This is a movie recommender system that is based on the following algorithm.
- Content Based Filtering
- Item-Based Collaborative Filtering with SVD
- Hybrid Recommender - (Content Based + SVD)
This movie recommender is built based on MovieLens Latest 100k Dataset.
The movie recommeder is then deploy on Flask Web App with RestAPI.
-
EDA.ipynb - Exploratory Data Analysis of the Dataset
-
main.py - Main python file for feature engineering and running of Movie Recommender System
-
recommender.py - Code for recommender system class
-
app.py - Code for Flask App Deployment
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
Ensure the correct environment is created
conda create --name <env>
conda activate <env>
pip install -r requirements.txt
The recommender can be run by using the following command
python3 app.py
- Build recommender with Tensorflow TFRS