%global _empty_manifest_terminate_build 0
Name:		python-pandas-schema
Version:	0.3.6
Release:	1
Summary:	A validation library for Pandas data frames using user-friendly schemas
License:	MIT
URL:		https://github.com/TMiguelT/PandasSchema
Source0:	https://mirrors.nju.edu.cn/pypi/web/packages/17/2a/d302fd983cdf3fb9a3d24d981e4a3c7340994030c0c46b397b4d9db83bea/pandas_schema-0.3.6.tar.gz
BuildArch:	noarch

Requires:	python3-numpy
Requires:	python3-pandas
Requires:	python3-packaging

%description
PandasSchema is a module for validating tabulated data, such as CSVs
(Comma Separated Value files), and TSVs (Tab Separated Value files).
It uses the incredibly powerful data analysis tool Pandas to do so
quickly and efficiently.
For example, say your code expects a CSV that looks a bit like this:
   Given Name,Family Name,Age,Sex,Customer ID
   Gerald,Hampton,82,Male,2582GABK
   Yuuwa,Miyake,27,Male,7951WVLW
   Edyta,Majewska,50,Female,7758NSID
Now you want to be able to ensure that the data in your CSV is in the
correct format:
   import pandas as pd
   from io import StringIO
   from pandas_schema import Column, Schema
   from pandas_schema.validation import LeadingWhitespaceValidation, TrailingWhitespaceValidation, CanConvertValidation, MatchesPatternValidation, InRangeValidation, InListValidation
   schema = Schema([
       Column('Given Name', [LeadingWhitespaceValidation(), TrailingWhitespaceValidation()]),
       Column('Family Name', [LeadingWhitespaceValidation(), TrailingWhitespaceValidation()]),
       Column('Age', [InRangeValidation(0, 120)]),
       Column('Sex', [InListValidation(['Male', 'Female', 'Other'])]),
       Column('Customer ID', [MatchesPatternValidation(r'\d{4}[A-Z]{4}')])
   ])
   test_data = pd.read_csv(StringIO('''Given Name,Family Name,Age,Sex,Customer ID
   Gerald ,Hampton,82,Male,2582GABK
   Yuuwa,Miyake,270,male,7951WVLW
   Edyta,Majewska ,50,Female,775ANSID
   '''))
   errors = schema.validate(test_data)
   for error in errors:
       print(error)
PandasSchema would then output
   {row: 0, column: "Given Name"}: "Gerald " contains trailing whitespace
   {row: 1, column: "Age"}: "270" was not in the range [0, 120)
   {row: 1, column: "Sex"}: "male" is not in the list of legal options (Male, Female, Other)
   {row: 2, column: "Family Name"}: "Majewska " contains trailing whitespace
   {row: 2, column: "Customer ID"}: "775ANSID" does not match the pattern "\d{4}[A-Z]{4}"

