Hope you are all well and safe.
I have an issue with the decision tree. I will appreciate it if someone could provide help.
I have two datasets, and I used the first one as the training set( training, validation and test). And I have no idea about predicting the second dataset by using the training set.
I will appreciate it if someone could provide advice for solving my problem.
It sounds like you may be asking about deployment (using a trained model on new data). There is a blog article for this explaining how to write your model in order to use on new data.
After training your can then use the trained model connect it to the predictor node and use the test (new unseen data) as input for the predictor node.
Thank you and that’s really helpful. Do you think the test database needs to have the same structure as the training dataset?
Thank you. Does the test database need to have the same structure as the training dataset? Do I need to add a specific column to get the required test results?
yes the structure (aka the features you used for training the model) need to be in the test set as well (only the target which you like to predict will not be there of course). I you have preprocessed the data (scaling,…) then you also need to apply that on the test set before predicting.
hope that helps
This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.