https://github.com/prajjwal6969/recommender-system-using-python

A collection of content-based recommendation systems for songs and movies using Python and machine learning.
https://github.com/prajjwal6969/recommender-system-using-python

content-based-filtering cosine-similarity machine-learning movie-recommendation python recommender-system scikit-learn song-recommendation

Last synced: 5 months ago
JSON representation

A collection of content-based recommendation systems for songs and movies using Python and machine learning.

• Host: GitHub
• URL: https://github.com/prajjwal6969/recommender-system-using-python
• Owner: Prajjwal6969
• Created: 2025-06-18T18:36:03.000Z (7 months ago)
• Default Branch: main
• Last Pushed: 2025-06-18T18:50:27.000Z (7 months ago)
• Last Synced: 2025-06-18T19:42:51.673Z (7 months ago)
• Topics: content-based-filtering, cosine-similarity, machine-learning, movie-recommendation, python, recommender-system, scikit-learn, song-recommendation
• Language: Jupyter Notebook
• Homepage:
• Size: 9.2 MB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# 🎯 Recommender Systems Collection

This repository contains two mini-projects built using Python and machine learning for content-based recommendation:

- 🎵 **Song Recommender System**

- 🎬 **Movie Recommender System**

Both projects demonstrate how similarity metrics and feature engineering can be used to recommend relevant items to users.

---

## 🔍 Project 1: Song Recommender System

### 📌 Description:

This project recommends songs based on audio features using **content-based filtering**. It analyzes attributes like danceability, energy, tempo, valence, etc., and uses similarity metrics to suggest songs that sound similar.

### 🧠 Methodology:

- Features Used:

  - Danceability

  - Energy

  - Valence

  - Tempo

  - Acousticness

  - Liveness

- Techniques:

  - Cosine Similarity or K-Nearest Neighbors

  - Feature scaling and preprocessing

### ✅ Output:

Given a song name, it returns a list of similar songs based on their audio characteristics.

---

## 🎥 Project 2: Movie Recommender System

### 📌 Description:

This system recommends movies based on genres, cast, director, and keywords using **content-based filtering**. The project builds a "tag" feature by combining various metadata.

### 🧠 Techniques Used:

- Text preprocessing and vectorization using `CountVectorizer` or `TfidfVectorizer`

- Cosine Similarity to calculate similarity between movies

- Metadata parsing (cast, crew, overview, genres)

### 🛠️ Input:

- User provides a movie name.

### 🎯 Output:

- Returns top 5–10 similar movies.

---

## 📁 How to Use

1. Clone the repository:

   ```bash

   git clone https://github.com/Prajjwal6969/recommender-systems.git

   cd recommender-systems

2. Install required libraries:

    pip install -r requirements.txt

   

4. Launch the Jupyter notebooks:

    jupyter notebook