%package -n python3-pandas-schema
Summary:	A validation library for Pandas data frames using user-friendly schemas
Provides:	python-pandas-schema
BuildRequires:	python3-devel
BuildRequires:	python3-setuptools
BuildRequires:	python3-pip
%description -n python3-pandas-schema
PandasSchema is a module for validating tabulated data, such as CSVs
(Comma Separated Value files), and TSVs (Tab Separated Value files).
It uses the incredibly powerful data analysis tool Pandas to do so
quickly and efficiently.
For example, say your code expects a CSV that looks a bit like this:
   Given Name,Family Name,Age,Sex,Customer ID
   Gerald,Hampton,82,Male,2582GABK
   Yuuwa,Miyake,27,Male,7951WVLW
   Edyta,Majewska,50,Female,7758NSID
Now you want to be able to ensure that the data in your CSV is in the
correct format:
   import pandas as pd
   from io import StringIO
   from pandas_schema import Column, Schema
   from pandas_schema.validation import LeadingWhitespaceValidation, TrailingWhitespaceValidation, CanConvertValidation, MatchesPatternValidation, InRangeValidation, InListValidation
   schema = Schema([
       Column('Given Name', [LeadingWhitespaceValidation(), TrailingWhitespaceValidation()]),
       Column('Family Name', [LeadingWhitespaceValidation(), TrailingWhitespaceValidation()]),
       Column('Age', [InRangeValidation(0, 120)]),
       Column('Sex', [InListValidation(['Male', 'Female', 'Other'])]),
       Column('Customer ID', [MatchesPatternValidation(r'\d{4}[A-Z]{4}')])
   ])
   test_data = pd.read_csv(StringIO('''Given Name,Family Name,Age,Sex,Customer ID
   Gerald ,Hampton,82,Male,2582GABK
   Yuuwa,Miyake,270,male,7951WVLW
   Edyta,Majewska ,50,Female,775ANSID
   '''))
   errors = schema.validate(test_data)
   for error in errors:
       print(error)
PandasSchema would then output
   {row: 0, column: "Given Name"}: "Gerald " contains trailing whitespace
   {row: 1, column: "Age"}: "270" was not in the range [0, 120)
   {row: 1, column: "Sex"}: "male" is not in the list of legal options (Male, Female, Other)
   {row: 2, column: "Family Name"}: "Majewska " contains trailing whitespace
   {row: 2, column: "Customer ID"}: "775ANSID" does not match the pattern "\d{4}[A-Z]{4}"

%package help
Summary:	Development documents and examples for pandas-schema
Provides:	python3-pandas-schema-doc
%description help
PandasSchema is a module for validating tabulated data, such as CSVs
(Comma Separated Value files), and TSVs (Tab Separated Value files).
It uses the incredibly powerful data analysis tool Pandas to do so
quickly and efficiently.
For example, say your code expects a CSV that looks a bit like this:
   Given Name,Family Name,Age,Sex,Customer ID
   Gerald,Hampton,82,Male,2582GABK
   Yuuwa,Miyake,27,Male,7951WVLW
   Edyta,Majewska,50,Female,7758NSID
Now you want to be able to ensure that the data in your CSV is in the
correct format:
   import pandas as pd
   from io import StringIO
   from pandas_schema import Column, Schema
   from pandas_schema.validation import LeadingWhitespaceValidation, TrailingWhitespaceValidation, CanConvertValidation, MatchesPatternValidation, InRangeValidation, InListValidation
   schema = Schema([
       Column('Given Name', [LeadingWhitespaceValidation(), TrailingWhitespaceValidation()]),
       Column('Family Name', [LeadingWhitespaceValidation(), TrailingWhitespaceValidation()]),
       Column('Age', [InRangeValidation(0, 120)]),
       Column('Sex', [InListValidation(['Male', 'Female', 'Other'])]),
       Column('Customer ID', [MatchesPatternValidation(r'\d{4}[A-Z]{4}')])
   ])
   test_data = pd.read_csv(StringIO('''Given Name,Family Name,Age,Sex,Customer ID
   Gerald ,Hampton,82,Male,2582GABK
   Yuuwa,Miyake,270,male,7951WVLW
   Edyta,Majewska ,50,Female,775ANSID
   '''))
   errors = schema.validate(test_data)
   for error in errors:
       print(error)
PandasSchema would then output
   {row: 0, column: "Given Name"}: "Gerald " contains trailing whitespace
   {row: 1, column: "Age"}: "270" was not in the range [0, 120)
   {row: 1, column: "Sex"}: "male" is not in the list of legal options (Male, Female, Other)
   {row: 2, column: "Family Name"}: "Majewska " contains trailing whitespace
   {row: 2, column: "Customer ID"}: "775ANSID" does not match the pattern "\d{4}[A-Z]{4}"

%prep
%autosetup -n pandas-schema-0.3.6

%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-schema -f filelist.lst
%dir %{python3_sitelib}/*

%files help -f doclist.lst
%{_docdir}/*

%changelog
* Mon Apr 10 2023 Python_Bot <Python_Bot@openeuler.org> - 0.3.6-1
- Package Spec generated