Random Forest Learner

Learns a random forest*, which consists of a chosen number of decision trees. Each of the decision tree models is built with a different set of rows (records) and for each split within a tree a randomly chosen set of columns (describing attributes) is used. The row sets for each decision tree are created by bootstrapping and have the same size as the original input table. The attribute set for an individual split in a decision tree is determined by randomly selecting sqrt(m) attributes from the available attributes where m is the total number of learning columns. The attributes can also be provided as bit (fingerprint), byte, or double vector. The output model describes a random forest and is applied in the corresponding predictor node.

This node provides a subset of the functionality of the Tree Ensemble Learner corresponding to a random forest. If you need additional functionality please check out the Tree Ensemble Learner .

Experiments have shown the results on different datasets are very similar to the random forest implementation available in R .

The decision tree construction takes place in main memory (all data and all models are kept in memory).

The missing value handling corresponds to the method described here . The basic idea is that for each split to try to send the missing values in every possible direction; the one yielding the best results (i.e. largest gain) is then used. If no missing values are present during training, the direction of the split that the most records are following is chosen as the direction for missing values during testing.

Nominal columns are split in a binary manner. The determination of the split depends on the kind of problem:

• For two-class classification problems the method described in section 9.4 of "Classification and Regression Trees" by Breiman et al. (1984) is used.
• For multi-class classification problems the method described in "Partitioning Nominal Attributes in Decision Trees" by Coppersmith et al. (1999) is used.

(*) RANDOM FORESTS is a registered trademark of Minitab, LLC and is used with Minitab’s permission.

Input ports

1. Type: Table
   Input Data
   The data to be learned from. They must contain at least one nominal target column and either a fingerprint (bit-vector/byte-vector) column or another numeric or nominal column.

Output ports

1. Type: Table
   Out-of-bag Predictions
   The input data with the out-of-bag predictions, i.e. for each input row this is the majority vote of all models that did not use the row during their training. The appended columns are equivalent to the columns appended by the corresponding predictor node. There is one additional column model count , which contains the number of models used for the voting (number of models not using the row throughout learning.) The out-of-bag predictions can be used to get an estimate of the generalization error of the random forest by feeding them into the Scorer node.
2. Type: Table
   Attribute Statistics
   A statistics table on the attributes used in the different trees. Each row represents one training attribute with these statistics: #splits (level x) as the number of models, which use the attribute as split on level x (with level 0 as root split); #candidates (level x) is the number of times an attribute was in the attribute sample for level x (in a random forest setup these samples differ from node to node). If no attribute sampling is used #candidates is the number of models. Note, these numbers are uncorrected, i.e. if an attribute is selected on level 0 but is also in the candidate set of level 1 (but will not be split on level 1 because it has been split one level up), the #candidate number will still count the attribute as candidate.
3. Type: Tree Ensembles
   Random Forest Model
   The trained model.