Loading repository data…
DrAdrianDC / repository
This repository contains a collection of end-to-end machine learning and data science projects I have worked on
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
Here, you'll find a collection of End-to-End Machine Learning and Data Science projects I've worked on, showcasing my skills and expertise in machine learning, deep learning, data analysis, model development. predictive analytics and real-world problem-solving. Each project includes a brief description, the tools and techniques used, and links to the code and any related information.
Description: A comprehensive process of cleaning and preparing raw data for analysis and modeling.
Tools & Techniques: Python, pandas, numpy, matplotlib, plotly, seaborn, scikit-learn
Links: GitHub Repository
Description: Classification problem using Support Vector Machine (SVM) in biomedical research
Tools & Techniques: Python, Machine Learning, SVM, scikit-learn, numpy, pandas, matplotlib, seaborn
Links: GitHub Repository
Description: Predicting the quality of wines using physicochemical variables.
Tools & Techniques: Python, Machine Learning, XGBoost, Logistic regression, Random Forest, Neural networks,
pandas, scikit-learn, tensorflow, keras, numpy, matplotlib, data visualization, Streamlit web app.
Links: GitHub Repository
Streamlit web app: https://wine-quality-ml-app.streamlit.app/
Description: Anomaly detection in West Texas Intermediate (WTI) Crude Oil Prices
Tools & Techniques: Python, Deep Learning, yfinance, pandas, tensorflow, keras, numpy, matplotlib, data visualization,
LSTM autoencoders
Links: GitHub Repository
Description: Apple stock market prediction using Deep Learning
Tools & Techniques: Python, yfinance, pandas,tensorflow, keras, numpy, matplotlib, data visualization,
Deep Learning, LSTM
Links: GitHub Repository
Selected from shared topics, language and repository description—not editorial ratings.
sumehta /
Deep learning experiments: This repository contains jupyter notebooks for training image classification models on MNIST, CIFAR100, language models and autoencoder using Tensorflow.
30/100 healthDescription: Image Classification using Transfer Learning
Tools & Techniques: Python, Machine Learning, tensorflow, keras, seaborn, numpy, matplotlib, data visualization,
Deep Learning, Transfer Learning,
Links: GitHub Repository
Description: Predicting hydrogen adsorption energies on rocksalt complex oxides
combining DFT calculations and machine learning.
Tools & Techniques: Python, Machine Learning, Deep Learning, Linear Regression, Random Forest,
Neural networks, pandas, scikit-learn, tensorflow, keras, numpy, matplotlib, data visualization
Links: GitHub Repository
Description: Clustering using the K-Means and DBSCAN algorithms on the famous Iris dataset.
Tools & Techniques: Python, Machine Learning, K-Means, DBSCAN, pandas, numpy, matplotlib, seaborn, scikit-learn
Links: GitHub Repository
| Project | Description | Stack |
|---|---|---|
| Agentic Search Graph | Production-ready ReAct agent with persistent memory, web search, and LangGraph Studio integration | LangGraph, Groq, Tavily, Streamlit |
This repository is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. (See LICENSE.txt file).
I am a data scientist and Machine Learning expert. I hold a PhD in Physics (Dr. rer. nat. certificate) from the University of Bremen, Germany, and a Bachelor's degree in Radiochemistry (5 years program) from the Higher Institute of Technologies and Applied Sciences (InSTEC), Havana, Cuba. My scientific career has taken me to 4 countries (Canada, The Netherlands, Germany, USA) and 4 academic institutions, with co-authored peer-reviewed publications on quantum chemistry, simulations on computational chemistry, and machine learning. I am enthusiastic about solving real-world problems. Feel free to contact me via email or connect with me on LinkedIn.