Publications by Mark Edney

Custom OpenAI Chatbot Pt2: Fun with Lang Chain

29.11.2023

Photo by Google DeepMindIntroductionThis is a continuation from a previous post about creating a custom ChatGPT bot with Langchain. From the previous post, we have created a CSV file which contains the text captured from a folder full of different PDF files. We will continue from there, creating a custom ChatGPT bot from that CSV files.Loading pack...

6884 sym Python (16657 sym/15 pcs) 2 img

Custom OpenAI Chatbot Pt1: PDF scanning

30.10.2023

Photo by Levart_Photographer on UnsplashIntroductionI have recently completed a project at work, the creation of a custom ChatGPT chatbot. I will break the project into two parts, the first part will scan a folder of PDF files into a dataframe and the second part will pass the data to OpenAI API. This entire project was completed in python.Project ...

3887 sym Python (1328 sym/2 pcs) 2 img

Tree Based Methods: Exploring the Forest

14.11.2022

Forest: Generated by Nightcafe AI Introduction I was recently reading my copy of “An Introduction to Statistical Learning” (my Amazon affiliate link) and got the chapter about the different tree based methods. I am pretty familiar with Random Forest, but a few of the other methods are new to me. Let’s explore these different techniques. Fo...

7042 sym R (1736 sym/14 pcs) 8 img

Python in R Markdown

03.03.2022

Photo by David Clode on UnsplashThe main advantage of using the R Markdown format is the utility of running R code within the text. This is clearly more advantageous than just writing code in a Markdown file. R Markdown is however limited to R code, unable to run Python scripts. The R library reticulate looks to add this capability.Initial SetupT...

2274 sym R (976 sym/13 pcs) 6 img

Python in R Markdown

03.03.2022

Photo by David Clode on UnsplashThe main advantage of using the R Markdown format is the utility of running R code within the text. This is clearly more advantageous than just writing code in a Markdown file. R Markdown is however limited to R code, unable to run Python scripts. The R library reticulate looks to add this capability.Initial SetupT...

2274 sym R (976 sym/13 pcs) 6 img

Simple Neural Networks in Python

20.03.2022

Neural Networks (NN) have become incredibly popular due to their high level of accuracy. The creation of a NN can be complicated and have a high level of customization. I wanted to explore just the simplest NN that you could create. A framework as a workhorse for developing new NN.The SciKitlearn provides the easiest solution with the Multi-Laye...

2751 sym Python (1787 sym/8 pcs) 2 img

Simple Neural Networks in Python

20.03.2022

Neural Networks (NN) have become incredibly popular due to their high level of accuracy. The creation of a NN can be complicated and have a high level of customization. I wanted to explore just the simplest NN that you could create. A framework as a workhorse for developing new NN.The SciKitlearn provides the easiest solution with the Multi-Laye...

2751 sym Python (1787 sym/8 pcs) 2 img

Merging PDFs with Python

14.04.2022

I am currently looking for a new job, which means I need to create many resumes and cover letters. When creating a resume, it is good practice to create a PDF file. PDFs cannot be edited, which can make them difficult to work with, but they retain their formatting. It is impossible to tell which version of Microsoft Word a hiring manager is using...

2355 sym Python (479 sym/3 pcs) 2 img

Level up your programming skills

01.05.2022

How do you become a better programmer? Well, there is strong scientific evidence for the support of the principle of deliberate practice. Deliberate practice is a method of skill development first written by Anders Ericsson in the book “Peak: Secrets from the New Science of Expertise”. I would also recommend reading “Talent Is Overrated: Wh...

3945 sym 2 img

Formatting our output with Python’s F strings

09.05.2022

I have recently been on a tear of different challenges on the site HackerRank. I am about halfway through their 30 days of code and 10 days of statistics. These challenges often require to output number to a certain a number of significant digits. I’ve always thought that the round function can be used for this, but I am wrong. The F string see...

2709 sym 2 img