Learn R Programming
⚠️There's a newer version (1.3.0) of this package.Take me there.

dials

Overview

This package contains tools to create and manage values of tuning parameters and is designed to integrate well with the parsnip package.

The name reflects the idea that tuning predictive models can be like turning a set of dials on a complex machine under duress.

Installation

You can install the released version of dials from CRAN with:

install.packages("dials")

You can install the development version from Github with:

devtools::install_github("tidymodels/dials")

Copy Link

Version

Install

install.packages('dials')

Monthly Downloads

30,765

Version

0.0.8

License

GPL-2

Issues

14

Pull Requests

1

Stars

113

Forks

27

Maintainer

Max Kuhn

Last Published

July 8th, 2020

Functions in dials (0.0.8)

max_times

Word frequencies for removal
max_tokens

Maximum number of retained tokens
max_num_terms

Parameters for possible engine parameters for earth models
dropout

Neural network parameters
num_breaks

Number of cut-points for binning
mixture

Mixture of penalization terms
num_comp

Number of new features
num_tokens

Parameter to determine number of tokens in ngram
encode_unit

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

Functions to finalize data-specific parameter ranges
over_ratio

Parameters for class-imbalance sampling
rbf_sigma

Kernel parameters
mtry

Number of randomly sampled predictors
prune_method

MARS pruning methods
degree

Parameters for exponents
weight

Parameter for "double normalization" when creating token counts
range_validate

Tools for working with parameter ranges
value_validate

Tools for working with parameter values
regularization_factor

Parameters for possible engine parameters for ranger
max_nodes

Parameters for possible engine parameters for randomForest
smoothness

Kernel Smoothness
weight_func

Kernel functions for distance weighting
learn_rate

Learning rate
grid_regular

Create grids of tuning parameters
trees

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

Term frequency weighting methods
penalty

Amount of regularization/penalization
threshold

General thresholding parameter
predictor_prop

Proportion of predictors
token

Token types
neighbors

Number of neighbors
grid_max_entropy

Space-filling parameter grids
freq_cut

Near-zero variance parameters
min_dist

Parameter for the effective minimum distance between embedded points
type_sum.param

Succinct summary of parameter objects
min_unique

Number of unique values for pre-processing
parameters

Information on tuning parameters within an object
update.parameters

Update a single parameter in a parameter set
parameters_constr

Construct a new parameter set object
unknown

Placeholder for unknown parameter values
new-param

Tools for creating new parameter objects
window_size

Parameter for the moving window size
surv_dist

Parametric distributions for censored data
num_hash

Text hashing parameters
dials-package

dials: Tools for working with tuning parameters
deg_free

Degrees of freedom (integer)
cost

Support vector machine parameters
confidence_factor

Parameters for possible engine parameters for C5.0
activation

Activation functions between network layers
Laplace

Laplace correction parameter
dist_power

Minkowski distance parameter
Chicago

Chicago Ridership Data
extrapolation

Parameters for possible engine parameters for Cubist