Applying an online logistic regression model using Apache Mahout

In this recipe, we will demonstrate how you can apply an online logistic regression model on unseen, unlabeled test data using Apache Mahout. Note that this recipe is very closely related to the previous recipe and requires you to build a model using training data. This requirement is demonstrated in the previous recipe.

Getting ready

1. After completing the previous recipe, go to the project folder that you created, and go inside the directory named model that you created in the last recipe. You should see a model file there.

2. Next, create a test file. Go to the data folder that you created in your project folder in the last recipe. Create a test file named weather.numeric.test.csv with the following data:

           outlook,temperature,humidity,windy,play 
           overcast,90,80,TRUE,yes 
           overcast,95,88,FALSE,yes 
           rainy,67,78,TRUE,no 
           rainy,90,97,FALSE,no 
           sunny,50,67,FALSE,yes...