Datamining Viewer Client Problem

Hello!

I am running a SQL Server 2005. I created the mining models from the tutorials. I can connect with the DataminingViewerClient directly on the SQL Server(i.e. to localhost), but when i try to connect to the Server from my other computer it is not working i always get connection faild and i should check that the server is running. I can connect to the Server with other programms but the viewer is not working. Any ideas what that could be?

Can you connect to other servers from the machine where the DataminingViewerClient application works? If so, it may be that there are additional client components that need to be installed. Let us know and we can continue to diagnose.

Thanks

-Jamie

|||Ok i now tried to connect from Server A to Server B, not working either. It works on both when i run the viewer directly on the server and connect to localhost but not from Server A to B or vice versa or from any other computer. Could it be that some permissions are missing, because in the dataminingviewer client i dont have to specify a user/password for the server where the analysis-service runs. I dont think that components are missing because i can compile the source code without errors, but i'll be happy about any hint that might help.

Another thing i tried: When i create a datasource on Server A to connect to Server B(or from any other computer) it only works when I use the sa user(Windows Authentication doesnt work), otherwise i cant browse/select the databases.|||In general AS only uses Windows Authentication, unless you connect over http (requires configuration - see books online). Connecting over http allows you to specify a username and password. For the DM Viewer Client, you cna modify the code to use a http connection, or prompt for username and password. The source code is provided.|||

Hello again!

I found the error...the server was not in the domain, after we added it it worked.

DATAMINING tasks

what are the different data mining tasks...........

The most common basic data mining tasks (supported by SQL Server 2005) are classification, regression, clustering, forecasting, association analysis, correlation analysis.

All tasks act as blocks in solving a really large set of business problems.

A few starting points:

- http://www.microsoft.com/sql/technologies/dm/default.mspx -- The tutorial and the Webcast ("Introduction to Data Mining in SQL Server 2005") provide a good description of what data mining tasks are supported in SQL Server, plus details on the tools

- http://www.sqlserverdatamining.com -- lots of information, tutorials etc.

|||

A nice classification of data mining tasks is given by David Hand et.al in Principles of Data Mining (2001):

1. Exploratory data analysis (Visualization)

2. Descriptive modelling (Cluster analysis, relationships between variables...)

3. Predictive Modelling (Regression, Classification,...)

4. Pattern Discovery (Association Rules, outlier detection,...)

5. Retrieval by content (start from a given pattern and try to find similar patterns)

This provides a very general viewpoint on all different kinds of tasks.

dataMining

i create a model mining to know percent of product, which is like more by customer is have percent biger than other products that is don't like by customer.

i use DTS to get result to sql server.

select flattened

predict([modelName].[tablePredict],Include_statistic)

from

[modelName]

prediction join

.....

i have result with a table A in sql server:

productid $support ... $adjustedprobability

1 0.0 ...

1 0.0 ...

1 63.3 .....

how can i write in Dts so that table A not have record with value $support=0.0

- second: percent people like that product is knowned by $adjustedprobability or $support and value small or big

I've moved you thread to a forum where you are more likely to get an answer. You had submitted your question to the LINQ forum which isn't related to DTS.|||answered here: http://forums.microsoft.com/MSDN/ShowPost.aspx?PostID=829881&SiteID=1

Dataming of subsets question

Have not found an active general data mining forum yet so asking here.

I'm new to data mining band have been given the task of setting up a data mining system. The problem is that our setup seems pretty non standard and I'm not sure how to use data mining on it or what my expectations should be. The situation is:

We have a large and growing set of strings which we get requests for (> 100,000). The requests have many, mostly nominal (non-numeric), variables associated with them. We can only handle a subset (probably less than 10,000) or the strings at any one time. We want to use data mining to analyze historic requests so we can figure out which strings we are going to handle under a given set of variables. So given that our variable currently have values X1, ..., Xn, what subset should be use given than a large database of historic string requests.

