Package: scR 0.7.0

Perry Carter

scR: Empirical Sample Complexity Bounds

Provides tools for estimating empirical sample complexity bounds for supervised learning tasks. The package supports simulation-based estimates of generalization curves, parametric extrapolation of empirical sample complexity bounds, theoretical bounds based on Vapnik-Chervonenkis dimension, and optional monotone Gaussian process extrapolation for users who install the external 'cmdstanr' workflow. For more details, see Carter and Choi (2024) <doi:10.31219/osf.io/evrcj>.

Authors:Perry Carter [aut, cre], Dahyun Choi [aut]

scR_0.7.0.tar.gz
scR_0.7.0.zip(r-4.7)scR_0.7.0.zip(r-4.6)scR_0.7.0.zip(r-4.5)
scR_0.7.0.tgz(r-4.6-any)scR_0.7.0.tgz(r-4.5-any)
scR_0.7.0.tar.gz(r-4.7-any)scR_0.7.0.tar.gz(r-4.6-any)
scR_0.7.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
scR/json (API)

# Install 'scR' in R:
install.packages('scR', repos = c('https://pjesscarter.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/pjesscarter/scr/issues

On CRAN:

Conda:

3.18 score 5 scripts 232 downloads 12 exports 75 dependencies

Last updated from:8fe5769fd1. Checks:9 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-x86_64OK165
source / vignettesOK238
linux-release-x86_64OK202
macos-release-arm64OK156
macos-oldrel-arm64OK192
windows-develOK109
windows-releaseOK110
windows-oldrelOK99
wasm-releaseOK185

Exports:acc_simconduct_interpolationcreate_scb_modelcreate_scb_predictionestimate_accuracyfit_gp_scb_curvegendatagetpacinterpolate_scbinterpolate_scb_gpscbsimvcd

Dependencies:askpassbase64encbslibcachemclicodetoolscpp11crosstalkcurldata.tabledigestdplyrevaluatefarverfastmapfontawesomefsfurrrfuturegenericsggplot2globalsgluegtablehighrhtmltoolshtmlwidgetshttrisobandjquerylibjsonliteknitrlabelinglaterlatticelazyevallifecyclelistenvmagrittrMatrixmemoisemimeminpack.lmopensslotelparallellypbapplypillarpkgconfigplotlyprogressrpromisespurrrR6rappdirsRColorBrewerRcpprlangrmarkdownS7sassscalesstringistringrsystibbletidyrtidyselecttinytexutf8vctrsviridisLitewithrxfunyaml

Readme and manuals

Help Manual

Help pageTopics
Utility function to generate accuracy metrics, for use with 'estimate_accuracy()'acc_sim
Conduct interpolation on a single simulationconduct_interpolation
Create custom model fitting functioncreate_scb_model
Create custom prediction functioncreate_scb_prediction
Estimate sample complexity bounds for a binary classification algorithm using either simulated or user-supplied data.estimate_accuracy
Fit an extrapolation model using nonlinear least squaresfit_and_predict
Fit a monotone Gaussian process sample-complexity curvefit_gp_scb_curve
Simulate data with appropriate structure to be used in estimating sample complexity boundsgendata
Recalculate achieved sample complexity bounds given different parameter inputsgetpac
Conduct interpolation on a list of datainterpolate_scb
Interpolate sample-complexity curves using monotone Gaussian processesinterpolate_scb_gp
Utility function to define the least-squares loss function to be optimized for 'simvcd()'loss
Plot a monotone Gaussian process sample-complexity fitplot.empirical_scb_gp
Plot method for an 'empirical_scb_list' objectplot.empirical_scb_list
Plot method for simulated sample complexity bounds ('scb_data' object)plot.scb_data
Utility function to generate data points for estimation of the VC Dimension of a user-specified binary classification algorithm given a specified sample size.risk_bounds
Calculate sample complexity bounds for a classifier given target accuracyscb
Estimate the Vapnik-Chervonenkis (VC) dimension of an arbitrary binary classification algorithm.simvcd
Summarize a monotone Gaussian process sample-complexity fitsummary.empirical_scb_gp
Summary of empirical sample complexity bound resultssummary.empirical_scb_list