# **Projects Portfolio** Last updated on October 1st, 2025
Welcome to my professional portfolio. Here you will find a curated collection of my work in **data analytics**, **teaching**, **machine learning**, and **web-based publications**. Each section contains links to the corresponding project files, hosted in Google Drive or deployed online, along with short explanations of what was done. πŸ”— **[Click here to visit the full folder](https://drive.google.com/drive/folders/1VlUBy_3N27N2qtWSml1wZM3lN0GgFtTo)** --- ## 1. πŸ“š Courses and Presentations in LaTeX This section showcases the training sessions and workshops I have delivered. All presentations are designed in **LaTeX Beamer**, demonstrating both technical expertise and presentation clarity. πŸ”— **[Click here to visit the presentations folder](https://drive.google.com/drive/folders/13b3zkw-RH6-qkMRu5lFVBXL9URuINpH6?dmr=1&ec=wgc-drive-globalnav-goto)** ### 1.1 Introduction to Natural Language Processing and topic modeling [View Materials](https://drive.google.com/drive/folders/1Pc74-ZdNZHoP5m2XQcp-2g2NC_gB5CY8?dmr=1&ec=wgc-drive-globalnav-goto) This module introduces the fundamentals of Natural Language Processing (NLP), explaining how computers process and represent text. It covers tokenization methods, language models, and explores real-world applications such as sentiment analysis, machine translation, and chatbots. ### 1.2 Neural Networks [View Materials](https://drive.google.com/drive/folders/1d0XBXQIfZsHq_gjVIYlAENdau-JciuPc?dmr=1&ec=wgc-drive-globalnav-goto) This module explains how artificial neural networks work, starting from simple perceptrons to deep learning architectures. It covers training workflows, activation functions, and backpropagation, with practical examples in computer vision and text processing. ### 1.3 Statistics [View Materials](https://drive.google.com/drive/folders/13b3zkw-RH6-qkMRu5lFVBXL9URuINpH6?dmr=1&ec=wgc-drive-globalnav-goto) This course provides a foundation in statistics for data-driven decision-making. Topics include descriptive statistics, inference, hypothesis testing, and regression, with a focus on applying statistical tools to solve real-world problems. ### 1.4 Streamlit [View Materials](https://drive.google.com/drive/folders/1hd3W83YKlPYOrHw595XE9o_-jvpEke_b?dmr=1&%3Bec=wgc-drive-globalnav-goto) A hands-on course on building interactive applications with **Streamlit** using Python. Students will learn how to integrate trained models (pickle), create dashboards, and deploy user-friendly tools to share insights and predictions. ### 1.5 Machine Learning and Business Applications [View Materials](https://drive.google.com/drive/folders/1cQARbg-6ZpM8pFf8R2MS2dCIlJsRbBG_?dmr=1&ec=wgc-drive-globalnav-goto) This course focuses on applying machine learning techniques to business problems. It explores predictive modeling, classification, and clustering, emphasizing their use in business intelligence, market forecasting, and process optimization to support better decision-making. --- ## 2. 🌐 Streamlit and GitHub Projects Web-based publications and technical guides deployed on GitHub Pages. These projects combine **technical content** with **user-friendly navigation** for public access. πŸ”— **[GitHub Pages Full Folder](https://drive.google.com/drive/folders/1T2WW1VXkXGer2b2t7fmU9lNqpVC8yuuR?dmr=1&ec=wgc-drive-globalnav-goto)** ### 2.1 Shakira's Lyrics Topic Modeling using LDA (Streamlit) [Visit Shakira's Lyrics Topic Modeling using LDA β€” Streamlit App](https://lda-shakira.streamlit.app/) and check how it was built. **Repository:** [https://github.com/cdaniellopez8/LDA-Shakira](https://github.com/cdaniellopez8/LDA-Shakira) **Overview:** An interactive Streamlit app that applies **Latent Dirichlet Allocation (LDA)** to the lyrics of Shakira’s songs. The goal is to identify latent topics in her discography and analyze how they evolve across time. The app includes: - An interface to explore song lyrics and their topic distribution. - Interactive **Plotly graphs** to visualize the evolution of the main topics over the years (line plots with selectable legends). - Bar charts showing the distribution of topics for a selected song. - Integration with CSV/Excel datasets of songs and topic-word distributions. The repository contains the `app.py` file, preprocessing scripts, datasets (`lyrics`, `topics`, `topic_words`), and the `requirements.txt` listing dependencies (Streamlit, pandas, plotly, scikit-learn, etc). ### 2.2 Embeddings Visualization (Streamlit) [Visit Embeddings Visualization β€” Streamlit App](https://embedding-visualization.streamlit.app/) and check how it was built. **Repository:** [https://github.com/cdaniellopez8/Embedding](https://github.com/cdaniellopez8/Embedding).
