Here is the latest bag of tweets^*, which covers April 2015.

(*) These are interesting news that I found on Twitter and that I archive periodically.

• dloss: Code Maat: command line tool to mine and analyze data from version-control systems. See also the book. https://t.co/COiA6zUINc (26 Apr)
• aflyax: Highly recommend @Udacity’s Intro to #MachineLearning class. Taught with #scikitlearn and #python: https://t.co/RZ99W3ZCWj (26 Apr)
• VikParuchuri: A cooperative machine learning contest that anyone can participate in: https://t.co/yBXiUODKLI #machinelearning #DataScience (25 Apr)
• mmparker: And one for Markov chains: http://t.co/lcq5pIC6rb And several others: http://t.co/DUGlnBxDDT (25 Apr)
• knime: New whitepaper “Seven Techniques for data Dimensionality Reduction” http://t.co/4dQNWSqTVv #statistics #predictiveanalytics #ETL #bigdata (25 Apr)
• DrBunsen: This is a pretty clever web app. Sort of like follow the leader for text transformations: http://t.co/Ado2iNNRQD (25 Apr)
• aria42: F# is fantastic and http://t.co/mIrdZ5qSA4 highlights why it’s a great choice for data engineering. Now we just need full .NET on Mac/Linux (25 Apr)
• carlcarrie: Factor Friday - here is R source code and paper on bounded regression technique to combine alphas #rstats http://t.co/ymcuLzOR1n (24 Apr)
• YhatHQ: Practical Bayesian Optimization of #machinelearning Algorithms (pdf) | http://t.co/X8IoDxAtY9 (24 Apr)
• majmurr: My money is on George Box. http://t.co/xAMGcjTzPd (23 Apr)
• HarlanH: .@Springcoil slides abt getting Python models into production: http://t.co/6Tg1v5aisZ Related to my talk Sat at #rstatsnyc , but funnier. (23 Apr)
• mnijenhuis020: 10 essential Finder tricks every Mac user should know http://t.co/aIAwrKwnKR http://t.co/02ebf23ptK (18 Apr)
• ramnath_vaidya: Interactive Statebins using D3. R package and JS API (alpha) http://t.co/oHiZOOC0Om http://t.co/LxZkt48MXl #d3js #rstats (17 Apr)
• Barkerjas: History of PLS from a master of PLS… http://t.co/iFjpyCFErp (17 Apr)
• revodavid: The new R 3.2.0 update: no big surprises, better performance, big data support and compiler: http://t.co/oJC88hZnkI (17 Apr)
• matt_blackwell: Want to estimate joint effects in experiments w/ >1 treatment? You might be interested in my new paper on iV: http://t.co/PWBI0opWYY (17 Apr)
• RLangTip: Use ggplot2 ‘Themes’ to draw your #rstats charts in the style of publications like “The Economist”: http://t.co/ChgU6DYxqK #rstats (17 Apr)
• KirkDBorne: Visualising data structures & algorithms thru animation: http://t.co/vLT6QlHTMs #BigData #DataScience #DataViz http://t.co/pEcRIaI1gy (16 Apr)
• bayesian_stats: Notes for course on Statistical Data Mining and Machine Learning http://t.co/dHz38wLplN by @sejDino – via B… http://t.co/Aca0O102My (16 Apr)
• danmaclean: Apple’s research kit on GitHub. Way cool. http://t.co/MD2dqb0Gk8 (16 Apr)
• Postgresapp: New Mac PostgreSQL client http://t.co/Om7x48sJWu @SQLitePro (16 Apr)
• BestGit: Very nice article: The secret to great commit messages. http://t.co/k1JW1RdYsz #allDev #coding #git via @lencioni (16 Apr)
• DrBunsen: Extracting Structured Data From Recipes Using Conditional Random Fields: http://t.co/tyI1mGkh1c (16 Apr)
• hadleywickham: Get your data out of excel and into #rstats with readxl: http://t.co/Oi0dHhPPQ5. Now on CRAN :) (15 Apr)
