From 32814bd4118d9abdb809c9e5ec55293a839b4203 Mon Sep 17 00:00:00 2001
From: Scott Davis <stdavis@utah.gov>
Date: Mon, 18 Aug 2025 13:29:49 -0600
Subject: [PATCH 1/2] add training data for some state of utah address anomalys

---
 measure_performance/test_data/labeled.xml | 16 +++++++++++-
 training/labeled.xml                      | 31 +++++++++++++++++++++++
 2 files changed, 46 insertions(+), 1 deletion(-)

diff --git a/measure_performance/test_data/labeled.xml b/measure_performance/test_data/labeled.xml
index 362889c..a136476 100644
--- a/measure_performance/test_data/labeled.xml
+++ b/measure_performance/test_data/labeled.xml
@@ -79,7 +79,7 @@
   <AddressString><AddressNumber>10502</AddressNumber> <StreetName>shadow</StreetName> <StreetName>ridge</StreetName> <StreetNamePostType>ln</StreetNamePostType> <OccupancyType>apt</OccupancyType> <OccupancyIdentifier>103</OccupancyIdentifier> <PlaceName>louisville</PlaceName> <StateName>ky</StateName></AddressString>
   <AddressString><SubaddressType>msc</SubaddressType> <SubaddressIdentifier>410833</SubaddressIdentifier> <USPSBoxType>p.o.</USPSBoxType> <USPSBoxType>box</USPSBoxType> <USPSBoxID>415000</USPSBoxID> <PlaceName>nashville</PlaceName> <StateName>tn</StateName> <ZipCode>37241</ZipCode></AddressString>
   <AddressString><Recipient>customer</Recipient> <Recipient>#</Recipient> <Recipient>55-0044943</Recipient> <USPSBoxType>lock</USPSBoxType> <USPSBoxType>box</USPSBoxType> <USPSBoxID>427</USPSBoxID> <PlaceName>jamison</PlaceName> <StateName>pa</StateName> <ZipCode>18929</ZipCode></AddressString>
-  <AddressString><AddressNumber>2207</AddressNumber> <StreetName>d</StreetName> <StreetName>gault</StreetName> <StreetNamePostType>ave</StreetNamePostType> <StreetNamePostDirectional>n</StreetNamePostDirectional> <PlaceName>ft</PlaceName> <PlaceName>payne</PlaceName> <StateName>al</StateName> <ZipCode>35967</ZipCode></AddressString>
+  <AddressString><AddressNumber>2207</AddressNumber> <AddressNumberSuffix>d</AddressNumberSuffix> <StreetName>gault</StreetName> <StreetNamePostType>ave</StreetNamePostType> <StreetNamePostDirectional>n</StreetNamePostDirectional> <PlaceName>ft</PlaceName> <PlaceName>payne</PlaceName> <StateName>al</StateName> <ZipCode>35967</ZipCode></AddressString>
   <AddressString><USPSBoxType>po</USPSBoxType> <USPSBoxType>box</USPSBoxType> <USPSBoxID>33701</USPSBoxID> <SubaddressType>dept</SubaddressType> <SubaddressIdentifier>33701</SubaddressIdentifier> <PlaceName>sn</PlaceName> <PlaceName>francisco</PlaceName> <StateName>ca</StateName> <ZipCode>94139</ZipCode></AddressString>
   <AddressString><AddressNumber>1950</AddressNumber> <StreetNamePreDirectional>n.</StreetNamePreDirectional> <StreetName>stemmons</StreetName> <StreetNamePostType>freeway</StreetNamePostType></AddressString>
   <AddressString><AddressNumber>93</AddressNumber> <StreetNamePreDirectional>s</StreetNamePreDirectional> <StreetName>jackson</StreetName> <StreetNamePostType>st</StreetNamePostType> <OccupancyIdentifier>#</OccupancyIdentifier> <OccupancyIdentifier>75108</OccupancyIdentifier> <PlaceName>seattle</PlaceName> <StateName>wa</StateName> <ZipCode>98104-2818</ZipCode></AddressString>
@@ -164,4 +164,18 @@
   <AddressString><AddressNumber>1090-1092</AddressNumber> <StreetName>Berkeley</StreetName> <StreetNamePostType>St</StreetNamePostType> <BuildingName>Forest</BuildingName> <BuildingName>Cove</BuildingName> <BuildingName>Apartments,</BuildingName> <PlaceName>Charleston,</PlaceName> <StateName>SC</StateName> <ZipCode>29410</ZipCode></AddressString>
