Comments (2)
As you have probably seen, the Domain
and Table
classes allow for multiple targets, but most widgets can't handle them. For this reason, even if the user constructs such data, e.g. in Select Columns, Orange shows a warning that this data won't be very useful.
The object that is output by Test and Score, Orange.evaluation.Results
has a 1d array for predictions (actually 2d, because these are predictions of all models that are being tested) and a 2d array for probabilities (that is, 3d, for all models). Supporting multiple targets would require adding another dimension, which would break all downstream widgets.
But the question is - what would you do with this? Even Test and Score would probably only show scores (ca, auc, prec, recall, ...) for a single output at a time. If you then want to analyze this in, say, the ROC widget, you would also analyze one output at a time.
The most doable solution, I think, is to modify the Test and Score widget as follows. When training, it would trains multi-output models. But then it would construct multiple instances of Orange.evaluation.Results
, one per each output. The widget would have an additional combo (which would be hidden for "normal" data, and shown only for multi-output models) in which the user would select a single output. The widget would show the scores for this output, and the widget would also only output the corresponding Result
object.
Alternatively, the widget could show scores for all target variables (e.g. multiple ca's at once), but the user would stil have to choose which results to output, so that the widget would output the same object as it does now.
Would this make sense?
from orange3.
Sorry for my late response. I understand, that not all widgets support multi target, but this does not matter. I modified the code already and introduced a new modelling type "multi_regression" in addition to "classification" and "regression". I use this indicator to introduce a special treatment in to build the proper ANN model, but my biggest problem at the moment is the handling of the results in the test and score widget, because I cannot fix a dimension issue. Maybe I can pass over my code to give me some hints. Also I found a bug in the way results are treated.
I will try to follow your hints in the Test&Score widget.
The main reason to make this extension is caused by the fact, that in industrial applications for process modelling MI-MO is my preferred architecture. I also plan to add a new explain model widget, which is based calculating the derivative of an ANN, which supports MI-SO and MI-MO models.
I am looking forward to your thoughts.
:-)
from orange3.
Related Issues (20)
- Datasets: output corresponding type HOT 1
- Installation via Miniconda fails on Ubuntu 23.10 HOT 7
- Sorting in Box Plot is not correct for non-ascii labels HOT 1
- Feature Statistics: legend for "Color", and "Selected Feature Statistics" output with richer data HOT 1
- Widget Predictions error HOT 2
- Datasets: combo for folder selection
- Problem installing Orange with Python 3.12 HOT 2
- A new Melt widget icon HOT 5
- Add Report capability for Orange-Spectroscopy Widgets HOT 1
- No internet connection problem with add-on manager HOT 13
- sklearn 1.1.3 can be upgraded?
- Report doesn't displayed and I can't download report HOT 3
- Aggregate Columns: silent fail on sparse
- Allow Neighbors to accept sparse data HOT 3
- Bugs in SOM
- Import Images Widget Info Typo HOT 1
- File with large string crashes Orange
- Error launching Orange in Anaconda: cannot import name 'astype_nansafe' from 'pandas HOT 2
- Cannot view tabs to load data or start working with orange after upgrading HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from orange3.