K Nearest Neighbor (Distance Function)

Classifies a set of test data based on the k Nearest Neighbor algorithm using the training data.

Note that for the Euclidean distance on numeric columns the other K Nearest Neighbor node performs better as it uses an efficient index structure. The implementation of this node performs an exhaustive search of all points to all potential neighbors and is therefore suited for small to medium data sets only.

Options

Column with class labels: Select the column to be used as classification attribute. This column must contain nominal values.
Number of neighbors to consider (k): The number of nearest neighbors used to classify a new instance. An odd number is recommended to avoid ties.
Weight neighbors by distance: If enabled, the distance of each neighbor to the query pattern influences its weight in the classification. Closer neighbors have greater influence on the result. Note: Only k neighbors are considered, regardless of weighting.
Output class probabilities: If enabled, additional columns containing the class probabilities for each predicted class will be appended to the output.

Input Ports

: Input port for the training data
: Input port for the test data
: The distance function to use.

Output Ports

: Output data with class labels

Popular Predecessors

Popular Successors

Views

This node has no views

Workflows

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.

Installation

To use this node in KNIME, install the extension KNIME Distance Matrix from the below update site following our NodePit Product and Node Installation Guide:

v5.11

A zipped version of the software site can be downloaded here.

Plugin provider: KNIME AG, Zurich, Switzerland

Plugin version: 5.11.0.v202602191530

On NodePit since: 2026-03-10

Last update: 2026-03-11

Tags: Modern UI

KNIME versions: Since v3.7

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

Try NodePit Runner!