Database Reference
In-Depth Information
print "Decision Tree - Mean Squared Error: %2.4f" % mse_dt
print "Decision Tree - Mean Absolute Error: %2.4f" % mae_dt
print "Decision Tree - Root Mean Squared Log Error: %2.4f"
% rmsle_dt
You should see output similar to this:
Decision Tree - Mean Squared Error: 11560.7978
Decision Tree - Mean Absolute Error: 71.0969
Decision Tree - Root Mean Squared Log Error: 0.6259
Looking at the results, we can see that our initial guess about the decision tree model be-
ing the better performer is indeed true.
Note
The Kaggle competition leaderboard lists the Mean Value Benchmark score on the test set
at about 1.58. So, we see that our linear model performance is not much better. However,
the decision tree with default settings achieves a performance of 0.63.
The winning score at the time of writing this topic is listed as 0.29504.
