What is Kaggle, and how can I use it as a beginner data scientist?
In this article, we will consider Kaggle as a platform for beginner Data Scientists. How to get started with it?
Why Kaggle? A beginner data scientist needs practice, and Kaggle solves this problem very well. Let me explain this further.
This article is part of a series where we walk step by step through solving fintech problems with different Machine Learning techniques using the “All lending club loan” dataset. Here you can find the complete end-to-end data science project for beginners to learn data science.
Kaggle is a platform that offers a no-setup, customisable, Jupyter Notebooks environment. It is easy to start even for complete beginners, requires no installation and is easy to access from anywhere at any time.
Kaggle is popular among data scientists and machine learning engineers. It has a huge amount of public datasets, and shared notebooks. But Kaggle is not a learning platform, it is a great platform to practice your knowledge and participate in competitions available there. It is the perfect place to Learn by Doing!
Kaggle is used by beginners and experienced data scientists from all over the world. There is a user rating — you can earn points for solving or discussing data or machine learning problems, and by publishing your code and new datasets. When hiring, sometimes many companies pay attention to the position of the applicant in the Kaggle ranking.
Kaggle could help you master the basic principles of Data Science.
You could find a lot of useful courses in the Kaggle learn section like Python, Intro to Machine Learning, Data Visualization, Data Cleaning and so on. These courses will not explain the mathematics behind machine learning algorithms but will teach you the principles needed for a data scientist. This will help save time that is usually spent on studying materials.
As a beginner data scientist, you could start exploring datasets available on Kaggle, there are more than 50,000 of them available by now. Or you could start building your first prediction model or participate in a competition. You should give it a try, and this is how.
To start using Kaggle, you need to register here. You will have two options: register with a Google account or with an email address, after registration you will receive a confirmation by mail, log in — and done, you are now part of the Kaggle community!
Kaggle has a Progression System. Once you sign up, your account will be at the lowest level: Novice. There are five performance tiers that can be achieved in accordance with the quality and quantity of work you produce: Novice, Contributor, Expert, Master and Grandmaster.
The Kaggle Progression System is created for different categories of data science expertise: Competitions, Notebooks, Datasets, and Discussion and it is done independently within each category.
For example, you could be a Competitions Master, a Datasets Expert, a Notebooks Grandmaster, and a Discussion Expert:
Instead of looking for tasks according to the studied theory, you can start working on a real project and be in the process of “getting” the necessary practical knowledge. This makes learning Data Science more fun and more productive.
An online editor on Kaggle allows you to create a Jupyter Notebook or a simple Python and R script. You simply plug in the dataset and work in the browser without having to install libraries or dependencies on your local machine.
Once you select the chosen dataset — it is time to explore and learn from experienced people. You could find notebooks from the same dataset with all the code snippets, as well as user ratings that will help you to choose the best examples to learn from.
To create your first notebook, first, choose the dataset you are interested in, click on the 3 dots button, then “create new notebook”.
Yet, before writing your first rows of code, why not see what others have done with this dataset? This can facilitate your analysis! For example, on the screenshot below you could find the dataset “Supermarket store branches sales analysis” has 53 notebooks which are available to explore!
From community notebooks, you can learn a lot, and spend some time exploring the community to understand what analyses other data scientists perform. Try to understand the logic of written code by understanding and re-executing line by line to practice or reuse these experiences in your other projects.
While you are exploring and learning from other experienced data scientists you will have a good improvement in the quality of the model/solution you are building!
Want to learn more? Here is the complete end-to-end data science project for beginners to learn data science. By completing this project: 1) you will experience the entire data science cycle yourself, 2) you will develop a project that you can use to prove your experience, and 3) you will answer the most popular interview questions in case you decide to pursue the career of a data scientist.
What do you struggle with in your early journey? Please share it with me here, and I am happy to help! I listen to your stories carefully and want to produce content that helps you in this journey. For more content like this, sign up for my newsletter.
