In the Mining Accuracy Chart, the predictable columns of nested tables does not show up in the "Select predictable mining model columns to show in the lift chart" table. The "Predictable column name" is empty.
Predictable columns in the case table shows up, but not the predictable columns in the nested table. What am I missing?
-Young K
Hi,
I am not getting Mining Accuracy Chart and Min ing Model Prediction
Plz tel me how to do.And how to use the filter input data used to generate the lift chart and
select predictable mining model columns to show in the lift chart
I ran a decision tree, clustering and neural network mining model across a dataset of about 200,000 records. I am trying to evaluate the accuracy of each of my models but I can't view the results.
I get the following error:
Failed to execute the query due to the following error:
XML for Analysis parser: The XML for Analysis request timed out before it was completed.
Execution of the managed stored procedure GenerateLiftTableUsingDatasource failed with the following error: Exception has been thrown by the target of an invocation.Microsoft::AnalysisServices::AdomdServer::AdomdException.
How does cross-validation work in the case of models with predictable nested tables? Is it supported? For classification and regression with a flat structure, during the testing phase (that is, validation phase) of cross-validation I can think of the inputs being presented and comparing the predicted value with the real value. But in the case of nested tables, the input is not a subset of the attributes (a subset of the input vector), but whole input vectors. (For instance, complete itemsets in the case of association rules). Can you please explain some more how the validation phase works in the case of the association rules and decision trees with predictable nested tables?
thanks,
Gustavo Frederico
Hi ,all here,
Thank you very much for your kind attention.
I just found that I am not able to view the accuracy chart for my mining model. The error message is: no mining models are selected for comparision. Which is quite strange.
Any guidance? thank you very much.
With best regards,
Yours sincerely,
Hi ...I can't figure out how to put nested tables into the Data Mining Model Training Transform (SSIS). Can anybody help me? some example please...!!!??
Diego B.
Hi All
I have installed SP2 for SQL server 2005, i just want to try datamining like in the tutorial, i found error if i click "Mining Accuracy Chart" for comparing model with error
"TITLE: Microsoft Visual Studio
An error prevented the view from loading.
ADDITIONAL INFORMATION:
Class not registered (Exception from HRESULT: 0x80040154 (REGDB_E_CLASSNOTREG)) (System.Windows.Forms)
"
any body can help.
thanks
Hello
I've created models with Decision Tree and Neural Network algorithms that predict continous target. But I don't know how to interpret scores that occure under scatter accuracy plot. How should I interpret scores under scatter accuracy plot?
How can I estimate occuracy of model created with Time Series? How can I compare accuracy of model created with Time Series with models created with Decision Trees and Neural Network algorithms?
Thanks in advance.
Hi,
I tried to utilize Mining Accuracy to analyze my models.
Mining Model Predictable Column Name Predictable Value
-----------------------------------------------------------------------------------------------------
NaiveBayesModel
DecisionTreeModel
When I want to choose an option for "Predictable Column Name" on NaiveBayesModel row or DecisionTreeModel row, there is no option/value/choice on the drop box. There is also no option/value/choice for the "Predictable Value" column.
When I clicked "Lift Chart" tab to see the accuracy chart, it gave me this error message: "No mining models are selected for comparison."
The models are as follows:
(
[CustKey] KEY,
[Gender] TEXT DISCRETE,
[BikeModels] TABLE PREDICT_ONLY
(
[Model] TEXT KEY
)
)
Please assist!
Mary
I can't figure out how to put nested tables into the Data Mining Model Training Transform (SSIS). I can do a simple case table, but how do you get those nested tables with DM Training Transformation? Any ideas? Samples?
Thanks in advance,
-Young K
Hello!
I have a problem getting information about accuracy (percentage of the right predictions) of the model using DMX. Is it possible to get information about accuracy of the model using DMX? I didn't find any useful function... My second idea was to build and process the model. And then compare states of the predictable columns of the test data to states that the model predicts on the same data. And count them. That would be the way to get percantage of the right predictions... The problem is that usage of the function COUNT is not allowed??? I tried:SELECT COUNT(*) FROM [My Model Name].Cases and it didn't work like in standard SQL...
