The data is the same as the data in the previous recipe, but we use Random Forest and the Multi metrics API to solve the classification problem:
- RandomForest.trainClassifier()
- MulticlassMetrics()
We have a lot of options with Random Forest Trees that we can adjust to get the right edges for classifying complex surfaces. Some of the parameters are listed here:
val numClasses = 2 val categoricalFeaturesInfo = Map[Int, Int]() val numTrees = 3 // Use more in practice. val featureSubsetStrategy = "auto" // Let the algorithm choose. val maxDepth = 4 val maxBins = 32
Noteworthy is the confusion matrix in this recipe. The confusion matrix is obtained via the MulticlassMetrics() API call. To interpret the preceding confusion metrics, ...
