Creating an interactive world map of country populations with a couple of sentences. — On July 6th, 2023, OpenAI announced that Code Interpreter will be available to ChatGPT Plus users over the next week. It might be the greatest of all plugins that enhance the power and capabilities of ChatGPT. Code Interpreter runs code and allows for uploading data so you can use it…

Complex tasks completed in a quick and simple way — Third-party libraries are created and developed in response to a need. No one sits down and says “I’m gonna create a tool and wait for circumstances to arise in which others need it”. Instead, they realize a problem and think of a solution to help solve it. That’s how tools…

How to convert raw data into a more usable and structured format. — When learning a new tool, we usually go over the docs, watch tutorials, read articles, and solve examples. This is a good-enough approach and will help you learn the tool to a certain extent. However, when we start using the tool in real-life settings or for solving real issues, we…

From quadratic to linear time with a few small touches. I’ll show you a question that you’re likely to encounter in the live-coding session of an interview. It’s not a difficult one. You can tackle it down if you’re familiar with Python basics and its built-in data structures. However, there…

Use category data type when working with low-cardinality categorical features — Categorical variables can take on a value from a limited number of values, which are usually fixed. Here are some examples of categorical variables: English skill level indicator (A1, A2, B1, B2, C1, C2) Blood type of a person (A, B, AB, 0) Demographic information such as race and gender …

Otherwise you may end up with silent mistakes or harsh consequences — To most of us (or all of us), LLMs are mysterious boxes that get complicated things done surprisingly quickly. We’re usually not interested in the “how” part as long as they give us what we need. ChatGPT, and other LLMs, are surely a productivity booster. They can easily handle a…

Similar yet very different tools, explained — Python’s built-in functions and methods make it a highly versatile programming language that allows for short development times. Amongst the rich selection of functions and methods, there are some similar ones in terms of what they do. But, of course, they’re not the same. …

Let’s see how good and bad it can be — A big part of most data-related jobs is cleaning the data. There is usually no standard way of cleaning data, as it can come in numerous different ways. We encounter inconsistencies, data entry errors, and many other types of issues that need to be handled before the data can be…

Whether you are performing exploratory data analysis or building a complex ML system, you need to make sure the data is cleaned — The web is a highly-valuable asset as a data source. For instance, a substantial amount of training data used to create large language models comes from the web. However, it’s usually not in the most suitable format. Web data is mainly unstructured (i.e. in the form of free text). Even…