Your Guide to Quality Data Science Products

In this tutorial I will explain the concept behind the Monte Carlo Tree Search (MCTS) algorithm and tell you about how it was used at the European Space Agency for planning interplanetary flights.

Zipf’s law is an empirical law that states that many different datasets found in nature can be described using Zipf’s distribution.

Filip personal experience from Gartner Data & Analytics Summit London 2019

Useful tips and shortcuts to be more productive while working with RStudio.

Unveiling secrets of black box models is no longer a novelty but a new business requirement.

Useful tips to be more productive while working with R Studio. Part 2.

A diversity of panels at the hottest R event in Europe: Shiny dashboards, R implementations, , machine learning, community! + beer and a tour of Old Town Gdansk!

Our CTO used transfer learning to build an object detection model on a small dataset - the model can recognize certain animals in images.

shiny.info is an open-source package that allows developers to display R Shiny diagnostic information - Here's how to use it!

Data scientists must check if the story behind the data makes sense. This requires business knowledge about the data. It's our responsibility to be curious, to explore and challenge to avoid logical problems in the data to save clients money.

Appsilon Data Science offers R Shiny open source packages that you can use for UI improvements, UI themes, translation, URL routing, and diagnostic display

How to use R in AWS Lambda With AWS Lambda, small and frequent jobs can be done without setting up an instance and keeping it “alive” waiting for requests

A short summary on useR conference in Toulouse, France.

AI will transform the insurance sector. Two techniques that will have the biggest impact are convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The 3rd key to successful AI implementation: productionization

In this article we explore if machines can replace us (R programmers) in writing Shiny code. I'll show you some easy applications of a simple model of a recurrent neural network implemented in an R version of Keras

Learn how to add custom CSS to your Shiny apps and make them visually stunning by using style sheets in your project’s www folder.

SASS gives you variables, conditions, and loops to generate CSS. Learn how to use it with this SASS tutorial in R.

Is R Shiny better than Excel? Explore 8 Shiny alternatives to Excel, both for table data and data visualization.

At Appsilon, we design, develop, and maintain enterprise R Shiny dashboards. These 6 best practices include tips for user adoption, architecture, and testing.

I used a Kaggle database to show how to separate customers into groups based on their purchase behavior.  You can customize your interactions with customers to increase loyalty. For R enthusiasts -- I used ggradar, ggplot2, animation, and factoextra

Learn how to use the session argument as a global list for passing parameters between modules in advanced Shiny apps to simplify the objects’ flow in code., organize app content, simplify objects flow logic, decrease bugs, increase speed

See how an exploratory machine learning approach can inspire new ways to fight climate change and empower global stakeholders.

EARL is the conference that you don't want to miss if you're an R enthusiast or just getting started with R. I've worked on numerous R Shiny projects with Appsilon Data Science Consulting, and I still learn new things each time I go

Three methods for using javascript code in Shiny applications to build faster apps, avoid unnecessary re-rendering, and add components beyond Shiny's limits. Part 2 of a 5 part series on super solutions for Shiny architecture. 

Catch highlights from the WhyR 2019 Conference in Warsaw, covering NLP, geocomputation, spatial analysis, random forests, and more.

Two methods for keeping your Shiny app organized while avoiding hardcoding. Also, a tip for adding multiple languages (internationalization) to your app.

Artificial Intelligence receives a great deal of hype with good reason but is it appropriate for your enterprise? You might want to consider the same tech with a different approach for your decision support system -- Intelligence Augmentation.

For advanced R Shiny applications, R6 classes help you organize your code. The Hows and Whys of using object-oriented programming (OOP) in Shiny applications...

Intelligence Augmentation is concerned with leveraging machines to enhance human intelligence. It’s a partnership between person and machine in which both parties contribute their strengths. It's AI that partners with humans for decision support

Describes the best practices for setting automated test architecture for R Shiny apps. Automate and test early and often with unit tests, user interface tests, and performance tests.

What are the differences between AI and IA? When is Intelligence Augmentation superior to a pure Artificial Intelligence approach? Which solution makes the most sense for your problem set? Consider IA solutions when a limited amount of data exists

To achieve IA implementation success, plan for a partnership between humans and machines, not replacement. Buy-in is crucial, of course. So educate your workforce about IA and plan for hero moments. Automate tasks, not jobs and start small.

I had the honor to meet people who preserve biodiversity and genetic resources at the GenRes Bridge conference in Tuusula, Finland. I represented Appsilon Data Science's Data for Good initiative and shared pathways for incorporating DS and AI.

How to help an organization turn piles of paper into a data lake - Now easier with Optical Character Recognition (OCR).

Explore ways NGOs can use AI for species conservation or find out how AI pros and data scientists can contribute to real-world projects.

