Hello all,
I haven't been on CodeCall for months now, mainly because I have been working on my blog, and thinking about what I want to do with my developing.
I want to start Data Mining and I want to make a program to run the algorithm on the data.
I don't really know where to start or what to do-any help would be great.
Thanks.
5 replies to this topic
#1
Posted 12 November 2010 - 11:43 PM
|
|
|
#2
Posted 13 November 2010 - 07:17 AM
Start with what you want to analyze. If you want to get in index of words/phrases you've used, that's very different from trying to find out who's commented on your blog the most, and where their blogs are.
#3
Posted 13 November 2010 - 01:38 PM
I probably want to analyse raw data like from a scientific aspect or more of a business sense (example: the types of chemicals being exported and for what price).
Those would be the two types of stuff I'd want to analyse. Once again, I really didn't know where to start so I asked the forum.
Those would be the two types of stuff I'd want to analyse. Once again, I really didn't know where to start so I asked the forum.
#4
Posted 13 November 2010 - 09:01 PM
As always, start with what data you have. What format is it in, what analysis options do you have, etc. Understand the nature of the data in front of you, and then you can start digging into it.
For example, do you have the chemical and price as distinct fields? In that case, it could be as simple as:
SELECT SUM(qty), chemical, price FROM sales GROUP BY chemical, price
For example, do you have the chemical and price as distinct fields? In that case, it could be as simple as:
SELECT SUM(qty), chemical, price FROM sales GROUP BY chemical, price
#5
Posted 13 November 2010 - 09:38 PM
Well, the chemical idea was just an example but I see your point.
Most probably it will be from a relational database so I suppose it would be similar to that. Collecting it or getting it from some source is another thing, but I don't think I would have too much trouble dealing with that.
I would hope to store it in a relational database for ease of access and organisation. Creating the algorithm and then implementing it on the data is my problem.
Most probably it will be from a relational database so I suppose it would be similar to that. Collecting it or getting it from some source is another thing, but I don't think I would have too much trouble dealing with that.
I would hope to store it in a relational database for ease of access and organisation. Creating the algorithm and then implementing it on the data is my problem.
#6
Posted 28 December 2010 - 03:23 AM
This thread gave a lot of information thanks for everyone who posted the replies. It was very much useful for me. As I am working for one of leading company I gain much knowledge. Our company is Icon Infosystem who is mainly deal with Data Mining.
1 user(s) are reading this topic
0 members, 1 guests, 0 anonymous users


Sign In
Create Account


Back to top









