Machine learning – learning path

When to use what for Data Mining.

 

It is been a while since MVP Miguel Egea ( @miguelEgea ) introduce me to data mining in SQL Server, I was already finishing my graduate project on Artificial Intelligence using WEKA back in 2005, I found the product really interesting, and decided to learn everything about it.

We ( Solidq.com ) have been delivering solutions based on SQL server Analysis Services data mining since then. For long years that was pretty much what we had within Microsoft. Also, the Excel/Visio add in that came for SQL 2005.

Today, I was delivering a session about Big Data Mining with Mahout at SQL Saturday Nashville when someone asked me. Where do I start?, what would be the right Microsoft data mining tool for learning.

WOW, it is true, there have been many news in last two years so….

Here goes what we have:


If you are starting right now. Go for Azure Machine Learning, as for 01/2014 you can go to https://studio.azureml.net/ and start running experiments for free. It is well documented and come with a lot of samples.

Also you can read the book, for a great introduction: http://www.amazon.com/Predictive-Analytics-Microsoft-Machine-Learning

Azure Machine Learning is my first choice for POC and real projects. There will always be pieces that can only be solve with customization (tsql, ssis, hive, pig, SSAS, Mahout) but by default it is my data mining tool at this point.

There is a 10GB limit for training sets, 10GB is already a big number, and there are always ways to divide and conquer if larger dataset must be used for training ( rare…)

 

Paco Gonzalez —

Windows Phone Nokia Lumia 635 with AT&T

Better than expected

 

I have been a Windows Phone user since the beginning. Suffering and enjoying it. At the same time my wife have been enjoying Samsungs and iPhones…, so always had something to compare to.

Last year (2014) I had Nokia 925. It was perfect, fast really fast, but… battery did not even last a morning of my regular usage, awesome front and Back camera, but… the physical design made me drop it over and over. Not only me, when someone else was grabbing it for taking pics, they will go and say wow, this cell phone is easy to drop!!!!. I was mad that battery and physical design was killing it. After too many drops it died. I should have bought a case, so it would be easy to hold it, but the battery would have been still an issue.

When I moved to the US, I went to Walmart and got a prepaid T-Mobile Nokia Lumia 521 for $100. I was not expecting a lot, but it didn’t do the job. It was probably ok when released but after a couple updates things just toke ages to load. About T-Mobile, my wife Samsung S4 mini, which is not an LTE but it is a 4G did not make at home or around in terms of bandwidth. Not enough for Skype.

I went to Walmart and bought the prepaid Nokia Lumia 635, it was discounted so I got it for $69, WOW, after that, I went to AT&T and after 2 long hours I have my number migrated to AT&T .

Great, I got home, I was scared, I knew I paid $69 so was not expecting anything big. Here I start my review for the Nokia Lumia 635.

pro et contra

Cons:

This is not a con, since I knew it before buying it. The camera is not really good, it is just 5MP, so it is what it is. It does not have a front camera, It is not been an issue for me before, but know that I have a 3 month old daughter I have to continuously do video Skype and without having a front camera you cannot see the other party.

Pros:.

It works really fast, apps open instantly. I woke up and grabbed it. It immediately connected to my BOSE Bluetooth speaker, I open OneDrive looking for my mother paella receipt, I was checking email, WhatsApp. Then I did skype for 45 minutes with my sister, wait I didn’t even touched it: “Hello Cortana Skype Call mom”, it just worked, really convenient when you have a baby on the other arm. I checked my LTE speed, it was 25 down 10 up, 20ms ping, so Microsoft and AT&T did the homework.

I got in to my car, again, Bluetooth worked immediately, arrived to the gym, made a couple skype calls using LTE to my friends in Spain, while in the elliptical, after that started TuneIn Radio to listen CNN for half an hour.

Got back home, twitter, LinkedIn and Facebook …

Great, it is now 9pm and my battery is 45 %, so it stays alive in a heavy day.

Holding it in my hand is by far the Best Windows Phone I got, it feels like the iPhone 4 or 5, so well built.

