Utilities for Multi-Label Learning


[Up] [Top]

Documentation for package ‘utiml’ version 0.1.3

Help Pages

A B C D E F H I L M N P R S T U misc

utiml-package utiml: Utilities for Multi-Label Learning

-- A --

as.bipartition Convert a mlresult to a bipartition matrix
as.matrix.mlresult Convert a mlresult to matrix
as.mlresult Convert a matrix prediction in a multi label prediction
as.mlresult.default Convert a matrix prediction in a multi label prediction
as.mlresult.mlresult Convert a matrix prediction in a multi label prediction
as.probability Convert a mlresult to a probability matrix
as.ranking Convert a mlresult to a ranking matrix

-- B --

baseline Baseline reference for multilabel classification
br Binary Relevance for multi-label Classification
brplus BR+ or BRplus for multi-label Classification

-- C --

cc Classifier Chains for multi-label Classification
clr Calibrated Label Ranking (CLR) for multi-label Classification
compute_multilabel_predictions Compute the multi-label ensemble predictions based on some vote schema
create_holdout_partition Create a holdout partition based on the specified algorithm
create_kfold_partition Create the k-folds partition based on the specified algorithm
create_random_subset Create a random subset of a dataset
create_subset Create a subset of a dataset
ctrl CTRL model for multi-label Classification

-- D --

dbr Dependent Binary Relevance (DBR) for multi-label Classification

-- E --

ebr Ensemble of Binary Relevance for multi-label Classification
ecc Ensemble of Classifier Chains for multi-label Classification
eps Ensemble of Pruned Set for multi-label Classification

-- F --

fill_sparse_mldata Fill sparse dataset with 0 or " values
fixed_threshold Apply a fixed threshold in the results
fixed_threshold.default Apply a fixed threshold in the results
fixed_threshold.mlresult Apply a fixed threshold in the results

-- H --

homer Hierarchy Of Multilabel classifiER (HOMER)

-- I --

is.bipartition Test if a mlresult contains crisp values as default
is.probability Test if a mlresult contains score values as default

-- L --

lcard_threshold Threshold based on cardinality
lcard_threshold.default Threshold based on cardinality
lcard_threshold.mlresult Threshold based on cardinality
lift LIFT for multi-label Classification
lp Label Powerset for multi-label Classification

-- M --

mbr Meta-BR or 2BR for multi-label Classification
mcut_threshold Maximum Cut Thresholding (MCut)
mcut_threshold.default Maximum Cut Thresholding (MCut)
mcut_threshold.mlresult Maximum Cut Thresholding (MCut)
merge_mlconfmat Join a list of multi-label confusion matrix
mldata Fix the mldr dataset to use factors
mlpredict Prediction transformation problems
mlpredict.baseKNN Prediction transformation problems
mlpredict.C5.0 Prediction transformation problems
mlpredict.default Prediction transformation problems
mlpredict.emptyModel Prediction transformation problems
mlpredict.J48 Prediction transformation problems
mlpredict.majorityModel Prediction transformation problems
mlpredict.naiveBayes Prediction transformation problems
mlpredict.randomForest Prediction transformation problems
mlpredict.randomModel Prediction transformation problems
mlpredict.rpart Prediction transformation problems
mlpredict.SMO Prediction transformation problems
mlpredict.svm Prediction transformation problems
mlpredict.xgb.Booster Prediction transformation problems
mltrain Build transformation models
mltrain.baseC5.0 Build transformation models
mltrain.baseCART Build transformation models
mltrain.baseJ48 Build transformation models
mltrain.baseKNN Build transformation models
mltrain.baseMAJORITY Build transformation models
mltrain.baseNB Build transformation models
mltrain.baseRANDOM Build transformation models
mltrain.baseRF Build transformation models
mltrain.baseSMO Build transformation models
mltrain.baseSVM Build transformation models
mltrain.baseXGB Build transformation models
mltrain.default Build transformation models
multilabel_confusion_matrix Compute the confusion matrix for a multi-label prediction
multilabel_evaluate Evaluate multi-label predictions
multilabel_evaluate.mlconfmat Evaluate multi-label predictions
multilabel_evaluate.mldr Evaluate multi-label predictions
multilabel_measures Return the name of all measures
multilabel_prediction Create a mlresult object