Is it possible to count rows in DMX? Any idea how to get accuracy (percentage) of the model? I would need this information in my application...
Thanx for any idea,
Ziga
Lets take the following example:
Movie train table:
ID Class
1 +
2 +
3 -
4 +
5 -
Actor train nested table:
ID MovieID Gender
1 1 F
2 1 M
3 1 F
4 1 F
5 2 M
6 2 M
7 2 F
8 3 F
9 3 F
10 4 M
11 4 M
12 4 F
13 4 F
14 5 F
15 5 M
We want to build a classifier model in order to predict the Class of a Movie based on the Gender of movie's actors. To deal with the nested table Analysis Services maps each record of the nested table to an attribute of the case table. These attributes are named Actor(n).Gender with n = 1..15, and so they are dependent on the nested table record numbers. Both Microsoft Decision Trees and Microsoft Naive Bayes algorihms use these attributes without any modification.
We are implementing a Relational Naive Bayes algorithm and we are planning to aggregate such attributes in order to make them independent of the nested table record numbers.
Next step we tried to predict some unseen cases and here we face with
a very huge problem.
Lets take more two tables of unseen cases:
Movie test table:
ID Class
6 +
7 NULL
8 NULL
Actor test nested table:
ID MovieID Gender
1 6 F
2 6 M
3 6 F
4 6 F
16 7 F
17 7 M
18 7 F
19 7 F
20 7 F
21 8 M
22 8 M
23 8 F
Predicting the movie 6 Class is not a problem since the movie actors were included in the training dataset and when the records are mapped to attributes because they already exist in the model. But when you
try to predict movies (7 an 8) with unseen actors all new attributes are simply ignored in the ALGORITHM:redict call (in_ulCaseValues is zero!) because they do not exist in the model!
What is the solution?
Hi, all experts here,
I am a bit confused for the model evaluation (lift chart), should we map all the columns for both the mining structure and the case table? I mean for those predictive models, we have a predict column, shouldnt we ignore the mapping of the predictive column between the mining structure and the case table? But it seemes we are not allowed to miss the predictive column mapping between the mining structure and the case table.
Why is that? Could any experts here give me some explanation on that?
Hope my question is clear for your help.
Thanks a lot and I am looking forward to hearing from you shortly.
With best regards,
Yours sincerely,
Hi,
I have just run a simple data set through a model to predict a simple true or false value (i.e. binary output)
The Lift Chart/Mining Legend in Analysis Services shows three results €“ Score, Population Correct (%), and Predict Probability (%)
Population Correct I beleive is the percentage of predictions it got right out of the total number of predictions it tried to make. Is this correct?
However, I can€™t work out how the other two are derived in particular the 'SCORE'. To give a live example the scores were as follows:
Model Score Pop Correct Pred Probability
Decision Trees 0.83 76.59% 54.28%
Neural Network 0.75 67.63% 50.05%
Ideal Model 100.00%
Can anyone help with this and give a detailed explanation?
Many thanks,
S Rajput
In Neural Network model, is that a way to have table column as predictable?
Mary
Hi,
I tried to create a lift chart with my custom plugin-algorithmn. The chart seems to be correct, but before it is drawn, an error occours:
Function ... Row 1 ... Column 43 ... cannot be used in this context.
(I've translated the key facts of this error message from german)
What did I do wrong?
Best wishes,
Manfred
Hi,
I am having trouble really understanding what makes a model accurate and effective at predicting some attribute. I can't seem to find any clear documentation about the mining legend of the lift chart on the Mining Accuracy Chart tab when working with the Data Mining Structure designer in VS 2005. Specifically, I would like to know more about what numbers in the Score, Population Correct and Predict Probability columns mean, and why they change when you move the vertical gray bar on the Lift Chart. Also, what is generally a good score to be aiming for, provided that it is highly difficult to get 100% accuracy with the kind of data that I am using.
Any more information on this subject is much appreciated. Thank you for your time,
Chris Burns
Hello . Because of my graduation project , I interested in data mining application , Adventureworks DW on MS VS 2005 . I opened File->Open->project/solution ->Enterprise -> AdventureworksDW .then I successfully deployed the algorithms decision tree and Clustering . Then I opened tab Mining Accuracy Chart then selected input table "testing" , which I had created before , from vTargetMail . After that , mining structure table and target mail table has automaticaly linked each other .Next , I selected predictive input as 1 , of the predictable row "BikeBuyer" . But , when I clicked "Lift Chart ", I only got a 45 degree line , everytime .. How can I fix it ?
