Prototype Hierarchical Clustering Learner

Hierarchical clustering using minimax linkage with prototypes. Calls protoclust::protoclust() from package protoclust.

The predict method cuts the tree at the current k via protoclust::protocut() and assigns each new observation to the cluster of its nearest prototype, using the same distance method as during training. The model is therefore a list containing the fitted protoclust::protoclust() object, along with the training data and the arguments passed to stats::dist().

Custom mlr3 parameters

• k:

  • Not an argument of protoclust::protoclust(). The number of clusters to cut the tree into, passed to protoclust::protocut(). Initialized to 2.

Dictionary

This mlr3::Learner can be instantiated via the dictionary mlr3::mlr_learners or with the associated sugar function mlr3::lrn():

mlr_learners$get("clust.protoclust")
lrn("clust.protoclust")

Meta Information

• Task type: “clust”

• Predict Types: “partition”

• Feature Types: “logical”, “integer”, “numeric”

• Required Packages: mlr3, mlr3cluster, protoclust

Parameters

Id	Type	Default	Levels	Range
method	character	euclidean	euclidean, maximum, manhattan, canberra, binary, minkowski	-
diag	logical	FALSE	TRUE, FALSE	-
upper	logical	FALSE	TRUE, FALSE	-
p	numeric	2		\([0, \infty)\)
verb	logical	FALSE	TRUE, FALSE	-
k	integer	-		\([1, \infty)\)

References

Bien, Jacob, Tibshirani, Robert (2011). “Hierarchical Clustering with Prototypes via Minimax Linkage.” Journal of the American Statistical Association, 106(495), 1075–1084.

See also

• Chapter in the mlr3book: https://mlr3book.mlr-org.com/chapters/chapter2/data_and_basic_modeling.html#sec-learners

• Package mlr3extralearners for more learners.

• Dictionary of Learners: mlr3::mlr_learners

• as.data.table(mlr_learners) for a table of available Learners in the running session (depending on the loaded packages).

• mlr3pipelines to combine learners with pre- and postprocessing steps.

• Package mlr3viz for some generic visualizations.

• Extension packages for additional task types:

  • mlr3proba for probabilistic supervised regression and survival analysis.

  • mlr3cluster for unsupervised clustering.

• mlr3tuning for tuning of hyperparameters, mlr3tuningspaces for established default tuning spaces.

Other Learner: mlr_learners_clust.MBatchKMeans, mlr_learners_clust.SimpleKMeans, mlr_learners_clust.agnes, mlr_learners_clust.ap, mlr_learners_clust.bico, mlr_learners_clust.birch, mlr_learners_clust.clara, mlr_learners_clust.cmeans, mlr_learners_clust.cobweb, mlr_learners_clust.dbscan, mlr_learners_clust.dbscan_fpc, mlr_learners_clust.diana, mlr_learners_clust.em, mlr_learners_clust.fanny, mlr_learners_clust.featureless, mlr_learners_clust.ff, mlr_learners_clust.flexmix, mlr_learners_clust.genie, mlr_learners_clust.gmeans, mlr_learners_clust.hclust, mlr_learners_clust.hdbscan, mlr_learners_clust.kcca, mlr_learners_clust.kkmeans, mlr_learners_clust.kmeans, mlr_learners_clust.kmeans_rcpp, mlr_learners_clust.kmodes, mlr_learners_clust.kproto, mlr_learners_clust.mclust, mlr_learners_clust.meanshift, mlr_learners_clust.movMF, mlr_learners_clust.optics, mlr_learners_clust.pam, mlr_learners_clust.skmeans, mlr_learners_clust.som, mlr_learners_clust.specc, mlr_learners_clust.stdbscan, mlr_learners_clust.tclust, mlr_learners_clust.xmeans

Super classes

mlr3::Learner -> LearnerClust -> LearnerClustProtoclust

Active bindings

native_model

(protoclust)
The fitted model returned by protoclust::protoclust().

Methods

Public methods

• LearnerClustProtoclust$new()

• LearnerClustProtoclust$clone()

Inherited methods

• mlr3::Learner$base_learner()
• mlr3::Learner$configure()
• mlr3::Learner$encapsulate()
• mlr3::Learner$format()
• mlr3::Learner$help()
• mlr3::Learner$predict()
• mlr3::Learner$predict_newdata()
• mlr3::Learner$print()
• mlr3::Learner$selected_features()
• mlr3::Learner$train()
• LearnerClust$reset()

---

LearnerClustProtoclust$new()

Creates a new instance of this R6 class.

Usage

LearnerClustProtoclust$new()

---

LearnerClustProtoclust$clone()

The objects of this class are cloneable with this method.

Usage

LearnerClustProtoclust$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# Define the Learner and set parameter values
learner = lrn("clust.protoclust")
print(learner)
#> 
#> ── <LearnerClustProtoclust> (clust.protoclust): Prototype Hierarchical Clusterin
#> • Model: -
#> • Parameters: k=2
#> • Packages: mlr3, mlr3cluster, and protoclust
#> • Predict Types: [partition]
#> • Feature Types: logical, integer, and numeric
#> • Encapsulation: none (fallback: -)
#> • Properties: complete, exclusive, and hierarchical
#> • Other settings: use_weights = 'error', predict_raw = 'FALSE'

# Define a Task
task = tsk("usarrests")

# Train the learner on the task
learner$train(task)

# Print the model
print(learner$native_model)
#> 
#> Call:
#> protoclust::protoclust(d = d)
#> 
#> Cluster method   : minimax 
#> Distance         : euclidean 
#> Number of objects: 50 
#> 

# Make predictions for the task
prediction = learner$predict(task)

# Score the predictions
prediction$score(task = task)
#> clust.dunn 
#> 0.08975081