-- N --

normalize_mldata Normalize numerical attributes
ns Nested Stacking for multi-label Classification

-- P --

partition_fold Create the multi-label dataset from folds
pcut_threshold Proportional Thresholding (PCut)
pcut_threshold.default Proportional Thresholding (PCut)
pcut_threshold.mlresult Proportional Thresholding (PCut)
ppt Pruned Problem Transformation for multi-label Classification
predict.BASELINEmodel Predict Method for BASELINE
predict.BRmodel Predict Method for Binary Relevance
predict.BRPmodel Predict Method for BR+ (brplus)
predict.CCmodel Predict Method for Classifier Chains
predict.CLRmodel Predict Method for CLR
predict.CTRLmodel Predict Method for CTRL
predict.DBRmodel Predict Method for DBR
predict.EBRmodel Predict Method for Ensemble of Binary Relevance
predict.ECCmodel Predict Method for Ensemble of Classifier Chains
predict.EPSmodel Predict Method for Ensemble of Pruned Set Transformation
predict.HOMERmodel Predict Method for HOMER
predict.LIFTmodel Predict Method for LIFT
predict.LPmodel Predict Method for Label Powerset
predict.MBRmodel Predict Method for Meta-BR/2BR
predict.NSmodel Predict Method for Nested Stacking
predict.PPTmodel Predict Method for Pruned Problem Transformation
predict.PruDentmodel Predict Method for PruDent
predict.PSmodel Predict Method for Pruned Set Transformation
predict.RAkELmodel Predict Method for RAkEL
predict.RDBRmodel Predict Method for RDBR
predict.RPCmodel Predict Method for RPC
print.BRmodel Print BR model
print.BRPmodel Print BRP model
print.CCmodel Print CC model
print.CLRmodel Print CLR model
print.CTRLmodel Print CTRL model
print.DBRmodel Print DBR model
print.EBRmodel Print EBR model
print.ECCmodel Print ECC model
print.EPSmodel Print EPS model
print.kFoldPartition Print a kFoldPartition object
print.LIFTmodel Print LIFT model
print.LPmodel Print LP model
print.majorityModel Print Majority model
print.MBRmodel Print MBR model
print.mlconfmat Print a Multi-label Confusion Matrix
print.mlresult Print the mlresult
print.NSmodel Print NS model
print.PPTmodel Print PPT model
print.PruDentmodel Print PruDent model
print.PSmodel Print PS model
print.RAkELmodel Print RAkEL model
print.randomModel Print Random model
print.RDBRmodel Print RDBR model
print.RPCmodel Print RPC model
prudent PruDent classifier for multi-label Classification
ps Pruned Set for multi-label Classification

-- R --

rakel Random k-labelsets for multilabel classification
rcut_threshold Rank Cut (RCut) threshold method
rcut_threshold.default Rank Cut (RCut) threshold method
rcut_threshold.mlresult Rank Cut (RCut) threshold method
rdbr Recursive Dependent Binary Relevance (RDBR) for multi-label Classification
remove_attributes Remove attributes from the dataset
remove_labels Remove labels from the dataset
remove_skewness_labels Remove unusual or very common labels
remove_unique_attributes Remove unique attributes
remove_unlabeled_instances Remove examples without labels
replace_nominal_attributes Replace nominal attributes Replace the nominal attributes by binary attributes.
rpc Ranking by Pairwise Comparison (RPC) for multi-label Classification

-- S --

scut_threshold SCut Score-based method
scut_threshold.default SCut Score-based method
scut_threshold.mlresult SCut Score-based method
subset_correction Subset Correction of a predicted result
summary.mltransformation Summary method for mltransformation

-- T --

toyml Toy multi-label dataset.