   <AddressString><AddressNumber>102</AddressNumber> <StreetName>Sottile</StreetName> <StreetNamePostType>St</StreetNamePostType> <BuildingName>The</BuildingName> <BuildingName>Merchant,</BuildingName> <OccupancyType>Unit</OccupancyType> <OccupancyIdentifier>06-305</OccupancyIdentifier> <PlaceName>Charleston,</PlaceName> <StateName>SC</StateName> <ZipCode>29403</ZipCode></AddressString>
   <AddressString><AddressNumber>3420</AddressNumber> <StreetName>Legacy</StreetName> <StreetName>Eagle</StreetName> <StreetNamePostType>Dr</StreetNamePostType> <BuildingName>Legacy</BuildingName> <BuildingName>Mount</BuildingName> <BuildingName>Pleasant</BuildingName> <BuildingName>Apartments,</BuildingName> <OccupancyType>Apt</OccupancyType> <OccupancyIdentifier>B2L</OccupancyIdentifier> <PlaceName>Mount</PlaceName> <PlaceName>Pleasant,</PlaceName> <StateName>SC</StateName> <ZipCode>29466</ZipCode></AddressString>
+  <AddressString><AddressNumber>123</AddressNumber> <StreetNamePreDirectional>N</StreetNamePreDirectional> <StreetName>Gallio</StreetName> <StreetNamePostType>Ave,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
+  <AddressString><AddressNumber>3847</AddressNumber> <AddressNumberSuffix>b</AddressNumberSuffix> <StreetNamePreDirectional>South</StreetNamePreDirectional> <StreetName>Steven</StreetName> <StreetNamePostType>Lane</StreetNamePostType></AddressString>
+  <AddressString><AddressNumber>333</AddressNumber> <StreetNamePreDirectional>N</StreetNamePreDirectional> <StreetName>Silver</StreetName> <StreetName>Springs</StreetName> <StreetNamePostType>Way,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
+  <AddressString><AddressNumber>5432</AddressNumber> <StreetNamePreDirectional>south</StreetNamePreDirectional> <StreetName>Harvest</StreetName> <StreetName>Crop</StreetName> <StreetNamePostType>Dr,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
+  <AddressString><AddressNumber>2040</AddressNumber> <StreetNamePreDirectional>E</StreetNamePreDirectional> <StreetName>7525</StreetName> <StreetNamePostDirectional>S</StreetNamePostDirectional></AddressString>
+  <AddressString><AddressNumber>442</AddressNumber> <StreetNamePreDirectional>N</StreetNamePreDirectional> <StreetName>Temple</StreetName> <StreetNamePostType>Run,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
+  <AddressString><AddressNumber>910</AddressNumber> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetNamePreType>SR</StreetNamePreType> <StreetName>22</StreetName></AddressString>
+  <AddressString><AddressNumber>9998</AddressNumber> <StreetNamePreDirectional>N</StreetNamePreDirectional> <StreetName>Gazelle</StreetName> <StreetNamePostType>Run,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
+  <AddressString><AddressNumber>457</AddressNumber> <AddressNumberSuffix>B</AddressNumberSuffix> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>Main</StreetName> <StreetNamePostType>St</StreetNamePostType></AddressString>
+  <AddressString><AddressNumber>345</AddressNumber> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>El</StreetName> <StreetName>Dorado</StreetName> <StreetNamePostType>Rd</StreetNamePostType> <PlaceName>City</PlaceName> <PlaceName>of</PlaceName> <PlaceName>Holladay</PlaceName></AddressString>
+  <AddressString><AddressNumber>9258</AddressNumber> <StreetNamePreDirectional>e</StreetNamePreDirectional> <StreetName>3090</StreetName> <StreetNamePostDirectional>n</StreetNamePostDirectional></AddressString>
+  <AddressString><AddressNumber>9258</AddressNumber> <StreetNamePreDirectional>e</StreetNamePreDirectional> <StreetName>3090</StreetName> <StreetNamePostDirectional>no.</StreetNamePostDirectional></AddressString>
+  <AddressString><AddressNumber>123</AddressNumber> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>Gazelle</StreetName> <StreetNamePostType>Run,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
