Learns an ensemble of decision trees (such as random forest* variants). Typically, each tree is built with a different set of rows (records) and/or columns (attributes). See the options for Data Sampling and Attribute Sampling for more details. The attributes can also be provided as bit (fingerprint), byte, or double vector. The output model describes an ensemble of decision tree models and is applied in the corresponding predictor node using the selected aggregation mode to aggregate the votes of the individual decision trees.
The following configuration settings learn a model that is similar to the random forest™ classifier described by Leo Breiman and Adele Cutler:
- Tree Options - Split Criterion: Gini Index
- Tree Options - Limit number of levels (tree depth): unlimited
- Tree Options - Minimum node size: unlimited
- Ensemble Configuration - Number of models: Arbitrary (arguably, random forest does not overfit)
- Ensemble Configuration - Data Sampling: Use all rows (fraction = 1) but choose sampling with replacement (bootstrapping)
- Ensemble Configuration - Attribute Sampling: Sample using a different set of attributes for each tree node split; usually square root of number of attributes - but this can vary
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 and send the missing values in every possible direction and 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.
The tree ensemble nodes now also support binary splits for nominal columns. Depending on the kind of problem (two- or multi-class), different algorithms are implemented to enable the efficient calculation of splits.
- 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.
Options
Attribute Selection
Tree Options
Ensemble Configuration
Input Ports
- The data to be learned from. It must contain at least one nominal target column and either a fingerprint (bit/byte/double vector) column or another numeric or nominal column.
Output Ports
- The input data with the out-of-bag predictions, i.e. for each input row the majority vote of all models that did not use the row during their training. If the entire data was used to train the individual models then this output will contain the input data with missing values in the prediction columns. 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 voting (number of models not using the row throughout the learning.) The out-of-bag predictions can be used to get an estimate of the generalization error of the tree ensemble by feeding them into the Scorer node.
- 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 is not split on level 1 because it has been split one level up), the #candidate number still counts the attribute as a candidate.
- The trained model.
Popular Predecessors
- Partitioning9 %
CSV Reader4 %Table Row to Variable3 %- Scorer3 %
- File Reader2 %
Excel Reader (XLS)2 %- Tree Ensemble Learner2 %
- Denormalizer2 %
- Value Counter2 %
- Statistics2 %
- Math Formula (Variable)2 %
- Reference Column Filter1 %
- Low Variance Filter1 %
- Bootstrap Sampling1 %
- Parallel Chunk Start1 %
- Joiner1 %
- Concatenate1 %
- Column Appender1 %
Table Row To Variable Loop Start1 %- X-Partitioner1 %
- SMOTE1 %
- Missing Value1 %
Row Splitter (deprecated)1 %- Column Filter Widget1 %
- Column Filter< 1 %
- Normalizer< 1 %
- Number to String< 1 %
- One to Many< 1 %
- Correlation Filter< 1 %
Row Filter (deprecated)< 1 %- IF Switch< 1 %
- Table Row to Variable< 1 %
- CSV Reader< 1 %
- String to Number< 1 %
- Excel Reader< 1 %
Scorer< 1 %- Domain Calculator< 1 %
- Equal Size Sampling< 1 %
Column Rename< 1 %- Row Sampling< 1 %
- Color Manager< 1 %
- Parameter Optimization Loop Start< 1 %
- Feature Selection Loop Start (1:1)< 1 %
