100 Days of ML Code – Day 2

Day 2 of the 100 Days of ML Code journey is about Simple Linear Regression. Linear regression is a class of foundational statistical methods used to model the relationship between a dependent variable and one or more independent variables by fitting a straight line, flat surface (in higher dimensions) or polynomial, etc to the observed data. Using the fitting line/surface it is possible to make predictions about variables not yet available in the given data.

Day 2 Lab Exercise

Day 2 lab introduces Matplotlib, a comprehensive library for creating static, animated, and interactive visualizations. The exercise is about a dataset called „studentscores.csv„. The dataset maps hours to scores. Using Matplotlib the lab exercise results into a nice plot. The lab exercise builds on the libraries, classes and functions from day 1. I am then encouraged to use simple linear regression as provided by scikit-learn. This results into follwing plot:

The red dots mark the data points from the dataset studentscores.csv and the blue line is the graph of a linear function found by linear regression. As in day1 I had to update outdated imports and also in order to get the desired plot I had to add

# show on screen
plt.show()
# save to file
plt.savefig("day2.png")

at the end of the file in order to have the plot either beeing saved to a file or shown on the screen.

Clarifying Artifical Intelligence, Machine Learning and Data Science

I found that the „100 Days of ML Code“-Journey is rather compact and – as the name implies – code centric. I appreciate this, since I am software developer, and also like to code. Also with todays available tools at hand (google, wikipedia, llm’s) it is very possible to get answers to specific questions, that come up during the journey. One question that came up for me was: „What is the relationship between Artificial Intelligence, Machine Learning and Data Science“. Since the time of ancient Greece is over, I didn’t have to embark on the long and arduous journey to the Oracle of Delphi to get answers to my question 😉 Instead, I could open my browser and entered „gemini.google.com„!

„Explain the relationship between data science, machine learning and artificial intelligence.“

The relationship between Artificial Intelligence (AI), Machine Learning (ML), and Data Science (DS) is one of overlapping fields, often visualized as a set of concentric circles or intersecting domains, with data as their common foundation.

🤖 Artificial Intelligence (AI) – The Goal

AI is the broadest concept and the ultimate goal. It refers to a machine’s ability to mimic human intelligence and perform tasks like reasoning, learning, problem-solving, and understanding language.
The objective of AI is to enable machines to act intelligently, whether through simple coded logic (classical AI) or advanced learning techniques.

🧠 Machine Learning (ML) – The Technique

ML is a subset of AI and is one of the most popular modern techniques for achieving AI.
ML focuses on developing algorithms that allow computers to learn patterns and make predictions or decisions directly from data, without being explicitly programmed for every possible outcome. It provides the „learning“ and predictive capability that powers much of today’s AI.

📊 Data Science (DS) – The Process

Data Science is a multidisciplinary field that uses scientific methods, processes, algorithms, and systems to extract knowledge and insights from data in various forms (structured and unstructured).
Data Science uses ML (and deep learning) as powerful tools to build predictive models. The overall process includes everything from data collection, cleaning, and preparation to statistical analysis, visualization, and communicating the results to solve a business or real-world problem.

The Interplay

Think of it this way:

AI is the goal of creating a self-driving car (the ultimate intelligent action).
ML is the technique used to achieve that goal, specifically the part that teaches the car to recognize and predict traffic patterns from sensor data (learning from experience).
Data Science is the entire process of gathering, cleaning, analyzing, and structuring all the data (sensor readings, GPS logs, speed data) that feeds and validates the ML models, ensuring the car’s decisions are accurate and safe.

A good explaination I also found on www.clicdata.com.