How to Get Started with Data Science

Technologists and business analysts alike have been quoted as saying that data will be the lifeblood of the 21st century’s economy much like petroleum was for the 20th. At first, it may sound like a gross exaggeration but when you start considering how the world’s biggest corporations use data in pretty much every facet of their operations, the idea starts to sound less and less farfetched.

Apple, Amazon, Tesla, Microsoft, and ExxonMobil all pride themselves on using data to guide their every move. They prove it by being tenacious in the way they gather it and meticulous in how they process it. They are fiercely protective of their digital information – in many cases, more so than they would be with hard cash. As such, it’s easy to see why people who handle and process data are of paramount importance to an ever-growing number of businesses. Data scientists are highly influential in how businesses, economies and even governments are run.

Having said that, it’s not hard to see why data scientist, data analyst and machine learning expert are some of today’s hottest job titles. People in this field are highly sought after and they’re paid very well to do what they do. If you’re considering a career in data science but you aren’t quite sure where to begging, you’ve come to the right place. In this post, we’ll tackle what it takes to become a data scientist and what you need to learn to get started as one.

Qualities and Aptitudes of a Good Data Scientist

Embarking on a data science path isn’t just about crunching numbers or coding; most people of average intellect can do that. People who go on to become highly effective data scientists possess some innate aptitudes and attributes that make them better at this job than the rest of the pack.

Over the past 15 years, I’ve seen people enter and leave the world of data analytics. The ones who’ve lasted and succeeded often had most – if not all – of these qualities:

  • Natural Curiosity: The best data scientists have a relentless urge to understand and question. They’re the ones who look at a dataset and wonder, “What’s the story here?” This curiosity drives them to explore data deeper, unraveling insights that others might miss.
  • Problem-Solving Prowess: At its core, data science is about solving complex puzzles. It’s not just logical thinking; it’s about approaching problems with creativity and an innovative mindset. Whether it’s optimizing a process or forecasting trends, the ability to think outside the box is key.
  • A Strong Grip on Statistics: Having a solid footing in statistics is non-negotiable. It’s not just about loving numbers; it’s about understanding how statistical methods unlock the meaning behind data. This skill is vital for setting up experiments, making predictions, and verifying results.
  • Mathematical Foundation. You don’t need to be a math prodigy, but a good foundation in mathematics goes a long way. It helps in understanding the mechanics behind algorithms and statistical models.
  • Data science often involves a lot of trial and error. The ability to keep going, even when solutions aren’t immediately apparent, is a valuable trait. It’s about tackling complex challenges head-on and not getting discouraged by setbacks.
  • Attention to Detail. In data science, the devil is often in the details. Small data errors can lead to big mistakes, so being meticulous and precise is crucial. It’s about ensuring that every piece of analysis is accurate and reliable.
  • Clear Communication. Being able to translate technical findings into plain language is an art. Good data scientists can tell a compelling story with data, making complex results understandable to everyone.
  • Adaptability and Eagerness to Learn. Data science is a field that’s constantly evolving. Keeping up means being open to learning new techniques, tools, and staying on top of industry trends.

If these qualities resonate with you, or if you’re keen on developing them, then data science might just be your calling. It’s a field that’s not only intellectually stimulating but also opens up a world of opportunities to make a real impact with data.

Background Knowledge for Aspiring Data Scientists

Before diving into the deep end of data science, it’s important to shore up your foundational knowledge. This preparation sets the stage for a smoother learning curve and a more profound understanding of advanced concepts down the line. Here are some key areas of knowledge that are essential for anyone starting out in data science:

  • Basic Python. Python is the lingua franca of data science. It’s a versatile programming language favored for its readability and the extensive libraries specifically designed for data analysis (like Pandas, NumPy, and SciPy). Familiarity with Python’s basic syntax, data structures, and common libraries will provide a solid foundation for more complex data science tasks.
  • Basic Statistics. Data science and statistics go hand in hand. A basic understanding of statistical concepts like mean, median, mode, standard deviation, and distributions is crucial. These concepts form the backbone of data exploration, hypothesis testing, and the interpretation of data-driven insights.
  • Basic Algebra. Algebra is the mathematical toolkit for dealing with equations and understanding relationships between variables. In data science, algebraic concepts, especially linear algebra, are central to building and understanding algorithms and machine learning models.
  • Basic Business Concepts. Data science isn’t just about crunching numbers; it’s about solving real-world business problems. Basic knowledge of business principles, like how businesses operate, what drives profit, and an understanding of different industry sectors, can greatly enhance the relevance and impact of your data science projects.
  • Data Visualization. The ability to present data visually (using tools like Matplotlib, Seaborn, or Tableau) is key. Effective data visualization aids in communicating findings and telling stories with data.
  • Programming Logic and Algorithms. Beyond specific programming languages, understanding the logic behind programming and basic algorithmic thinking helps in problem-solving and developing efficient code.

Starting with these foundational areas, you can build the confidence and skills needed to delve deeper into the more complex aspects of data science. Remember, the journey into data science is as much about building on these basics as it is about exploring new frontiers in data.