Anyone know what techniques would work well for this kind of problem? This is a quick and dirty kind of project, no special purpose hardware or expensive software on this one. I've been looking at using rapid miner but not sure that it's a great tool in this case.

thanks in advance,
max

A first ideea is to use Microsoft Clustering Algorithm to cluster your requests and find similare requests- for this situation you don't have to have a predictable attribute.

A second way is to define an objective by selecting one (or more) columns from your requests, let's say Xj and put the question :

What are the links/influences of X1,..., Xn with Xj?

Or create another attribute Xn+1 which same question.

Let see as Microsoft example that is presented in it's tutorials;it have following attributes:

CommuteDistance(X1)

Gender(X2)

HouseOwnerFlag(X3)

MaritalStatus(X4)

...

NumberCarsOwned(Xn)

and a predictible attribute:

BikeBuyer(Xj)

that mean if customer buy or not a bicycle; so in this case the question/objective is in the some way formulated:

What are the links/influences of X1,..., Xn with Xj?

There is a good book presented here

|||

You could try using and classification method with the other fields as input and the target string as output. Then you could rank the likelihood of each string given some input.

Candidate algorithms are

- Naive Bayes

- Logistic Regression

- Neural Nets (slow)

- Association Rules (not traditionally a classification method, but could work in this case)

After creating the model you would do something like

SELECT FLATTENED (SELECT TOP 10000 TargetString FROM PredictHistogram(TargetString) ORDER BY $Probability) FROM MyModel NATURAL PREDICTION JOIN

(SELECT 'Factor1' AS Factor1, 'Factor2' AS Factor2) AS t

HTH

-Jamie

Dataming of subsets question

Have not found an active general data mining forum yet so asking here.

I'm new to data mining band have been given the task of setting up a data mining system. The problem is that our setup seems pretty non standard and I'm not sure how to use data mining on it or what my expectations should be. The situation is:

We have a large and growing set of strings which we get requests for (> 100,000). The requests have many, mostly nominal (non-numeric), variables associated with them. We can only handle a subset (probably less than 10,000) or the strings at any one time. We want to use data mining to analyze historic requests so we can figure out which strings we are going to handle under a given set of variables. So given that our variable currently have values X1, ..., Xn, what subset should be use given than a large database of historic string requests.

Anyone know what techniques would work well for this kind of problem? This is a quick and dirty kind of project, no special purpose hardware or expensive software on this one. I've been looking at using rapid miner but not sure that it's a great tool in this case.

thanks in advance,
max

A first ideea is to use Microsoft Clustering Algorithm to cluster your requests and find similare requests- for this situation you don't have to have a predictable attribute.

A second way is to define an objective by selecting one (or more) columns from your requests, let's say Xj and put the question :

What are the links/influences of X1,..., Xn with Xj?

Or create another attribute Xn+1 which same question.

Let see as Microsoft example that is presented in it's tutorials;it have following attributes:

CommuteDistance(X1)

Gender(X2)

HouseOwnerFlag(X3)

MaritalStatus(X4)

...

NumberCarsOwned(Xn)

and a predictible attribute:

BikeBuyer(Xj)

that mean if customer buy or not a bicycle; so in this case the question/objective is in the some way formulated:

What are the links/influences of X1,..., Xn with Xj?

There is a good book presented here

|||

You could try using and classification method with the other fields as input and the target string as output. Then you could rank the likelihood of each string given some input.

Candidate algorithms are

- Naive Bayes

- Logistic Regression

- Neural Nets (slow)

- Association Rules (not traditionally a classification method, but could work in this case)

After creating the model you would do something like

SELECT FLATTENED (SELECT TOP 10000 TargetString FROM PredictHistogram(TargetString) ORDER BY $Probability) FROM MyModel NATURAL PREDICTION JOIN

(SELECT 'Factor1' AS Factor1, 'Factor2' AS Factor2) AS t

HTH

-Jamie