I want to perform Association Rules on this dataset http://archive.ics.uci.edu/ml/machine-learning-databases/00222/. It's a dataset with customers and y is the result, if the campaign persuaded them to subscribe to a product or not.
and the rest that didn't fit in the first image
I added an ID column in the dataset so when I am running the Association Node it doesn't generate any rules. In Properties I have ID as id, y(which is the subscription result yes or no) as Target and everything else as Inputs. Role is set to Transaction. I tried with 2 and 4 Association Items.
But it gives me: There are no rules that match the specified constraints.
Any idea what should I change to have some rules?
Thanks and have a happy new year.
"Everything else as inputs" does not sound like you want an association rule algorithm. The Enterprise Miner node expects data in a format like this:
id item
1 Apple
1 Orange
1 Pear
2 Banana
It does not seem like your data is in that format; hence, you are not getting any rules.
Related
I need some sort of guidance on what would be the best way of accomplishing such kind of task in SAS EG environment (on a 9.4 server). Let's say I have table named ITEM_EVALUATION like in the following example. The missing evaluations (rows: 4,5 and 6) should be filled in by the user. Although there may be better solutions, I would prefer if SAS iterated over the missing rows, give the user the row information (item) and take the input (evaluation) then update the table by that input.
Since this task is going to be a part of another sas eg project (egp), I need to do it within this project, so please advise...
ITEM_EVALUATION.sas7bdat
ROW
ITEM
EVALUATION
1
car
owned
2
house
rent
3
cat
none
4
phone
5
job
6
vacation
7
Make sure your dataset occurs in your project. (Drag it to a flow, for instance.)
Ask your user to double click any empty cell in the table and accept to go to edit mode.
If the empty cells are rare, the user can enter a filter missing(ITEM) or missing(EVALUATION) on top of the data to find them.
If that is too complex for your user, Enterprise Guide is not the tool for this person.
This might be a basic question, but I'm struggling with it:
I've got a dataset that includes a long list of accounts. Those accounts are all tied to premises. Multiple accounts can exist at the same premise (many to one). No account exists at more than one premise.
I'd like to search by account and return details at its premise level. Using the simple dataset below, for example, how can the user enter an account as a search term but return all the names associated with that premise?
I realize that one could just search by premise, but the end-user for this case will not (and cannot) have the premise number.
Account
Premise
Active?
Name
45623
3216
Y
Jim
92734
3216
N
Sue
37528
7645
Y
John
13465
7645
N
Will
66572
1847
Y
Erin
Set the relationship to Bidirectional cross-filtering for filters to propagate from the "many side of the relationship to the "one" side.
I am pretty new to RLS and have been trying to implement it in a certain way.
My table above is a sample. I am trying to create RLS here based on the levels. Normally I can create 3 roles for 3 levels where,
Level 1 is regular employees
Level 2 is supervisor of employees
Level 3 is the manager/head of the building (based on the BuildingID)
I am trying to create RLS where the manager (Level 3) will be able to see the data for people below them by filtering through. For example when the manager of BuildingID='233' logs in, they can filter through the report to see people they are assigned to.
It would be clickable in the filter pane. However, I am more used to on doing DAX calculations when the manager ID is on a different column and this seems to be a new scenario. I have tried a couple of methods and so far have not been successful. Any kind of help here would be much appreciated.
I could only advise you review something like this to see if you can use the comparable logic in your scenario https://radacad.com/dynamic-row-level-security-with-organizational-hierarchy-power-bi
I need your help.
I work for a survey company and I am responsible for creating its architecture and modeling a data warehouse that analyzes the results of an international survey (50 countries).
For the architecture, we decided to create a tabular model in PowerBI to analyze our data and to create our reports.
Here below is the model as I thought:
However, I have a design problem.
Since the survey is international, the wording of my dimensions differs from country to country.
My 1st question:
-Would it make more sense to create only one PowerBI embedded model for all countries or 50 PowerBI reports?
My 2nd question:
My model must be multilingual
With my 50 countries, I have several languages (5 languages) and for the same language, I have several variants.
The British English labels differ from the US English labels.
