get_scores: Calculate cluster uncertainty

In spruce: Spatial Random Effects Clustering of Single Cell Data

Calculate cluster uncertainty

Description

Use posterior estimates to calculate uncertainty scores

Usage

get_scores(fit)

Arguments

fit	A model fit returned by one of the fit_*_PG model functions

Value

An n x (K + 1) matrix. First K columns are continuous phenotypes, and last column is uncertainty scores

Examples

# parameters
data(coords_df_sim)
coords_df <- coords_df_sim[,1:2]
z <- remap_canonical2(coords_df_sim$z)
                                 
n <- nrow(coords_df) # number of observations
g <- 3 # number of features
K <- length(unique(coords_df_sim$z)) # number of clusters (mixture components)
pi <- table(z)/length(z) # cluster membership probability

W <- matrix(0, nrow = n, ncol = 2)
W[,1] <- 1
W[,2] <- sample(c(0,1),size = n, replace = TRUE, prob = c(0.5,0.5))

# Cluster Specific Parameters
Mu <- list(
  Mu1 = rnorm(g,-5,1),
  Mu2 = rnorm(g,0,1),
  Mu3 = rnorm(g,5,1),
  Mu4 = rnorm(g,-2,3)
)
# cluster specific variance-covariance
S <- matrix(1,nrow = g,ncol = g) # y covariance matrix
diag(S) <- 1.5
Sig <- list(
  Sig1 = S,
  Sig2 = S, 
  Sig3 = S,
  Sig4 = S
)

Y <- matrix(0, nrow = n, ncol = g)
for(i in 1:n)
{
  Y[i,] <- mvtnorm::rmvnorm(1,mean = Mu[[z[i]]],sigma = Sig[[z[i]]])
}

# fit model
# in practice use more mcmc iterations
fit <- fit_mvn_PG_smooth(Y = Y, coords_df = coords_df, W = W, K = K, nsim = 10, burn = 0)
scores_df <- get_scores(fit)

spruce documentation built on March 18, 2022, 7:01 p.m.