https://github.com/mehrab-kalantari/book-recommender-system

Building a collaborative filtering recommender systems on books dataset
https://github.com/mehrab-kalantari/book-recommender-system

collaborative-filtering item-based-recommendation machine-learning recomender-system user-based-recommendation

Last synced: about 2 months ago
JSON representation

Building a collaborative filtering recommender systems on books dataset

• Host: GitHub
• URL: https://github.com/mehrab-kalantari/book-recommender-system
• Owner: Mehrab-Kalantari
• Created: 2023-08-05T22:58:35.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-08-05T23:02:35.000Z (over 1 year ago)
• Last Synced: 2024-10-24T15:52:58.065Z (2 months ago)
• Topics: collaborative-filtering, item-based-recommendation, machine-learning, recomender-system, user-based-recommendation
• Language: Jupyter Notebook
• Homepage:
• Size: 2.39 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Books Dataset Recommender System

Building a collaborative filtering recommender systems on books dataset

[Dataset on kaggle](https://www.kaggle.com/datasets/arashnic/book-recommendation-dataset)

## Contents

We have 3 dataframes and we do data cleaning and EDA for each

### Data cleaning

* Removing unnecessary columns

* Renaming columns

* Check for NaN and duplicates

* convert types

### Data understanding and EDA

* Different plots

* Data queries

* Relation between datasets

### Data preprocessing

* Merging datasets

* Removing columns

* Removing NaN and duplicates

* Removing no rating values (zero)

### Modeling 

In this part we use collaborative filtering method to build a recommender system. We use both item-based and user-based.

* ### Item-based 

    Here, we explore the relationship between the pair of items (the user who bought Y, also bought Z)

  **Sample for Wild Animus book**

    ![p](sample/item.png)

* ### User-based

  Here, we look for the users who have rated various items in the same way

  

  **Sample for a random user**

  ![s](sample/user.png)

  

  ![ss](sample/user2.png)