proximity_matrix_RF: Plot binary rule-based heatmaps

In NourMarzouka/multiclassPairs: Build MultiClass Pair-Based Classifiers using TSPs or RF

Plot binary rule-based heatmaps

Description

proximity_matrix_RF Plot clustering heatmaps showing which out-of-bag samples are predicted in the same class and in the same trees during the training process for the rule-based random forest classifier

Usage

proximity_matrix_RF(object,
            classifier,
            plot=TRUE,
            return_matrix=TRUE,
            title         = "",
            top_anno      = c("ref","platform")[1],
            classes       = NULL,
            sam_order     = NULL,
            ref_col       = NULL,
            platform_col  = NULL,
            platforms_ord = NULL,
            show_platform = TRUE,
            cluster_cols  = FALSE,
            legend        = TRUE,
            anno_height   = 0.03,
            margin        = c(0, 5, 0, 5))

Arguments

object	data_object generated by ReadData function which was used in the training process.
classifier	classifier as a rule_based_RandomForest object, generated by train_RF function
plot	logical. To plot the proximity matrix or not. Default is TRUE.
return_matrix	logical. To return the proximity matrix or not. Default is TRUE.
title	Character input as a title for the whole heatmap. Default is "".
top_anno	Determine the top annotation level. Samples will be grouped based on the top_anno. Input can be one of two options: "ref", "platform". Default is "ref".
classes	Optional vector with the class names. Classes will determine which classes will be plotted and in which order. It is not recommended to use both "classes" and "platforms_ord" arguments together.
sam_order	Optional vector with the samples order in the heatmap.
ref_col	optional named vector determines the colors of classes for the reference labels. Default is NULL. Vector names should match with the ref labels.
platform_col	optional named vector determines the colors of platforms/study labels. Default is NULL. Vector names should match with the platforms/study labels.
platforms_ord	Optional vector with the platform/study names. This will determine which platform/study will be plotted and in which order. This will be used when top_anno="platform". It is not recommended to use both "classes" and "platforms_ord" arguments together.
show_platform	logical. Determines if the platform/study labels will be plotted or not. If the top_anno argument is "platform" then show_platform will be ignored.
cluster_cols	logical. samples will be grouped based on the class then will be Clustered in each class (i.e. not all samples in the cohort). If top_anno is "platform" then the rules from all classes are used to cluster the samples in each platform.
legend	logical. Determines if a legend will be plotted under the heatmap.
anno_height	Determines the height of the annotations. It is recommended not to go out of this range 0.01<height<0.1. Default is 0.03.
margin	Determines the margins of the heatmap. Default is c(0, 5, 0, 5).

Value

returns the proximity matrix and/or a heatmap plot for the proximity matrix.

Author(s)

Nour-al-dain Marzouka <nour-al-dain.marzouka at med.lu.se>

Examples

# generate random data
Data <- matrix(runif(8000), nrow=100, ncol=80,
               dimnames = list(paste0("G",1:100), paste0("S",1:80)))

# generate random labels
L <- sample(x = c("A","B","C","D"), size = 80, replace = TRUE)

# generate random platform labels
P <- sample(c("P1","P2","P3"), size = 80, replace = TRUE)

# create data object
object <- ReadData(Data = Data,
                   Labels = L,
                   Platform = P,
                   verbose = FALSE)

# sort genes
genes_RF <- sort_genes_RF(data_object = object,
                          seed=123456, verbose = FALSE)

# to get an idea of how many genes we will use
# and how many rules will be generated
# summary_genes_RF(sorted_genes_RF = genes_RF,
#                  genes_altogether = c(10,20,50,100,150,200),
#                  genes_one_vs_rest = c(10,20,50,100,150,200))

# creat and sort rules
# rules_RF <- sort_rules_RF(data_object = object,
#                           sorted_genes_RF = genes_RF,
#                           genes_altogether = 100,
#                           genes_one_vs_rest = 100,
#                           seed=123456,
#                           verbose = FALSE)

# parameters <- data.frame(
#   gene_repetition=c(3,2,1),
#   rules_one_vs_rest=0,
#   rules_altogether=c(2,3,10),
#   run_boruta=c(FALSE,"produce_error",FALSE),
#   plot_boruta = FALSE,
#   num.trees=c(100,200,300),
#   stringsAsFactors = FALSE)
# parameters

# Or you can use expand.grid to generate dataframe with all parameter combinations
# parameters <- expand.grid(
#   gene_repetition=c(3,2,1),
#   rules_one_vs_rest=0,
#   rules_altogether=c(2,3,10),
#   num.trees=c(100,500,1000),
#   stringsAsFactors = FALSE)
# parameters


# test <- optimize_RF(data_object = object,
#                     sorted_rules_RF = rules_RF,
#                     test_object = NULL,
#                     overall = c("Accuracy"),
#                     byclass = NULL, verbose = FALSE,
#                     parameters = parameters)
# test
# test$summary[which.max(test$summary$Accuracy),]
#
# # train the final model
# # it is preferred to increase the number of trees and rules in case you have
# # large number of samples and features
# # for quick example, we have small number of trees and rules here
# # based on the optimize_RF results we will select the parameters
# RF_classifier <- train_RF(data_object = object,
#                           gene_repetition = 1,
#                           rules_altogether = 0,
#                           rules_one_vs_rest = 10,
#                           run_boruta = FALSE,
#                           plot_boruta = FALSE,
#                           probability = TRUE,
#                           num.trees = 300,
#                           sorted_rules_RF = rules_RF,
#                           boruta_args = list(),
#                           verbose = TRUE)
#
# # training accuracy
# # get the prediction labels
# # if the classifier trained using probability	= FALSE
# training_pred <- RF_classifier$RF_scheme$RF_classifier$predictions
# if (is.factor(training_pred)) {
#   x <- as.character(training_pred)
# }
#
# # if the classifier trained using probability	= TRUE
# if (is.matrix(training_pred)) {
#   x <- colnames(training_pred)[max.col(training_pred)]
# }
#
# # training accuracy
# caret::confusionMatrix(data =factor(x),
#                 reference = factor(object$data$Labels),
#                 mode = "everything")

# not to run
# visualize the binary rules in training dataset
# plot_binary_RF(Data = object,
#                classifier = RF_classifier,
#                prediction = NULL, as_training = TRUE,
#                show_scores = TRUE,
#                top_anno = "ref",
#                show_predictions = TRUE,
#                title = "Training data")

# not to run
# Extract and plot the proximity matrix from the classifier for the training data
# it takes long time for large data
# proximity_mat <- proximity_matrix_RF(object = object,
#                       classifier = RF_classifier,
#                       plot=TRUE,
#                       return_matrix=TRUE,
#                       title = "Test",
#                       cluster_cols = TRUE)

# not to run
# predict
# test_object # any test data
# results <- predict_RF(classifier = RF_classifier, impute = TRUE,
#                       Data = test_object)
#
# # visualize the binary rules in training dataset
# plot_binary_RF(Data = test_object,
#                classifier = RF_classifier,
#                prediction = results, as_training = FALSE,
#                show_scores = TRUE,
#                top_anno = "ref",
#                show_predictions = TRUE,
#                title = "Test data")

NourMarzouka/multiclassPairs documentation built on May 3, 2023, 7:20 p.m.