All Questions
6 questions
1vote
1answer
97views
Why is the optimal C chosen by GridSearchCV so small?
I'm trying to use GridSearchCV to select the optimal C value in this simple SVM problem with non-separable samples. The issue I'm having is that when I run the code the optimal C is chosen to be ...
- 13
3votes
1answer
4kviews
GridSearchCV results are different to directly applied default model (SVM)
I run a Support Vector Machines model on part of my train set with following result: ...
1vote
0answers
64views
AUC for basic models is higher than bagged models
Is correct to get a bit lower AUC with bagged algorithms than no bagged algorithms? The first figure shows the ROC with bagged algorithms and the second figure shows the ROC without bagging. The ...
- 111
1vote
1answer
1kviews
Using GridSearchCV for custom kernel SVM in scikit-learn
I would like to use scikit-learn's GridSearchCV() to do a grid search on custom parameters in a kernel I have specified. Specifically, the kernel is of the form <...
1vote
0answers
818views
GridSearchCV with SVM estimator AUC score not reproduced on SVM run
I've run GridSearchCV to determine 'best parameters' for a linear SVM, and then passed these [in a dictionary along with non-tuned parameters] into a new SVM. I've ...
- 111
6votes
3answers
4kviews
Linear kernel in SVM performing much worse than RBF or Poly
When trying to train a SVM on some Kaggle data, I have encountered a situation where the linear kernel fails to give any results. This doesn't make sense to me because the RBF kernel works just fine, ...
- 219
