Daily news about using open source R for big data analysis, predictive modeling, data science, and visualization since 2008. The City of Melbourne has collected data on the more than 70,000 trees. In the urban forest of this Australian metropolis. The data include the species, the health status of the tree and its life expectancy, all shown on a lovely map. Do trees have genders? Posted by David Smith.

Thoughts on learning about and teaching chemistry, cheminformatics and other miscellaneous junk. Wednesday, January 18, 2012. Apparently there are some people on twitter who are confused. Follow the links for a more detailed explanation.

Ramblings on social science, social networks, statistics, data analysis, computing, game theory and alike. Dear readers, this blog is moving out from wordpress.

Post più letti su questo blog. Come citare un blog su un articolo o una tesi. Diluizione paraformaldeide per fissaggio cellulare. One R tip a day.

Explaining and interpreting predictive models. A couple of years ago, I participated in a workshop on academic data science at SICS. It gives a useful overview of how to think about interpretability in machine learning. Ideas on interpreting machine learning.

Welcome to the MacManes Lab. We explore these links in a wide variety of taxonomic groups including desert mice, rock doves, ladybug beetles, and poison dart frogs using functional and population genomics.

The peaceful collision of computing and data analysis. Dopo circa due anni di utilizzo, posso dire che data. table sia la libreria alla quale non credo si possa rinunciare nello sviluppo di un qualunque script di analisi dati in R. Esistono diversi tutorial in rete. Moltissime discussioni nella relativa help-list. Tante discussioni su Stack Overflow. Quindi il progetto è davvero maturo e molto supportato.

Beautiful plots while simulating loss in two-part procrustes problem. Today I was working on a two-part procrustes problem and wanted to find out why my minimization algorithm sometimes does not converge properly or renders unexpected results. The loss function to be minimized is.