Climate change will exacerbate the consequences of natural disasters. Developing countries will be hit the hardest. We helped Dr. Junko Mochizuki build a decision support tool for policymakers in Madagascar to better mitigate this risk.

A recap of satRday Cardiff 2019. New R packages, rstats, education, a hackathon for inclusivity, community, fantasy football, live coding and pizza.

We live in a competitive time, filled with regional and global challenges, both physical and digital, and yet we are empowered with access to ever-growing data sets and tools at our fingertips: cyber-security, NewSpace, asymmetry of information

We need to build a culture where AI is built with a focus on the entire outcome, not just metrics or profit.

The algorithms we build affect lives. We have an ethical obligation not to teach our machines to be prejudiced. Here are some lessons and examples that will help you achieve this in your machine learning model assembly and use.

The city of Poznań wanted to know why it didn't rate highly with tourists. So they gave loads of data to a gathering of developers to gain some insight. TL;DR: we learned a lot from the hackathon & won the thing. R Shiny gave us a slight edge. :)

Learn to create R apps with this R Shiny Dashboard Tutorial! We'll go from simple R Shiny to Bootstrap, Semantic UI, and then cover the custom version.

Building Deep Learning vision models satellite imagery to assist in identifying and labeling property damage from natural disasters.

Why stick to Excel and risk poorly maintained data or serious miscalculations? Discover efficiency gains brought by R Shiny and Python Dash

Many AI projects languish in pilot purgatory. Filip Stachura points out known risks in deploying and maintaining AI models. The question becomes, do you have the right people in place to respond to potential and likely issues?

Appsilon is an RStudio Certified Partner offering R Shiny dashboards, Managed Services, and RStudio product implementations.

"So we sat down with the project manager on the client side, re-ordered the priorities, estimated additional work and were able to start coding on the very same day."

rstudio::conf 2020 is here! Appsilon Data Science is proud to be a co-sponsor of the conference. Here is some information about the presentations we are doing and others that we hope to attend.

We recently took part in Hakuna-ma Data, a competition organised by DrivenData in partnership with Microsoft’s AI for Earth, which asked participants to build an algorithm for wildlife detection that would generalise well across time and locations...

RStudio::conf 2020 is a wrap!

Appsilon engineers Paweł and Pedro share their perspective on rstudio::conf 2020, especially news and updates about R packages...

We'll show you how to import the proper libraries, set up a dashboard, add UI components, and more!

Have you considered adding AI/ML to your organization's operations? AI models can significantly reduce costs when they are implemented properly, but can end up in "purgatory" with the wrong approach. Here's how to properly implement AI models.

Learn how to find and use satellite image datasets for data science and machine learning projects with this beginner-friendly guide.

Can you build Shiny apps without any R knowledge? This R Shiny Dashboard Tutorial shows you my experience with learning R creating R Shiny dashboards in 2 days.

As part of our D4G Initiative and with the support of a Google grant, Appsilon Data Science will be contributing to to the work of biodiversity conservationists at the National Parks Agency in Gabon in collaboration with the University of Stirling.

Artificial Intelligence, Machine Learning, and Deep Learning models have demonstrated significant power to grow and improve businesses. This article explains how to properly approach developing an AI model.

Appsilon’s open source shiny.info package just received a major update and is now available on CRAN. A great solution for development and testing, shiny.info allows for displaying diagnostic information from inside Shiny apps.

This is the first of two blog posts about our recent participation in the Pandemic Response Hackathon. Our project (CoronaRank) was one of only 5 projects out of 230 submissions chosen to present at the closing ceremony.

In this article, we focus on the technical aspects of the machine learning solution we implemented for the xView2 competition. We used PyTorch to build our models for satellite image analysis and fast.ai to develop their critical parts.

Our submission to the Pandemic Response Hackathon (CoronaRank) is inspired by Google’s PageRank and utilizes geolocation data in the Apache Parquet format from Veraset for effective exposure risk assessment using R and Markov Chain modeling.

Introduction to object detection and image classification featuring the YOLO algorithm and its Darknet implementation

Distributed data science teams bring unique challenges. Managers may be looking for new tools. In this article we’ll explain how RStudio Connect helps organizations to properly organize teams and overcome the typical inefficiencies of remote work.

Our favorite RStudio shortcuts, tips, and tricks to increase productivity while working with the RStudio IDE. We cover keyboard shortcuts, custom code snippets, addins, and more.

Dynamic Shiny Modules can destabilize the Shiny environment and cause its reactive graph to be rendered multiple times. Here is how to safely remove deleted module leftovers and make sure that your Shiny graph observers are rendered properly.

R Shiny has historically been used for data-driven applications and as a rapid development tool, but it's a highly adaptable technology. Is it possible to build a functioning video game in R Shiny? Let's find out.

Appsilon created a dashboard in collaboration the International Institute for Applied Systems Analysis to deliver information about COVID-19 to policymakers. We implemented the solution with Python and Svelte.

