Wednesday, April 10, 2013

Week 1 - Summarizing Data

As I mentioned in my last post the class I'm taking is through Coursera and the University of Toronto. Statistics: Making Sense of Data Disclaimer: These posts will attempt to document my journey as I'm thinking it. I will likely not stop to edit for readability. I'm taking this class along with 45,000 other people. Mind boggling when you stop to think about it. Yeah, there's another interesting post there but I want to focus on my actual journey. What got me interested in documenting this journey was my first half an hour with R. If you're not familiar with the tool, it's a free software programming language for statistical computing and graphics. This course is using it implement their course content. The first lecture was Five Number Summary (min, max, median, first quartile and third quartile). After the lecture, I went to the R tutorial and I realized something. The tutorial isn't going to teach me R. The point of the class is to teach me statistics. R is just the tool they use to implement the concepts. But for some reason, I became totally obsessed with the fact that I'll end up being an R jockey. Now that I've reflected on a bit, I realize that's silly, but it was that fact that caused me to want to document this journey. So here we go...my journey from Data Science Groupie, to a small role in the band. Five-Number Summary in R with two attributes is pretty straightforward. Our data set is life expectancy (in years) by Country. 2 columns, 197 rows. Pretty simple stuff. Wait, there are only 197 countries in the world? Or maybe only 197 that report on their life expectancy? Hmmm...is that worth a google search? Yeah, it is. As of July 2011 there are 195. Okay, close enough. In the lecture, we're supposed to learn what is meant by Minimum Maximum Median First Quartile Third Quartile The prof explained the concepts and then drew (whiteboard style) the graphs on the screen. The tutorial then takes those concepts and shows you how to implement in R. We start with Changing Our Working Directory. This points R to the folder where your data "lives." Wait a minute, what data? I haven't downloaded my data yet. Ah okay, there it is. They have it posted as text file next to the lecture. Simple enough with 2 columns and 197 rows. Super simple. But wait, what would I do if I had terabytes of control panel log data? That would probably take hours! Focus, Grant. This is not supposed to teach you R. Nor about data collection and parsing. ETL. Okay, when do I learn that stuff? #Create variable data that is the data set. Simple enough. data=read.table("data_lifeExpTable.txt') #Type in data and the data is loaded. data #(first column is the country, second column is life expectancy value) #Set second variable to the data you want to plot. In this case, it's the life expectancy value lifeexp=data[,2] #Yeah, so what am I doing here? I am creating a value called "lifeexp" and I am setting it to "data" that is the first #variable I created and the brackets say just look at the second column of that data. Okay, got it. Damn it, I'm trying #to learn R again. #Cool, now I've loaded my data and created a simple scatter plot. plot(lifeexp) #and of course you have to label your x and y axis. plot(lifeexp, xlab='Country, ylab="Life Expectancy") #and then you want to limit your results plot(lifeexp, xlab='Country, ylab="Life Expectancy", ylim=c(0,86)) # and then you want to sort them for display plot(sort(lifeexp, xlab='Country, ylab="Life Expectancy", ylim=c(0,86)) #and then create a box plot. had a little too much trouble with this one. That last paren throws me off. boxplot(lifeexp, ylab="Life Expectancy", ylim=c(0,86)) # and then list the five number summary summary(lifeexp) # and then a new chart. ugh, struggling with this one, too. Damn paren again! plot(sort(six_grades), type='b', xlab="Student", ylab="Grades", ylim=c(60, 100)) 1.3 The Center of the Data and the Effects of Extreme Values

My New Journey

Wow! Has it really been since August since my last post? Sabbatical seems like so long ago. I hate to admit that my only posts since then have been micro-posts to twitter and facebook. Ah, the 21st century. In my head, blogging is for something different. A kind of diary, not quite as tactical, more for a documenting a journey. Hence the posts from London and traveling in Europe, then of course my Sabbatical. Well today, I will start documenting a different type of journey. A journey through learning statistics and R. Through Coursera.org I am currently enrolled in a MOOC (massive, open, online, course) put on by the University of Toronto (kinda cool that I walked around the campus when I was there to see the Blue Jays). As I'm going through this class and future MOOCs that I'm enrolled in: * An Introduction to Interactive Programming in Python - Rice University * Machine Learning - Stanford University * Introduction to Data Science - University of Washington * Startup Engineering - Stanford University I will attempt to document the experience for my sake and the sake of anyone interested in taking a similar journey. A little bit of context may help on why I'm taking this journey... At Rackspace, I am currently a Product Manager for Predictive Analytics for our SMB Marketing team. I think it's a cool story on how I got here and what I'm doing but I'll save that for another day. The point I want to bring up is that I work with people strong in math, statistics, programming and infrastructure/cloud/hosting etc. I doing okay but I feel like a groupie or poser. The purpose of this journey is to change that. One more thing before I start...the last time I did any serious programming was with PowerBuilder and WinRunner circa 2002 (good ol' MetaSolv), so it's been a while. This is going to be fun. =)

Tuesday, August 7, 2012

Mission Complete! And Thank You!

