Python is an easy language to pick up, but mastering it requires understanding a lot of concepts.

In my last post, I talked about using a multiprocessing module to do parallel processing. Python also offers users the power to work with concurrency using the Asyncio module from version 3.4 forward.

For people who come from a JavaScript background, this concept might not be new, but for people coming from Python 2.7 (yes, that’s me), Asyncio may prove to be hard to understand, as does the difference between concurrency and parallelism. …

Finally, my program is running! Should I go and get a coffee?

We data scientists have got powerful laptops. Laptops which have quad-core or octa-core processors and Turbo Boost technology. We routinely work with servers with even more cores and computing power. But do we really use the raw power we have at hand?

Instead of taking advantage of our resources, too often we sit around and wait for time-consuming processes to finish. Sometimes we wait for hours, even when urgent deliverables are approaching the deadline. Can we somehow do better?

In this post, I will explain how to use…

In one of my previous posts, I talked about how to become a data Scientist using some awesome resources from Coursera. This post is still one of the posts I ask my readers to read on as this defines the actual rigorous curriculum a data scientist should go through in order to succeed.

But just recently I came to know from Coursera that they have floated few of there courses for learners in India in these trying times for free and I couldn’t stop myself to rave about them in this post.

So what’s stopping you now?

1. Code Yourself! An Introduction to Programming

This course is…

In my last post on BERT, I talked in quite a detail about BERT transformers and how they work on a basic level. I went through the BERT Architecture, training data and training tasks.

But, as I like to say, we don’t really understand something before we implement it ourselves. So, in this post, we will implement a Question Answering Neural Network using BERT and HuggingFace Library.

What is a Question Answering Task?

In this task, we are given a question and a paragraph in which the answer lies to our BERT Architecture and the objective is to determine the start and end span for the…

Algorithms Interviews

Algorithms are an integral part of data science. While most of us data scientists don’t take a proper algorithms course while studying, they are important all the same. Many companies ask data structures and algorithms as part of their interview process for hiring data scientists.

Now the question that many people ask here is what is the use of asking a data scientist such questions. The way I like to describe it is that a data structure question may be thought of as a coding aptitude test.

We all have given aptitude tests at various stages of our life, and…

In my last series of posts on Transformers, I talked about how a transformer works and how to implement one yourself for a translation task.

In this post, I will go a step further and try to explain BERT, one of the most popular NLP models that utilize a Transformer at its core and which achieved State of the Art performance on many NLP tasks including Classification, Question Answering, and NER Tagging when it was first introduced.

Specifically, unlike other posts on the same topic, I will try to go through the highly influential BERT paper — Pre-training of Deep…

In my last post, I talked about Object-Oriented Programming(OOP). And I specifically talked about a single magic method __init__ which is also called as a constructor method in the OOP terminology.

The magic part of __init__ is that it gets called whenever an object is created automatically. But it is not the only one in any sense. Python provides us with many other magic methods that we end up using without even knowing about them. Ever used len(), print() or the [] operator on a list? You have been using dunder methods.

In this post, I would talk about five…

ROC curves, or receiver operating characteristic curves, are one of the most common evaluation metrics for checking a classification model’s performance. Unfortunately, many data scientists often just end up seeing the ROC curves and then quoting an AUC (short for the area under the ROC curve) value without really understanding what the AUC value means and how they can use them more effectively.

Other times, they don’t understand the various problems that ROC curves solve and the multiple properties of AUC like threshold invariance and scale invariance, which necessarily means that the AUC metric doesn’t depend on the chosen threshold…