Comparing logistic regression and SVM

Python'da Lineer Sınıflandırıcılar

Michael (Mike) Gelbart

Instructor, The University of British Columbia

Logistic regression:

Is a linear classifier
Can use with kernels, but slow
Outputs meaningful probabilities
Can be extended to multi-class
All data points affect fit
L2 or L1 regularization

Support vector machine (SVM):

Is a linear classifier
Can use with kernels, and fast
Does not naturally output probabilities
Can be extended to multi-class
Only "support vectors" affect fit
Conventionally just L2 regularization

Use in scikit-learn

Logistic regression in sklearn:

linear_model.LogisticRegression

Key hyperparameters in sklearn:

C (inverse regularization strength)
penalty (type of regularization)
multi_class (type of multi-class)

SVM in sklearn:

svm.LinearSVC and svm.SVC

Use in scikit-learn (cont.)

Key hyperparameters in sklearn:

C (inverse regularization strength)
kernel (type of kernel)
gamma (inverse RBF smoothness)

SGDClassifier

SGDClassifier: scales well to large datasets

from sklearn.linear_model import SGDClassifier

logreg = SGDClassifier(loss='log_loss')

linsvm = SGDClassifier(loss='hinge')

SGDClassifier hyperparameter alpha is like 1/C

Let's practice!

Python'da Lineer Sınıflandırıcılar

Preparing Video For Download...