diff options
Diffstat (limited to 'python-tfidf-matcher.spec')
| -rw-r--r-- | python-tfidf-matcher.spec | 107 |
1 files changed, 107 insertions, 0 deletions
diff --git a/python-tfidf-matcher.spec b/python-tfidf-matcher.spec new file mode 100644 index 0000000..5cc5b21 --- /dev/null +++ b/python-tfidf-matcher.spec @@ -0,0 +1,107 @@ +%global _empty_manifest_terminate_build 0 +Name: python-tfidf-matcher +Version: 0.3.0 +Release: 1 +Summary: A small package that enables super-fast TF-IDF based string matching. +License: MIT License +URL: https://github.com/louistsiattalou/tfidf_matcher +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/cc/cd/af378c05b1f199879f2deed7c31abc4175dad73052f08832a4b4752cdbf6/tfidf_matcher-0.3.0.tar.gz +BuildArch: noarch + +Requires: python3-scikit-learn +Requires: python3-pandas + +%description +This package provides two functions: +- `ngrams()`: Simple ngram generator. +- `matcher()`: Matches a list of strings against a reference corpus. + Does this by: + - Vectorizing the reference corpus using TF-IDF into a + term-document matrix. + - Fitting a K-NearestNeighbours model to the sparse matrix. + - Vectorizing the list of strings to be matched and passing it in + to the KNN model to calculate the cosine distance (the OOTB + `cosine_similarity` function in sklearn is very + memory-inefficient for our use case). + - Some data manipulation to emit `k_matches` closest matches. + +%package -n python3-tfidf-matcher +Summary: A small package that enables super-fast TF-IDF based string matching. +Provides: python-tfidf-matcher +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-tfidf-matcher +This package provides two functions: +- `ngrams()`: Simple ngram generator. +- `matcher()`: Matches a list of strings against a reference corpus. + Does this by: + - Vectorizing the reference corpus using TF-IDF into a + term-document matrix. + - Fitting a K-NearestNeighbours model to the sparse matrix. + - Vectorizing the list of strings to be matched and passing it in + to the KNN model to calculate the cosine distance (the OOTB + `cosine_similarity` function in sklearn is very + memory-inefficient for our use case). + - Some data manipulation to emit `k_matches` closest matches. + +%package help +Summary: Development documents and examples for tfidf-matcher +Provides: python3-tfidf-matcher-doc +%description help +This package provides two functions: +- `ngrams()`: Simple ngram generator. +- `matcher()`: Matches a list of strings against a reference corpus. + Does this by: + - Vectorizing the reference corpus using TF-IDF into a + term-document matrix. + - Fitting a K-NearestNeighbours model to the sparse matrix. + - Vectorizing the list of strings to be matched and passing it in + to the KNN model to calculate the cosine distance (the OOTB + `cosine_similarity` function in sklearn is very + memory-inefficient for our use case). + - Some data manipulation to emit `k_matches` closest matches. + +%prep +%autosetup -n tfidf-matcher-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-tfidf-matcher -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Mon May 29 2023 Python_Bot <Python_Bot@openeuler.org> - 0.3.0-1 +- Package Spec generated |