The Tools of the Data Science Trade


Learning data science doesn’t involve too many tools that you need to shell out money for. As a matter of fact, you can have most of them for free. Here’s what you’ll be needing to get started and what each one is for:

  • Jupyter Notebook. This open-source web application is a favorite among data scientists for a good reason. Jupyter Notebooks allow you to create and share documents that contain live code, equations, visualizations, and narrative text. It’s an invaluable tool for exploratory data analysis, data cleaning, statistical modeling, and visualization. Its interactive environment makes it perfect for trying out code, seeing the results, and iterating quickly. Simply download the Anaconda platform, install it on your PC or Mac and launch it. In the navigator, you’ll find Jupyter Notebook and you’ll be set to go.
  • Google Colab. Think of Google Colab as Jupyter Notebook’s cloud-based alternative much like Google Docs is for Microsoft Word. It offers a similar interface but with the added benefits of free access to GPUs and TPUs (Tensor Processing Units), making it an excellent platform for machine learning projects. Colab’s seamless integration with Google Drive and other Google services enhances its appeal, especially for collaborative projects. Like Jupyter Notebook, it’s free to use. Its edge over Jupyter Notebook is the fact that it runs on Google’s cloud, meaning Google does all the computing for you remotely rather than on your own hardware. This platform is a great choice for people with low-end machines that struggle with more advanced data science projects.
  • Microsoft Excel Yes, good old Excel still holds its ground in the data science toolkit. In this field, you’ll be handling CSV files all the time and what better application to use in opening and editing them than the one we’ve all grown accustomed to during the past 30 years?
  • ChatGPT. As an aspiring data scientist, keeping up with the latest advancements is crucial, and ChatGPT, developed by OpenAI, is one of those innovations. It’s an AI-driven tool that can help you understand complex concepts, code snippets, or even debug your code. While it’s not a push button solution to your every data science problem, it does help a great deal when you have a tool that can help you formulate problem solving strategies and tell you what’s wrong when a block of code refuses to run as intended.
  • A Decent Computer. If you choose to use Anaconda/Jupyter Notebook rather than Colab, you may want to do so on decent hardware. Processing and manipulating large volumes of data can take a lot of computing power to execute, and the beefier your machine is, the less time you’ll spend waiting for processes to finish.

For PC users, a rig with at least a Core i5 or its AMD equivalent is the baseline. As far as RAM goes, 8GB is fine for light operations but 16GB or better is recommended. For Mac users, the current ARM-based CPUs are a godsend. These chips are excellent at running advanced algorithms on large datasets. RAM is fine at 8GB, but more is always better.

Each of these tools has its unique strengths and will serve you differently at various stages of your data science journey. Jupyter Notebook and Google Colab are essential for hands-on coding and advanced analysis, while Excel is great for basic data manipulation and visualization. ChatGPT, meanwhile, can provide supplemental learning support. Familiarizing yourself with these tools will not only enhance your skill set but also significantly boost your efficiency and effectiveness in solving data-driven problems.

Foundational Knowledge for Aspiring Data Scientists

Much like any other body of knowledge, data science is built on several pillars that will serve as your foundations for more advanced skills as you go along. If you’ve made up your mind and you’ve decided to go down this path, here’s what you can expect to learn in your immediate future:

  • Basic Python. In your first foray, you’ll get hands-on with Python’s syntax and its foundational concepts like loops and conditionals. Plus, you’ll get a taste of powerful libraries like Pandas for data wrangling, Matplotlib for making your data visually appealing, and Scikit for Machine Learning.
  • Business Statistics. Here’s where numbers start to make more sense. You’ll learn how to take a heap of data and find the story it tells. This includes mastering the art of descriptive statistics, probability, and hypothesis testing – tools that turn raw numbers into business insights.
  • Supervised Learning. Picture yourself teaching a machine the way you’d teach a kid – with clear examples. That’s what supervised learning is about. You’ll delve into regression techniques for predicting values like sales figures and classification methods for sorting data into categories, like identifying spam emails.
  • Unsupervised Learning. This is where the training wheels come off. In unsupervised learning, you’ll tackle unlabeled data and learn to find patterns and structures on your own. It’s about uncovering hidden groupings in data, like clustering similar customer profiles, without explicit guidance.
  • Ensemble Techniques. Think of this as the ‘teamwork makes the dream work’ approach in data science. You’ll learn how combining different models can give you better results than any single model. It’s like assembling a supergroup of models, each bringing its strength to the table.
  • Model Tuning. Even the best models can be improved. This is where you’ll learn to tweak and tune your machine learning models to perfection. Using techniques like cross-validation and grid search, you’ll fine-tune your models to strike the right balance between complexity and accuracy.

As you embark on this learning journey, each of these areas will open up new horizons in data science for you. They’re your first steps towards building a versatile and robust toolkit that will empower you to tackle real-world data challenges with confidence.

Let the Journey Begin!

Overall, data science is an exciting field with many challenges and even more rewards. While it’s not necessarily for everyone, it offers an exciting career path for those who have the desire and ability to get into it. In the next posts, we’ll start with lessons in earnest to help you get started with analytics, machine learning and other data science concepts.

About Glen Dimaandal

Glen Dimaandal
Glen Dimaandal is a data scientist from the Philippines. He has a post-graduate degree in Data Science and Business Analytics from the prestigious McCombs School of Business in the University of Texas, Austin. He has nearly 20 years of experience in the field as he worked with major brands from the US, UK, Australia and the Asia-Pacific. Glen is also the CEO of SearchWorks.PH, the Philippines’ most respected SEO agency.
Glen Dimaandal
Glen Dimaandal is a data scientist from the Philippines. He has a post-graduate degree in Data Science and Business Analytics from the prestigious McCombs School of Business in the University of Texas, Austin. He has nearly 20 years of experience in the field as he worked with major brands from the US, UK, Australia and the Asia-Pacific. Glen is also the CEO of SearchWorks.PH, the Philippines’ most respected SEO agency.

Check our latest news

In our last post on Python programming for data science, we discussed the list data structure…

In the previous entry, we touched upon commonly occurring distributions: Bernoulli distribution, binomial distribution, uniform distribution,…

In our last coding post, we discussed the concept of data structures in Python and the…

Ready to get started?

Reveal the untapped potential of your data. Start your journey towards data-driven decision making with Griffith Data Innovations today.