View 7 Replies View RelatedHi,I am studying data mining features of SSAS and for a workshop I'vecreated 2 views derived from vTargetMail view of AdventureWorksDW.Train data consists every record except those in Pacific, and testview consists only records from Pacific area.1. I've created a mining structure based on Decision Tree and selectedBikeBuyer as predictable column.2. According to input column suggestions, I've selected Age,Eng.Education, NumberCarsOwned, YearlyIncome, CommuteDistance,NumberChildsatHome and TotalChildren as input columns,3. I've modified no other setting, and deployed project.I can get training results in decision tree browser and dependencynetwork (and both seem to give rather logical results) however, when Itry to browse lift chart or classification matrix I get an emptyclass.matr. and a lift chart of a single 45 degree line.Am I missing a step, or must I do some fine-tuning on (what)parameters?Thanks...
View 2 Replies View RelatedHi,
I am studying data mining features of SSAS and for a workshop I've
created 2 views derived from vTargetMail view of AdventureWorksDW.
Train data consists every record except those in Pacific, and test
view consists only records from Pacific area.
1. I've created a mining structure based on Decision Tree and selected
BikeBuyer as predictable column.
2. According to input column suggestions, I've selected Age,
Eng.Education, NumberCarsOwned, YearlyIncome, CommuteDistance,
NumberChildsatHome and TotalChildren as input columns,
3. I've modified no other setting, and deployed project.
I can get training results in decision tree browser and dependency
network (and both seem to give rather logical results) however, when I
try to browse lift chart or classification matrix I get an empty
class.matr. and a lift chart of a single 45 degree line.
Am I missing a step, or must I do some fine-tuning on (what)
parameters?
Hi, all here,
Thank you very much for your kind attention.
I dont think we should sample any nested tables for data mining model training? Since I think any nested tables are bound to the case table. Therefore whenever we sample the case table, the nested tables are like any other input attributes within the case table to be rectrieved as inputs accordingly?
Thank you very much for any guidance to clear my confusion.
With best regards,
Yours sincerely,
Hoping someone will have a solution for this error
Errors in the metadata manager. The data type of the '~CaseDetail ~MG-Fact Voic~6' measure must be the same as its source data type. This is because the aggregate function is not set to count or distinct count.
Is the problem due to the data type of the column used in the mining structure is Long, and the underlying field in the cube has a type of BigInt,or am I barking up the wrong tree?
Hi, all here,
I am wondering where can I store my mining results in data mining engine? For example, I got mining results like accuracy chart, decision trees, and other formats of results based on different mining algorithms I used for my data mining, so where can I actually store the results for reporting service use later? Is it possible to do that in SQL Server 2005?
Thanks a lot for any help and guidance in advance.
Hi All,
I am working on a column chart type (stacked column sub-type) report.
Our customer requires us that the space(padding) between the columns should be a constant(including the space between the Y-axis and the first column). I know how to set the width of the columns, but I really don't know how to set the width of the space between them. The columns just varies the space between them automatically according to the number of the columns (the number of the columns is not certain).
Thanks a lot in advance!
Danny
Hi!