+  <AddressString><AddressNumber>9258</AddressNumber> <StreetNamePreDirectional>s</StreetNamePreDirectional> <StreetName>3090</StreetName> <StreetNamePostDirectional>east</StreetNamePostDirectional></AddressString>
 </AddressCollection>
diff --git a/training/labeled.xml b/training/labeled.xml
index d72837a..e32b84f 100644
--- a/training/labeled.xml
+++ b/training/labeled.xml
@@ -1557,4 +1557,35 @@
   <AddressString><AddressNumber>1840</AddressNumber> <StreetName>Ashbourne</StreetName> <StreetNamePostType>Rd</StreetNamePostType> <BuildingName>Lynnewood</BuildingName> <BuildingName>Gardens,</BuildingName> <PlaceName>Elkins</PlaceName> <PlaceName>Park,</PlaceName> <StateName>PA</StateName> <ZipCode>19027</ZipCode></AddressString>
   <AddressString><AddressNumber>853</AddressNumber> <StreetNamePreDirectional>W</StreetNamePreDirectional> <StreetName>Blackhawk</StreetName> <StreetNamePostType>St</StreetNamePostType> <BuildingName>Post</BuildingName> <BuildingName>Chicago</BuildingName> <BuildingName>Apartments,</BuildingName> <PlaceName>Chicago,</PlaceName> <StateName>IL</StateName> <ZipCode>60642</ZipCode></AddressString>
   <AddressString><AddressNumber>2274-2284</AddressNumber> <StreetName>Ashley</StreetName> <StreetName>River</StreetName> <StreetNamePostType>Rd</StreetNamePostType> <BuildingName>Middleton</BuildingName> <BuildingName>Cove,</BuildingName> <PlaceName>Charleston,</PlaceName> <StateName>South</StateName> <StateName>Carolina</StateName> <ZipCode>29414</ZipCode></AddressString>
+  <AddressString><AddressNumber>3188</AddressNumber> <StreetNamePreDirectional>South</StreetNamePreDirectional> <StreetName>1725</StreetName> <StreetNamePostDirectional>East</StreetNamePostDirectional></AddressString>
+  <AddressString><AddressNumber>9258</AddressNumber> <StreetNamePreDirectional>w</StreetNamePreDirectional> <StreetName>3090</StreetName> <StreetNamePostDirectional>so.</StreetNamePostDirectional></AddressString>
+  <AddressString><AddressNumber>9258</AddressNumber> <StreetNamePreDirectional>w</StreetNamePreDirectional> <StreetName>3090</StreetName> <StreetNamePostDirectional>south</StreetNamePostDirectional></AddressString>
+  <AddressString><AddressNumber>9258</AddressNumber> <StreetNamePreDirectional>w</StreetNamePreDirectional> <StreetName>3090</StreetName> <StreetNamePostDirectional>s</StreetNamePostDirectional></AddressString>
+  <AddressString><AddressNumber>9258</AddressNumber> <StreetNamePreDirectional>w</StreetNamePreDirectional> <StreetName>3090</StreetName> <StreetNamePostDirectional>no.</StreetNamePostDirectional></AddressString>
+  <AddressString><AddressNumber>3188</AddressNumber> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>1725</StreetName> <StreetNamePostDirectional>E</StreetNamePostDirectional></AddressString>
+  <AddressString><AddressNumber>1940</AddressNumber> <StreetNamePreDirectional>E</StreetNamePreDirectional> <StreetName>5625</StreetName> <StreetNamePostDirectional>S</StreetNamePostDirectional></AddressString>
+  <AddressString><AddressNumber>9258</AddressNumber> <StreetNamePreDirectional>w</StreetNamePreDirectional> <StreetName>3090</StreetName> <StreetNamePostDirectional>no</StreetNamePostDirectional></AddressString>
+  <AddressString><AddressNumber>911</AddressNumber> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetNamePreType>SR</StreetNamePreType> <StreetName>23</StreetName></AddressString>
+  <AddressString><AddressNumber>1010</AddressNumber> <StreetNamePreDirectional>N</StreetNamePreDirectional> <StreetNamePreType>SR</StreetNamePreType> <StreetName>89</StreetName></AddressString>
