From 406d5685eb60bab68ab29ab78af7cdcb35536f3e Mon Sep 17 00:00:00 2001 From: CoprDistGit Date: Wed, 12 Apr 2023 03:53:38 +0000 Subject: automatic import of python-pandas-plink --- .gitignore | 1 + python-pandas-plink.spec | 428 +++++++++++++++++++++++++++++++++++++++++++++++ sources | 1 + 3 files changed, 430 insertions(+) create mode 100644 python-pandas-plink.spec create mode 100644 sources diff --git a/.gitignore b/.gitignore index e69de29..7a362e6 100644 --- a/.gitignore +++ b/.gitignore @@ -0,0 +1 @@ +/pandas_plink-2.2.9.tar.gz diff --git a/python-pandas-plink.spec b/python-pandas-plink.spec new file mode 100644 index 0000000..824d1d3 --- /dev/null +++ b/python-pandas-plink.spec @@ -0,0 +1,428 @@ +%global _empty_manifest_terminate_build 0 +Name: python-pandas-plink +Version: 2.2.9 +Release: 1 +Summary: Read PLINK files into Pandas data frames +License: MIT +URL: https://github.com/limix/pandas-plink +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/32/98/3a9ce4ab7cc8274fdb7e9d2911cdb946e953280214c06f70943fc02b5b2a/pandas_plink-2.2.9.tar.gz + +Requires: python3-Deprecated +Requires: python3-cffi +Requires: python3-dask[array,dataframe] +Requires: python3-numpy +Requires: python3-pandas +Requires: python3-pytest +Requires: python3-tqdm +Requires: python3-xarray +Requires: python3-zstandard + +%description +# pandas-plink + +Pandas-plink is a Python package for reading [PLINK binary file format](https://www.cog-genomics.org/plink2/formats) andrealized relationship matrices (PLINK or GCTA). +The file reading is taken place via [lazy loading](https://en.wikipedia.org/wiki/Lazy_loading), meaning that it saves up memory by actually reading only the genotypes that are actually accessed by the user. + +Notable changes can be found at the [CHANGELOG.md](https://raw.githubusercontent.com/limix/pandas-plink/master/CHANGELOG.md). + +## Install + +It can be installed using [pip](https://pypi.python.org/pypi/pip): + +```bash +pip install pandas-plink +``` + +Alternatively it can be intalled via [conda](http://conda.pydata.org/docs/index.html): + +```bash +conda install -c conda-forge pandas-plink +``` + +## Usage + +It is as simple as + +```python +>>> from pandas_plink import read_plink1_bin +>>> G = read_plink1_bin("chr11.bed", "chr11.bim", "chr11.fam", verbose=False) +>>> print(G) + +dask.array +Coordinates: + * sample (sample) object 'B001' 'B002' 'B003' ... 'B012' 'B013' 'B014' + * variant (variant) object '11_316849996' '11_316874359' ... '11_345698259' + father (sample) >> print(G.sel(sample="B003", variant="11_316874359").values) +0.0 +>>> print(G.a0.sel(variant="11_316874359").values) +G +>>> print(G.sel(sample="B003", variant="11_316941526").values) +2.0 +>>> print(G.a1.sel(variant="11_316941526").values) +C +``` +Portions of the genotype will be read as the user access them. + +Covariance matrices can also be read very easily. +Example: + +```python +>>> from pandas_plink import read_rel +>>> K = read_rel("plink2.rel.bin") +>>> print(K) + +array([[ 0.885782, 0.233846, -0.186339, -0.009789, -0.138897, 0.287779, + 0.269977, -0.231279, -0.095472, -0.213979], + [ 0.233846, 1.077493, -0.452858, 0.192877, -0.186027, 0.171027, + 0.406056, -0.013149, -0.131477, -0.134314], + [-0.186339, -0.452858, 1.183312, -0.040948, -0.146034, -0.204510, + -0.314808, -0.042503, 0.296828, -0.011661], + [-0.009789, 0.192877, -0.040948, 0.895360, -0.068605, 0.012023, + 0.057827, -0.192152, -0.089094, 0.174269], + [-0.138897, -0.186027, -0.146034, -0.068605, 1.183237, 0.085104, + -0.032974, 0.103608, 0.215769, 0.166648], + [ 0.287779, 