I have a "little" problem with nested case model:
-- "normal" database:
DROP TABLE [unitInfo] ;
GO
CREATE TABLE unitInfo (
unitID INT PRIMARY KEY
, beginDate SMALLDATETIME
, area VARCHAR(10)
, partSize INT
, y2predict MONEY
) ;
go
INSERT INTO unitInfo
VALUES (1, '2007-02-01', 'home', 42, 10.0) ;
INSERT INTO unitInfo
VALUES (2, '2007-03-05', 'home', 43, 11.0) ;
INSERT INTO unitInfo
VALUES (3, '2007-02-02', 'office', 11, 11.4) ;
INSERT INTO unitInfo
VALUES (4, '2007-02-01', 'office', 10, 33.6) ;
INSERT INTO unitInfo
VALUES (5, '2007-02-01', 'office', 42, 44.1) ;
CREATE TABLE unitLog (
id INT IDENTITY(1, 1)
PRIMARY KEY
, logtime SMALLDATETIME
, -- combination of logtime/unitID is unique
unitID INT
, -- "FK" on unitInfo
m1 FLOAT
, m2 FLOAT
)
INSERT INTO [unitLog]
VALUES ('2007-01-01', 1, 43.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-01', 2, 43.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-01', 3, 63.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-02', 4, 432.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-02', 1, 43.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-03', 1, 423.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-04', 1, 432.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-05', 2, 43.0, 441.0)
INSERT INTO [unitLog]
VALUES ('2007-01-06', 2, 43.0, 4.0)
INSERT INTO [unitLog]
VALUES ('2007-01-06', 3, 43.0, 4.0)
INSERT INTO [unitLog]
VALUES ('2007-01-07', 1, 4.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-08', 1, 3.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-08', 1, 43.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-08', 1, 43.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-09', 2, 143.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-10', 3, 143.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-11', 4, 43.0, 144.0)
INSERT INTO [unitLog]
VALUES ('2007-01-11', 5, 43.0, 144.0)
INSERT INTO [unitLog]
VALUES ('2007-01-12', 2, 43.0, 144.0)
INSERT INTO [unitLog]
VALUES ('2007-01-13', 4, 413.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-14', 4, 43.0, 414.0)
INSERT INTO [unitLog]
VALUES ('2007-01-14', 1, 43.0, 44.0)
INSERT INTO [unitLog]
VALUES ('2007-01-20', 1, 43.0, 414.0)
INSERT INTO [unitLog]
VALUES ('2007-01-22', 1, 43.0, 414.0)
-- SSAS:
CREATE MINING STRUCTURE NestedStructure
( unitID LONG KEY, beginDate DATE CONTINUOUS, area TEXT DISCRETE
, partSize LONG CONTINUOUS, y2predict DOUBLE CONTINUOUS
, logdata table ( [id] LONG KEY, unitID LONG CONTINUOUS
, m1 DOUBLE CONTINUOUS, m2 DOUBLE CONTINUOUS
)
)
ALTER MINING STRUCTURE NestedStructure
ADD MINING MODEL nestedModel ( unitID , beginDate REGRESSOR, area , partSize REGRESSOR
,y2predict REGRESSOR PREDICT_ONLY
, logdata ([id] , unitID
, m1, m2
)
) USING Microsoft_Decision_Trees
/* version 1*/
insert into NestedStructure ( unitID, beginDate, area, partSize, y2predict
, logdata(skip,unitID, m1, m2))
openrowset('sqloledb', Server=myserver;Trusted_Connection=yes;,
'Shape {select * FROM mydb.dbo.unitInfo }
Append ( { select id, unitID, m1, m2 from mydb.dbo.unitLog }
Relate unitID to unitID ) as logdata ')
Parsing the query ...
OLE DB error: OLE DB or ODBC error: Syntax error or access violation; 42000.
Parsing complete
Where is the error?
/*version 2*/
CREATE MINING STRUCTURE NestedStructure1
( unitID LONG KEY, beginDate DATE CONTINUOUS, area TEXT DISCRETE
, partSize LONG CONTINUOUS, y2predict DOUBLE CONTINUOUS
, logdata table ( [id] LONG KEY, unitID LONG CONTINUOUS
, m1 DOUBLE CONTINUOUS, m2 DOUBLE CONTINUOUS
)
)
ALTER MINING STRUCTURE NestedStructure1
ADD MINING MODEL nestedModel1 ( unitID , beginDate REGRESSOR, area , partSize REGRESSOR
,y2predict REGRESSOR PREDICT_ONLY
, logdata ([id] , unitID
, m1, m2
)
) USING Microsoft_Decision_Trees
insert into mining structure NestedStructure1 ( unitID, beginDate, area, partSize, y2predict
, logdata(skip,unitID, m1, m2))
Shape {openquery(dsnDB,'select * FROM mydb.dbo.unitInfo') }
Append ( { openquery(dsnDB,'select id, unitID, m1, m2 from mydb.dbo.unitLog') }
Relate unitID to unitID ) as logdata
Parsing the query ...
