cemco (version 0.2)

CemCO: Fit CemCO algorithm using multiple threads of the machine

Description

Model-based clustering based on parameterized finite Gaussian mixture models with covariates effects on the distribution means. Models are estimated by an EM algorithm running in multiple threads of the machine

Usage

CemCO(data, y, G, max_iter=100, n_start=20, cores=4)

Value

The function output is a list

fitted parameters

The estimated parameters of the CemCO algorithm, including clusters centroids, covariance matrix, covariate effects of each cluster and a priori probability of each cluster.

log likelihood

The optimal log likelihood estimated by the model

Arguments

data

A numeric vector, matrix, or data frame of observations. Non-numerical values should be converted to integer or float (e.g. dummies). If matrix or data frame, rows and columns correspond to observations (n) and variables (P).

y

numeric matrix of data to use as covariates. Non-numerical values should be converted to integer or float (e.g. dummies).

G

An integer specifying the numbers of mixture components (clusters)

max_iter

maximum number of iterations of the EM optimization (default value equals to 100)

n_start

how many random sets should be chosen? (default value equals to 20)

cores

number of cores for EM optimization (default value equals to 4)

Author

Relvas, C. & Fujita, A.

Details

This function optimizes the log likelihood of the CemCO algorithm using a implementation of the EM algorithm. If categorial features need to be used, please create dummies or use another encode method.

References

Stage I non-small cell lung cancer stratification by using a model-based clustering algorithm with covariates, Relvas et al.

Examples

set.seed(42)
X = cbind(rnorm(60), rnorm(60))
Y = cbind(rnorm(60), rnorm(60))
K = 2

fit <- CemCO(X, Y, K, max_iter=10, n_start=1, cores=1)
params <- fit[[1]]  ## fitted parameters
ll <- fit[[2]]  ## log likelihood