Set, add, remove or query properties of learners
Result of multi-criteria tuning.
Aggregation object.
Failure model.
Generate dummy variables for factor features.
European Union Agricultural Workforces clustering task
Convert large/infinite numeric values in a data.frame or task.
crossover
Internal construction / wrapping of learner object.
Boston Housing regression task
BenchmarkResult object.
Aggregation methods.
Get underlying R model of learner integrated into mlr.
Result of tuning.
Show and visualize the steps of feature selection.
Specifiy your own aggregation of measures
Iris cost-sensitive classification task
Description object for task.
Return error message of FailureModel.
Configures the behavior of the package.
getPredictionProbabilities
Get probabilities for some classes.
Construct performance measure.
Extract data in task.
Create learner object.
Fuse learner with SMOTE oversampling for imbalancy correction in binary classification.
Get a summarizing task description.
Is the model a FailureModel?
generateLearningCurveData
Generates a learning curve
Get the name(s) of the target column(s).
Get predictions from resample results.
Get the id of the task.
Get tuning parameters from a learner of the caret R-package.
Create a description object for a resampling strategy.
Perform overall Friedman test for a BenchmarkResult.
Create a classification, regression, survival, cluster, cost-sensitive classification or
multilabel task.
Performance measures.
Get number of features in task.
makeModelMultiplexerParamSet
Creates a parameter set for model multiplexer tuning.
Get a description of all possible parameter settings for a learner.
Create control structures for multi-criteria tuning.
Wisconsin Breast Cancer classification task
makeMultilabelBinaryRelevanceWrapper
Use binary relevance method to create a multilabel learner.
plotPartialPredictionGGVIS
Plot a partial prediction using ggvis
mergeBenchmarkResultLearner
Merge different learners of BenchmarkResult objects
Fuse learner with a feature filter method.
Benchmark experiment for multiple learners and tasks.
Fuse learner with multiclass method.
Find matching measures.
Convert BenchmarkResult to a rank-matrix.
Get current parameter settings for a learner.
ResampleResult object.
Generate binary classification predictions via ROCR ROC curves.
Drop some features of task.
estimateRelativeOverfitting
Estimate relative overfitting.
Get response / truth from prediction object.
Fuse learner with the bagging technique and oversampling for imbalancy correction.
Return learners used in benchmark.
Fuse learner with simple downsampling (subsampling).
Estimate the residual variance
Convert arguments to control structure.
Return task ids used in benchmark.
Return learner ids used in benchmark.
Plot learning curve data using ggvis.
Downsample (subsample) a task or a data.frame.
Get the tuned hyperparameter settings from a nested tuning.
Returns the filtered features.
Create control structures for tuning.
Extract the tuning results from a benchmark result.
getHomogeneousEnsembleModels
Deprecated, use getLearnerModel
instead.
Get formula of a task.
Get number of observations in task.
Fuse learner with an imputation method.
Converts predictions to a format package ROCR can handle.
Filter features by thresholding filter values.
Extract the aggregated performance values from a benchmark result.
Prediction object.
Predict new data.
Iris classification task
Extract costs in task.
Merge different tasks of BenchmarkResult objects
Plot a partial prediction with ggplot2
Result of feature selection.
generateCritDifferencesData
Generate data for critical-differences plot.
Confusion matrix.
Re-impute a data set
Generate a fixed holdout instance for resampling.
Plot filter values using ggplot2.
Built in imputation methods
The built-ins are:
imputeConstant(const)
for imputation using a constant value,imputeMedian()
for imputation using the median,imputeMode()
for imputation using the mode,imputeMin(multiplier)
for imputing constant values shifted below the minimum
usingmin(x) - multiplier * diff(range(x))
,imputeMax(multiplier)
for imputing constant values shifted above the maximum
usingmax(x) + multiplier * diff(range(x))
,imputeNormal(mean, sd)
for imputation using normally
distributed random values. Mean and standard deviation will be calculated
from the data if not provided.imputeHist(breaks, use.mids)
for imputation using random values
with probabilities calculated usingtable
orhist
.imputeLearner(learner, preimpute)
for imputations using the response
of a classification or regression learner. Fuse learner with preprocessing.
Perform a posthoc Friedman-Nemenyi test.
Fuse learner with tuning.
Create a Trellis-plot for a selected measure.
Return measures used in benchmark.
