This ETL (Extract, Transform, Load) project employs several Python libraries, including Airflow, Soda, Polars, YData Profiling, DuckDB, Requests, Loguru, and Google Cloud to streamline the extraction, transformation, and loading of CSV datasets from the U.S. government's data repository at https://catalog.data.gov.

A python project using Streamlit, Pycaret and Pandas to demo an automated data modelling🤖 workflow.

Repositório para geração de relatórios exploratórios a partir de arquivos CSV utilizando a biblioteca ydata-profiling.

YData Profiling

Comparison between several Python data profile libraries.

The model predicts household energy usage using historical data and weather factors to optimize consumption and promote sustainability.

Pancreatic disease prediction from biomarker tabular data (Debernardi et al., 2020) — EDA, classical ML (CatBoost/LightGBM/XGBoost), PyTorch MLP, LightAutoML, Optuna HPO, and rigorous evaluation

🤖 A set of tools and examples for working with artificial intelligence.

This repository contains the code snippets, short and long scripts for EDA, and some useful libraries to save time.

Exploratory Data Analysis on Titanic Dataset.

End-to-end BI pipeline on IMDb datasets using Azure Data Factory, Snowflake, and Tableau to deliver insights through scalable modeling and visualization.

Generate reports with ydata_profiling

An interactive data cleaning, profiling, and prediction platform built with Streamlit.

A modern, web-based Exploratory Data Analysis (EDA) tool built with Streamlit and ydata-profiling. Transform your CSV data into comprehensive insights with just a few clicks!

Creating quick visualizations and summary statistics using python

Read, Visualize, Automate and..

Analyzed food safety inspection records across Chicago and Dallas to identify violation patterns, risk factors, and operational insights for public health departments.

This repository showcases my learning process of automating EDA using 'ydata-profiling'

Multi-environment CSV data analysis orchestrator that resolves dependency conflicts between profiling engines through isolated conda environments while providing a unified interface.

ensoML is a beginner-friendly, no-code AutoML platform, providing a modern, intuitive, and responsive interface that empowers users to upload datasets, generate rich EDA reports, and train optimized ML models—all without writing a single line of code.