At Qxf2, we have always been curious on how to test and validate the datasets and models. A good machine learning team should continuously monitor the model to identify any changes in model performance. You need to be confident that your models are accurate, reliable, and fair. Deepchecks can help you achieve this by providing a comprehensive set of tools […]
Dataset and Model Evaluation using Deepchecks
Data Generation for Text Classification
I set out to evaluate a ML model (emotion classifier) from a human/user perspective. The heart of my attempt was going to be around designing the right set of data to evaluate the performance of the model. Very quickly, I realized that there is more to this task than meets the eye. In this post, I will share several problems […]
Auditing OS level resources with Chef InSpec
Many of Qxf2‘s clients store their Infrastructure as Code. This means that new infrastructure is spun using code and then the application is deployed. So, as testers, we now have to verify that the right infrastructure was spun up and configured correctly. In this post, I will show you how to use Chef InSpec – a tool to write tests […]
Test Lambda before deployment on CI using LocalStack
In my previous posts, I covered how to write tests for Lambdas, run them on LocalStack and addressed the issue I encountered while working on LocalStack. Now, in this post, I will show you how to set up a GitHub Action job to run tests on LocalStack before deploying Lambdas to production. At Qxf2, we place high importance on CI/CD, […]
Using Airflow to start and stop EC2 instances
In this post we will show you how to use Airflow to start and stop EC2 instances. Airflow is a popular open-source platform that engineering teams use to manage workflows. It uses a concept called Directed Acyclic Graphs (DAGs) which lets you chain multiple steps into a workflow. Airflow’s popularity is also partly due to an extensive library of operators. […]
Robustness Testing of Machine Learning Models
In the world of machine learning, assessing a model’s performance under real-world conditions is important to ensure its reliability and robustness. Real-world data is usually not perfect, it may contain messy data or data with noise, outliers, and variations. During model training, these types of data could be limited, and the model may not have received sufficient training to handle […]
Validating Data Made Easy: A Dive into Soda Core
This post is a hands-on example to help you start writing data quality checks with Soda Core. We realize a lot of our readers are fairly new to the topic of writing data quality checks. So, in this post, we will also go over some of the most common data checks you might want to implement on your structured data. […]
Exploring Smart Contract Testing in DApps
At Qxf2, recently we began exploring blockchain technology to understand its potential applications and benefits in various industries. Our journey into testing DApps started with research and self-learning. We immersed ourselves in learning about Ethereum, the leading platform for developing DApps, and its ecosystem of tools and frameworks. Understanding the nuances of Solidity, the programming language for smart contracts, was […]
LocalStack Issue: Security token included in the request is invalid
While I was engaged in creating tests for our URL Filter Lambda at Qxf2, I encountered a problem related to an invalid security token. You can access the code for our URL Filter on GitHub through the following link here. If you encounter an error message stating “The security token included in the request is invalid” while using LocalStack, it […]
Testing Charts with Transformers using Visual Question Answering (VQA)
I tried testing charts using VQA. What that means is that I showed several charts to an AI model and made it answer questions about it. My idea was to use these answers as part of test automation. This post will show you what (sort of) worked for me and what techniques did not work. I hope people use this […]