Error (Data mining):
INSERT INTO error: The '[logdata].[id]' nested table key column is not bound to an input rowset column.
Parsing complete
Remark that combination logtime/unitID is the natural key in unitLog.
"ID" is the surrugate key.
What is wrong here...?
I am working on a report that has 3 bars per series. I would like to add some gapping or whitespace between each bar in each series. Also how do you deal with overlapping. I know it can be done in Excel, I can't find the property of how to do it in SSRS. Any assistance would be appreciated.
View 1 Replies View RelatedIt seems i face a problem with the Microsoft Decision Trees model when i have a predictable variable that is continuous.
I have created the whole model according to the AdventureWorks tutorial (and it informs me that the same procedure is followed with a continuous variable) and i have flagged the variable as continuous. Even though everything seems be going well, the results i get are not correct (after a cross check with another project already done and checked).
Is there something i am missing or i skipped while creating the model? Any suggestions that may help me are appreciated
Thank you in advance
I've got a dataset bound to a Table in my report. Running the report takes a good 15-20 seconds as there's a metric ton of data coming back...that part works great as is.
Now I need to be able to Nest some additional Detail Data inside the main row group footer for each row (or not, depending if a field != null). I pass the subreport a value from the row, and it displays the returned data.
Normally if I was doing this from scratch I'd just include the data in the stored proc results, however I'm not doing it from scratch and I have no idea how to get this done so it's not taking 5 minutes to show the report
The "detail" stored proc might not even return data, it only really ever has 30-100 records. It seems almost a shame to keep requerying to check for results for all XThousand rows. Is there a way to maybe run it once and just keep re-filtering the data into the column I need?
ANY info would be great
Thanks
Steve
I have a decision tree mining model that has two nested tables and that amount of inputs processes in under a minute. When I add a third nested table in what I think is exactly the same way (I've tried two different ones), it never returns from counting the cases. Is there a limit on the number of nested tables one can have in a DT model? It does process the rest of the objects and measure groups but can never seem to return from counting cases, perpetually showing "Counting Cases 0".
I should probably add that the only way to stop it from processing after it hangs for 5 mins or 5 hours is to stop and start the service. After I remove a nested table and replace it with one of the new ones, it flies right through again. Something seems magical about the third nested table.
Thanks!
Brian
Is there a way to change the width of the bars in a bar chart?
I know that there is an option to 'Plot the data as line', but for some reason this is greyed out.
Any ideas on both?
Can I add borders to my bars in the column chart? My bars don't appear to have any border, and I can't see a place to set one. I am using SSRS Express.
Thanks!
Michael
I have a database available and it is in live production.
I want to show only three tables in the front end. asp.net application in dropdown menu. I checked the internet and found only query for seeing all the tables from the DB.
Hi,
I am trying to revamp our product database with a view to making it search-optmised and would like some guidance (or confirmation of method, if you will!!). We currently use a three table structure (Product, Brand, Cat(egory)) along the lines of :
create table product
(prod_id int not null,
brand_id int not null,
cat_id int not null,
other stuff e.g. tech. specs, displayed text on web page, etc....
)
with corresponding brand_id and cat_id in the other tables. While this seems relationally sound I see it as being inefficient for searching, particularly after reading the theory behind nested sets.
A new function I am building will enable users to drill down through the product list or runs searches against all or part of the db :
e.g. all products from one category,
all products fitting certain search criteria,
products from several selected brands fitting certain criteria,
and any combination of the above you can think of!
The problem is, not all products have the same criteria list (in fact I would be surprised if any did) and may also be of more than one category (a digital camera with movie mode might easily fit into the digital camcorder search). I think I am correct in that a nested set would make the structure fit the requirement - things like criteria, displayable text, etc. could be nodes in their own right and each logical level might have its own criteria. For example, if a category is selected then certain text must be displayed and could list further categories or products. The next level down would then require its own displayable text - I am mainly thinking about SEO tags here. Also, I am not precious about retaining the current table structure and would like an open ended solution where I can add further data/functionality in a dynamic fashion, which nested sets seem to embody.
Does this make sense to anybody coz I think I've confused myself even more!!
Thanks in advance,
G