Function reference • RiverML

Getting target data
Geospatial data
`get_input_data()`	Loading input data
`get_input_polygons()`	Get the polygons for a set of locations defined by `input_data` and `n`
`get_points_from_input_data()`	Get the SpatialPoint from input data
`get_pol()`	Get a SpatialPolygons around a point
`get_target_points()`	Extracts mid-points from streamlines
`get_target_streamlines()`	Load a SpatialLinesDataFrame containing values for valley confinement, GIS slope and RUSLE. The SpatialDataFrame source data is the NHDv2Plus dataset which is segmented into 200-m stream intervals.
`snap_points_to_points()`	Snaps points to points
Terrain analysis
`get_stats_df()`	Wrapper function to calculate terrain analysis statistics for a RasterStack
`get_terrain_metrics()`	Get the terrain analysis metrics
`near_channel_stats()`	Derive near-channel statistics: "median","mean", "min", "max", "sd", "skew"
`raster_stats()`	Derive raster statistics: "median","mean", "min", "max", "sd", "skew"
`terrain_()`	Modified `terrain()` function
Statistical roughness
`get_H_rasters()`	Retrieve rasters of statistical roughness of topography
`join_streamlines_with_H_rasters()`	Extract the values of all H_rasters along streamlines
StreamCat
`drops_streamcat_df()`	Remove some variables from `streamcat_df`
`get_streamcat_df()`	Get the StreamCat data
`get_target_streamcat_df()`	Matches `streamcat_df` and `target_streamlines` using `COMID`
Machine learning
Data loading
`fmt_labels()`	Format the class labels
`get_coords()`	Retrieve the coordinates of the observations
`get_target_data()`	Load target features
`get_training_data()`	Load training features
`make_training_data()`	Transform training data from `list` to `data.frame`
`sanitize_data()`	Ensures that non-finite values are flagged as `NA`
Data transformation
`get_ppc()`	Get the preprocessing
`get_smote_coords()`	Produces noisy coordinates for SMOTE data
`get_smote_data()`	Resolve the class imbalance using the SMOTE algorithm
`preproc_data()`	Process the data according to a `preProcess` object
`resolve_class_imbalance()`	Resolve class imbalances using `UBL` package
Constructing learners
`get_final_learners()`	Get the final learners from the benchmark tuning results
`get_learners()`	Get the learners
`get_learners_internal()`	Internal function to get the learners
`get_ps()`	Get the values for the hyper-parameter(s) set
Benchmark
`compute_benchmark()`	Computes the benchmark in parallel mode
`compute_final_model()`	Compute the final models in sequential mode
`get_bestBMR_tuning_results()`	Retrieve the value of the benchmark tuning results
`get_inner()`	Get the inner folds for the nested resampling
`get_outers()`	Get the outer folds for the nested resampling
`regional_benchmark()`	Wrapper function to compute the benchmark
`savePARAMETERS()`	Saves the benchmark parameters
Benchmark post-processing
`fixVarNames()`	Fixes variable names for data visualization purpose
`getAllBMRS()`	Get all the benchmark result in a directory of directories
`getBMRTuningEntropy()`	Compute the tuning entropy
`getBMR_perf_tune()`	Selecting elements from `BMR_res` and cosmetic changes
`getBestBMRTune()`	Get the tuning results of the optimal models
`getBestBMRTuningEntropy()`	Get the tuning entropy corresponding to the optimal models
`getFreqBestFeatureSets()`	Get the frequency of selection of a given feature across all regions
`getHyperparNames()`	Get hyper-parameters names
`getTunePlot()`	Plot the distribution of hyper-parameters resulting from the nested resampling
`get_BMR()`	Retrieve benchmark results
`get_bestFeatureSets()`	Get the optinmal feature sets
`makeAllFeatureImportancePlotFS()`	Create feature importance across all regions of study
`makeAverageAUCPlot()`	Make average AUC plot
`makeAverageAccPlot()`	Make average accuracy plot
`makeBestTuneAUCPlot()`	Make a violin plot comparing the results from the optimal models
`makeExampleModelSelectionPlot()`	Make an example plot of model selection
`makeFeatureImportancePlot()`	Makes a dot chart of feature importance
`makeTotalTimetrainPlot()`	Make training time plot
`makeTuningEntropyPlot()`	Create a plot of the evolution of tuning entropy with the number of selected features
`makeWindowInfluencePlot()`	Visualize the influence of window size on model selection
`normH()`	Calculates entropy
Predictions
`calibrated_predictions()`	Calibrate machine learning predictions
`compute_predictions()`	Retrieve the final (optimal) models
`get_calibrations()`	Performs a posterior multinomial calibration of machine learning predictions
`get_entropy_df()`	Formats entropy rate results
`get_final_models()`	Retrieve the final (optimal) models
`get_predictions()`	Get predictions
`richness()`	Calculate the richness (number of different species)
`shannon_weiner()`	Calculates Shannon-Weiner entropy
`simpson_evenness()`	Calculate Simpson's evenness
Datasets
`BMR_res`	Benchmark results
`CA_geology`	Geological map of California
`SFE_all_data_df`	Target data for SFE region
`regional_characteristics`	Regional characteristics
`target_streamlines_K`	Target streamlines for the K region
`target_streamlines_NC`	Target streamlines for the NC region
`target_streamlines_NCC`	Target streamlines for the NCC region
`target_streamlines_SAC`	Target streamlines for the SAC region
`target_streamlines_SC`	Target streamlines for the SC region
`target_streamlines_SCC`	Target streamlines for the SCC region
`target_streamlines_SECA`	Target streamlines for the SECA region
`target_streamlines_SFE`	Target streamlines for the SFE region
`target_streamlines_SJT`	Target streamlines for the SJT region
Misc
`HPC_optim()`	Computes an optimized repartition of the HPC computing

Reference

Getting target data

Geospatial data

Terrain analysis

Statistical roughness

StreamCat

Machine learning

Data loading

Data transformation

Constructing learners

Benchmark

Benchmark post-processing

Predictions

Datasets

Misc