Unsupervised anomaly detection in vibration signal using PyCaret vs BiLSTM

Python Phishing URL Detection

Using PyCaret to Predict Apple Stock Prices

Sample Code :PyCaret is an open-source, low-code machine learning library in Python

Real time streaming of a time series with corresponding forecasts.

This is the Streamlit web application that allows users to upload a dataset, generate an automated exploratory data analysis (EDA) report using the pandas-profiling library, and and train a machine learning model for regression or classification tasks.

Utilizes pycaret to automates machine learning workflows (Deployed at streamlit)

All of my PyCaret's notebooks covering both Supervised & Unsupervised Machine Learning.

Our project leverages Python, pandas, Tableau, and machine learning techniques to analyse and predict student outcomes in higher education. Using a comprehensive dataset, we employ data preprocessing, visualisation with Tableau, and advanced machine learning models built with Python to uncover insights into graduation rates and factors influencing

This repository contains a practice streamlit app that automatically builds, trains and downloads(optional) the best performing machine learning model

A research study on How do factors like alcohol consumption, age, ethnic background, and medical history affect the risk of developing Alzheimer's disease?

Testing PyCaret, Fugue, and Dask

An AutoML-powered system 🤖 that automatically selects, trains, and tunes the best machine learning models for any given dataset 📊. Ideal for quick, accurate model building with minimal manual intervention 🚀.

How to access time series data from QuestDB Data storage and train a forecasting model using Pycaret Library

Low-code machine learning library in Python - Pycaret

Analyzed large-scale patient data from multiple sources, including electronic health records. Developed a predictive model with high accuracy, for early disease detection using 6 ML algorithms in model.

This repository showcases a comparison of AutoML frameworks—PyCaret, Lazy Predict, and H2O AutoML—by evaluating multiple models automatically and analyzing their performance. 🚀

🎮 Trabalho Prático - Tecnologias para Data Science

CatBoost regressor for Predicting alcohol level based on chemical properties of the white wine

This is a Streamlit application that allows users to explore the Washington DC Bike Dataset and showcases the modeling process for predicting the number of users per hour on a given day. The app includes two main sections: exploratory data analysis (EDA) and predictive modeling.