Category: Data Vizualisation

Feed: R-bloggers. Author: Laura Swales. At this years’ online version of the Enterprise Applications of R Language Conference, we have four workshops fo you to join.Tickets for half-day workshops are £90 and all profits will be donated to Data for Black Lives.Hosted by Mango’s Nick Howlett and Joe Russell, you will discover the principles required to create powerful visualisations and understand how and why, they effectively and accurately communicate the stories inside data.Using the powerful and expressive {ggplot2} package, you will learn how to apply these principles while exploring the common pitfalls to avoid when creating your own visualisations.Many companies ... Read More

Feed: R-bloggers. Author: free range statistics - R. Caution / who should read this – although this blog post uses some data on reporting times for Covid-19 deaths in Florida, it’s not really about that issue at all. It’s a quick dip into how to model data that comes from a mixture of two or more different probability distributions.Mixture distributionsI have thoughts about mixture distributions. Sometimes we get data that could be modelled simply with classical techniques if we make assumptions about its distribution which are mostly right. But the distribution is ‘contaminated’ with another distribution. Very small departures from ... Read More

Feed: AWS Big Data Blog. This is a guest post by Steven Collings, Senior Data Consultant at ZooplaZoopla is a property website that enables users to find residential or commercial property to buy or rent in the UK and overseas. Since acquiring Property Software Group and Expert Agent, we also offer a backend software that agents can use to build their businesses. Amidst the growth and acquisitions, we needed a way to bring together data from disparate systems to drive key performance indicators (KPIs) for all the Salesforce and NetSuite data we store in Amazon Redshift. Building a flexible and ... Read More

Feed: R-bloggers. Author: A Blog on Data Analytics. Problem!ML algorithms, although their proclaimed effectiveness on predictive accuracy might be suspect, are often the first tool that a data scientist resorts to when tackling a prediction problem. Such an attitude is not the best in my opinion, and I generally favour a statistical/probabilistic model over a black box. Nevertheless, there are situations when one is asked (read: told) to use the latter.Solution?Then, typically xgboost is an ML model resorted to quite often, due to its good performance straight out-of-the-box. Once such a model has been trained and tested, the analyst is ... Read More

Feed: What's New. Author: Andrew Grinaker. “Together, we are extraordinary”: This is the guiding principle of the Tableau Community. What makes our community so special is its diverse members, and the rich and varied perspectives they contribute. The Tableau Community is a place where passionate data people of all backgrounds can come together and learn from each other. Data visualization is a process of discovery, and a powerful tool for understanding different perspectives and communicating across contexts, geographies, and experiences. We are committed to ensuring that our community reflects, prioritizes, and elevates the diversity of its members. Recently, Tableau CEO ... Read More

Feed: R-bloggers. Author: A Blog on Data Analytics. BackgroundBack in June, Julia Silge analysed the uncanny X-men comic book series. If, perchance, you are not familiar with her work, check out her blog and Youtube screencasts – invaluable resources for when I want to learn about any new tidyverse packages!In her analyses of X-men comic series data from #tidytuesday, she proceeded to generate bootstrap confidence intervals for parameters of a logistic regression model. This is a very convenient way to show the variability in model parameters, but there is another package around — ggdist — that allows estimating and visualising ... Read More

Feed: R-bloggers. Author: Roel M. Hogervorst. So you want to compete in a kaggle competition with R and you want to usetidymodels. In this howto I show how you can use CatBoost with tidymodels. I give very terse descriptionsof what the steps do, because I believe you read this post for implementation, not background on how the elements work. This tutorial is extremely similar to my previous post about using lightGBM with Tidymodels.Why tidymodels? It is a unified machine learning framework that uses sanedefaults, keeps model definitions andimplementation separate and allows youto easily swap models or change parts of the ... Read More

Feed: R-bloggers. Author: free range statistics - R. For a few weeks now I’ve been publishing estimates of the time-varying effective reproduction number for Covid-19 in Victoria (and as bonuses, NSW and Australia as a whole). Reproduction number is the average number of people each infected person infects in turn. My modelling includes nowcasts up to “today” of that number (and forecasts for another 14 days ahead), a risky enterprise because the evidence of today’s number of infections is obviously only going to turn up in 7-14 days time, after incubation, presentation, testing and making its way onto the official ... Read More

Feed: R-bloggers. Author: Roel M. Hogervorst. So you want to compete in a kaggle competition with R and you want to usetidymodels. In this howto I show how you can use lightgbm (LGBM) with tidymodels. I give very terse descriptionsof what the steps do, because I believe you read this post for implementation, not background on how the elements work.Why tidymodels? It is a unified machine learning framework that uses sanedefaults, keeps model definitions andimplementation separate and allows youto easily swap models or change parts of the processing.In this howto I signify r packages by using the {packagename} convention, f.e.: ... Read More

Feed: R-bloggers. Author: R Views. [This article was first published on R Views, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.One hundred sixty-one new packages made it to CRAN in July. Here are my “Top 40” picks in seven categories: Computational Methods, Data, Genomics, Machine Learning, Science, Statistics, and Utilities.Computational Methodslibgeos v3.8-1-3: Implements API access the Open Source Geometry Engine GEOS which can be used to write high-performance C and C++ geometry operations. Look ... Read More