- Tree Ensemble Predictor< 1 %
- Random Forest Learner< 1 %
- Random Forest Predictor< 1 %
- Feature Selection Filter< 1 %
- String Manipulation< 1 %
- Rule Engine Variable< 1 %
- Fingerprint Bayesian Learner< 1 %
- Chunk Loop Start< 1 %
- Tree Ensemble Model Extract< 1 %
- Missing Value (Apply)< 1 %
- Data Generator< 1 %
- Scorer (JavaScript)< 1 %
- Feature Selection Loop End< 1 %
Counting Loop Start< 1 %- Naive Bayes Learner< 1 %
- Hierarchical Cluster Assigner (local)< 1 %
- Decision Tree Predictor< 1 %
- Tree Ensemble Learner (Regression)< 1 %
- Similarity Search< 1 %
- Tree Ensemble Predictor (Regression)< 1 %
Cell Replacer< 1 %- Denormalizer (PMML)< 1 %
Table Row to Variable< 1 %File Reader< 1 %Table Reader< 1 %- k-Means< 1 %
- Linear Regression Learner< 1 %
- Logistic Regression Learner< 1 %
- Random Forest Predictor (Regression)< 1 %
- Numeric Binner< 1 %
String To Number< 1 %- Constant Value Column Filter< 1 %
- Reference Row Splitter< 1 %
- Boosting Learner Loop End< 1 %
- Table View (JavaScript)< 1 %
- ROC Curve (JavaScript)< 1 %
- Test Data Generator< 1 %
- Group Loop Start< 1 %
- Auto-Binner< 1 %
- Numeric Outliers< 1 %
Active Learn Loop Start< 1 %Table Column to Variable< 1 %- Feature Selection Loop Start (2:2)< 1 %
PCA Apply< 1 %Number To String< 1 %Joiner< 1 %- String Replacer< 1 %
- Target Shuffling< 1 %
Color Appender< 1 %- Math Formula< 1 %
- Integer Input (legacy)< 1 %
- R to Table< 1 %
- Fingerprint FOLD< 1 %
- Outlier Removal< 1 %
- Create Collection Column< 1 %
- Split Collection Column< 1 %
- ARFF Reader< 1 %
Database Reader< 1 %- Table Creator< 1 %
- Java Snippet< 1 %
Loop End (2 ports)< 1 %- X-Aggregator< 1 %
Naive Bayes Predictor< 1 %- Fuzzy c-Means< 1 %
PCA< 1 %- Regression Predictor< 1 %
Numeric Scorer< 1 %- PMML Gradient Boosted Trees Predictor< 1 %
- Random Forest Learner (Regression)< 1 %
- Line Chopper< 1 %
Column Appender< 1 %- Double to Integer< 1 %
- Duplicate Row Filter< 1 %
- Missing Value Column Filter< 1 %
- Nominal Value Row Filter< 1 %
- Nominal Value Row Splitter< 1 %
- Reference Row Filter< 1 %
- GroupBy< 1 %
- Number to String (PMML)< 1 %
- XML to PMML< 1 %
- Number Rounder< 1 %
- Shuffle< 1 %
- Rule-based Row Splitter< 1 %
- ROC Curve (legacy)< 1 %
- Distance Matrix Calculate< 1 %
- Boosting Learner Loop Start< 1 %
- PMML Ensemble Predictor< 1 %
- H2O to Table< 1 %
Excel Reader (XLS)< 1 %- Decision Tree View (JavaScript)< 1 %
- Parameter Optimization Loop End< 1 %
Python Script (2⇒2)< 1 %- Python Source (legacy)< 1 %
- Date&Time-based Row Filter< 1 %
- Fingerprints< 1 %
- Conformal Calibration Loop Start< 1 %
- File Reader (Complex Format)< 1 %
- Line Reader< 1 %
Interval Loop Start< 1 %- Table Row to Variable Loop Start< 1 %
- Decision Tree Learner< 1 %
- SVM Predictor< 1 %
- Gradient Boosted Trees Predictor< 1 %
- Cell Splitter< 1 %
- Column Auto Type Cast< 1 %
- Row Filter (Labs)< 1 %
- Table Manipulator< 1 %
- Rule-based Row Filter< 1 %
- Rule Engine< 1 %
- Decision Tree to Ruleset< 1 %
- Rank Correlation< 1 %
- Numeric Outliers (Apply)< 1 %
- Merge Variables< 1 %
- Stresser< 1 %
- Column Expressions< 1 %
- Column Selection Configuration< 1 %
- Column Selection Widget< 1 %
- RDKit Descriptor Calculation< 1 %
Views
- Tree Views
- A decision tree viewer for all the trained models. Use the spinner to iterate through the different models.
Workflows
_Learner_FlowKNIME Hub- 01_Guided_Analytics_for_ML_AutomationKNIME Hub
- 01_Guided_Analytics_for_ML_AutomationKNIME Hub
- 01_Guided_Analytics_for_ML_AutomationKNIME Hub
- 01_Guided_Analytics_for_ML_AutomationKNIME Hub
- Show all 72 workflows
Links
- No links available
Developers
You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.