KNN Classifier Job Plugin

Plugin Name: KNNClassifierJobPlugin

This plugin runs a K-Nearest Neighbors Classification using the SciKit Learn library.

More information on this Classifier is available at http://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html

Note

Tags in the Example and Source TagSets SHOULD be the EXACT same length. Currently, features will be padded to the length of the longest Tag.

Launching a Job

Jobs are launched via the Plugin Job interface, by selecting “Launch Plugin Jobs” on the Project Files page.

Job Settings

Setting Name Description
name Not used internally. This is meant as a book-keeping item for later reference by the user.
n_neighbors Number of neighbors to use
weights

weight function used in prediction.

  • uniform

    uniform weights. All points in each neighborhood are weighted equally.

  • distance

    weight points by the inverse of their distance. Closer neighbors of a query point will have a greater influence than neighbors which are further away.
algorithm

Algorithm used to compute the nearest neighbors.

  • Auto

    Attempt to decide the most appropriate algorithm based on the data

  • Ball Tree

  • KD Tree

  • Brute Force
exampleTagSet The TagSet from which the Class Examples are loaded.
sourceTagSet Tags which will be classified.
destinationTagSet TagSet into which new Tags are created - these are copied from the sourceTagSet, with a new tagClass corresponding to the exampleTagSet examples.
Spectra Details
numFrequencyBands The number of bands (sections) in the spectra creation between minFrequency and maxFrequency.
numTimeFramesPerSecond The number of times per second in an audio file that a line of spectra is computed.
dampingRatio  
minFrequency The minimum frequency used for the spectra creation.
maxFrequency The maximum frequency used for the spectra creation.

Priority

This will set the Job priority to ‘0’, the default priority.