Function reference • renoir

Evaluation

This is the main function to evaluate a learning method

renoir(): Evaluation of a learning method

List supported methods

These functions list the supported strategies

list_supported_learning_methods(): Supported Learning Methods

list_supported_sampling_methods(): Supported Sampling Methods

list_supported_performance_metrics(): Supported Performance Metrics

list_supported_unsupervised_screening_methods(): Supported Unsupervised Screening

list_supported_supervised_screening_methods(): Supported Supervised Screening

Unsupervised Screening

These functions are used to pre-process the predictors matrix and reduce its dimensionality

filter(): Unsupervised Screening

filter_by_na(): Filter by missing values

filter_by_intensity(): Filter by intensity

filter_by_variability(): Filter by variability

Random sampling

These functions are used to randomly sample data from an initial population

Supervised Screening

These functions are used to pre-process the predictors matrix and reduce its dimensionality in a supervised manner

ebayes_screener(): Compute the significance of the filtering test

permutation_screener(): Compute the significance of the filtering test

multiresponse_screener(): Multi-response screen

default_screener(): Compute the significance of the filtering test

screen(): Features screening

Performance metrics

These functions are used to compute the performance metrics

absolute_error(): Absolute Error

absolute_percentage_error(): Absolute Percentage Error

mean_absolute_error(): Mean Absolute Error

mean_absolute_percentage_error(): Mean Absolute Percentage Error

mean_squared_error(): Mean Squared Error

root_mean_squared_error(): Root-Mean-Square Error

mean_squared_log_error(): Mean Squared Logarithmic Error

r2_score(): R squared

area_under_roc_curve(): Area Under the ROC Curve

f1_score(): F1 Score

fbeta_score(): F-beta Score

sensitivity(): Sensitivity

precision(): Precision

classification_error_rate(): Classification Error Rate

accuracy_score(): Accuracy Classification Score

threat_score(): Jaccard Score

confusion_matrix(): Confusion Matrix

confusion_matrix_outcomes(): Confusion Matrix outcomes

ACC(): Accuracy

BAS(): Balanced accuracy score

BMI(): Informedness, bookmaker informedness (BM)

CSI(): Threat score (TS), critical success index (CSI), Jaccard index

DOR(): Diagnostic odds ratio

ERR(): Error rate

F1S(): F1 score

FBS(): Fbeta score

FDR(): False discovery rate (1 - PPV)

FMI(): Fowlkes-Mallows index

FNR(): False negative rate, miss rate, (1 - TPR)

FOR(): False omission rate (1 - NPV)

FPR(): False positive rate, probability of false alarm, fall-out, (1 - TNR)

MCC(): Matthews correlation coefficient

MKD(): Markedness (MK),deltaP

NLR(): Negative likelihood ratio (LR-)

NPV(): Negative predictive value (1 - FOR)

PLR(): Positive likelihood ratio (LR+)

PPV(): Positive predictive value, precision (1 - FDR)

PRT(): Prevalence threshold (PT)

PRV(): Prevalence

TNR(): True negative rate, specificity (SPC), selectivity, (1 - FPR)

TPR(): True Positive Rate

Quantifying uncertainty

These functions are used to compute the confidence interval for the mean performance metric

ci(): Confidence Interval

ciwm(): Confidence Interval for the Weighted Mean

sewm(): Standard Error of Weighted Mean

uevarwm(): Unbiased Variance of the Weighted Mean

quantify(): Quantify Uncertainty

Learning

These functions are used for learning

learn(): Learn

Training

These functions are used for training

renoir_gbm(): Generalized Boosted Regression Modeling (GBM)

