From 7f97180ebb80aff752923a8c77ebe55f39c8c889 Mon Sep 17 00:00:00 2001 From: CoprDistGit Date: Mon, 10 Apr 2023 13:23:33 +0000 Subject: automatic import of python-spark-sklearn --- .gitignore | 1 + python-spark-sklearn.spec | 105 ++++++++++++++++++++++++++++++++++++++++++++++ sources | 1 + 3 files changed, 107 insertions(+) create mode 100644 python-spark-sklearn.spec create mode 100644 sources diff --git a/.gitignore b/.gitignore index e69de29..f3e01c3 100644 --- a/.gitignore +++ b/.gitignore @@ -0,0 +1 @@ +/spark-sklearn-0.3.0.tar.gz diff --git a/python-spark-sklearn.spec b/python-spark-sklearn.spec new file mode 100644 index 0000000..3a200be --- /dev/null +++ b/python-spark-sklearn.spec @@ -0,0 +1,105 @@ +%global _empty_manifest_terminate_build 0 +Name: python-spark-sklearn +Version: 0.3.0 +Release: 1 +Summary: Integration tools for running scikit-learn on Spark +License: Apache 2.0 +URL: https://github.com/databricks/spark-sklearn +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/b0/3f/34b8dec7d2cfcfe0ba99d637b4f2d306c1ca0b404107c07c829e085f6b38/spark-sklearn-0.3.0.tar.gz +BuildArch: noarch + + +%description +This package contains some tools to integrate the `Spark computing framework `_ +with the popular `scikit-learn machine library `_. Among other things, it can: +- train and evaluate multiple scikit-learn models in parallel. It is a distributed analog to the + `multicore implementation `_ included by default in ``scikit-learn`` +- convert Spark's Dataframes seamlessly into numpy ``ndarray`` or sparse matrices +- (experimental) distribute Scipy's sparse matrices as a dataset of sparse vectors +It focuses on problems that have a small amount of data and that can be run in parallel. +For small datasets, it distributes the search for estimator parameters (``GridSearchCV`` in scikit-learn), +using Spark. For datasets that do not fit in memory, we recommend using the `distributed implementation in +`Spark MLlib `_. +This package distributes simple tasks like grid-search cross-validation. +It does not distribute individual learning algorithms (unlike Spark MLlib). + +%package -n python3-spark-sklearn +Summary: Integration tools for running scikit-learn on Spark +Provides: python-spark-sklearn +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-spark-sklearn +This package contains some tools to integrate the `Spark computing framework `_ +with the popular `scikit-learn machine library `_. Among other things, it can: +- train and evaluate multiple scikit-learn models in parallel. It is a distributed analog to the + `multicore implementation `_ included by default in ``scikit-learn`` +- convert Spark's Dataframes seamlessly into numpy ``ndarray`` or sparse matrices +- (experimental) distribute Scipy's sparse matrices as a dataset of sparse vectors +It focuses on problems that have a small amount of data and that can be run in parallel. +For small datasets, it distributes the search for estimator parameters (``GridSearchCV`` in scikit-learn), +using Spark. For datasets that do not fit in memory, we recommend using the `distributed implementation in +`Spark MLlib `_. +This package distributes simple tasks like grid-search cross-validation. +It does not distribute individual learning algorithms (unlike Spark MLlib). + +%package help +Summary: Development documents and examples for spark-sklearn +Provides: python3-spark-sklearn-doc +%description help +This package contains some tools to integrate the `Spark computing framework `_ +with the popular `scikit-learn machine library `_. Among other things, it can: +- train and evaluate multiple scikit-learn models in parallel. It is a distributed analog to the + `multicore implementation `_ included by default in ``scikit-learn`` +- convert Spark's Dataframes seamlessly into numpy ``ndarray`` or sparse matrices +- (experimental) distribute Scipy's sparse matrices as a dataset of sparse vectors +It focuses on problems that have a small amount of data and that can be run in parallel. +For small datasets, it distributes the search for estimator parameters (``GridSearchCV`` in scikit-learn), +using Spark. For datasets that do not fit in memory, we recommend using the `distributed implementation in +`Spark MLlib `_. +This package distributes simple tasks like grid-search cross-validation. +It does not distribute individual learning algorithms (unlike Spark MLlib). + +%prep +%autosetup -n spark-sklearn-0.3.0 + +%build +%py3_build + +%install +%py3_install +install -d -m755 %{buildroot}/%{_pkgdocdir} +if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi +if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi +if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi +if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi +pushd %{buildroot} +if [ -d usr/lib ]; then + find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/lib64 ]; then + find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/bin ]; then + find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/sbin ]; then + find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst +fi +touch doclist.lst +if [ -d usr/share/man ]; then + find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst +fi +popd +mv %{buildroot}/filelist.lst . +mv %{buildroot}/doclist.lst . + +%files -n python3-spark-sklearn -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Mon Apr 10 2023 Python_Bot - 0.3.0-1 +- Package Spec generated diff --git a/sources b/sources new file mode 100644 index 0000000..8b12113 --- /dev/null +++ b/sources @@ -0,0 +1 @@ +4460d6c8402a5b46d361c442c2e47f19 spark-sklearn-0.3.0.tar.gz -- cgit v1.2.3