0.171027, -0.204510, 0.012023, 0.085104, 0.956921, + 0.065427, -0.043752, -0.091492, -0.227673], + [ 0.269977, 0.406056, -0.314808, 0.057827, -0.032974, 0.065427, + 0.714746, -0.101254, -0.088171, -0.063964], + [-0.231279, -0.013149, -0.042503, -0.192152, 0.103608, -0.043752, + -0.101254, 1.423033, -0.298255, -0.074334], + [-0.095472, -0.131477, 0.296828, -0.089094, 0.215769, -0.091492, + -0.088171, -0.298255, 0.910274, -0.024663], + [-0.213979, -0.134314, -0.011661, 0.174269, 0.166648, -0.227673, + -0.063964, -0.074334, -0.024663, 0.914586]]) +Coordinates: + * sample_0 (sample_0) object 'HG00419' 'HG00650' ... 'NA20508' 'NA20753' + * sample_1 (sample_1) object 'HG00419' 'HG00650' ... 'NA20508' 'NA20753' + fid (sample_1) object 'HG00419' 'HG00650' ... 'NA20508' 'NA20753' + iid (sample_1) object 'HG00419' 'HG00650' ... 'NA20508' 'NA20753' +>>> print(K.values) +[[ 0.89 0.23 -0.19 -0.01 -0.14 0.29 0.27 -0.23 -0.10 -0.21] + [ 0.23 1.08 -0.45 0.19 -0.19 0.17 0.41 -0.01 -0.13 -0.13] + [-0.19 -0.45 1.18 -0.04 -0.15 -0.20 -0.31 -0.04 0.30 -0.01] + [-0.01 0.19 -0.04 0.90 -0.07 0.01 0.06 -0.19 -0.09 0.17] + [-0.14 -0.19 -0.15 -0.07 1.18 0.09 -0.03 0.10 0.22 0.17] + [ 0.29 0.17 -0.20 0.01 0.09 0.96 0.07 -0.04 -0.09 -0.23] + [ 0.27 0.41 -0.31 0.06 -0.03 0.07 0.71 -0.10 -0.09 -0.06] + [-0.23 -0.01 -0.04 -0.19 0.10 -0.04 -0.10 1.42 -0.30 -0.07] + [-0.10 -0.13 0.30 -0.09 0.22 -0.09 -0.09 -0.30 0.91 -0.02] + [-0.21 -0.13 -0.01 0.17 0.17 -0.23 -0.06 -0.07 -0.02 0.91]] +``` + +Please, refer to the [pandas-plink documentation](https://pandas-plink.readthedocs.io/) for more information. + +## Authors + +* [Danilo Horta](https://github.com/horta) + +## License + +This project is licensed under the [MIT License](https://raw.githubusercontent.com/limix/pandas-plink/master/LICENSE.md). + + + + +%package -n python3-pandas-plink +Summary: Read PLINK files into Pandas data frames +Provides: python-pandas-plink +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +BuildRequires: python3-cffi +BuildRequires: gcc +BuildRequires: gdb +%description -n python3-pandas-plink +# pandas-plink + +Pandas-plink is a Python package for reading [PLINK binary file format](https://www.cog-genomics.org/plink2/formats) andrealized relationship matrices (PLINK or GCTA). +The file reading is taken place via [lazy loading](https://en.wikipedia.org/wiki/Lazy_loading), meaning that it saves up memory by actually reading only the genotypes that are actually accessed by the user. + +Notable changes can be found at the [CHANGELOG.md](https://raw.githubusercontent.com/limix/pandas-plink/master/CHANGELOG.md). + +## Install + +It can be installed using [pip](https://pypi.python.org/pypi/pip): + +```bash +pip install pandas-plink +``` + +Alternatively it can be intalled via [conda](http://conda.pydata.org/docs/index.html): + +```bash +conda install -c conda-forge pandas-plink +``` + +## Usage + +It is as simple as + +```python +>>> from pandas_plink import read_plink1_bin +>>> G = read_plink1_bin("chr11.bed", "chr11.bim", "chr11.fam", verbose=False) +>>> print(G) + +dask.array +Coordinates: + * sample (sample) object 'B001' 'B002' 'B003' ... 