An Intersection of Engineering, Agriculture, Data Science and Innovation

Welcome to the Intersection of Engineering, Agriculture, Data Science and Innovation Greetings, fellow enthusiasts! I'm Erick, an Industrial and Systems Engineer with a diverse background in Organic Agriculture and Food Systems, Automotive Engineering, and Lean Manufacturing. As I venture into the realm of data science and applied research, particularly in the intriguing field of digitizing fish behavior, I am eager to explore the cross-disciplinary connections that foster innovation and growth. This website serves as a comprehensive repository of my academic, professional, and personal experiences, showcasing the wealth of knowledge I have amassed through various projects and endeavors. From my time in the Automotive Engineering Master Program and work in lean manufacturing to the lessons learned in a Data Science Bootcamp and my personal adventures in home automation, Docker, and home lab experiments, I aim to provide a transparent account of my progress and a roadmap for future pursuits. While my primary objective is to document each step of my journey for my own reference and edification, I warmly invite you to explore and learn alongside me. Together, we can embark on a journey of discovery and growth, pushing the boundaries of what's possible in engineering, agriculture, and data-driven storytelling. Let's uncover the hidden stories that data has to offer and contribute to a sustainable and efficient future. Join me at the crossroads of expertise, where innovation thrives and knowledge grows when shared.

Posts

Fedora 39 - Python - Conda - Mamba

In this post I review the steps I follow to setup my workflow for Python3. I use mamba as package and environment manager, and Spyder-IDE as my choice of an Integrated Development Environment.

Fedora 38 Setup - Part IV - WSL

From time to time, I need to use a windows laptop to run a native program there. Nowadays, Windows allows us to have a Linux kernel running as a subsystem. There are plently of examples on how to install Ubuntu, as its available in the Windows Store. However as discussed previously, I like much better Fedora.

Fedora 38 Setup - Part III - TeX

In this post I review the steps to setup LaTeX with its flavor LuaLaTeX, TeXStudio and Pandoc.

Fedora 38 Setup - Part II - Workstation Version

WELL.. The KDE server version did not work well. The computer reboot when streaming while the CPU got temperatures around 61°C. Installing NVIDIA drivers did not resolved the issue. Black screens came after booting.. A possibility could be, missing the configuration in the boot setup to use the NVIDIA driver instead of the nouveau divers. Additionally there was mouse freezing, which could be fixed by using the solaar package. Bud did not had the opportunity to test it. I tried the KDE ISO version whit the same results than using the server version.

Fedora 38 Setup - KDE - Server Version

I have run Ubuntu on and off through the years, almost since the beginning around 17 years ago. Back then it was great. It helped me to get into the Linux world. Nowadays, it seems just boot-loaded. Specially the eternity that takes to update the libraries. And, I do not like today’s gnome in a Workstation. To me it is great in a laptop where a track pad is available. But not for a dedicated mouse. I know I could use a different flavor, but how old the libraries are in it, is a no in today’s world.

Image Protms for Midjourney

The importance of having the correct prompt to recreate an image in Midjourney is the base to achieve the expected results. A bad prom;t leads to find either not the target or nice surprises. Even when the main goal is to create an artistic image of our imagination, it is necessary to have a structure to meet our needs with the minimum use of resources.

Forecasting building energy demand

Final project done at the Neuefische bootcamp. The project focuses on forecasting hourly building energy demand of 9 buildings. The used data was from the 2021 CityLearn Challenge, based on 4 years energy consumption and weather data.

Exploratory Data Analysis - Seattle, WA

Exploratory Data Analysis (EDA) is a crucial step in the data science process that allows us to understand the structure and relationships within a dataset. It involves visualizing, summarizing, and transforming the data to uncover patterns and insights that inform the development of predictive models. Here are a few reasons why EDA is so important in data science:

Predicting Success in Kickstarter with Machine Learning

Machine learning has revolutionized our ability to predict outcomes by leveraging vast amounts of data to uncover hidden patterns and trends. By continually refining predictive models and adapting to new data, machine learning has not only enhanced the accuracy of predictions but also propelled innovation across industries, ultimately paving the way for a smarter, more efficient future.