Sukumar's Projects
This project is an exploration and analysis of Airbnb data with a focus on geospatial and exploratory data analysis. It includes interactive visualizations, statistical insights, and recommendations for users interested in Airbnb accommodations in specific countries and cities.
"Automated News Classifier NLP" is a tool that classifies news headlines (Technology, Automobile, Health and Science, Investing, Politics) using machine learning. It leverages Selenium for dynamic web scraping , ensuring the model is trained on up-to-date and diverse news data and text preprocessing is done using Spacy Library.
BisCardX is a Streamlit application that facilitates the extraction of information from images. It utilizes the EasyOCR library to recognize text content in the uploaded images and then extracts relevant details such as names, designations, phone numbers, email addresses, websites, addresses, and pin codes.
This project focuses on predicting department-wide sales for each store for the upcoming year while also considering the impact of markdowns during holiday weeks. The goal is to provide valuable insights to assist in decision-making and offer recommended actions to maximize business impact.
This repository serves as a practical guide on how to containerize a Streamlit web application using Docker. Whether you're new to Docker or Streamlit, this repository aims to provide a step-by-step demonstration of the process, making it easier for you to package and deploy your Streamlit applications in a containerized environment.
This project, titled "Industrial Copper Modeling," is an application of data analysis and machine learning techniques to address challenges in the copper industry. It involves building predictive models for both regression (predicting Selling Price) and classification (predicting the success or failure of leads)
This repository contains a machine learning project that uses an ElasticNet model to predict the quality of wine based on various features. The project demonstrates best practices for tracking experiments and managing machine learning models using MLflow.
This Streamlit application allows users to extract and explore images of T-shirts from Myntra. The process involves scraping data from the Myntra website using Selenium, followed by preprocessing the data and creating an interactive application with Streamlit. Users can browse through the images, view additional information, and download the images
The outcome of this project will be an interactive geo visualization dashboard that presents insights from the Phonepe Pulse Github repository in a visually engaging manner. The dashboard will have various dropdown options, allowing users to explore different facets of the data. Data stored in a MySQL database will ensure efficient Data retrieval
This project is an in-depth analysis of eCommerce data using PySpark for big data processing. It focuses on understanding customer behavior, sales trends, and providing valuable insights for business strategies.
This project implements a machine learning model to predict house rental prices. The model is trained on a dataset containing various features such as property type, lease type, etc
This Python application combines speech recognition with the power of ChatGPT by OpenAI to convert spoken language into text and generate text-based responses. It provides an interactive and user-friendly interface using Streamlit.
Config files for my GitHub profile.
This is a ETL(Extract Transform Load) project in which the Data from Youtube API is extracted and tranformed to MongoDB database and finally the data is fetched from the MongoDB database, inserted into MySQL Tables and Queries are executed for Data analysis