The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
used multiple methods
Contributor I
Dear,
I want to apply multiple methods to run a model; I want to apply Self Organizing Map (SOM), Spatial Temporal-Density-Based Spatial Clustering of Applications with Noise (ST-DBSCAN), and Local Interpretable Model-Agnostic Explanations (LIME).
Should I put all my variables in one Excel file or I have to use "Joint" to connect all my tables?
I want to apply multiple methods to run a model; I want to apply Self Organizing Map (SOM), Spatial Temporal-Density-Based Spatial Clustering of Applications with Noise (ST-DBSCAN), and Local Interpretable Model-Agnostic Explanations (LIME).
Should I put all my variables in one Excel file or I have to use "Joint" to connect all my tables?
1
Best Answers
-
kayman
Member Posts: 662 
Unicorn
For 1 : It's a wide question, but basically you would generate your models and then you could use one of the ensemble operators to either vote or boost etc. Or you could also group the models (group model operator). Start with looking for ensemble in the operator search box, and look at the examples provided.
For 2 : Do you mean attributes (like records) or variables (like parameters)?
If you talk about attributes and you have a single excel you can use this as source indeed and then start generating your models. If they are in different tables you can use the database operators to create your recordset on the fly and you do not need to convert it to excel first. It's in the end just what would work best for you. There are quite a few good training videos on https://academy.rapidminer.com/learning-paths/get-started-with-rapidminer-and-machine-learning -> drill down to data access and preparation7 -
BalazsBarany
Administrator, Moderator, Employee-RapidMiner, RapidMiner Certified Analyst, RapidMiner Certified Expert Posts: 955 Unicorn
Hi @asiddiq,
these models are used in different phases of the analysis. E. g. LIME is used on the output of other predictive models (i.e. in a supervised setting). DBSCAN is a clustering algorithm, used as an unsupervised method.
So you need to be clear on what you want to do and build your process step by step with the right operators appropriate for the analysis step you're doing.
To help you here, we would really need to know what the purpose of your analysis is. What problem are you trying to solve? How are your data looking like? Do you have a target variable (label)? Is it classification or regression? What are you hoping to achieve with the SOM? Etc.
Regards,
Balázs8 -
BalazsBarany
Administrator, Moderator, Employee-RapidMiner, RapidMiner Certified Analyst, RapidMiner Certified Expert Posts: 955 Unicorn
Hi @asiddiq,
this sounds interesting. I guess you'll first find a way to join together the datasets to one, possibly using geocoordinates.
When you built clusters and analyzed the data, you could have some hypotheses. Then you'll find a target attribute (label) (possibly the ratio or the number of dengue fever cases) and create models to predict it for other data. (E. g. districts you haven't been looking at.) This will enable the usage of LIME.
Regards,
Balázs6
Answers
1. how I use multiple methods (SOM), (ST-DBSCAN), and (LIME)?
2. Should I make all my variables in one Excel file or no needs?
I want to build a model that predicts the Dengue fever transmission. I have the following tables:
1. Dengue fever patients data.
2. Weather data.
3. Satellite images for the target location.
4. Population Data.
I want to (custering+find missing) data using these algorithms together ((SOM)+(ST-DBSCAN)), then I want to use (LIME) method for the output to explain the results.