'B012' 'B013' 'B014' + * variant (variant) object '11_316849996' '11_316874359' ... '11_345698259' + father (sample) >> print(G.sel(sample="B003", variant="11_316874359").values) +0.0 +>>> print(G.a0.sel(variant="11_316874359").values) +G +>>> print(G.sel(sample="B003", variant="11_316941526").values) +2.0 +>>> print(G.a1.sel(variant="11_316941526").values) +C +``` +Portions of the genotype will be read as the user access them. + +Covariance matrices can also be read very easily. +Example: + +```python +>>> from pandas_plink import read_rel +>>> K = read_rel("plink2.rel.bin") +>>> print(K) + +array([[ 0.885782, 0.233846, -0.186339, -0.009789, -0.138897, 0.287779, + 0.269977, -0.231279, -0.095472, -0.213979], + [ 0.233846, 1.077493, -0.452858, 0.192877, -0.186027, 0.171027, + 0.406056, -0.013149, -0.131477, -0.134314], + [-0.186339, -0.452858, 1.183312, -0.040948, -0.146034, -0.204510, + -0.314808, -0.042503, 0.296828, -0.011661], + [-0.009789, 0.192877, -0.040948, 0.895360, -0.068605, 0.012023, + 0.057827, -0.192152, -0.089094, 0.174269], + [-0.138897, -0.186027, -0.146034, -0.068605, 1.183237, 0.085104, + -0.032974, 0.103608, 0.215769, 0.166648], + [ 0.287779, 0.171027, -0.204510, 0.012023, 0.085104, 0.956921, + 0.065427, -0.043752, -0.091492, -0.227673], + [ 0.269977, 0.406056, -0.314808, 0.057827, -0.032974, 0.065427, + 0.714746, -0.101254, -0.088171, -0.063964], + [-0.231279, -0.013149, -0.042503, -0.192152, 0.103608, -0.043752, + -0.101254, 1.423033, -0.298255, -0.074334], + [-0.095472, -0.131477, 0.296828, -0.089094, 0.215769, -0.091492, + -0.088171, -0.298255, 0.910274, -0.024663], + [-0.213979, -0.134314, -0.011661, 0.174269, 0.166648, -0.227673, + -0.063964, -0.074334, -0.024663, 0.914586]]) +Coordinates: + * sample_0 (sample_0) object 'HG00419' 'HG00650' ... 'NA20508' 'NA20753' + * sample_1 (sample_1) object 'HG00419' 'HG00650' ... 'NA20508' 'NA20753' + fid (sample_1) object 'HG00419' 'HG00650' ... 'NA20508' 'NA20753' + iid (sample_1) object 'HG00419' 'HG00650' ... 'NA20508' 'NA20753' +>>> print(K.values) +[[ 0.89 0.23 -0.19 -0.01 -0.14 0.29 0.27 -0.23 -0.10 -0.21] + [ 0.23 1.08 -0.45 0.19 -0.19 0.17 0.41 -0.01 -0.13 -0.13] + [-0.19 -0.45 1.18 -0.04 -0.15 -0.20 -0.31 -0.04 0.30 -0.01] + [-0.01 0.19 -0.04 0.90 -0.07 0.01 0.06 -0.19 -0.09 0.17] + [-0.14 -0.19 -0.15 -0.07 1.18 0.09 -0.03 0.10 0.22 0.17] + [ 0.29 0.17 -0.20 0.01 0.09 0.96 0.07 -0.04 -0.09 -0.23] + [ 0.27 0.41 -0.31 0.06 -0.03 0.07 0.71 -0.10 -0.09 -0.06] + [-0.23 -0.01 -0.04 -0.19 0.10 -0.04 -0.10 1.42 -0.30 -0.07] + [-0.10 -0.13 0.30 -0.09 0.22 -0.09 -0.09 -0.30 0.91 -0.02] + [-0.21 -0.13 -0.01 0.17 0.17 -0.23 -0.06 -0.07 -0.02 0.91]] +``` + +Please, refer to the [pandas-plink documentation](https://pandas-plink.readthedocs.io/) for more information. + +## Authors + +* [Danilo Horta](https://github.com/horta) + +## License + +This project is licensed under the [MIT License](https://raw.githubusercontent.com/limix/pandas-plink/master/LICENSE.md). + + + + +%package help +Summary: Development documents and examples for pandas-plink +Provides: python3-pandas-plink-doc +%description help +# pandas-plink + +Pandas-plink is a Python package for reading [PLINK binary file format](https://www.cog-genomics.org/plink2/formats) andrealized relationship matrices (PLINK or GCTA). +The file reading is taken place via [lazy loading](https://en.wikipedia.org/wiki/Lazy_loading), meaning that it saves up memory by actually reading only the genotypes that are actually accessed by the user. + +Notable changes can be found at the [CHANGELOG.md](https://raw.githubusercontent.com/limix/pandas-plink/master/CHANGELOG.md). + +## Install + +It can be installed using [pip](https://pypi.python.org/pypi/pip): + +```bash +pip install pandas-plink +``` + +Alternatively it can be intalled via [conda](http://conda.pydata.org/docs/index.html): + +```bash +conda install -c conda-forge pandas-plink +``` + +## Usage + +It is as simple as + +```python +>>> from pandas_plink import read_plink1_bin +>>> G = read_plink1_bin("chr11.bed", "chr11.bim", "chr11.fam", verbose=False) +>>> print(G) + +dask.array +Coordinates: + * sample (sample) object 'B001' 'B002' 'B003' ... 