Well, I made it back to San Antonio safe and sound. I drove 10,750 miles over 47 days across the US and Canada and I am so thankful for so many things. I completed my goal of seeing 14 games in the MLB parks that I hadn't seen. I even added a game in Chicago to see the Cubs (the original inspiration) to make it 15. No accidents, no flat tires and no speeding tickets!

This is as close as I'll get to an Academy Awards speech and I have no time limit, so here goes...

First off, thank you to Rackspace for a wonderful benefit. Giving Rackers (after 7 years' service) an extended period of time to unplug and work on a bucket list event such as this is absolutely priceless.

To my Mom (despite the fact that I know you won't read this because it's on the inter webs), thank you for all your support. As always, you're incredible and I'll never be able to thank you for all you've done for me.

To Angela, thank you for taking care of my house and dogs. It meant so much to me knowing that both were in good hands.

To the Sklars, thank you for having Scott join me for Phoenix through San Francisco. It was really special to have him with me on those four legs of my journey. He's a great kid and we had a great time.

To Brian, thank you for Pittsburgh. It was a short visit but a special day. You're so right. Pittsburgh is a great city! And to Bob for the impromptu lesson on The Cathedral of Learning.

To Brad, thank you for fighting through cancelled flights and the flu to join me for the trip to Miami. Our 5-5-5 was a great experience and this one solidified the fact that you're a great friend and baseball buddy. Go sports!

To Doug, thank you for putting me up in Phoenix. And the pool game until 2am. And meeting your family and spending time with the Stevens' on Father's Day.

To the Cook and Pargas families in Chicago. As always, it was so great to spend time with you. And welcome to Jennifer's husband Rick. I really appreciate you guys going to the Cubs game with me!

To Dya, thank you for introducing me to Greg Simmons at Channel 12. The two Skype interviews we did went a long way to helping raise money for Windcrest Little League.

To Keith, thank for reminding me about "Men at Work" by George Will. You reminded me of a incredible book that articulates why I love baseball.

To Cara and Andrew (@Rackspace), thank you for posting a blog post about my journey. I appreciate the fact that Rackers appreciate what I tried to do for Windcrest LL.

To Laura, for all you great advice on what to do in Toronto. 

To John, for a great lunch in Atlanta.

To all of my Facebook friends, thank you for your "comments" and "likes" to my posts. Because most of my trip I was traveling alone, it really felt like I shared this journey with you. It really meant a lot to me knowing that you were keeping up with me. 

To Ty and Pablo with Windcrest LL, I hope I helped a little bit!

A sincere thank you to all for a successful trip!


Monday, July 30, 2012

Stage 15 Padres @ Marlins


Marlins Stadium (pictures to follow) is brand new and a huge place. The few pics I had seen of it, didn't indicate how big it was. It's so big that it looks like the baseball version of Jerry's World (Cowboys Stadium). After we got inside, we saw the roof closed and realized why it's so big. Seems to be a rule of physics that if you've got a retractable roof, you're going to have a big place. With the heat and humidity outside, it's understandable why they chose the retractable. 

It's an interesting park, lots of wild angles, green walls in the outfield and a crazy marlin display in center field. Surprisingly, they had 4 levels that made the upper deck a little high. There was even a crazy section that, from afar, kinda looked like a cave. 

Because it was a Sunday afternoon game, I expected more people. Especially because a big part of the crowd was there because they were playing a World Baseball tournament. I guess Miami summers are used for other things. Shame, cause the fans that were there seemed like a good baseball bunch. They definitely stayed and cheered the Marlins to a win in the 10th inning.  

All in all, a good stadium and cool to end with a stadium in it's inaugural year.

And a special thanks to Brad for fighting through a couple of days of cancelled flights and airport time to make it to Atlanta for the drive down to Miami to take in the last game with me.  

Saturday, July 28, 2012

Stage 14 Phillies @ Braves


Turner Field, Atlanta Georgia

I fought through the LONG drive from Pittsburgh to Atlanta to pick up Brad from the airport and then check out the Braves. Unfortunately, Brad's Thursday flight was cancelled. Because the game was on Friday, we'd still be good for the game. Well, on Friday, Brad ran into "flying" hell. He made it down to DC but then got stuck there. Not sure what the airline story was for why they suck so bad, the short of it was no Braves for Brad. I was so bummed.

