Post reply

Data Science, BI, and Reports

  • November 14, 2019 at 12:00 am

    #3693271

    Comments posted to this topic are about the item Data Science, BI, and Reports

  • November 14, 2019 at 7:46 am

    #3697567

    " Learn about them, experiment, understand the impact they have on your audience, and choose the best tools for the job."

    Any idea where to start with Data Mining?

    • Is there a good book anyone can recommend for SQL Server Data Mining or should i start with?
    • A Rickety Stairway to SQL Server Data Mining Blog series? 2012+ by SQLServerSteve
    • The Data Mining Stairway Steps by Daniel Calbimont 2015+?

     

    • This reply was modified 5 years ago by  ktflash.

    I want to be the very best
    Like no one ever was

    https://www.sqlservercentral.com/articles/forum-etiquette-how-to-post-datacode-on-a-forum-to-get-the-best-help

  • November 14, 2019 at 11:19 pm

    #3697900

    For data mining, I think the Data Mining levels from Daniel are good. They'll get you going, though some are a bit dated. I started this book, https://amzn.to/32Ir1fK, which I liked as well.

    The concepts are things to look at, not so much the implementation and syntax. I do think Python is starting to lead the way to write this type of code, with lots of examples and ease of use. Not to mention this is the primary language in notebooks.

     

  • November 17, 2019 at 3:02 pm

    #3698331

    I like your suggesting we experiment with the various tools, looking to see which will work for us in a given situation. I think there's a tendency to choose one tool and then use it as a hammer to make all your data analyses conform to that nail.

    Kindest Regards, Rod Connect with me on LinkedIn.

  • November 21, 2019 at 8:53 am

    #3699488

    I feel like articles written by the referenced author are extremely bias and have no real value to add to the discussion. The guy is basically arguing over semantics like it really matters to anyone. I say tomato, you say tomato...

    There are a number of different approaches to building a report that aims to answer one or more questions of the data as well hopefully either gives someone an idea of what's going on or something to actually act on. Data is ingested, data is stored, data retrieved, data is computated, data is visualized, and data is analyzed.

    Regardless of you accomplished any of those steps is irrelevant to what BI is or isn't. You can do this with SQL Server, T-SQL, and Excel or you can do this with HDFS, Hive, R, and Tableau. Who the hell cares what you call it as long as someone is using the data.

    P.S

    Stop freaking saying Data Science is not reporting or does not have reports. Almost every data science output I've ever worked with that is actionable goes into a freaking report with or without the help of traditional "BI" techniques (e.g.: entirely in R using a flat file that's still automated and repeatable).

Viewing 5 posts - 1 through 4 (of 4 total)

You must be logged in to reply to this topic. Login to reply