Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

dials

Tools for Creating Tuning Parameter Values

Many models contain tuning parameters (i.e. parameters that cannot be directly estimated from the data). These tools can be used to define objects for creating, simulating, or validating values for such parameters.

Functions (64)

Chicago

Chicago Ridership Data

Laplace

Laplace correction parameter

activation

Activation functions between network layers

adjust_deg_free

Parameters to adjust effective degrees of freedom

all_neighbors

Parameter to determine which neighbors to use

c5_parameters

Parameters for possible engine parameters for C5.0

conditional_min_criterion

Parameters for possible engine parameters for party models

cost

Support vector machine parameters

cubist_parameters

Parameters for possible engine parameters for Cubist

deg_free

Degrees of freedom (integer)

degree

Parameters for exponents

dials-package

dials: Tools for working with tuning parameters

dist_power

Minkowski distance parameter

dropout

Neural network parameters

earth_parameters

Parameters for possible engine parameters for earth models

encode_unit

Class for converting parameter values back and forth to the unit range

finalize

Functions to finalize data-specific parameter ranges

freq_cut

Near-zero variance parameters

grid_max_entropy

Space-filling parameter grids

grid_regular

Create grids of tuning parameters

learn_rate

Learning rate

max_times

Word frequencies for removal

max_tokens

Maximum number of retained tokens

min_dist

Parameter for the effective minimum distance between embedded points

min_unique

Number of unique values for pre-processing

mixture

Mixture of penalization terms

momentum

Gradient descent momentum parameter

mtry

Number of randomly sampled predictors

neighbors

Number of neighbors

new-param

Tools for creating new parameter objects

num_breaks

Number of cut-points for binning

num_comp

Number of new features

num_tokens

Parameter to determine number of tokens in ngram

over_ratio

Parameters for class-imbalance sampling

parameters

Information on tuning parameters within an object

parameters_constr

Construct a new parameter set object

penalty

Amount of regularization/penalization

predictor_prop

Proportion of predictors

prior_slab_dispersion

Bayesian PCA parameters

prune_method

MARS pruning methods

pull_dials_object

Return a dials parameter object associated with parameters

randomForest_parameters

Parameters for possible engine parameters for randomForest

range_validate

Tools for working with parameter ranges

ranger_parameters

Parameters for possible engine parameters for ranger

rbf_sigma

Kernel parameters

regularization_method

Estimation methods for regularized models

select_features

Parameter to enable feature selection

shrinkage_correlation

Parameters for possible engine parameters for sda models

smoothness

Kernel Smoothness

stop_iter

Early stopping parameter

surv_dist

Parametric distributions for censored data

texthash

Text hashing parameters

threshold

General thresholding parameter

token

Token types

trees

Parameter functions related to tree- and rule-based models.

type_sum.param

Succinct summary of parameter objects

unknown

Placeholder for unknown parameter values

update.parameters

Update a single parameter in a parameter set

value_validate

Tools for working with parameter values

weight

Parameter for "double normalization" when creating token counts

weight_func

Kernel functions for distance weighting

weight_scheme

Term frequency weighting methods

window_size

Parameter for the moving window size

xgboost_parameters

Parameters for possible engine parameters for xgboost

dials

Tools for Creating Tuning Parameter Values

v0.0.10

MIT + file LICENSE

Authors

Max Kuhn [aut], Hannah Frick [aut, cre], RStudio [cph]

Initial release

dials

Functions (64)

dials

We don't support your browser anymore