run.knn.classifier: run.knn.classifier - Run KNN classifier

In sydneycytometry/Spectre: A computational toolkit in R for the integration, exploration, and analysis of high-dimensional single-cell cytometry data.

Description

run.knn.classifier - Run KNN classifier

Usage

run.knn.classifier(train.dat, unlabelled.dat, use.cols, label.col, num.neighbours)

Arguments

train.dat	NO DEFAULT. data.frame. A dataframe containing cells (rows) vs features/markers (columns) to be used to train classifier.
unlabelled.dat	NO DEFAULT. data.frame. A dataframe containing cells (rows) vs features/markers (columns) that is the data classified.
use.cols	NO DEFAULT. Vector of column names to use for training k-nearest neighbour (KNN) classifier.
label.col	NO DEFAULT. Character. Name of the column representing the population name of the cells in dat.
num.neighbours	DEFAULTS to 1. Numeric. When using a k-nearest neighbour classifier, then this parameter specifies the number of nearest neighbours. Train a k-NN classifier on a training data, and use it to classify an unlabelled data. Note that for the classifier to work as intended, the unlabelled.data has to be normalised to the range of the train.data. Note make sure that train.data and unlabelled.data has exactly the same features/markers.

Value

The predicted label for the unlabelled data.

Author(s)

Givanna Putri, [e-mail]

References

https://sydneycytometry.org.au/spectre.

sydneycytometry/Spectre documentation built on March 20, 2021, 2:15 a.m.