For example, for the Response dimension for France the IdReponse = 1 has the wording 'Vrai' while for the USA the wording is 'True' and for the Britain is 'OK'.
Do you know how to model multi language in a data warehouse?
About question #1 - It's always better, if there is only one model. It will be much easier to maintain. It isn't clear from your question will these 50 reports show the same data (excluding the internationalization of texts like Vrai/True/OK), or each report/country should show it's own subset of the data. In case all reports will show the same data, then definitely it will be better to make one common model and all report use it. You can do this with Power BI by making one "master" report and publishing it, and then the rest of your "per country" reports use it as a data source. And you will need separate reports per country, because you will need to translate the texts (column names, static texts, etc.).
About question #2 - You can create lookup tables in your model (maybe even in the database, it's up to you). The key value (1) will be linked to the key of the table, and there will be columns per language. Depending on the language of the current report, you will select the appropriate column (e.g. French, British, etc.) and even you can fallback to let's say US English, in case there is no translation entered for the current language (e.g. by making a computed column). It is also an option to make separate lookup table per language, but I think it will be more cumbersome to maintain this way.
About question #1: Yes you need only one data model.
About question #2: You Load a question in the language it is asked and the response you get as is in the response DIM. You should create a new column in your response DIM such as Clean_response where you transformed original response to a uniformed value. for example "Vrai", "OK", "True" has same meaning so you may chose to put "Yes" in the Clean_response column. You can also convert different variation of "No", "Nada", "noops", "nah" to a clean value of "No", but keep the original value too.
Labeling a column in the report should be handle in the report code. For example writing a report in French should use your dim column name "Question" and show it as "interroger" as a heading on the report.
I am querying Amazon's Product Advertising API for Instant Video (streaming) results. Everything is working fine -- except that there is some missing information:
Descriptions are not included in results. For example, on Amazon's website the movie "Food, Inc" (http://www.amazon.com/Food-Inc/dp/B002VRZEYM) has the description "An unflattering look inside America's corporate controlled food industry.". When queried via the API, however, no description is returned at all.
Titles of TV shows are not included in results. For example, if you search for the 2nd episode of season 1 of Arrested Development (called "Top Banana") on Amazon's website (http://www.amazon.com/gp/product/B000N2VRJ8), you will get the full name of the TV show, season #, episode #, and episode name. When queried by the API, however, only the episode name is returned.
Does anyone know of a solution to these problems? FYI, the nodeId I am using for my search is 2858778011.
In order to get more details, you'll need to set the ResponseGroup parameter in your request. See the ResponseGroup section of the ItemLookup documentation to see the different Response Groups that you can use.
For example, setting the ResponseGroup parameter to Large or Medium or Small or even ItemAttributes will give you the description:
An unflattering look inside America's corporate controlled food industry.
for Food, Inc (B002VRZEYM) and the Title:
Top Banana
for Arrested Development season 1 episode 2 (B000N2VRJ8).
I had the same problem, while trying to query the Amazon API for Prime Instant Video content. Although this question is kinda old, there are probably some people like me who are interested in a detailed answer, especially for the second part (2.).
Like Jonathan Spooner already said, you have to set a response group
that returns the data you're interested in. Official documentation: Response Groups - Product Advertising API.
In your case, I think, the ResponseGroup Small should do.
If you want to get the title of a TV show, which contains a certain episode, you have to set the response group RelatedItems in your request, too (you can set multiple response groups in one request). You will also have to name a RelationshipType, otherwise the request will fail. For Episode -- Season - Relationships you choose Episode.
With RelatedItems, the result will contain a node named <RelatedItems>. You will find the season item in there, which's title should be something like " Arrested Development - Season 1 [HD]".
Note: If you really just want the TV show title, you could either parse the season name for it or you could make another ItemLookup with the seasons ASIN: set the response group RelatedItems again, but this time with RelationshipType=Season. This will return Season - TV Series - Relationships. The related item will contain the TV Show in general. (But the title could have a suffix like [HD] anyway)
Here you have a list with all relationship types: Relationship Types - Product Advertising API