Appsilon engineers Krystian Igras, Marcin Dubel, and Jędrzej Świeżewski, PhD will be giving virtual presentations on Friday, June 19th. Learn about xspliner, making production-ready R code, and using R for Machine Learning projects. 

In this presentation we present how to make use of the latest technical advancements in computer vision with an R setup even if they are originally implemented in Python.

In this talk you’ll learn tools and best practices for making clean, reproducible R code in a working environment ready to be shared and productionized. We cover the benefits of version control, plumber, RStudio Connect, and many other tools.

xspliner is an R package that helps explain black box ML models. In this presentation, you will learn what PDP curves and GLMs are and how you can calculate them based on black box models. I'll then show you a specific use-case for xspliner.

Appsilon engineer Pedro Silva has been named a Grand Prize Winner in RStudio's 2nd Annual Shiny Contest. He created a fully functional video game using Shiny.

Appsilon Data Science and RStudio will be hosting a joint webinar on Tuesday, July 28th at 11AM EST. The theme is "Enabling Remote Data Science Teams."

Learn best practices for setting up a data science team and kicking off a data analytics project – remote or otherwise. I'll cover Scrum methodology, Asana, GitHub, Docker, renv, linter, and a variety of other tools and workflows.

Recent research on weight poisoning attacks on pre-trained models in the area of NLP may transfer to the context of Computer Vision, where the usage of pre-trained weights is widespread.

This article will show you how to speed up R Shiny by pushing actions to the browser. You will learn how to omit the server bottleneck with updateInput, leverage CSS classes, and take advantage of JavaScript actions for smoother Shiny performance.

Appsilon has created a package to speed up R Shiny by offloading long-running calculations and unfreezing the Shiny UI.

In this video, Appsilon Senior Data Scientist Olga Mierzwa-Sulima explains best practices for data science teams – whether they are working in the office together or fully remote.

PP-YOLO is a machine learning object detection framework based on the YOLO algorithm. In this article, we’ll explain what PP-YOLO is, why it is an improvement over YOLOv4, and show you how to use PP-YOLO for object detection.

Version 0.4.0 of shiny.semantic includes a CSS grid to a well-known R package. Learn how to make a Shiny App with CSS Grid.

Switching from Excel to R Shiny? Learn how to migrate an analytics tool built with Excel and Google Sheets to an interactive Shiny dashboard.

Convolutional neural networks and deep learning don't have to be difficult subjects. Read this article if topics like input and output channels, kernels, strides, and receptive fields feel a bit fuzzy to you.

In this video, Appsilon Engineer Pedro Silva explains the basics of Shiny UI and provides multiple Shiny dashboard examples.

How does R Shiny compare to drag and drop visualization tools like Tableau? Let's compare performance, aesthetics, and ease of use.

Defining custom neural network architectures isn't necessary. Learn how to build a 99% accurate image classifier with Transfer Learning and PyTorch.

In this video, Appsilon Co-Founder Damian Rodziewicz explains best practices for scaling Shiny applications in production to hundreds or even thousands of users.

Learn about best practices and tools for starting your first deep learning image classification project. This article discusses PyTorch, TensorFlow, fastai, ResNet-50, ResNet-101, MobileNet, and several other concepts and tools.

Learn about how shiny.i18n allows you to quickly implement multi-language functionality in Shiny apps and take the user experience to the next level.

How does R Shiny compare to drag and drop visualization tools like PowerBI? Let's compare connectivity, performance, aesthetics, and ease of use.

How do satellites take pictures? Can you process satellite images with R? Also, can you go to Space? Your questions meet our answers.

Vote for the People's Choice Award winner of the 2020 Appsilon shiny.semantic PoContest.

Appsilon team members Jędrzej Świeżewski, PhD and Damian Budelewski will be giving presentations at the Why R? Conference on November 12th.

Appsilon's list of tips for managing a successful kickoff meeting.

Here are the winners of our shiny.semantic PoContest as chosen by the Shiny team at R Studio. There's still time to vote for the People's Choice Award.

Are you a developer or a business professional interested in technology? Appsilon is hiring in multiple departments - from Growth to Tech. We are looking for R Shiny Developers, Front-end Specialists, Infrastructure Engineers, and more.

The R Community has spoken! See who won the People's Choice Award for Appsilon's internal shiny.semantic PoContest.

Exciting news! Appsilon has been listed as a Rising Star in the Deloitte Fast 50 CEE ranking list.

How to use shiny.router to implement routing in Shiny apps, plus some tips on styled navigation bars.

Explore the top 3 business intelligence tools and learn if building data-driven dashboards from scratch is worth the effort.

How can a programmer benefit from using R? Whether you want to create web apps, REST APIs, machine learning models, or visualize data, R has something for you.