-- U --

utiml utiml: Utilities for Multi-Label Learning
utiml_all_measures_names MEASURES METHODS --- Return the tree with the measure names
utiml_compute_ensemble Compute binary predictions
utiml_ensemble_average Average vote combination for a single-label prediction
utiml_ensemble_check_voteschema Verify if a schema vote name is valid
utiml_ensemble_majority Majority vote combination for single-label prediction
utiml_ensemble_maximum Maximum vote combination for single-label prediction
utiml_ensemble_method Define the method name related with the vote schema
utiml_ensemble_minimum Minimum vote combination for single-label prediction
utiml_ifelse Conditional value selection
utiml_is_equal_sets Define if two sets are equals independently of the order of the elements
utiml_iterative_split Internal Iterative Stratification
utiml_labels_correlation Phi Correlation Coefficient
utiml_labels_IG Calculate the Information Gain for each pair of labels
utiml_lapply Select the suitable method lapply or mclaplly
utiml_measure_accuracy MULTILABEL MEASURES --- Multi-label Accuracy Measure
utiml_measure_average_precision Multi-label Average Precision Measure
utiml_measure_binary_accuracy BINARY MEASURES --- Compute the binary accuracy
utiml_measure_binary_AUC Compute the binary AUC
utiml_measure_binary_balacc Compute the binary balanced accuracy
utiml_measure_binary_f1 Compute the binary F1 measure
utiml_measure_binary_precision Compute the binary precision
utiml_measure_binary_recall Compute the binary recall
utiml_measure_coverage Multi-label Coverage Measure
utiml_measure_f1 Multi-label F1 Measure
utiml_measure_hamming_loss Multi-label Hamming Loss Measure
utiml_measure_is_error Multi-label Is Error Measure
utiml_measure_macro_accuracy Multi-label Macro-Accuracy Measure
utiml_measure_macro_AUC Multi-label Macro-AUC Measure
utiml_measure_macro_f1 Multi-label Macro-F1 Measure
utiml_measure_macro_precision Multi-label Macro-Precision Measure
utiml_measure_macro_recall Multi-label Macro-Recall Measure
utiml_measure_margin_loss Multi-label Margin Loss Measure
utiml_measure_micro_accuracy Multi-label Micro-Accuracy Measure
utiml_measure_micro_AUC Multi-label Macro-AUC Measure
utiml_measure_micro_f1 Multi-label Micro-F1 Measure
utiml_measure_micro_precision Multi-label Micro-Precision Measure
utiml_measure_micro_recall Multi-label Micro-Recall Measure
utiml_measure_names Return the name of measures
utiml_measure_one_error Multi-label One Error Measure
utiml_measure_precision Multi-label Precision Measure
utiml_measure_ranking_error Multi-label Ranking Error Measure
utiml_measure_ranking_loss Multi-label Hamming Loss Measure
utiml_measure_recall Multi-label Recall Measure
utiml_measure_subset_accuracy Multi-label Subset Accuracy Measure
utiml_newdata Return the newdata to a data.frame or matrix
utiml_newdata.default Return the newdata to a data.frame or matrix
utiml_newdata.mldr Return the newdata to a data.frame or matrix
utiml_normalize Internal normalize data function
utiml_predict_binary_ensemble Predict binary predictions
utiml_predict_ensemble Compute the multi-label ensemble predictions based on some vote schema
utiml_preserve_seed Preserve current seed
utiml_random_split Random split of a dataset
utiml_rename Rename the list using the names values or its own content
utiml_restore_seed Restore the current seed
utiml_stratified_split Labelsets Stratification Create the indexes using the Labelsets Stratification approach.
utiml_validate_splitmethod Return the name of split method and validate if it is valid

-- misc --

+.mlconfmat Join two multi-label confusion matrix
[.mlresult Filter a Multi-Label Result