Project Reference Notebooks

This repository is a collection of reference notebooks for various projects. The initial drafts of these notebooks were created with the aid of GPT-4, utilizing the June 22nd model with the Wolfram Alpha and Scholar AI plug-ins. They have since been meticulously reviewed and reformatted to ensure accuracy and clarity.

• Machine Learning Directory
• Data Analysis Directory
• Project Template Repository

Disclaimer

While these reference sheets offer valuable insights, they might contain inaccuracies due to potential limitations in my expertise on certain topics. It’s recommended to cross-reference any information here when learning new concepts or applying them in a professional context.

Use Case

These notebooks are not just a mere collection; they have been instrumental in many of my projects, providing quick access to code snippets and refreshing key concepts. I believe that they can be of great utility to others, and hence, I am making them available here.

GPT-4 Prompts Used

For transparency and a better understanding of the content genesis, here are some example prompts I provided to GPT-4 during the creation process:

- Please give me a MarkDown cheatsheet for these classification and regression algorithms in the sklearn library for ML:
    - Logistic Regression
    - K-Nearest Neighbors Algorithm
    - Decision Tree
    - Linear Regression
    - Support Vector Machines
    - Naive Bayes Algorithm

- Structure the content with the following bullet points:
    - Intuition behind the ML algorithm
    - Use cases for the ML algorithm
    - Intuition for classification application (if relevant)
    - Intuition for regression application (if relevant)
    - Probability formula (if relevant)
    - Cost function formula (if relevant)
    - Coding the ML algorithm
    - Key hyperparameters to consider (if relevant)
        - Include tuning code (if relevant)
    - Comprehensive list of model assumptions
    - Interpreting the model's coefficients

Feedback & Contributions

Your feedback is invaluable. If you find any discrepancies or areas of improvement, please raise an issue or submit a pull request. Let’s collaborate to make this resource even better!

---