James McDonald

 Week 6 - New Tools in AI This week, I got to learn about a cool new tool in AI, Replit. Replit is a super cool tool. It is an automated app developer. It has a similar UI as RStudio and PowerBI, making it super easy to use if you have some coding experience. However, the coolest part about this tool is that you do not need much coding experience to be able to use it. Simply give it a prompt, and you will work together with the tool to create an app that works for you. Starting out with a development phase, test phase and a usage phase, you can work real time with AI to create a well functioning app. Given this experience, I decided to write this weeks blog post by working with AI, about the new tool in AI. I worked with OpenAI to create an image about Replit, and worked with it to create the actual blog post.  ChatGPT Response: Replit: Coding Without the Chaos If you’ve ever tried to start coding and felt overwhelmed by things like setting up environments, downloading package...

Probability and Statistics for Data Science  (image created using Canva AI) This week I decided to write my blog on the chapter we went over. I absolutely love everything to do with data science. However, there are about three main points that are my favorite. Visualizations top the chart, then analyzing statistics, and then probability. During this chapter, we went over both probability and statistics, so I loved the reading.  The first topic covered was descriptive statistics. Some common descriptive statistics are mean, median, modem standard deviation, etc. These are statistics that we have seen since a young age, and continue to be a prominent statistic as we grow older and get in higher levels of math, in either school or the workplace. All of these statistics are highly important and they can all give us important information. Such as average age of employees at your company, or the median value of a certain dataset. We then move on to probability. Probability distribut...

   Maca Juto Kasi Scoto Gethido For week 4 in BALT 4363 , I decided to change my focus for this blog. In our reading, we learned about linear algebra for data science. Learning linear algebra allows you to manipulate and organize your data in a more efficient manner. An example of this is using vectors. I have used vectors in RStudio in order to better organize my data. The example used in our reading is by taking two values of a house, the size of the house in square feet and the number of bedrooms. Using a vector would put this as "house = [1500,3]. Understanding this topic is very important, however, I want to shit my focus in this blog to discussing Maca Juto Kasis Scoto Gethido. This is an acronym that starts out with Maca Juto, which is basically just saying that math and coding are just tools. You don't have to have everything memorized, but having the basic principle of it understood is essential. The world is evolving, and using AI is very important, but having a...

  Chapter 3:  Handling and Cleaning Data with Python Libraries This past week in BALT 4363 , I learned about handling and cleaning data with python libraries. This is a very important topic to understand. During this semester, I have learned how to create nice visuals using RStudio and Python. Creating visuals is not highly difficult, the difficulty comes from organizing data to be able to create them. The trickiest part of this is cleaning the data to be able to create better visuals. Pandas Pandas is a library that provides easy, high performance data structures and data analysis tools. It is very useful for handling large datasets by offering flexible data manipulation tools. Inside of pandas, there are two primary data structures: Series and DataFrame. Series is a one dimensional array, DataFrame is a two dimensional data structure. NumPy NumPy (Numerical Python) is a library for Python that adds support for large arrays and matrices, while also having a large collection o...

Chapter 2: Python Data Manipulation In data science, visualizations are seen as one of the most important things to know how to do. This allows for easy ways to analyze data, recognize potential trends, predict where trends are going, etc. While this is very easy to do with data sets that are clean, set up nicely and organized, it can sometimes be very tricky if you have a data set that is not organized in a way that you want it. This is where data manipulation comes in. Using Python data manipulation, you can organize data how you want to read it. Here are some examples of this manipulation: For and While Loops Loops allow you to repeat code. FOR loops are used fore when you want to repeat the code a specific amount of time, and While loops are for when you want to execute code as long as a condition runs as true. Conditional Statements Conditional statements are a very simple form of code that allow you to execute different codes depending on a condition. These are by using IF or i...

  Python libraries are essential for AI development, offering a diverse range of tools and resources. TensorFlow, from Google Brain, stands out as a comprehensive framework for building and training deep learning models, favored for its flexibility and community support. PyTorch, developed by Facebook's AI Research lab, is renowned for its dynamic computational graph, ideal for research and experimentation in deep learning. Beyond these, specialized libraries like scikit-learn for traditional ML tasks and NLTK and spaCy for NLP further enrich Python's AI ecosystem. These libraries collectively empower researchers and developers to create powerful AI solutions across various domains.