Project Overview
Engineered and launched a Flask-based search engine on EC2, recommending books based on text queries by leveraging relevance scores calculated from TF-IDF (Term Frequency-Inverse Document Frequency), after applying advanced NLP techniques to the text data of books stored in DynamoDB. Used Python, Hadoop and MapReduce for cleaning and to handle large text files efficiently, improving data processing performance
- Category: AI/ML
- Tech Stack: Python, NLP, AWS (DynamoDB, S3, EC2), Flask, Hadoop, Docker, Spark
- GitHun Link: Book Recommendation System
Project Report
Autem ipsum nam porro corporis rerum. Quis eos dolorem eos itaque inventore commodi labore quia quia. Exercitationem repudiandae officiis neque suscipit non officia eaque itaque enim. Voluptatem officia accusantium nesciunt est omnis tempora consectetur dignissimos. Sequi nulla at esse enim cum deserunt eius.