renoir_gknn(): Generalized k-Nearest Neighbors Classification or Regression

renoir_random_forest(): Random Forest

renoir_svm(): Support Vector Machine

renoir_glmnet(): GLM with elastic-net

renoir_nearest_shrunken_centroid(): Nearest Shrunken Centroid

train(): Train the model

Predicting

These functions are used for predictions

forecast(): Forecast method

forecast_by_gbm(): Forecaster for GBM Model Fits

forecast_by_gknn(): Forecaster for Generalized kNN Model Fits

forecast_by_randomForest(): Forecaster for Random Forest Model Fits

forecast_by_svm(): Forecaster for SVM Model Fits

forecast_by_glmnet(): Forecaster for GLM Elastic-Net Fits

forecast_by_nsc(): Forecaster for Nearest Shrunken Centroid Model Fits

Scoring

These functions are used for scoring

score(): Score

mean_score(): Score Estimate

summary_score(): Score

Marking

These functions are used for marking

mark_gbm(): Features Marker

mark_gknn(): Features Marker

mark_randomForest(): Features Marker

mark_svm(): Features Marker

mark_glmnet(): Features Marker

mark_nsc(): Features Marker

mark(): Mark the features of the trained model

Features importance

These functions are used to compute the features importance

importance(): Compute feature importance

Visualisation

These functions are used for visualisation

plot(<Renoir>): Plot method for Renoir object

plot(<RenoirList>): Plot method for RenoirList object

plot(<RenoirSummaryTable>): Plot method for RenoirSummaryTable object

plot(<Renoir>,<missing>): Plot method for Renoir object

Summary

These functions are used for summarising objects

summary_table(): Get the Summary of a Tested Object

Reports

These functions are used for creating reports

create_report(<Renoir>): Create an interactive report

create_report(<Trained>): Create an interactive report

Logging

These functions are used for logging

log_all(<Logger>): Log Method

log_trace(<Logger>): Log Method

log_debug(<Logger>): Log Method

log_info(<Logger>): Log Method

Recording

These functions are used for recording

record_glmnet(): Features Recorder

record_randomForest(): Features Recorder

record_gbm(): Features Recorder

record_svm(): Features Recorder

record_gknn(): Features Recorder

record_nsc(): Features Recorder

record(): Features Recorder

Classes

Main classes

Evaluated-class: Evaluator Class

EvaluatedList-class: EvaluatedList Class

Evaluator(): Evaluator Class

Filter(): Filter Class

FilterList(): FilterList Class

Filtered-class: Filtered Class An S4 class providing a container for the results of pre-processing.

Forecaster(): Forecaster Class An S4 class providing the methods to test the trained models on provided data.

ForecasterList(): Forecaster List Class

Learner(<missing>) Learner(<character>) is.Learner(): Learner Class

LearnerList(): Learner List Class

Logger(): Logger Class

Looper(): Looper Class An S4 class providing methods for loop constructs.

Marked(): Marked An S4 class to represent a marked model

MarkedList(): MarkedList Class An S4 class to represent a renoir trained and tested models list

Marker(): Marker Class An S4 class to represent a features marker.

Quantifier(): Quantifier Class

Recorder(): Recorder Class An S4 class to represent a recorder.

Renoir(): Renoir Class

Resampler(): Resampler Class An S4 class providing the re-sampling methods.

Sampler(): Sampler Class

Scorer(): Scorer Class

ScorerList() create_ScorerList(): ScorerList Class

Screened(): Screened Class

Screener(): Screener Class An S4 class providing the methods to perform a features screening.

ScreenerList(): ScreenerList Class

Selector(): Selector Class An S4 class providing the methods to select a model from a list.

Tested(): Tested An S4 class to represent a tested model

TestedList(): TestedList Class An S4 class to represent a renoir tuned and tested models list

Tester(): Tester Class An S4 class providing the methods to test the trained models on provided data.

TesterList(): Tester List Class

Trained(): An S4 class to represent a renoir trained model

TrainedList(): TrainedList Class An S4 class to represent a renoir trained and tested models list

Trainer(): Trainer Class An S4 class representing a learning method.

Tuned(): Tuned Class

TunedList(): TunedList Class An S4 class to represent a list of tuned models.

Tuner(): Tuner Class

Others

Other functions

get_sample(): Get Sample

get_model(): Get Trained/Tuned Model

stability(): Stability

evaluate(): Evaluate Learning Method

features(): Get features in the model

nfeatures(): Get number of features in the model

resample(): Resample

select(): Select a model

test(): Test

predict(<relaxed>): Predict

signature(): Extract a signature

multiresponse_error(): Multi-response error