Hosting sklearn - SVM Classifier on AWS Sagemaker

Question

I have a model running on my jupyter notebook instance with very basic SVM classifier

# Text lassifier - Algorithm - SVM
# fit the training dataset on the classifier
SVM = svm.SVC(C=1.0, kernel='linear', degree=3, gamma='auto',probability=True)
SVM.fit(Train_X_Tfidf,Train_Y)
# predict the labels on validation dataset
predictions_SVM = SVM.predict(Test_X_Tfidf)
# Use accuracy_score function to get the accuracy
print("SVM Accuracy Score -> ",accuracy_score(predictions_SVM, Test_Y)*100)

Use Case : Host the model on Sagemaker and create an endpoint.Use the end point via Lambda for text classification

I saw AWS has few posts on creating an endpoint E.g. https://docs.aws.amazon.com/sagemaker/latest/dg/ex1-train-model.html but majority of the content is not applicable to scikit-learn : SVM

Is there an another approach I should be looking at ?

Banjo Obayomi Banjo Obayomi · Accepted Answer · 2020-02-19T16:57:59

If your model is small enough, you can create a lambda function that loads the model and does predictions based on input passed in from user.

Hosting sklearn - SVM Classifier on AWS Sagemaker

1 Answers