'B012' 'B013' 'B014' + * variant (variant) object '11_316849996' '11_316874359' ... '11_345698259' + father (sample) >> print(G.sel(sample="B003", variant="11_316874359").values) +0.0 +>>> print(G.a0.sel(variant="11_316874359").values) +G +>>> print(G.sel(sample="B003", variant="11_316941526").values) +2.0 +>>> print(G.a1.sel(variant="11_316941526").values) +C +``` +Portions of the genotype will be read as the user access them. + +Covariance matrices can also be read very easily. +Example: + +```python +>>> from pandas_plink import read_rel +>>> K = read_rel("plink2.rel.bin") +>>> print(K) + +array([[ 0.885782, 0.233846, -0.186339, -0.009789, -0.138897, 0.287779, + 0.269977, -0.231279, -0.095472, -0.213979], + [ 0.233846, 1.077493, -0.452858, 0.192877, -0.186027, 0.171027, + 0.406056, -0.013149, -0.131477, -0.134314], + [-0.186339, -0.452858, 1.183312, -0.040948, -0.146034, -0.204510, + -0.314808, -0.042503, 0.296828, -0.011661], + [-0.009789, 0.192877, -0.040948, 0.895360, -0.068605, 0.012023, + 0.057827, -0.192152, -0.089094, 0.174269], + [-0.138897, -0.186027, -0.146034, -0.068605, 1.183237, 0.085104, + -0.032974, 0.103608, 0.215769, 0.166648], + [ 0.287779, 0.171027, -0.204510, 0.012023, 0.085104, 0.956921, + 0.065427, -0.043752, -0.091492, -0.227673], + [ 0.269977, 0.406056, -0.314808, 0.057827, -0.032974, 0.065427, + 0.714746, -0.101254, -0.088171, -0.063964], + [-0.231279, -0.013149, -0.042503, -0.192152, 0.103608, -0.043752, + -0.101254, 1.423033, -0.298255, -0.074334], + [-0.095472, -0.131477, 0.296828, -0.089094, 0.215769, -0.091492, + -0.088171, -0.298255, 0.910274, -0.024663], + [-0.213979, -0.134314, -0.011661, 0.174269, 0.166648, -0.227673, + -0.063964, -0.074334, -0.024663, 0.914586]]) +Coordinates: + * sample_0 (sample_0) object 'HG00419' 'HG00650' ... 'NA20508' 'NA20753' + * sample_1 (sample_1) object 'HG00419' 'HG00650' ... 'NA20508' 'NA20753' + fid (sample_1) object 'HG00419' 'HG00650' ... 'NA20508' 'NA20753' + iid (sample_1) object 'HG00419' 'HG00650' ... 'NA20508' 'NA20753' +>>> print(K.values) +[[ 0.89 0.23 -0.19 -0.01 -0.14 0.29 0.27 -0.23 -0.10 -0.21] + [ 0.23 1.08 -0.45 0.19 -0.19 0.17 0.41 -0.01 -0.13 -0.13] + [-0.19 -0.45 1.18 -0.04 -0.15 -0.20 -0.31 -0.04 0.30 -0.01] + [-0.01 0.19 -0.04 0.90 -0.07 0.01 0.06 -0.19 -0.09 0.17] + [-0.14 -0.19 -0.15 -0.07 1.18 0.09 -0.03 0.10 0.22 0.17] + [ 0.29 0.17 -0.20 0.01 0.09 0.96 0.07 -0.04 -0.09 -0.23] + [ 0.27 0.41 -0.31 0.06 -0.03 0.07 0.71 -0.10 -0.09 -0.06] + [-0.23 -0.01 -0.04 -0.19 0.10 -0.04 -0.10 1.42 -0.30 -0.07] + [-0.10 -0.13 0.30 -0.09 0.22 -0.09 -0.09 -0.30 0.91 -0.02] + [-0.21 -0.13 -0.01 0.17 0.17 -0.23 -0.06 -0.07 -0.02 0.91]] +``` + +Please, refer to the [pandas-plink documentation](https://pandas-plink.readthedocs.io/) for more information. + +## Authors + +* [Danilo Horta](https://github.com/horta) + +## License + +This project is licensed under the [MIT License](https://raw.githubusercontent.com/limix/pandas-plink/master/LICENSE.md). + + + + +%prep +%autosetup -n pandas-plink-2.2.9 + +%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-pandas-plink -f filelist.lst +%dir %{python3_sitearch}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Wed Apr 12 2023 Python_Bot - 2.2.9-1 +- Package Spec generated diff --git a/sources b/sources new file mode 100644 index 0000000..df56c3f --- /dev/null +++ b/sources @@ -0,0 +1 @@ +28d3fd16c5b5f4b39464d0216926af20 pandas_plink-2.2.9.tar.gz -- cgit v1.2.3