AnkurKumar77/book_recommender_kaggle_dataset

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Book Recommendation System

Overview

This project provides a book recommendation system based on book summaries. It uses TF-IDF vectorization and cosine similarity to find similar books.

Dependencies

• —pandas (Used in load_data, preprocess_data)
• —sklearn.feature_extraction.text.TfidfVectorizer (Used in compute_tfidf)
• —sklearn.metrics.pairwise.cosine_similarity (Used in compute_tfidf)
• —numpy (Used in recommend_books)
• —gradio (Used in the interface setup)

Functionality Breakdown

1. load_data(csv_path)

• —Dependencies: pandas
• —Description: Loads the dataset from a CSV file and removes missing values.

2. preprocess_data(df)

• —Dependencies: pandas
• —Description: Groups multiple summaries for the same book and combines them into a single entry.

3. compute_tfidf(df)

• —Dependencies: sklearn.feature_extraction.text.TfidfVectorizer, sklearn.metrics.pairwise.cosine_similarity
• —Description: Converts book summaries into TF-IDF feature vectors and computes cosine similarity between them.

4. recommend_books(book_name, df, cosine_sim)

• —Dependencies: numpy, pandas
• —Description: Finds the most similar books based on the cosine similarity scores.

5. Gradio Interface

• —Dependencies: gradio
• —Description: Provides a simple user interface to input a book name and get recommendations.