• PatSchloss: I really liked this review/tutorial on speeding up code and the associated R package http://t.co/HzpKocIr9D #rstats (13 Apr)
• RyanMDK: @hadleywickham Big-ish Data Workflow in R http://t.co/L8iKZF9cbg . Replicated @plotlygraphs article in R. (13 Apr)
• renkun_ken: #formattable with glyphicons http://t.co/DEgzj5Q3oM and bar! gist: https://t.co/MqcIxnBYkG http://t.co/3BdBZ8nTij http://t.co/qRWF2Hv0pP (13 Apr)
• enthought: Teaching with the IPython Notebook http://t.co/CxZF5oCSp9 via @ThomasArildsen (13 Apr)
• mharrison: Pstatsviewer. Explore profiling output in your notebook < https://t.co/gEwgFeZl7w (12 Apr)
• msgbi: statisticians-have-a-biased-view-on-data-science http://t.co/106cmeIuUh (11 Apr)
• mja: Structural equation modelling package for pedigree data. Now we can do the kind of cool modelling done with twins. http://t.co/Hn8BFgVBH0 (11 Apr)
• Atabey_Kaygun: Rate-limiting anonymous accounts https://t.co/aZWphYChiW (11 Apr)
• freakonometrics: [free ebook] “Principles of Distributed Computing” http://t.co/DWe5onJPOh by Roger Wattenhofer (11 Apr)
• andrew_cooke: http://t.co/OtwwczLzOE Oblique Strategies in bash (11 Apr)
• DrBunsen: The history of Joy Divisions’s iconic data viz: http://t.co/gwPogTIS3i (11 Apr)
• ogrisel: @arnicas @fmailhot @JoelKuiper you can do great RNN demos on MNIST https://t.co/rzzVY1NaHz :) (10 Apr)
• justmarkham: Solution code (scikit-learn) from my winning submission to @kaggle competition at #PyCon2015: https://t.co/YjYDq8mn2S http://t.co/zO54LSJ5Cf (10 Apr)
• YhatHQ: Tutorial: Data Science with #python | #datascience | http://t.co/2NQHTIVZ39 (10 Apr)
• YhatHQ: #Python Sparse Random Projections| ŷhat | http://t.co/hcC9TM2nzA (10 Apr)
• WolframResearch: How Stephen Wolfram is expanding the frontiers of computational thinking with the WL: http://t.co/AKYbggdbTv http://t.co/X8SlrwXcVZ (10 Apr)
• blattnerma: #MachineLearning https://t.co/mpV1KMTB1q (10 Apr)
• cournape: @yhathq @erchiang I like David McKay book, very insightful http://t.co/bu6swrtdE0 (10 Apr)
• DrBunsen: Awesome Courses—list of awesome university courses for learning math, CS, and scientific computing: https://t.co/JiV0OoF7cT (10 Apr)
• huitseeker: “Scikit-Learn : the Vision” @GaelVaroquaux ’s Keynote at #PyData2015 <https://t.co/Gn2GgWBlmJ – great general engineering insights tow. end (10 Apr)
• YhatHQ: Extracting Structured Data From Recipes Using Conditional Random Fields | http://t.co/Fn0h5zXKHq | http://t.co/j64tJi294W (9 apr)
• YhatHQ: 100 numpy exercises | #python | http://t.co/YfkJqE6Ivw (9 Apr)
• YhatHQ: The Statistical Crisis in Science - why many statistically significant comparisons don’t hold up | http://t.co/uCGInGzgv5 (9 Apr)
• darrenjw: #Scala for Machine Learning [book review] http://t.co/hlHM5MXOzu (9 Apr)
• jacob414: A few basic but useful #python dictionary techniques http://t.co/al2HN4Wsb4 (8 Apr)
• recology_: Run SQL directly on CSV or TSV files https://t.co/vDQ14p9DEA (7 Apr)
• fullstackpython: Really good read on “Learning #Python the methodical way” by @RealPython https://t.co/9qgOXmCE3F (7 Apr)
• fonnesbeck: Create, edit and display a journal article, entirely in GitHub. https://t.co/ftn0MiXRoI (7 Apr)
• DrBunsen: @nathangrigg Yes. You might be interesting in this SO post that @jrmontag directed me to. There are some real gems! http://t.co/356R9capNy (7 Apr)
