%global __brp_check_rpaths %{nil}
%global __requires_exclude ^libmpi
%global packname  SynthesizerPlus
%global packver   0.4.0
%global rlibdir   /usr/local/lib/R/library

Name:             R-CRAN-%{packname}
Version:          0.4.0
Release:          1%{?dist}%{?buildtag}
Summary:          Synthetic Data Generation with Copulas, Evaluation and Multi-Format I/O

License:          EUPL (>= 1.2)
URL:              https://cran.r-project.org/package=%{packname}
Source0:          %{url}&version=%{packver}#/%{packname}_%{packver}.tar.gz


BuildRequires:    R-devel >= 4.1.0
Requires:         R-core >= 4.1.0
BuildArch:        noarch
BuildRequires:    R-CRAN-ggplot2 >= 3.4.0
BuildRequires:    R-splines 
BuildRequires:    R-stats 
BuildRequires:    R-tools 
BuildRequires:    R-utils 
Requires:         R-CRAN-ggplot2 >= 3.4.0
Requires:         R-splines 
Requires:         R-stats 
Requires:         R-tools 
Requires:         R-utils 

%description
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.

%prep
%setup -q -c -n %{packname}

# fix end of executable files
find -type f -executable -exec grep -Iq . {} \; -exec sed -i -e '$a\' {} \;
# prevent binary stripping
[ -d %{packname}/src ] && find %{packname}/src -type f -exec \
  sed -i 's@/usr/bin/strip@/usr/bin/true@g' {} \; || true
[ -d %{packname}/src ] && find %{packname}/src/Make* -type f -exec \
  sed -i 's@-g0@@g' {} \; || true
# don't allow local prefix in executable scripts
find -type f -executable -exec sed -Ei 's@#!( )*/usr/local/bin@#!/usr/bin@g' {} \;

%build

%install

mkdir -p %{buildroot}%{rlibdir}
%{_bindir}/R CMD INSTALL -l %{buildroot}%{rlibdir} %{packname}
test -d %{packname}/src && (cd %{packname}/src; rm -f *.o *.so)
rm -f %{buildroot}%{rlibdir}/R.css
# remove buildroot from installed files
find %{buildroot}%{rlibdir} -type f -exec sed -i "s@%{buildroot}@@g" {} \;

%files
%{rlibdir}/%{packname}