**Overview:** An interactive Streamlit app to explore text embeddings. Users can search for words, view the most and least similar words in tables, and visualize embeddings in 3D. The repository contains the `app.py` file, example embeddings, and `requirements.txt` listing dependencies (Streamlit, pandas, plotly, scikit-learn, etc). ### 2.3 EDA Breast Cancer (Streamlit) [Visit EDA Breast Cancer β€” Streamlit App](https://exploratorio.streamlit.app/) and check how it was built. **Repository:** [https://github.com/cdaniellopez8/Exploratorio](https://github.com/cdaniellopez8/Exploratorio).
**Overview:** An interactive exploratory data analysis on a breast cancer dataset. The app allows users to visualize variable distributions, correlation matrices, and preprocessing results including a machine learning model using pickle. The repository contains the `app.py` file/notebooks, the dataset, and the `requirements.txt` listing dependencies (Streamlit, pandas, matplotlib, etc). ### 2.4 AI-Powered Document Chatbot (Streamlit) [Visit AI-Powered Document Chatbot β€” Streamlit App](https://chatbot-orders.streamlit.app/) and check how it was built. **Repository:** [https://github.com/cdaniellopez8/chatbot_documentos](https://github.com/cdaniellopez8/chatbot_documentos) **Overview:** A Streamlit chatbot that integrates **AI with document processing**. The app allows users to upload files, obtain summaries, and ask questions about their content. It demonstrates how to connect large language models to Streamlit apps using **API keys**, providing a practical example of AI-powered document interaction. ### 2.5 Gradient Descent Simulator (Streamlit) [Visit Gradient Descent Simulator β€” Streamlit App](https://descenso-gradiente-simulador.streamlit.app/) and check how it was built. **Repository:** [https://github.com/cdaniellopez8/descenso_gradiente](https://github.com/cdaniellopez8/descenso_gradiente).
**Overview:** An interactive simulator demonstrating gradient descent applied to neural networks (with initial data and learning rate adjustments). The app includes the simulator code, configuration examples, and dependencies required to run the app. ### 2.6 Streamlit Basic Commands (Pedagogical Tool) [Visit Streamlit Basic Commands β€” Streamlit App](https://comandos-basicos.streamlit.app/) and check how it was built. **Repository:** [https://github.com/cdaniellopez8/comandos_streamlit](https://github.com/cdaniellopez8/comandos_streamlit) **Overview:** A pedagogical app showcasing the most common **Streamlit commands** with their outputs. Designed as a teaching resource, it helps beginners understand how each command works by providing interactive examples and visual demonstrations. ### 2.7 Waste Management Best Practices Guide [Visit Website](https://cdaniellopez8.github.io/Guia-De-Buenas-Practicas-Y-Gestion-De-Residuos-Para-Terminales-Portuarios/1-intro.html) **Repository:** [https://github.com/cdaniellopez8/Guia-De-Buenas-Practicas-Y-Gestion-De-Residuos-Para-Terminales-Portuarios](https://github.com/cdaniellopez8/Guia-De-Buenas-Practicas-Y-Gestion-De-Residuos-Para-Terminales-Portuarios)
**Overview:** A practical guide for port terminals to implement sustainable waste management strategies. ### 2.8 Carlos Lopez Blog [Visit Blog](https://cdaniellopez8.github.io/Carlos_Lopez/1-intro.html). **Repository:** [https://github.com/cdaniellopez8/Carlos_Lopez](https://github.com/cdaniellopez8/Carlos_Lopez).
**Overview:** A personal and technical blog covering data science, AI, and analytics. --- ## 3. πŸ“Š Power BI Projects This section presents **interactive dashboards** and **data reports** developed in Power BI, showcasing skills in **data modeling, visualization, and KPI tracking**. πŸ”— **[Visit the Power BI Full Folder](https://drive.google.com/drive/folders/11QYbWJEz9zVrkJK3U8eR5K3J61gVsib3?dmr=1&ec=wgc-drive-globalnav-goto)** - **Sales Report** – Sales performance analysis with monthly trends and product segmentation. - **Sales Scorecard** – KPI monitoring for sales teams with interactive filters. - **Bank Performance** – Financial performance and operational efficiency reporting. - **Procurement Management Indicator** – Monitoring supplier efficiency and purchase order timelines. - **Palermo Report** – Operational performance tracking. - **Waste Management Guide Dashboard** – Visualization of waste classification and disposal processes. --- ## πŸ“Œ About This Portfolio The portfolio is organized by **type of work** rather than chronological order. All materials are my own work, either as individual projects or as part of professional engagements.