friendly web application with Streamlit. This application will help users discover new anime based on their preferences and past interactions, enhancing their viewing experience.
Content-Based Recommendations: Suggests anime based on the user's selected favorites, analyzing genres and themes. Collaborative-Based Recommendations: Provides recommendations based on the ratings of similar users, helping to find hidden gems. Exploratory Data Analysis (EDA): Offers insights into the dataset, including popular genres, ratings distribution, and more. Team Introduction: Meet the team behind the project with brief bios and LinkedIn profiles.
base_app.py: The main Streamlit app file that handles the user interface and interaction logic. Models/: Directory containing the machine learning models used for recommendations. EDA/: Folder with visualizations and exploratory data analysis images. Images/: Contains images used in the app, including team member photos. requirements.txt: Lists all the Python packages required to run the app.
-
Clone this repository to your local machine: git clone https://github.com/your-username/anime-recommender-app.git
-
Navigate to the project directory:
cd anime-recommender-app
-
Create a virtual environment:
python -m venv env
-
Activate the virtual environment:
On Windows: .\env\Scripts\activate
On macOS/Linux:
source env/bin/activate
- Install the required packages:
pip install -r requirements.txt
- Run the Streamlit app:
streamlit run base_app.py
Once the app is running, users can:
-
Select their favorite anime and receive personalized recommendations.
-
Explore data insights on the EDA page.
-
Learn about the team members who contributed to the project.
Khululiwe Hlongwane - Project Manager
Ntembeko Mhlungu - Data Scientist
Judith Kabongo - Data Scientist
Tselani Moeti - Github Manager