CODEWITHSUNDEEP
pythonmachine-learningscikit-learnlibsvmoutliers
taga
taga

Reputation: 3895

Why am I getting `[LibSVM]` when im doing outlier detection with OneClassSVM

Im doing outlier detection with Python's Scikit-Learn lib. Im using OneClassSVM. I have a problem with that because when ever I run my code (I do not get error), it prints [LibSVM].

I do not know why am I getting this, I do not have print function anywhere in my code.

out_cls = [['One class SVM',OneClassSVM(cache_size=80, coef0=0.5, gamma ='auto', kernel = 'poly', random_state= None, shrinking=True, tol = 0.1, verbose = True, nu = 0.2)],          
           ['Isolation Forest', IsolationForest(behaviour='new', contamination='auto',max_features=4, max_samples=2, n_estimators= 90, random_state=1)]]

r = df
for out in out_cls:

    cls = out[1]
    model = cls.fit(x)
    prediction = model.predict(x)

   # print(model.best_params_)

    result = []
    for i in prediction:
        if i == -1:
            result.append('BOT')

        else:
            result.append('good')

    r[out[0]] = result

Upvotes: 0

Views: 234

Answers (1)

desertnaut
desertnaut

Reputation: 60370

All underlying SVM functionality in scikit-learn is actually based on LibSVM; from the docs of OneClassSVM:

The implementation is based on libsvm.

See also the numerous references of this in the source code.

This console output is just an artifact of setting verbose=True in the model definition; adapting the simple example from the docs:

from sklearn.svm import OneClassSVM
X=[[0], [0.44], [0.45], [0.46], [1]]
clf = OneClassSVM(gamma='auto', verbose=True)
clf.fit(X)

The display output is:

[LibSVM]

OneClassSVM(cache_size=200, coef0=0.0, degree=3, gamma='auto', kernel='rbf',
            max_iter=-1, nu=0.5, random_state=None, shrinking=True, tol=0.001,
            verbose=True)

Setting verbose=False dismisses the [LibSVM] indication, which, in any case, is not a problem, as it does not affect your code in any way.

Upvotes: 1

Related Questions