It is amazingly fast, something I love.

This phone is going to stay with me for a long time, it is definitely worth the price. Apart from the camera it can easily beat Samsung and iPhones, Windows Phone software is cool, it costs $69. I would spend a lot of money for a better front and back camera but the same phone. Please Microsoft do it.


Cortana

I liked Cortana, I am not really into managing my agenda or texting using Cortana,

I am more about calling people, or opening apps. I love being able to say Skype Call Mom,

I would love to say Spotify play list David Guetta or

TuneIn Radio CNN,

Or, read twitter!!!

 

Paco Gonzalez –

HBase: Architecture and Use Cases

Language: English

Event Type: Online

Online Meeting URL: https://attendee.gotowebinar.com/register/4588775858636390145

RSVPURL: https://attendee.gotowebinar.com/register/4588775858636390145

Abstract:

​This session will provide a high-level overview of HBase internals and architecture and describe common use cases for implementing HBase in your organization. We will discuss the advantages of the platform and ways in which you can leverage the power and features of the HBase and HDFS platform to nearly infinitely scale your storage and processing.

Scott Shaw, Solutions Engineer, Hortonworks

Scott Shaw has over a decade experience in data management, He is a frequent speaker at local and national community events and has co-authored two books on T-SQL. He teaches as well as implements Pig, Hive, Hadoop, as well as teaches courses on SQL Server, and Microsoft BI. He is currently working on a book titled “Practical Hive” to be published by Apress publishing. He lives in Saint Louis and is a Solutions Engineer for Hortonworks

When

 

iCal

UTC : Tue, Jan 27 2015 19:00 – 20:00

Event Time : Tue, Jan 27 2015 14:00 – 15:00 (UTC-05:00) Eastern Time (US & Canada)

Scott Shaw: Hive: SQL on Hadoop

 

Our next Big Data virtual chapter meeting is: Tue, Dec 02 2014

Language: English
Event Type: Online
Online Meeting URL:https://attendee.gotowebinar.com/register/7468077951705725697
RSVPURL: https://attendee.gotowebinar.com/register/7468077951705725697

Abstract: 

Hive is the most widely used SQL on Hadoop solution. It is open-source, fast, and adaptable. The Hive stinger initiative started by Hortonworks involved 145 developers and 44 companies, including Microsoft. This session will go over the structure of Hive and demo how easy it is to begin querying data on Hadoop using the SQL skills you already know. We will also discuss the many exciting new features coming up in the next release, including ACID transactions! 

Scott Shaw, Solutions Engineer, Hortonworks

Scott Shaw has over a decade experience in data management, He is a frequent speaker at local and national community events and has co-authored two books on T-SQL. He teaches as well as implements Pig, Hive, Hadoop, as well as teaches courses on SQL Server, and Microsoft BI. He is currently working on a book titled “Practical Hive” to be published by Apress publishing. He lives in Saint Louis and is a Solutions Engineer for Hortonworks

When

iCal
UTC : Tue, Dec 02 2014 19:00 – 20:00
Event Time : Tue, Dec 02 2014 14:00 – 15:00 (UTC-05:00) Eastern Time (US & Canada)
Your Local Time: 12/2/2014 14:00 – 15:00

with member [Measures].[Paco] as “Hello World”

My brand new blog

Why a blog?, writing will improve my English, so far I have blogged in different Spanish blogs, now it is time for English.

I have so much to write about, I will write about things that may be outdated but always wanted to write about it, and of course, all my crazy brand new uses of data mining.

I am in love with SEM, and the use of machine learning for optimizing conversions. You will see a lot about Bing Ads + Azure Machine Learning.

I plan to keep this informal but I am SolidQ Mentor so expect this to be too technical sometimes.

I will use this blog to upload content that I present in conferences, mostly around the Atlanta area, I am so glad I moved from south east Spain( where I had so little opportunities to speak ) to Atlanta, where there are lots of opportunities. I already spoke at Atlanta .Net codecamp!!!.

I hope you enjoy.

 

Paco Gonzalez – SolidQ