Support Vector Regression
Support Vector Regression(SVR) is a supervised learning algorithm that is based on Support Vector Machines(SVM). SVM uses support vectors or margin of tolerance to identify the categories in Classification problems called Support vector Classifiers and to predict continuous features in Regression problems called Support Vector Regressors.
For deeper understanding behind the mathematics of Support Vector Machines, use the following resources:
- Support Vector Machines
- An Introduction To Support Vector Machines And Other Kernel-Based Learning Methods
In this practice session, we will learn to code Support Vector Regression.
We will perform the following steps to build a simple Support Vector Regressor using the Beer dataset from How To Choose The Perfect Beer Hackathon.
Step 1. Data Preprocessing
- Importing the libraries.
- Importing the data set.
- Dealing with categorical data.
- Classifying dependent and independent variables.
- Creating training and test sets.
Step 2. Support Vector Regression
- Create a Support vector Regressor.
- Training the regressor with training data.
- predicting the salary for a test set.
- Calculating the score from Root Mean Log Squared Error.
Click on Start/Continue Hackathon to go to the practice page.