compare_synthetic

<code>compare_synthetic()</code> evaluates the fidelity, utility and disclosure risk
of a synthetic data set in one call:<ul>
<li>marginal: <code>marginal_metrics()</code> per variable;</li>
<li>association: <code>association_matrix()</code> of both data sets and their
difference;</li>
<li>utility: <code>pmse()</code> and cross-validated <code>discriminator_auc()</code>;</li>
<li>privacy: <code>dcr()</code> distance to closest record.</li>
</ul>The result has <code><a href="/link/print()?package=SynthesizerPlus&version=0.4.0" data-mini-rdoc="SynthesizerPlus::print()">print()</a></code>, <code><a href="/link/summary()?package=SynthesizerPlus&version=0.4.0" data-mini-rdoc="SynthesizerPlus::summary()">summary()</a></code>, <code><a href="/link/plot()?package=SynthesizerPlus&version=0.4.0" data-mini-rdoc="SynthesizerPlus::plot()">plot()</a></code> and
<code><a href="https://ggplot2.tidyverse.org/reference/autoplot.html">ggplot2::autoplot()</a></code> methods.

Generates synthetic versions of numeric, categorical, mixed-type
and time-series data. Marginal distributions are modelled with
interpolated empirical quantile functions and dependence with Gaussian or
Student-t copulas (Sklar, 1959). Discrete and categorical variables enter
the copula through the distributional transform (Ruschendorf, 2009,
<doi:10.1016/j.jspi.2009.05.030>), and their latent correlations are
estimated by maximum likelihood as polychoric (Olsson, 1979,
<doi:10.1007/BF02296207>) and polyserial (Olsson, Drasgow and Dorans,
1982, <doi:10.1007/BF02294164>) correlations. Unordered categories are
placed on their latent coordinate in an order estimated from their
association with the other variables. Missing values are
modelled by missingness indicators inside the copula, so that
missingness may depend on other variables. Supports stratified models,
a closeness parameter with calibration to a target distance or
disclosure-risk level, chunked generation of very large data sets,
optional hybrid copula and conditional CART or GAM synthesis for
one continuous response (requiring 'rpart' or 'mgcv'), training-only
automatic selection of the conditional engine, experimental nominal
conditional synthesis of one unordered categorical response (requiring
'nnet'), copula vector-autoregressive and bootstrap time-series synthesis,
augmentation of small training sets for machine learning, and random
generation from multivariate distributions and elliptical and
Archimedean copulas. Fidelity, utility and disclosure risk are assessed
with marginal distances, association matrices, propensity score
mean-squared error (Snoke et al., 2018, <doi:10.1111/rssa.12358>),
confidence-interval overlap, correct attribution probability and
distance to closest record, with 'ggplot2' visualisations. Data can be
read from and written to CSV, TSV, RDS, RData, Parquet, Feather, HDF5,
JSON, NDJSON, Excel, SPSS, Stata, SAS and fst files. The
empirical-quantile and copula approach builds on ideas of the
'synthesizer' package by Mark van der Loo.

Bogdan Oancea

SynthesizerPlus

Synthetic Data Generation with Copulas, Evaluation and
Multi-Format I/O

compare_synthetic function

<dl><dt>real, synthetic</dt>
<dd>Data frames (or objects coercible to data frames)
with common columns.</dd>
<dt>vars</dt>
<dd>Optional subset of variables.</dd>
<dt>metrics</dt>
<dd>Which groups of metrics to compute.</dd>
<dt>max_rows</dt>
<dd>Maximum rows per data set for the classifier and distance
computations.</dd>
<dt>seed</dt>
<dd>Optional random seed.</dd></dl>

Arguments

<code>compare_synthetic()</code> evaluates the fidelity, utility and disclosure risk
of a synthetic data set in one call:<ul>
<li>marginal: <code>marginal_metrics()</code> per variable;</li>
<li>association: <code>association_matrix()</code> of both data sets and their
difference;</li>
<li>utility: <code>pmse()</code> and cross-validated <code>discriminator_auc()</code>;</li>
<li>privacy: <code>dcr()</code> distance to closest record.</li>
</ul>

The result has <code><a href='https://rdrr.io/r/base/print.html'>print()</a></code>, <code><a href='https://rdrr.io/r/base/summary.html'>summary()</a></code>, <code><a href='https://rdrr.io/r/graphics/plot.default.html'>plot()</a></code> and
<code><a href='https://ggplot2.tidyverse.org/reference/autoplot.html'>ggplot2::autoplot()</a></code> methods.

Compare synthetic data with the real data — compare_synthetic

<dl>

<dt>real, synthetic</dt>
<dd>Data frames (or objects coercible to data frames)
with common columns.</dd>


<dt>vars</dt>
<dd>Optional subset of variables.</dd>


<dt>metrics</dt>
<dd>Which groups of metrics to compute.</dd>


<dt>max_rows</dt>
<dd>Maximum rows per data set for the classifier and distance
computations.</dd>


<dt>seed</dt>
<dd>Optional random seed.</dd>

</dl>

compare_synthetic: Compare synthetic data with the real data

Description

Usage

Value

Arguments

Examples