Icon

Decision Tree Number min number of records per node

Decision Tree select minimun number of records per node
This workflow makes a plot based on "the minimun records per node" parameter that helps to define the size of a decisión tree and its accuracy errorAt the beggining the user can define a list of numbers that defines "the minimun records per node" and then executes a loop that collects the error rate, for thatparameter.The idea is to check in the scatter plot if there is an "optimal""the minimun records per node" parameter given the error decrease in the decision tree read datacolor by classuse decision tree to predict classesNode 89append color to test databuild decision treescore resultssplit training set from test dataEmpty tableSelect sequence of numbers"the minimun records per node"Node 116Node 117Node 118Node 119Node 120Node 121Node 122Node 123Node 124Node 126Node 127Node 128Node 129Node 131Node 132Under thisexample with 7 leavesthe error decrease is the highest Table Reader(deprecated) Color Manager Decision TreePredictor Decision Treeto Ruleset Color Appender DecisionTree Learner Scorer (deprecated) Partitioning Add Empty Rows Table Creator Inputs Counter Generation Group Loop Start Table Rowto Variable Column Filter Row Filter Extract TableDimension Row Filter Joiner RowID RowID Extract Variables(Data) Variable toTable Column Column Rename Loop End Math Formula Column Filter Scatter Plot This workflow makes a plot based on "the minimun records per node" parameter that helps to define the size of a decisión tree and its accuracy errorAt the beggining the user can define a list of numbers that defines "the minimun records per node" and then executes a loop that collects the error rate, for thatparameter.The idea is to check in the scatter plot if there is an "optimal""the minimun records per node" parameter given the error decrease in the decision tree read datacolor by classuse decision tree to predict classesNode 89append color to test databuild decision treescore resultssplit training set from test dataEmpty tableSelect sequence of numbers"the minimun records per node"Node 116Node 117Node 118Node 119Node 120Node 121Node 122Node 123Node 124Node 126Node 127Node 128Node 129Node 131Node 132Under thisexample with 7 leavesthe error decrease is the highestTable Reader(deprecated) Color Manager Decision TreePredictor Decision Treeto Ruleset Color Appender DecisionTree Learner Scorer (deprecated) Partitioning Add Empty Rows Table Creator Inputs Counter Generation Group Loop Start Table Rowto Variable Column Filter Row Filter Extract TableDimension Row Filter Joiner RowID RowID Extract Variables(Data) Variable toTable Column Column Rename Loop End Math Formula Column Filter Scatter Plot

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
On NodePit since: 2022-03-11
Last update: 2024-04-27
Created with KNIME version: v4.5.1
Tags: Decision Trees

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!