qualityRange: Goodness of classifications for a range of k clusters.

In neobernad/evaluomeR: Evaluation of Bioinformatics Metrics

Goodness of classifications for a range of k clusters.

Description

The goodness of the classifications are assessed by validating the clusters generated for a range of k values. For this purpose, we use the Silhouette width as validity index. This index computes and compares the quality of the clustering outputs found by the different metrics, thus enabling to measure the goodness of the classification for both instances and metrics. More precisely, this measurement provides an assessment of how similar an instance is to other instances from the same cluster and dissimilar to the rest of clusters. The average on all the instances quantifies how the instances appropriately are clustered. Kaufman and Rousseeuw suggested the interpretation of the global Silhouette width score as the effectiveness of the clustering structure. The values are in the range [0,1], having the following meaning:

• There is no substantial clustering structure: [-1, 0.25].

• The clustering structure is weak and could be artificial: ]0.25, 0.50].

• There is a reasonable clustering structure: ]0.50, 0.70].

• A strong clustering structure has been found: ]0.70, 1].

Usage

qualityRange(
  data,
  k.range = c(3, 5),
  cbi = "kmeans",
  getImages = FALSE,
  all_metrics = FALSE,
  seed = NULL,
  ...
)

Arguments

data	A SummarizedExperiment. The SummarizedExperiment must contain an assay with the following structure: A valid header with names. The first column of the header is the ID or name of the instance of the dataset (e.g., ontology, pathway, etc.) on which the metrics are measured. The other columns of the header contains the names of the metrics. The rows contains the measurements of the metrics for each instance in the dataset.
k.range	Concatenation of two positive integers. The first value k.range[1] is considered as the lower bound of the range, whilst the second one, k.range[2], as the higher. Both values must be contained in [2,15] range.
cbi	Clusterboot interface name (default: "kmeans"): "kmeans", "clara", "clara_pam", "hclust", "pamk", "pamk_pam", "pamk". Any CBI appended with '_pam' makes use of pam. The method used in 'hclust' CBI is "ward.D2".
getImages	Boolean. If true, a plot is displayed.
all_metrics	Boolean. If true, clustering is performed upon all the dataset.
seed	Positive integer. A seed for internal bootstrap.

Value

A list of SummarizedExperiment containing the silhouette width measurements and cluster sizes from k.range[1] to k.range[2]. The position on the list matches with the k-value used in that dataframe. For instance, position 5 represents the dataframe with k = 5.

References

\insertRef

kaufman2009findingevaluomeR

Examples

# Using example data from our package
data("ontMetrics")
# Without plotting
dataFrameList = qualityRange(ontMetrics, k.range=c(2,3), getImages = FALSE)

neobernad/evaluomeR documentation built on Nov. 12, 2024, 11:29 p.m.