In this project I have built an UI framework, where a Python script that demonstrates how
to select the best algorithm for a given dataset.
The script provides functionality to perform various tasks such as data upload,
automated exploratory data analysis (EDA), missing value analysis, outlier handling,
target selection, and algorithm selection.
Starred by the creator of D-Tale on GitHub.
This application is designed to harvest data from YouTube using the YouTube Data API, store it in a MongoDB database, migrate it to a MySQL database, and perform various data analysis tasks.
This project provides an interactive dashboard for visualizing Phonepe Pulse data. Utilizing Streamlit and Plotly, users can explore various metrics derived from transaction and user data.
BizCardX is a Streamlit application designed to streamline the extraction and management of business card information. Users can upload an image of a business card, extract relevant details
using easyOCR, and store the information in a database.
This project analyzes Airbnb data using MongoDB Atlas, performs data cleaning, develops interactive visualizations (using Plotly and PowerBI), and creates dynamic plots to gain insights into pricing, availability patterns, and location-based trends.
This project aims to provide a comprehensive analysis of banking data, including Exploratory Data Analysis (EDA), customer segmentation,
credit risk assessment, and performance prediction. The goal is to gain insights into the data, identify key features influencing credit scores,
and build predictive models to assess credit risk and performance.
This project aims to develop machine learning models to predict selling prices and lead status in the copper industry using advanced techniques.
Integration of deep learning, real-time analytics, and AI-driven automation will further enhance efficiency and productivity in the copper industry.
The Singapore Resale Flat Price Predictor is a machine learning web application designed to estimate the resale prices of flats in Singapore.
This tool helps potential buyers and sellers make informed decisions based on various factors such as location, flat type, floor area, and lease duration.
This project aims to analyze crime data in Chicago to identify patterns, trends, and hotspots, supporting strategic decision-making for law enforcement.
By leveraging historical and recent crime data, we aim to provide actionable insights to improve resource allocation, reduce crime rates, and enhance public safety in Chicago.
This project aims to predict horse racing outcomes using machine learning techniques.
The dataset includes detailed information on horse races and individual horses from 1990 to 2020. Given the complexity and inherent unpredictability of horse racing, this project seeks to explore various machine learning models and feature engineering techniques to improve prediction accuracy.