List filter methods
Get default measure.
Impute and re-impute data
getMultilabelBinaryPerformances
Retrieve binary classification measures for multilabel classification predictions.
generateBenchmarkSummaryData
Generate data for a benchmark-summary plot.
Returns a list of mlr's options
Induced model of learner.
Get the class weight parameter of a learner.
Motor Trend Car Road Tests clustering task
Create control structures for feature selection.
PimaIndiansDiabetes classification task
Normalize features
Plot critical differences for a selected measure.
NCCTG Lung Cancer survival task
Creates a measure for non-standard misclassification costs.
Remove constant features from a data set.
Get the class levels for classification and multilabel tasks.
makeCustomResampledMeasure
Construct your own resampled performance measure.
Create model multiplexer for model selection to tune over multiple possible models.
Plot filter values using ggvis.
Visualize binary classification predictions via ViperCharts system.
Plots multi-criteria results after tuning using ggplot2.
Deprecated, use getPredictionProbabilities
instead.
Tune prediction threshold.
List of supported learning algorithms.
Plot threshold vs. performance(s) for 2-class classification using ggplot2.
Join some class existing levels to new, larger class levels for classification problems.
Over- or undersample binary classification task to handle class imbalancy.
Summarizes factors of a data.frame by tabling them.
Extract the feature selection results from a benchmark result.
Measure performance of prediction.
Returns the selected feature set and optimization path after training.
Extract the predictions from a benchmark result.
Wraps a regression learner for use in cost-sensitive learning.
Merges small levels of factors into new level.
Calculates feature filter values.
Get the type of the task.
Fuse learner with preprocessing
Generate threshold vs. performance(s) for 2-class classification.
Plots results from generateROCRCurvesData using ggvis.
Plot a benchmark-summary.
getNestedTuneResultsOptPathDf
Get the opt.path
s from each tuning step from the outer resampling.
Extract the feature selection results from a benchmark result.
Calculates feature filter values.
Convert a machine learning benchmark / demo object from package mlbench to a task.
makeCostSensClassifWrapper
Wraps a classification learner for use in cost-sensitive learning.
Find matching learning algorithms.
Generate classifier calibration data.
Get feature names of task.
Plot learning curve data using ggplot2.
Prediction from resampling.
Get target column of task.
Fit models according to a resampling strategy.
Create a stacked learner object.
plotTuneMultiCritResultGGVIS
Plots multi-criteria results after tuning using ggvis.
Plot threshold vs. performance(s) for 2-class classification using ggvis.
generateRankMatrixAsBarData
Generate data to plot a rank-matrix as a barplot.
Create a custom imputation method.
Fuse learner with feature selection.
Plots results from generateROCRCurvesData using ggplot2.
generatePartialPredictionData
Generate partial predictions
makeCostSensWeightedPairsWrapper
Wraps a classifier for cost-sensitive learning to produce a weighted pairs model.
Plot a rank-matrix as a barplot.
Returns the optimal hyperparameters and optimization path after training.
Return measures IDs used in benchmark.
makeWeightedClassesWrapper
Wraps a classifier for weighted fitting where each class receives a weight.
Instantiates a resampling strategy object.
Fuse learner with the bagging technique.
Plots a ROC curve using ggplot2
Fuse learner with simple ove/underrsampling for imbalancy correction in binary classification.
Plot calibration data using ggplot2.
Create a feature filter
Visualizes a learning algorithm on a 1D or 2D data set.
Yeast multilabel classification task
Set the id of a learner object.
Summarize columns of data.frame or task.
Train a learning algorithm.
Subset data in task.
getStackedBaseLearnerPredictions
Returns the predictions for each base learner.
Set the probability threshold the learner should use.
Set the hyperparameters of a learner object.
Train an R learner.
Synthetic Minority Oversampling Technique to handle class imbalancy in binary classification.
Set the type of predictions the learner should return.
Wisonsin Prognostic Breast Cancer (WPBC) survival task
Only exported for internal use.
Remove hyperparameters settings of a learner.
Predict new data with an R learner.
Deprecated, use hasLearnerProperties
instead.
Extract the test performance values from a benchmark result.
Set threshold of prediction object.
Feature selection by wrapper approach.
Sonar classification task
Hyperparameter tuning.
Set aggregation function of measure.
Hyperparameter tuning for multiple measures at once.