Visual MLOps you host yourself: canvas or Python pipelines, training, registry, serving and drift monitoring. Export models as standalone APIs, or run them on Databricks with MLflow.

react platform machine-learning deep-learning docker-compose databricks model-deployment mlops mlflow ml-pipeline model-registry experiment-tracking data-orchestration databricks-mlops feature-engineering-python

• Updated Nov 6, 2026
• Python

An automated pipeline that uses the YouTube Data API to extract video data based on specific keywords, storing the most-viewed videos in GitHub for trend analysis and actionable insights.

github-automation streamlit-dashboard data-visualization-python plotly-visualization google-translator-api python-data-pipeline youtube-data-extraction youtube-trends-analysis youtube-api-automation video-trends-insights devops-youtube-trends feature-engineering-python kaggle-data-pipeline data-cleaning-python api-integration-python iso-3166-alpha-2 youtube-video-analysis content-trend-analysis youtube-engagement-metrics streamlit-app-deployment

• Updated Nov 12, 2026
• Jupyter Notebook

Projeto de Machine Learning para previsão de cancelamentos de reservas hoteleiras, utilizando análise exploratória de dados, tratamento e Engenharia de Features, classificação e métricas de avaliação.

python machine-learning dataset dataset-generation predictive-analytics training-module machine-learning-models training-data training-project training-dataset machinelearning-python modelagem-de-dados tratamento-de-dados engenharia-de-dados analise-exploratoria-de-dados training-model ia-training feature-engineering-python feature-engineering-ml acuracia

• Updated Nov 8, 2026
• Jupyter Notebook

A streamlined, production‑ready analysis of Washington, DC property data featuring reproducible workflows, modular code, clear statistical insights, and a robust predictive modeling foundation designed for scalable pipelines and real‑world analytical use.

python machine-learning r reproducible-research scikit-learn sas pandas statistical-analysis feature-engineering predictive-modeling bayesian-statistics model-evaluation pandas-python professional-project modular-code reproducible-research-with-r real-estate-analytics feature-engineering-python feature-engineering-ml mlops-foundation

• Updated Sep 9, 2026
• R

AI-powered data preparation pipeline: upload messy files, review AI cleaning plans, download analysis-ready datasets. Built on Azure AI Foundry + 8-agent orchestration.

python machine-learning azure mcp multi-agent feature-engineering azure-ai streamlit data-cleaning-pipeline data-cleaning-automation data-cleaning-and-preprocessing llm-agent feature-engineering-python

• Updated Mar 14, 2026
• Python

End-to-end data preprocessing pipeline using the IBM HR Employee Attrition dataset with Python, Pandas, and Google Colab.

python pandas-dataframe data-preprocessing data-cleaning data-profiling google-colab-notebook employee-attrition-prediction data-engineering-project feature-engineering-python

• Updated Aug 7, 2026
• Jupyter Notebook

9段階のイテレーションを通じた心臓病予測の進化。統計学（標本誤差の最小化）を実戦投入し、5-Seed Averagingによる極めて高い汎化性能と実務的信頼性を実現したMLポートフォリオ。

data-science statistics cross-validation kaggle xgboost lightgbm ensemble-learning feature-engineering machine-learning-models robust-modeling feature-engineering-python validation-strategy

• Updated Mar 31, 2026
• Python

A machine learning project on the Ames Housing dataset covering data preprocessing, exploratory data analysis (EDA), feature engineering, model building, and evaluation.

python data-science machine-learning numpy scikit-learn regression eda pandas feature-engineering housing-price-prediction feature-engineering-python

• Updated Jul 17, 2026
• Jupyter Notebook