How to perform hyper-paramter tunning for SVC?

Question

I am trying to perform hyper-parameter tuning of my model but this error keeps showing

error :  Invalid parameter svc_c for estimator SVC(). Check the list of available parameters with `estimator.get_params().keys()

I am using the following code :

param_grid = {'svc_c': [5, 10, 100], 
              'svc_gamma': [1,0.1,0.01,0.001],
              'svc_dgree': [1,2,3,4,5,6],
              'svc_kernel': ['rbf']}
grid = GridSearchCV(SVC(),param_grid,refit=True,verbose=3)
grid.fit(x_train_poly,y_train)

Asked By: Mohanad Anas Taifour

||

Source

Answer 1

you need to use the correct key for the dictionary param_grid.
kernel , C , gamma , degree and … (see doc)

try this:

param_grid = {'kernel': ('linear', 'rbf','poly') , 
              'C':[5, 10, 100],
              'gamma': [1,0.1,0.01,0.001], 
              'degree' : [1,2,3,4,5,6]}

grid = GridSearchCV(SVC() , param_grid , refit=True , verbose=3)
grid.fit(x_train_poly,y_train)

Answered By: I'mahdi

Answer 2

As the error message states, you are setting invalid parameter names for each hyper-parameter. In this stackoverflow question, a way of showing a list of available hyper-parameters for a given estimator is shown. Then, I’d suggest you to change your code to this:

param_grid = {'C': [5, 10, 100], 
              'gamma': [1,0.1,0.01,0.001],
              'degree': [1,2,3,4,5,6],
              'kernel': ['rbf']}

Please, check if those hyper-parameters are actually included in the list that
estimator.get_params().keys() returns.

Answered By: MariCruzR

How to perform hyper-paramter tunning for SVC?

Question:

Answers: