Coursera is offering ‘computing for data analysis‘. There’s a high probability that it’ll be worth the five hour a week / 20 hour total investment. Why? It’s a guided, hands-on, experience with R You’ll have a large cohort of fellow explorers The learning curve appears to be fairly graduated And, you’ll learn a lot. *** I’m Christopher Berry.I’m a Data Scientist.I’m at Authintic.
Author: Christopher Berry
Check out this image. Each color group represent 15 trillion in GDP. India and China combined = 15 trillion. Most of Europe = 15 trillion. The United States = 15 trillion. And then there’s the other 30 trillion. The creator lumped Canada, Mexico, Brazil, Russia, South Korea, Japan and Indonesia into a group. Then everybody else into another group. Groupings like this are useful because they’re summaries. They enable really close comparisons. It’s a method doesn’t just have to apply to GDP on maps. You can make comparisons in analysis as well. Saying, for instance, that all the traffic in Inter-Mountain West are equivalent to Chicago, might be a good shorthand. *** I’m Christopher Berry.I’m a Data Scientist.I’m building Authintic
The argument is as follows: There are an infinite number of potential metrics offered up by your standard analytics software. In spite of there being an infinite number of metrics, the actual amount of knowledge or information is limited. The value of a metric should be based on how much it contributes to the understanding of a system. I’ll unpack that. There are an infinite number of potential metrics. Take, pageviews. Take visits. Now divide pageviews by visits and call it ‘pageviews per visit’. Now apply a filter and look at only New Yorkers. You get New York City pageviews per visit. Now run a 31 day exponential moving average on the measure. You’d then get the New York EMA(31)[…]
Have you seen this? Pretty neat. Three points: This is a fun, accessible, relevant experience – and let’s thank the authors for it It is not the best use of layering more than two (2) sources of information “Like People Clump Alike”, “Birds of a Feather Flock Together”, and “Homophily” all mean the same thing; evidence of the phenom can be seen in this experience The authors enable anybody to have a personal experience with information, and to gain their own intuition about the way we are. And that’s great. *** I’m Christopher Berry.I’m a Data Scientist.This is what I’m working.
Andrew Cherwenka and I soft launched our startup, Authintic, last week. Authintic is an analytics technology company enabling permission marketing. Andrew wrote a much more detailed piece for the Huffington Post on the topic. It’s worth a read. He’s very eloquent and accessible. I have nothing contradictory to add. Nothing really controversial to say. Being at the confluence of three mega-trends is where I’m comfortable. The first is privacy in marketing. The FTC and the EU have made their opinions known. There’s this big fear out there that consumers won’t opt-in. Why the fear? Is anybody doing anything wrong? Common’ people – let’s treat people with respect. The second are advancements in machine learning and processing power. There are more[…]
Harvard maintains a pretty awesome worldmap portal. It’s worth checking out. For instance, there’s an awesome series on China here. Information easier to process when it’s in layers. Using a map as the base layer is a great way to see the information. It can be intensely misleading if you don’t know where to zoom. But it’s comfortable. Check it out. It’s a great resource. *** I’m Christopher Berry.Follow me @cjpberryI blog at christopherberry.ca
The National Post had a rather large piece of data journalism yesterday. You can check it out here. Check out the two charts below. Alright – what should pop for you: More Canadians are employed in Health Care than Manufacturing. It’s only 2012. The knowledge economy is growing quickly. That labour mobility between these sectors isn’t nearly as efficient as you might think. There are alarm bells in there. Human bodies are far harder to service than oil extraction. Productivity growth is required, because there won’t be nearly enough people to take care of all those other people. It’s a good piece. *** I’m Christopher Berry.Follow me @cjpberryI blog at christopherberry.ca
“It’s murder on the dancefloor. But you better not kill the groove. Dj, gonna burn this goddamn house right down.” (British Kids will get it.) Owyang wrote on August 26 that it’s 1:50 am on the social software dance floor. Owyang’s summary is excellent and solid. It’s worth reading. It’s worth considering. I’m adding: I don’t know if it’s 1:50am, 12:05am, or 1755 for SMMS. The chart below is on reason why I’m not so sure: I don’t think we’ve even really gotten started. I don’t think we’ve even begun really using social technology to its potential at all. It’s 1755 and we’re unsatisfied with the amount of work that steam does. And meanwhile, old man McCraken is hollering about[…]
A pretty neat visualization from XKCD caught my eye. Check this out. It’s so much chart. Look at the big view. Wow. A few points: It’s a lot of chart. Look familiar? It’s very similar (identical) to the radiation exposure chart. It’s great take on a powers of 10 journey…it can be very hard for us to understand huge scales. *** I’m Christopher Berry.Follow me @cjpberryI blog at christopherberry.ca
This is pretty neat. Neil Fanthom put together this visualization of population pyramids of multiple countries. Demography is destiny. usually. It’s a pretty good implementation and worth checking out. *** I’m Christopher Berry.Follow me @cjpberryI blog at christopherberry.ca