Dedicated to exploring the realms of technology, and eager to contribute innovative solutions to the ever-evolving IT landscape.
PROJECT SHOWCASE
Introducing an intelligent book recommendation system driven by sophisticated content analysis. Using a comprehensive dataset featuring 1750 books from Kaggle, this project employs advanced content-based filtering techniques. By creating vectors based on various content features such as genre, author, and plot keywords, the system excels at understanding the unique difference and similarity of each book. Users can seamlessly discover new books by inputting their favorite book, and the system responds with a tailored list of content-wise related recommendations. Additionally, the system ensures to suggest all books of the same genre, providing users with a comprehensive selection within their preferred literary landscape. The streamlined frontend, crafted with Streamlit, ensures a user-friendly experience, making book exploration both personalized and enjoyable. This project gives book recommendations by prioritizing content relevance and user satisfaction, while also broadening the reader's horizons within their preferred genres.
During my internship at CodSoft, I led the development of several data science projects. These projects involved tasks like filtering data and building models to predict outcomes based on given inputs. I used tools like LogisticRegression, LinearRegression, RandomForestRegression, and Ridge from sklearn to train these models. Additionally, I used seaborn for easy-to-understand data visualization. The data for these projects was obtained from platforms like Kaggle, ensuring its quality and relevance. Some notable projects I worked on include predicting Titanic survival, movie ratings, iris flower types, and sales. Each project required a good grasp of data science concepts and careful model training.
Led a four-member team during my degree curriculum to develop a project centered around the placement cell. Additionally, I took charge of documentation and preparing the SRS report for the project.
The Placement Cell webapp is a dynamic hub connecting students and recruiters seamlessly. Designed for ease of use, students can register, login, and explore a curated list of job opportunities posted by recruiters. The intuitive interface allows students to apply directly to these positions. Recruiters, on the other hand, can effortlessly post job openings, creating a streamlined recruitment process. To foster communication and collaboration, the platform features a dedicated discussion forum where students and recruiters can engage in meaningful conversations, facilitating a robust exchange of information and ideas. This comprehensive solution aims to bridge the gap between talent and opportunities in a digital ecosystem, ensuring a smooth and efficient placement experience for both students and recruiters.
This project is an advanced virtual desktop assistant developed in Python. It allows users to interact with their computer using voice commands, and the assistant responds with a synthesized voice. The assistant can perform various tasks, such as playing specific music, opening predefined applications, navigating to particular websites, displaying the current time. It can also engage in voice-based conversations with ChatGPT 3.5. This comprehensive assistant provides a user-friendly and interactive experience, leveraging voice recognition and artificial voice generation technologies.
Introducing a responsive weather forecasting project seamlessly integrated with the OpenWeatherMap API. It provides users with real-time weather updates and future predictions for any location worldwide. With the option to input a specific location or utilize the "use current location" feature, users can effortlessly access accurate weather data tailored to their needs, whether on desktop or mobile devices. The project not only displays current weather conditions but also offers a detailed forecast for the next five days, empowering users to plan ahead with confidence. Through intuitive design and reliable data retrieval, this responsive project ensures a seamless user experience across all devices, making it easier than ever to stay informed about weather patterns and make informed decisions accordingly.
Introducing WhatsApp Chat Analyzer, a powerful tool crafted with Python and Streamlit, designed to provide users with comprehensive insights into their WhatsApp chat data. From total message counts to word frequencies, media shared, and even links exchanged, this tool offers a multifaceted analysis of your conversations. Delve deeper into your chat history with features like monthly activity timelines, identifying your most active periods, and visualizing geographic activity patterns through interactive maps. Uncover trends and patterns with ease through word clouds highlighting frequently used terms. Whether for personal reflection or group analysis, WhatsApp Chat Analyzer offers a robust platform for exploring the dynamics of your conversations in depth.