model2DE_cluster: Run model2DE on several bootstrap resamples in parallel.

In aruaud/endoR: Interpret and Visualize Stable Tree Ensemble Models

Run model2DE on several bootstrap resamples in parallel.

Description

Function to with the Q() function from the clustermq R-package with the following arguments in export: data, target, exec, classPos, dummy_var, prune, maxDecay, typeDecay, filter, in_parallel, n_cores. See preCluster() to obtain the list of boostraps resamples, the discretized data and exec dataframe with decisions.

Usage

model2DE_cluster(partition)

Arguments

partition

a vector with row numbers to subset data.

Examples

library(randomForest)
library(caret)

# import data and fit model
data(iris)
mod <- randomForest(Species ~ ., data = iris)

# Get decision ensemble with bootstrapping.

# Run 1 bootstrap after the other (times = 2 bootstraps)
endo_setosa <- model2DE_resampling(model = mod, model_type = "rf"
    , data = iris[, -5], target = iris$Species, classPos = "setosa"
    , times = 2, in_parallel = TRUE, n_cores = 2, filter = FALSE)

# Same but use different sample weights for bootstrapping
n_setosa <- sum(iris$Species == "setosa")
n_samp <- length(iris$Species)
samp_weight <- round(
    ifelse(iris$Species == "setosa", 1 - n_setosa/n_samp, n_setosa/n_samp)
    , digits = 2)
endo_setosa <- model2DE_resampling(model = mod, model_type = "rf"
    , data = iris[, -5], target = iris$Species, classPos = "setosa"
    , times = 2, sample_weight = samp_weight
    , in_parallel = TRUE, n_cores = 2, filter = FALSE)

# Run the bootstraps in parallel
# First do all steps before bootstrapping
preclu <- preCluster(model = mod, model_type = "rf", data = iris[, -5]
    , target = iris$Species, classPos = "setosa", times = 2
    , discretize = TRUE, in_parallel = FALSE)

# Remove the special characters from column names
colnames(preclu$data) <- compatibleNames(colnames(preclu$data))

# Parameters for clustermq: can also run on HPC environment
library(clustermq)
options(clustermq.scheduler = "multiprocess")
# ... and run in parallel on each bootstrap
# (preclu$partitions = list of sample indexes for each bootstraps)
endo_setosa <- Q(model2DE_cluster
    , partition = preclu$partitions
    , export = list(data = preclu$data
                , target = iris$Species
                , exec = preclu$exec
                , classPos = "setosa"
                , prune = TRUE, filter = FALSE
                , maxDecay = 0.05 # values needed for maxDecay and typeDecay
                , typeDecay = 2 # here default ones, see pruneDecisions()
                , in_parallel = FALSE # can parallelize within each boostrap!
           )
    , n_jobs = 2 # max number of bootstraps that can be ran in parallel
    , pkgs = c("data.table", "parallel", "caret", "stringr", "scales"
                , "dplyr", "inTrees", "endoR")
    , log_worker = FALSE # to keep a log of the runs, e.g. if it fails..
)


# Stability selection
# First we can look at the effect of the alpha parameter on selection;
# alpha = expected number of false decisions
alphas <- evaluateAlpha(rules = endo_setosa, alphas = c(1:5, 7, 10)
                        , data = preclu$data)
alphas$summary_table

# perform stability selection with alpha = 1
de_final <- stabilitySelection(rules = endo_setosa, alpha_error = 7)

# Plot the decision ensemble:
# Plants from the setosa species have small petal and narrow long sepals.
plotFeatures(de_final, levels_order = c("Low", "Medium", "High"))

# there is no interaction between variables (all decisions with len = 1,
# the number of variables in the rules)
de_final$rules_summary
# hence the network would be empty and couldn't be plotted...
# plotNetwork(de_final, hide_isolated_nodes = FALSE)

aruaud/endoR documentation built on Jan. 25, 2025, 2:20 a.m.