Especially because Turner Field was great. Walking to the field you get a sense of what they think about baseball...in the parking lot where Atlanta-Fulton County Stadium used to be, they have the wall standing there in the parking lot. Evidently, the actual outfield wall from the old park. Very cool.

I arrived two hours before game time, to see batting practice and to make sure I got my throwback Tim Hudson t-shirt that was the give away for the night. Arriving in center field is the right place. That's where all the action is...the Chop Club, 755 Club, lots of food and the main shop. 


At this point, it's super hot outside and I'm still bummed that Brad's not there, I knew it would be tough to fight through it but I did. I wanted to walk around and get a view from all part of the park (my standard first task) but you can't at Turner. There's one major ding. All of the new parks have it, and because Turner is and older park and not part of the trend at the time, they don't have it. Oh well, still gotta fight through it. 

And I'm glad. Turner has a great vibe. After watching batting practice for a bit, I looked up and saw something I haven't seen before...

Yes, it's an agenda for the activities leading up until game time. It seems like a small thing and a predictable sequence of events. And I suppose it is. But for someone who's been driving around, seeing all of these different ball parks, I don't want to have to think. I just want to soak in the park and let it guide me. So something small like this helps a lot. It's an easy thing to do and now that I think about it, I'm not sure why everyone else wouldn't do the same thing.

The On Deck show was also very cool, they had a good interview with Chipper Jones and they really built up the rivalry with the Phillies. It really made it feel like they try to treat each game like a special event, not just another of 81 home games. 

Well done Atlanta!

Friday, July 27, 2012

Stage 13 Cubs @ Pirates

PNC Park.

I got to share this with a good friend of mine. Brian took a bus (on a Wednesday mind you) from DC to Pittsburgh to catch this game with me. Cheers mate!

Brian had been to PNC and said it was great. Other people have made mention that it's a good one. And of course when you get there, you see signs and souvenirs with a bold proclamation.





I don't know if I'd go that far but it's up there. Great views, great vibe, great location. It's definitely a top 5. There was only one major thing that I didn't like about. Traffic flow. Right before game time and throughout the game, regardless of the level, there is a ton of congestion. I'm talking about rush hour, no moving, build up the blood pressure type of congestion. It really sucked and took away from the experience.
 

Tuesday, July 24, 2012

Stage 12 Athletics @ Blue Jays

Rogers Centre - Toronto, Ontario, Canada


I've been in Toronto since Thursday. If you're paying attention, you might notice that I was in Detroit for less than 24 hours. That gave my 5 full days to sight see in Toronto and I took advantage of the opportunity...Downtown, Yorkville, Queen Street, Yonge Street and Mt Pleasant, The Art Gallery of Ontario, CN Tower, Niagra Falls, Inniskillin Winery, Distillery District, plenty of good eating, the subway as my primary means of getting around and Rogers Centre for a football match between Toronto FC and Liverpool FC. 


Rogers Centre is not my favorite ball park. Okay, I'll be honest (although earlier I said I wouldn't rank the ball parks, I put together a working list that I'll publish later), it's one of my least favorites. In fact, I only prefer it to Tropicana and Oakland Coliseum. It's over twenty years old and back then they built them to be multi-purpose. It's everything you'd expect of that type of facility. Big, with no great views...it feels like you're sitting in a football stadium. 
That's the way they built them back then and that's the way it feels. 


In fact, in the Blue Jays program, their President and CEO wrote an article in which he said, this is my paraphrase...we know it's not like the new ballparks, but it's our outdated ball park. Let's love it for what it is. And hey, by the way, we went back to our cute and lovable old Blue Jays logo. We got rid of that stupid, mean looking "J" thing we were rolling with. So, love us, again because we are who we are. It was positive, in a tone that he has to take. He's still got to sell tickets with what he has.  In all fairness, the place works, it's not breaking at the seems. It's just not as cool as all the new ball parks. The new ballpark competition has gotten stiff over the last few years and Rogers Centre is outdated and blah. I guess you have to give them credit for not throwing it away. Kinda' like KC, I think, although KC did a much better job with their facelift.
I managed to get a good seat for this one. 

One thing that's kinda fun, is the great view you get of the CN Tower.

The next week is going to be busy as I'm back home a week from tomorrow. Yes, in one week I will see three more games. I have a quick 5 hour drive to Pittsburgh tomorrow morning. Gotta be quick as I have to make it down there for a 12:30 game (see you soon Brian!). On Thursday morning, I gotta wake up early for the 12 hour drive down to Atlanta. Brad, I'll pick you up from the airport. The Braves play on Friday night, then it's down to Miami for my last game on Sunday the 29th.