-
Instead of modifying pipeline.json to add pipeline rank, a separate pipeline rank file should be generated in the pipelines_ranked directory.
https://gitlab.com/datadrivendiscovery/metalearning/iss…
-
Continuing on #451, since `time_left_for_this_task` is not a very sensible budget in our application scenario due to differences of hardware and working load, we decide to use `runcount_limit`, follo…
-
Hi,
I'm trying to run your code with the SVM-CS head. I get an error in line 296 of the "classification_heads.py" file. The error is as follows:
File "/home/user/Desktop/MetaLearning/models/cl…
-
I'm trying to figure out how to keep MAML (model agnostic metalearning) working with all the architectural changes we're making. My changes in #1567 have broken it. I've verified that this is caused…
-
I am trying to new AutoML in order to automate ML pipeline and I realized that AutoML seems match what I need. So i tried the following sample code to check how can I use it. However, After executing …
-
Hi!
Since meta_learning is proved to be very effective,I have doubts about how to set this parameter. Is the default value 25 the best value verified by experiments? Or have you ever perform any expe…
-
```
pipe = autosklearn.classification.AutoSklearnClassifier()
pipe.fit(clf_x, labels)
probs = pipe.predict_proba(clf_x) # Error happens here
roc_auc = metrics.roc_auc_score(labels, p…
-
Hi,
I was reading the result from cv_results_ and trying to understand
1. If the holdout resampling strategy is used, how are the mean_test_score and mean_fit_time computed since holdout method …
-
@peastman
I saw that you implemented the MAML code, thus I thought I would ask you as you are most familiar with it.
I am not sure if I misunderstand something about your code, or if it is a mis…
-
develop a recommender that utilizes metafeature data to learn a mapping from dataset properties to ideal ML + parameters.