Author: Kevin Alexander Gomez

If you have a GitHub account, don’t forget to give the project a star ⭐ to help it grow

---

Try the code without installing Python !!!

Use the JupyterLite application by clicking here

---

Description

This academic project was created to facilitate learning Python for students and professionals in Geology and related fields.

By developing algorithmic thinking, you will learn how to use Python code to solve geological problems.

Perseverance is also important to learn each topic, as well as creativity to solve problems.

Note

Prior knowledge of general geology, statistics, and linear algebra is recommended.

---

Index

All chapters are available in the repository as Jupyter notebooks (.ipynb).
It is recommended to download the repository content and use it as a template to develop your own notebooks.

Introductory notebooks are ready (✔️), advanced notebooks are still under development (⏳).

• Fundamentals of Python
  • Fundamentals of programming
    • Variables ✔️
    • How to show a result in Python? ✔️
    • Computational logic ✔️
    • Data structures ✔️
    • Task automation ✔️
    • Object-oriented programming ✔️
    • Reserved words in Python ✔️
  • Core libraries
    • Numpy ✔️
    • Pandas ✔️
    • Matplotlib ✔️
  • Hands-on practice
    • Exercises ✔️
• Statistics
  • Fundamentals of statistics
    • Descriptive statistics ⏳
    • Probabilities ⏳
    • Random variables ⏳
    • Datasaurus ⏳
• Machine Learning
  • Introduction to Machine Learning
    • Fundamentals of Machine Learning ⏳
    • Gradient descent ⏳
  • Supervised learning
    • Linear regression ⏳
    • Logistic regression ⏳
    • Decision trees (DT) ⏳
    • Random Forest (RF) ⏳
  • Unsupervised learning
    • Clustering with KMeans ⏳
    • Principal Component Analysis (PCA) ⏳

---

How to use the content of this project?

The notebooks in this project are provided in .ipynb format and can be used in several ways, depending on your setup:

• Recommended: use Jupyterlite, a ready-to-use, web-hosted coding environment that runs directly in your browser.
• Use Google Colab, Google’s cloud-based notebook platform.
• Run the notebooks locally using a code editor such as Jupyter Lab, Jupyter Notebook, or Visual Studio Code.

---

References

• Bhattacharya, S. (2021). A Primer on Machine Learning in Subsurface Geosciences.
• GEOROC (2023). Geochemistry of Rocks of the Oceans and Continents. Geoscience Centre Göttingen, Germany.
• Kinsley, H., & Kukiela, D. (2020). Neural Networks from Scratch in Python. Sentdex.
• Petrelli, M. (2021). Introduction to Python in Earth Science Data Analysis. Repositorio en Github.
• Petrelli, M. (2023). Machine Learning for Geosciences
• Pyrcz, M. (2021). Python Numerical Demos.
• Trauth, M. (2022). Python Recipes for Earth Sciences. Institute of Geosciences, University of Potsdam, Potsdam, Brandenburg, Germany.