• DrBunsen: Great list—10 things statistics taught us about data analysis: http://t.co/9gNXA9KUg4 (7 Apr)
• stephensenn: nothing that was a consequence of increased temperatures counts as additional evidence of why the increase happens http://t.co/3Lvb8bbrhF (7 Apr)
• ben_fry: That article was also making me wistful for THINK Pascal https://t.co/XtpEfZxYqy a wonderful old Mac environment http://t.co/Dnfa8VyV7n (7 Apr)
• ben_fry: “Computing science education: the road not taken” a talk from Pascal’s creator, Nicklaus Wirth http://t.co/ilM1Zu3Nh5 http://t.co/oGQWMVA4HY (7 Apr)
• DrBunsen: Awesome Public Datasets: https://t.co/KthpdOcwfl (7 Apr)
• mja: Matching population genetic models to epidemiological evidence of autism. http://t.co/E8oeJHrd8a (7 Apr)
• masnick: I’ve been collecting some links related to reproducible research: https://t.co/pVS0Nyb9EP #OpenScience (6 Apr)
• OpenCPU: Efficient linked list (ordered set) in R http://t.co/E8DiqoBXA5 (5 Apr)
• gappy3000: @TomAugspurger @treycausey could be of interest: https://t.co/gHXeZybICH (5 Apr)
• abresler: By far best #rstats tutorial on the #NetworkGraph by @lincolnmullen, great examples & uses magrittr/dplyr!! http://t.co/cqcL958ENa (5 Apr)
• VenkatKaniti: @alignedleft Hello Scott, my review on your D3 video course http://t.co/dymlOf5yjq (5 Apr)
• BenSadeghi: Don’t enforce R as a standard http://t.co/7VJRT7QBPa #JuliaLang (5 Apr)
• david_colquhoun: Important reanalysis of the “cancer is mostly luck” data http://t.co/6wWrQ1DGdi Preprint in arXiv http://t.co/O5SPnLvqJQ HT @ChrisFahlman (5 Apr)
• abmathewks: http://t.co/qfOH0YHssy - Using Graphviz to generate automated system diagrams (5 Apr)
• genetics_blog: Stop using tail -f (mostly) http://t.co/TXf06k12kO (4 Apr)
• gregorypark: caretEnsemble: R package for ensembling predictive models from caret. Nice intro: http://t.co/nX1c3JCy9j #rstats (4 Apr)
• agramfort: Slides on my @PydataParis talk on using linear models with @scikit_learn https://t.co/F2YLBOolIp #pydata #python #machinelearning (4 Apr)
• YhatHQ: Python/Neo4j: Finding interesting computer sciency people to follow on Twitter | #python Mark Needham | http://t.co/8PMgjBJJrg (3 Apr)
• webbedfeet: Wrapper functions for converting files in #pydata http://t.co/fZ0KKPkp71 #datadc (3 Apr)
• zevross: A nice 5-part tutorial on using #python to collect, process and visualize data from an API | http://t.co/HQZzBthBrF, by @marcobonzanini (3 Apr)
• YhatHQ: Is Parallel Programming Hard, And, If So, What Can You Do About It? (pdf) | http://t.co/rVr7e9NinR (3 Apr)
• BenSadeghi: Eigenvectors and Eigenvalues, explained visually http://t.co/vwQfpfBemz (3 Apr)
• paulusj8: Great #rstats package for making pivot tables: https://t.co/3InRZgG9Kh (2 Apr)
• bbatsov: Magit 1.4 is out https://t.co/bqarciapGb (1 Apr)
• arnicas: @timelyportfolio fyi RT @Rbloggers: an example of drawing beast tree using ggtree http://t.co/Xoxpgs9IUT #rstats (1 Apr)
• JennyBryan: @adolfoalvarez some people are working on that https://t.co/Lyh1fZVtj6 @rOpenSci (1 Apr)
• robjhyndman: A new open source data set for anomaly detection http://t.co/4N2TJAXE5e (1 Apr)
• OpenCPU: Found that closures in R are much faster than I thought: https://t.co/j7w9sXVoLF Thanks to @winston_chang (1 Apr)