Harsh Gupta's Projects
Welcome to my Github! Here you'll find a collection of my projects and work experience in the field of data science and artificial intelligence. Feel free to explore the projects and reach out if you have any questions or collaboration opportunities.
Welcome to my portfolio! Here you'll find a collection of my projects and work experience in the field of data science and artificial intelligence. Feel free to explore the projects and reach out if you have any questions or collaboration opportunities.
An AI-powered application that can guess movie titles based on plot summaries. Built using LangChain, Google Palm LLM, CSVLoader, RetrievalQA, Google Palm Embeddings, and FAISS. Deployed on Streamlit for an interactive user experience, allowing you to enter a plot summary and receive a predicted movie title.
"š Build ML models effortlessly! Our user-friendly platform empowers beginners with no ML background. Features include drag-and-drop functionality, pre-built templates, AutoML, and visual model representation. Learn, create, and deploy with real-time feedback. Join our supportive community! š #MachineLearning #NoCodeML"
The Bank Management System is a Python-based application utilizing Tkinter for its graphical user interface and MySQL for database management. This project allows users to manage their bank accounts by providing functionalities to open new accounts, check balances, deposit and withdraw money, and close accounts.
BCA Result Analysis: š Dive into student performance trends with data-driven insights. Clean, visualize, and analyze data for informed decisions in education. šš”
The Blog Generation project uses advanced AI technologies like Llama 2, LangChain, and Hugging Face to create custom blog content. With Streamlit, users can input a topic, word count, and audience type to generate blogs quickly and efficiently. The project combines the power of LLms with a simple, interactive interface for easy content creation.
This repository contains a collaborative filtering-based book recommender system built with Python Flask. šāØ The system utilizes cosine similarity to suggest books based on user preferences and historical data. šš
"Chat with Databases using RAG" is a cutting-edge project that seamlessly integrates natural language inputs with database interactions. By leveraging advanced techniques like RAG and few-shot learning, it generates SQL queries from plain text and retrieves human-like responses from the database, revolutionizing the way we interact with data.
The Automated CUET MCA Score Checker simplifies score checking for CUET aspirants. This online tool matches your answers with the original sheet, providing quick and accurate scores. To use it, save your CUET answersheet as an HTML file and upload it. No installation is needed, making it a convenient solution for students. Contributions are welcome
Document QnA is a webapp that lets users upload multiple documents and ask questions about their content. It uses Llama3, Groq API, LangChain, FAISS, and Google Palm Embeddings to identify relevant documents and provide answers with page numbers. The Streamlit interface ensures easy and efficient use.
During my Data Science internship at Encryptix, I tackled three distinct tasks: predicting Titanic survival rates, classifying Iris flowers, and detecting credit card fraud. Each project provided valuable hands-on experience in diverse aspects of data analysis and machine learning.
This project features a web application that predicts house prices using a linear regression model. Users can enter details such as location, square foot, number of bathrooms, and bedrooms via a simple HTML form. The predictions are generated by a Flask backend that utilizes the trained model to provide accurate price estimates.
"Laptop Price Predictor š®š - ML-driven app using Random Forest Regressor. Predict prices based on features like RAM, memory, and processor. Achieved R2 score of 90%. Built with Scikit-learn, Pandas, and Numpy. #MachineLearning #DataScience #Streamlit š"
A simple and standalone Python module for displaying FIGlet fonts with no external dependencies. Enhance your programs with colorful and attractive text displays. Supports custom colors and a rainbow effect.
The Next Word Predictor using LSTM is a project that builds a text prediction model using Long Short-Term Memory (LSTM) neural networks. It predicts the most likely next word in a given sequence, useful for text composition and natural language processing tasks. The project allows customizable training and includes an interactive script for testing
This project adapts OpenAI's Whisper model to create an automated speech recognition system for Hindi. The goal is to accurately transcribe Hindi audio into text for applications like transcription, voice commands, and accessibility. By fine-tuning the model, the project aims to improve recognition accuracy and performance in Hindi-language context
Optimize linear regression parameters using a genetic algorithm. This project uses selection, crossover, and mutation to minimize the mean squared error all coded from scratch, demonstrating the application of genetic algorithms in machine learning model optimization.
A Python-based port scanner that identifies open ports and gathers service information. It resolves IP addresses and hostnames, performs banner grabbing, and can scan multiple targets for educational and network security purposes.
A beginner-friendly Python module designed for non-math coders to solve complex math problems effortlessly. With over 50+ math formulas and a powerful search() function, this module simplifies math tasks without requiring any mathematical background.
This project uses a genetic algorithm to search for a target string. By evolving a population of random strings through selection, crossover, and mutation, the algorithm progressively approximates the target string over multiple generations.
š¬ Analyze movie reviews sentiment in real-time with "Sentiment Analysis on Movie Reviews using Word2Vec"! Powered by advanced NLP and deployed using Streamlit, this app categorizes reviews as positive or negative. Perfect for film enthusiasts and industry professionals! šæš
"Sentiment Analysis using BERT" utilizes advanced NLP with BERT for precise sentiment analysis, surpassing traditional methods like Word2Vec. Gain valuable insights into customer feedback and social sentiment effortlessly. šš¬ #NLP #SentimentAnalysis #BERT
ML model for spam detection using Naive Bayes & TF-IDF. Achieved 0.98 accuracy. Utilized Scikit-learn, Numpy, nltk. Implements NLP concepts. Explore precise spam classification effortlessly. #MachineLearning #SpamDetection šāļøš±
This project features a TCP reverse shell, developed from scratch using Python, for educational use. It allows a server to securely connect and control multiple clients via AES-encrypted communication, with the client auto-starting on system boot.
Play Tic-Tac-Toe against a computer AI or challenge a friend in this Python command-line version. Enjoy dynamic board updates, intuitive controls, and ASCII art for game outcomes. Perfect for quick matches and sharpening your strategy skills!
This repository explores building a character-level transformer decoder in PyTorch, similar to GPT while focusing more on understanding individual components. My goal is to gain deep transformer knowledge and see if character-level learning improves handling of unseen words. The code allows for hyperparameter tuning and experiment customization.