Decision Tree to Ruleset

KNIME Java Snippet Nodes version 3.7.1.v201901281154 by KNIME AG, Zurich, Switzerland

Converts (a single) decision tree model to PMML RuleSet model and also to a table containing the rules in a textual form. The resulting rules are independent of each other, the order of rules is not specified, can be changed. Missing value strategies are ignored, it will always evaluate to missing value.

Options

Split rules to condition and outcome columns

When checked, two columns will be created for the rules, Condition and Outcome, otherwise the rules will reside in a single column, Rule.

Add confidence and weight columns

From PMML the confidence and weight attributes are extracted to columns. (It will create columns with missing values.)

Add Record count and Number of correct statistics columns

In PMML, the recordCount and the nbCorrect attributes provide statistics about the input (training/test/validation) data, with this option, this information can be extracted to the columns: Record count and Number of correct

Use additional parentheses to document precedence rules

If checked the output will contain additional parenthesis around rule parts to clearly document precedence. For instance, NOT is a stronger operator than AND than OR - using parenthesis improves readability. Checking this option does not change any of the rule logic.

Provide score distibution record count in PMML

PMML will store the information obtained from the rules on record counts of score distribution (how many times were the different values were present in the training data, not necessarily integer)

Provide score distibution record count in table with column name prefix

Information about the record count of score distribution is saved to the table with the specified prefix.

Provide score distibution probability in PMML

PMML will store the information obtained from the rules on probabilities of score distribution (in the training data what was the probability of certain values for that decision tree leaf)

Provide score distibution probability in table with column name prefix

Information about the probabilities of score distribution is saved to the table with the specified prefix

Input Ports

A PMML Decision Tree model.

Output Ports

The decision tree model represented as PMML RuleSets (with firstHit rule selection method).

The table contains the rules' text (in single (Rule) or two columns (Condition, Outcome), the rule Confidence and Weight information and optionally the Record count (for how many rows did the ruleset matched when created) and Number of correct values where the outcome of the rule matched the expected label when the model was created.

Best Friends (Incoming)

• Decision Tree Learner (94 %) Learner
• PMML Reader (1 %) Source
• Simple Regression Tree to PMML (1 %) Other
• Decision Tree to Ruleset (< 1 %) Manipulator
• PMML Reader (< 1 %) SourceDeprecated
• Naive Bayes Learner (< 1 %) LearnerDeprecated
• Scorer (< 1 %) Other
• Rule-based Row Filter (< 1 %) ManipulatorStreamable
• Ruleset Editor (< 1 %) LearnerStreamable
• k-Means (< 1 %) Learner
• Decision Tree To Image (< 1 %) Manipulator
• Table to PMML Ensemble (< 1 %) Other
• Cell To PMML (< 1 %) Other
• Show all 13 recommendations

Best Friends (Outgoing)

• Decision Tree Predictor (18 %) Predictor
• Ruleset Predictor (16 %) PredictorStreamable
• Math Formula (10 %) ManipulatorStreamable
• Decision Tree To Image (7 %) Manipulator
• Rule Viewer (4 %) Visualizer
• Ruleset to Table (4 %) Manipulator
• Scorer (3 %) Other
• Ruleset Editor (3 %) LearnerStreamable
• Excel Writer (XLS) (3 %) Sink
• PMML Writer (2 %) Sink
• XLS Writer (2 %) SinkDeprecated
• Data to Report (1 %) Other
• CSV Writer (1 %) SinkStreamable
• Association Rule Learner (1 %) Learner
• Tree Ensemble Learner (1 %) LearnerDeprecated
• Rule-based Row Filter (1 %) ManipulatorStreamable
• Decision Tree to Ruleset (1 %) Manipulator
• Rule Engine (Dictionary) (1 %) PredictorStreamable
• ROC Curve (1 %) Visualizer
• Interactive Table (1 %) Visualizer
• InformationGainCalculator (1 %) Manipulator
• Java Snippet (< 1 %) ManipulatorStreamable
• Random Forest Learner (< 1 %) LearnerDeprecated
• Simple Regression Tree Learner (< 1 %) Learner
• Cell Splitter (< 1 %) ManipulatorDeprecated
• Column Filter (< 1 %) ManipulatorStreamable
• Row Splitter (< 1 %) ManipulatorStreamable
• Joiner (< 1 %) Manipulator
• Low Variance Filter (< 1 %) Manipulator
• RowID (< 1 %) ManipulatorStreamable
• String Manipulation (< 1 %) ManipulatorStreamable
• Value Counter (< 1 %) Other
• Rule Engine (< 1 %) PredictorStreamable
• Statistics (< 1 %) Visualizer
• Pie chart (< 1 %) Visualizer
• PMML to SQL (< 1 %) Other
• Table View (JavaScript) (< 1 %) Visualizer
• Python Learner (< 1 %) LearnerDeprecated
• RDKit Interactive Table (< 1 %) Visualizer
• Image Column Writer (< 1 %) Sink
• Database Writer (< 1 %) SinkStreamable
• Table Writer (< 1 %) Sink
• Fuzzy Rule Learner (< 1 %) Learner
• Hierarchical Clustering (< 1 %) Learner
• Cross Joiner (< 1 %) ManipulatorStreamable
• CAIM Binner (< 1 %) Manipulator
• Row Filter (< 1 %) ManipulatorStreamable
• Partitioning (< 1 %) Manipulator
• Conditional Box Plot (< 1 %) Visualizer
• Table to PDF (< 1 %) Visualizer
• J48 (3.7) (< 1 %) 
• Show all 51 recommendations

Installation

To use this node in KNIME, install KNIME Java Snippet Nodes from the following update site: