diff options
Diffstat (limited to 'python-pandas-usaddress.spec')
| -rw-r--r-- | python-pandas-usaddress.spec | 338 |
1 files changed, 338 insertions, 0 deletions
diff --git a/python-pandas-usaddress.spec b/python-pandas-usaddress.spec new file mode 100644 index 0000000..58d9403 --- /dev/null +++ b/python-pandas-usaddress.spec @@ -0,0 +1,338 @@ +%global _empty_manifest_terminate_build 0 +Name: python-pandas-usaddress +Version: 0.21 +Release: 1 +Summary: The usaddress library made easy with Pandas. +License: MIT +URL: https://github.com/Lyonk71/pandas-usaddress +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/63/16/63e09bc175aee1a03dc6ba455e1f21902b3854d199b530a4cac8cf1ea9f4/pandas_usaddress-0.21.tar.gz +BuildArch: noarch + +Requires: python3-pandas +Requires: python3-usaddress + +%description +# pandas-usaddress +The usaddress library made easy with Pandas. + +Also supports standardizing addresses to meet USPS standards. + +# Installation + +pip install pandas-usaddress + +# Usage + +### Basic Parsing + + import pandas as pd + import pandas_usaddress + + #load dataframe + df = pd.read_csv('test_file.csv') + + #initiate usaddress + df = pandas_usaddress.tag(df, ['address_field']) + + #send output to csv + df.to_csv('parsed_output.csv') + + + #------------------------------additional details------------------------------ + + #Output and fields will be identical to usaddress + +### Parsing with Address Standardization + + import pandas as pd + import pandas_usaddress + + #load dataframe + df = pd.read_csv('test_file.csv') + + #initiate usaddress + df = pandas_usaddress.tag(df, ['address_field'], granularity='medium', standardize=True) + + #send output to csv + df.to_csv('parsed_output.csv') + + + #------------------------------additional details------------------------------ + + #The standard output for usaddress has a lot of fields. The granularity parameter + #allows you to condense the results you get back for different types of analysis. + #see parameter documentation below for all granularity options. + + #Addresses are often unstandardized. The same address can come as 123 1st ST, or + #123 First Street, etc. This can cause issues with analysis such as aggregation, + #or record matching. The standardize parameter attempts to standardize the address + #to US Postal Service (USPS) standards. + +### Parsing with Address Standardization + + import pandas as pd + import pandas_usaddress + + #load dataframe + df = pd.read_csv('test_file.csv') + + #initiate usaddress + df = pandas_usaddress.tag(df, ['street1', 'street2', 'city', 'state'], granularity='single', standardize=True) + + #send output to csv + df.to_csv('parsed_output.csv') + + + #------------------------------additional details------------------------------ + + #You can also use pandas-usaddress to concatenate and parse multiple address lines. + #This can be helpful when you are working with two datasets that have different + #field names and you want the field names to be standardized using a specific level of + #granularity. It's pretty common for instance that in one dataset will concatenate + #address line 1 and 2, and another will not. + + #You will help the parser do it's job if you try to concatenate fields in approximately + #same order that you would write them on an envelope. + + #In this instance, we are taking multiple address fields and converting them into a + #single address line. That's fine to do! + + + + + + +%package -n python3-pandas-usaddress +Summary: The usaddress library made easy with Pandas. +Provides: python-pandas-usaddress +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-pandas-usaddress +# pandas-usaddress +The usaddress library made easy with Pandas. + +Also supports standardizing addresses to meet USPS standards. + +# Installation + +pip install pandas-usaddress + +# Usage + +### Basic Parsing + + import pandas as pd + import pandas_usaddress + + #load dataframe + df = pd.read_csv('test_file.csv') + + #initiate usaddress + df = pandas_usaddress.tag(df, ['address_field']) + + #send output to csv + df.to_csv('parsed_output.csv') + + + #------------------------------additional details------------------------------ + + #Output and fields will be identical to usaddress + +### Parsing with Address Standardization + + import pandas as pd + import pandas_usaddress + + #load dataframe + df = pd.read_csv('test_file.csv') + + #initiate usaddress + df = pandas_usaddress.tag(df, ['address_field'], granularity='medium', standardize=True) + + #send output to csv + df.to_csv('parsed_output.csv') + + + #------------------------------additional details------------------------------ + + #The standard