SVM

Difference between logistic regression and SVM

Decision boundary when we classify using logistic regression-

Decision boundary when we classify using SVM-

As it can be observed, SVM tries to maintain a ‘gap’ on either side of the decision boundary. This proves helpful when we encounter new data.

With new data-

Logistic regression performs poorly (new red circle is classified as blue) -

Whereas SVM can classify it correctly (the new red circle is classified correctly in red side)-

Implementing SVM classifier using Scikit-learn:

from sklearn import svm
X = [[1, 2], [3, 4]] #Training Samples
y = [1, 2] #Class labels
model = svm.SVC() #Making a support vector classifier model
model.fit(X, y) #Fitting the data

clf.predict([[2, 3]]) #After fitting, new data can be classified by using predict()