Name: Sai Kiran Reddy Dyavadi
Type: User
Company: Texas A&M University
Bio: As a data enthusiast, I love to explore, analyze, and visualize data to uncover its hidden implications and applications.
Location: College Station
Sai Kiran Reddy Dyavadi's Projects
This repository contains a machine learning project aimed at predicting housing prices in Boston. This project showcases the end-to-end process of building and deploying a machine learning model, from data preprocessing and model training to serialization and deployment.
This repository contains wireframes, mockups, product canvas and other UI/UX related materials designed by myself.
Hello world, this is my Profile
This repository contains projects focused on EDA and Feature Engineering. It includes analyses on Zomato restaurant data, Black Friday sales, and flight price prediction. It features automated EDA techniques using Python libraries to streamline and enhance the analysis process. These projects provide insights, demonstrate various EDA methods
This project is developed using VGGFace. The pipeline includes data ingestion of 5,000+ images, MTCNN for face detection, TensorFlow and Keras for preprocessing, VGGFace for feature extraction, and cosine similarity for matching. Deployed with Streamlit for real-time predictions under 2 seconds, achieving 96% accuracy, enhances user engagement
The IPL Innings Wise Score Predictor uses Python, scikit-learn, XGBoost and Flask to predict IPL innings wise scores. It preprocesses 17 years IPL data, performs feature engineering, and trains models like Random Forest, XG Boost, Gradient Boost. The Flask app allows user input for score predictions, showcasing machine learning in sports analytics
The NYC Taxi Fare Prediction project leverages advanced machine learning to estimate fares based on historical data. Hyperparameter tuning is used select the best regression algorithm, with XGBoost showing the lowest error. Key features include distance calculation with Haversine formula and Part of the day (AM/PM) when the ride was taken
This repository uses a dataset of reviews to perform comprehensive text analysis. It employs NLTK for tokenization, POS tagging, and NER, and utilizes VADER and Hugging Face Transformers (RoBERTa) for sentiment analysis. The project visualizes sentiment distributions and compares model results, providing insights into text sentiment patterns.
SimpleFlaskApp is a minimalistic Flask application designed to showcase the basic setup and deployment of a Python web application using Flask and Docker. The application serves a simple greeting and is designed to demonstrate the essential components of a web application, including routing and application deployment on Heroku.
This project converts .wav files into text using a pipeline that reads files from Amazon S3, extracts features via STFT and MFCCs, and applies a CNN model fine-tuned with Wav2Vec2. Deployed via Flask on AWS EC2 with Docker and GitHub Actions, it improves transcription accuracy by 38% and streamlines deployment. Ideal for developers,data scientists
This repository contains a machine learning model aimed at predicting student performance across various metrics. Utilizing a diverse set of Machine Learning Regression algorithms, the model predicts scores based on demographic and academic variables.This project demonstrates robust approach to leveraging machine learning for educational outcomes.
This repository implements a robust text summarization system using Hugging Face Transformers. System processes over 10,000 text samples with 85% accuracy, utilizing the Pegasus model for efficient sequence-to-sequence tasks. An interactive web application built with FastAPI enables real-time text summarization for summarizing lengthy texts.
University Admission Predictor is a sophisticated Flask-based web application designed to predict the likelihood of admission to graduate programs based on student profiles. It leverages a range of regression techniques to evaluate admission chances.This project showcases the practical application of machine learning in educational forecasting.