output for usaddress has a lot of fields. The granularity parameter + #allows you to condense the results you get back for different types of analysis. + #see parameter documentation below for all granularity options. + + #Addresses are often unstandardized. The same address can come as 123 1st ST, or + #123 First Street, etc. This can cause issues with analysis such as aggregation, + #or record matching. The standardize parameter attempts to standardize the address + #to US Postal Service (USPS) standards. + +### Parsing with Address Standardization + + import pandas as pd + import pandas_usaddress + + #load dataframe + df = pd.read_csv('test_file.csv') + + #initiate usaddress + df = pandas_usaddress.tag(df, ['street1', 'street2', 'city', 'state'], granularity='single', standardize=True) + + #send output to csv + df.to_csv('parsed_output.csv') + + + #------------------------------additional details------------------------------ + + #You can also use pandas-usaddress to concatenate and parse multiple address lines. + #This can be helpful when you are working with two datasets that have different + #field names and you want the field names to be standardized using a specific level of + #granularity. It's pretty common for instance that in one dataset will concatenate + #address line 1 and 2, and another will not. + + #You will help the parser do it's job if you try to concatenate fields in approximately + #same order that you would write them on an envelope. + + #In this instance, we are taking multiple address fields and converting them into a + #single address line. That's fine to do! + + + + + + +%package help +Summary: Development documents and examples for pandas-usaddress +Provides: python3-pandas-usaddress-doc +%description help +# pandas-usaddress +The usaddress library made easy with Pandas. + +Also supports standardizing addresses to meet USPS standards. + +# Installation + +pip install pandas-usaddress + +# Usage + +### Basic Parsing + + import pandas as pd + import pandas_usaddress + + #load dataframe + df = pd.read_csv('test_file.csv') + + #initiate usaddress + df = pandas_usaddress.tag(df, ['address_field']) + + #send output to csv + df.to_csv('parsed_output.csv') + + + #------------------------------additional details------------------------------ + + #Output and fields will be identical to usaddress + +### Parsing with Address Standardization + + import pandas as pd + import pandas_usaddress + + #load dataframe + df = pd.read_csv('test_file.csv') + + #initiate usaddress + df = pandas_usaddress.tag(df, ['address_field'], granularity='medium', standardize=True) + + #send output to csv + df.to_csv('parsed_output.csv') + + + #------------------------------additional details------------------------------ + + #The standard output for usaddress has a lot of fields. The granularity parameter + #allows you to condense the results you get back for different types of analysis. + #see parameter documentation below for all granularity options. + + #Addresses are often unstandardized. The same address can come as 123 1st ST, or + #123 First Street, etc. This can cause issues with analysis such as aggregation, + #or record matching. The standardize parameter attempts to standardize the address + #to US Postal Service (USPS) standards. + +### Parsing with Address Standardization + + import pandas as pd + import pandas_usaddress + + #load dataframe + df = pd.read_csv('test_file.csv') + + #initiate usaddress + df = pandas_usaddress.tag(df, ['street1', 'street2', 'city', 'state'], granularity='single', standardize=True) + + #send output to csv + df.to_csv('parsed_output.csv') + + + #------------------------------additional details------------------------------ + + #You can also use pandas-usaddress to concatenate and parse multiple address lines. + #This can be helpful when you are working with two datasets that have different + #field names and you want the field names to be standardized using a specific level of + #granularity. It's pretty common for instance that in one dataset will concatenate + #address line 1 and 2, and another will not. + + #You will help the parser do it's job if you try to concatenate fields in approximately + #same order that you would write them on an envelope. + + #In this instance, we are taking multiple address fields and converting them into a + #single address line. That's fine to do! + + + + + + +%prep +%autosetup -n pandas-usaddress-0.21 + +%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-usaddress -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Mon Apr 10 2023 Python_Bot <Python_Bot@openeuler.org> - 0.21-1 +- Package Spec generated |