augment_data

augment_data.data.frame

augment_data.default

augment_data.matrix

augment_data.ts

Fits a synthesizer to <code>data</code> and returns the real records together with
synthetic ones, ready to train a machine-learning model.<ul>
<li>For a data frame (or matrix), <code>n</code> synthetic rows are appended to the
real rows. An indicator column can be added with <code>label</code>. A vector is
extended with <code>n</code> synthetic values.</li>
<li>For a time series, <code>nsim</code> synthetic series of length <code>n</code> are drawn
(see <code>fit_synthesizer.ts()</code>) and returned in a list, preceded by the real
series. Use <code>ts_windows()</code> to turn the list into a table of lagged
features.</li>
</ul>Synthetic data cannot add information that is not in the real data. What
they add is a smoothed version of the training distribution, which acts as
a regulariser and mainly helps flexible, high-variance learners (trees,
nearest neighbours, neural networks) trained on small samples. Always
fit the synthesizer on the training data only and measure the effect
on held-out real data; see <code>vignette("augmentation")</code>.

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

augment_data function

<dl><dt>data</dt>
<dd>Training data: a data frame, matrix or <code>ts</code> object.</dd>
<dt>...</dt>
<dd>Passed to <code>fit_synthesizer()</code> (e.g. <code>by</code>, <code>copula</code>, or for
time series <code>method</code>, <code>order</code>).</dd>
<dt>n</dt>
<dd>For tabular data: number of synthetic rows (default: 10 times the
training size). For time series: length of each synthetic series
(default: the length of <code>data</code>).</dd>
<dt>keep_real</dt>
<dd>Include the real data in the result?</dd>
<dt>label</dt>
<dd>Optional name of a logical column marking synthetic rows
(tabular data only).</dd>
<dt>closeness, perturb</dt>
<dd>How close the synthetic rows are to the real
ones (tabular data only); see <code>generate()</code>. Lower closeness gives more
diverse synthetic rows.</dd>
<dt>seed</dt>
<dd>Optional random seed.</dd>
<dt>nsim</dt>
<dd>For time series: number of synthetic series.</dd></dl>

Arguments

Fits a synthesizer to <code>data</code> and returns the real records together with
synthetic ones, ready to train a machine-learning model.<ul>
<li>For a data frame (or matrix), <code>n</code> synthetic rows are appended to the
real rows. An indicator column can be added with <code>label</code>. A vector is
extended with <code>n</code> synthetic values.</li>
<li>For a time series, <code>nsim</code> synthetic series of length <code>n</code> are drawn
(see <code>fit_synthesizer.ts()</code>) and returned in a list, preceded by the real
series. Use <code>ts_windows()</code> to turn the list into a table of lagged
features.</li>
</ul>

Synthetic data cannot add information that is not in the real data. What
they add is a smoothed version of the training distribution, which acts as
a regulariser and mainly helps flexible, high-variance learners (trees,
nearest neighbours, neural networks) trained on small samples. Always
fit the synthesizer on the training data only and measure the effect
on held-out real data; see <code>vignette("augmentation")</code>.

Augment a small training set with synthetic data — augment_data

<dl>

<dt>data</dt>
<dd>Training data: a data frame, matrix or <code>ts</code> object.</dd>


<dt>...</dt>
<dd>Passed to <code>fit_synthesizer()</code> (e.g. <code>by</code>, <code>copula</code>, or for
time series <code>method</code>, <code>order</code>).</dd>


<dt>n</dt>
<dd>For tabular data: number of synthetic rows (default: 10 times the
training size). For time series: length of each synthetic series
(default: the length of <code>data</code>).</dd>


<dt>keep_real</dt>
<dd>Include the real data in the result?</dd>


<dt>label</dt>
<dd>Optional name of a logical column marking synthetic rows
(tabular data only).</dd>


<dt>closeness, perturb</dt>
<dd>How close the synthetic rows are to the real
ones (tabular data only); see <code>generate()</code>. Lower closeness gives more
diverse synthetic rows.</dd>


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


<dt>nsim</dt>
<dd>For time series: number of synthetic series.</dd>

</dl>

augment_data: Augment a small training set with synthetic data

Description

Usage

Value

Arguments

See Also

Examples