Functions to calculate distance matrices using cpu computing

Functions to calculate distance matrices using cpu computing

calculate_distance_pearson_cpu(x)

calculate_distance_spearman_cpu(x)

calculate_distance_uncentered_cpu(x)

calculate_distance_euclidean_cpu(x)

select_distance(distancetype = "pearson")

Arguments

x	an expression matrix with features as rows and samples as columns
distancetype	a character that can be either 'pearson', 'uncentered', 'spearman' or 'euclidean'

Value

select_distance(distancetype) assigns global function calculate_distance according to the parameters specified

calculate_distance_pearson_cpu(x) returns columnwise pearson distance calculated using the CPU

calculate_distance_uncentered_cpu(x) returns columnwise uncentered pearson distance calculated using the CPU

calculate_distance_spearman_cpu(x) returns columnwise spearman distance calculated using the CPU

calculate_distance_euclidean_cpu(x) returns columnwise euclidean distance calculated using the CPU

Examples

# load example dataset
require(iC10TrainingData)
#> Loading required package: iC10TrainingData
require(pamr)
#> Loading required package: pamr
#> Loading required package: cluster
#> Loading required package: survival

data(train.Exp)

calculate_distance <- select_distance(distancetype = "pearson")
#> Using CPU for computing pearson distance
Dist <- calculate_distance(train.Exp)
k <- 4
Pam <- cluster_algorithm(Dist, k)
table(Pam$cluster)
#> 
#>   1   2   3   4 
#> 252 161 332 252