+  <AddressString><AddressNumber>1233</AddressNumber> <StreetNamePreDirectional>N</StreetNamePreDirectional> <StreetNamePreType>HWY</StreetNamePreType> <StreetName>22</StreetName></AddressString>
+  <AddressString><AddressNumber>3188</AddressNumber> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>1725</StreetName> <StreetNamePostDirectional>E</StreetNamePostDirectional> <PlaceName>City</PlaceName> <PlaceName>of</PlaceName> <PlaceName>Holladay</PlaceName></AddressString>
+  <AddressString><AddressNumber>123</AddressNumber> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>Main</StreetName> <StreetNamePostType>St</StreetNamePostType> <PlaceName>City</PlaceName> <PlaceName>of</PlaceName> <PlaceName>Holladay</PlaceName></AddressString>
+  <AddressString><AddressNumber>4447</AddressNumber> <StreetNamePreDirectional>E</StreetNamePreDirectional> <StreetName>Harvest</StreetName> <StreetName>Crop</StreetName> <StreetNamePostType>Dr,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
+  <AddressString><AddressNumber>4086</AddressNumber> <StreetNamePreDirectional>E</StreetNamePreDirectional> <StreetName>Gazelle</StreetName> <StreetNamePostType>Run,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
+  <AddressString><AddressNumber>123</AddressNumber> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>Main</StreetName> <StreetNamePostType>St</StreetNamePostType> <PlaceName>City</PlaceName> <PlaceName>of</PlaceName> <PlaceName>Holladay</PlaceName></AddressString>
+  <AddressString><AddressNumber>7260</AddressNumber> <StreetNamePreDirectional>N</StreetNamePreDirectional> <StreetName>Silver</StreetName> <StreetName>Spring</StreetName> <StreetNamePostType>Way,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
+  <AddressString><AddressNumber>3999</AddressNumber> <StreetNamePreDirectional>E</StreetNamePreDirectional> <StreetName>Gazelle</StreetName> <StreetNamePostType>Run,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
+  <AddressString><AddressNumber>8223</AddressNumber> <StreetNamePreDirectional>N</StreetNamePreDirectional> <StreetName>Gallio</StreetName> <StreetNamePostType>Ave,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
+  <AddressString><AddressNumber>4112</AddressNumber> <StreetNamePreDirectional>E</StreetNamePreDirectional> <StreetName>Gazelle</StreetName> <StreetNamePostType>Run,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
+  <AddressString><AddressNumber>3188</AddressNumber> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>1725</StreetName> <StreetNamePostDirectional>E</StreetNamePostDirectional> <PlaceName>City</PlaceName> <PlaceName>of</PlaceName> <PlaceName>Holladay</PlaceName></AddressString>
+  <AddressString><AddressNumber>3847</AddressNumber> <AddressNumberSuffix>b</AddressNumberSuffix> <StreetNamePreDirectional>South</StreetNamePreDirectional> <StreetName>Scott</StreetName> <StreetNamePostType>Lane</StreetNamePostType></AddressString>
+  <AddressString><AddressNumber>321</AddressNumber> <AddressNumberSuffix>B</AddressNumberSuffix> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>State</StreetName> <StreetNamePostType>St</StreetNamePostType></AddressString>
+  <AddressString><AddressNumber>3467</AddressNumber> <AddressNumberSuffix>b</AddressNumberSuffix> <StreetNamePreDirectional>South</StreetNamePreDirectional> <StreetName>Kevin</StreetName> <StreetNamePostType>Lane</StreetNamePostType></AddressString>
+  <AddressString><AddressNumber>301</AddressNumber> <AddressNumberSuffix>e</AddressNumberSuffix> <StreetNamePreDirectional>east</StreetNamePreDirectional> <StreetName>400</StreetName> <StreetNamePostDirectional>south</StreetNamePostDirectional></AddressString>
+  <AddressString><AddressNumber>23495</AddressNumber> <AddressNumberSuffix>Z</AddressNumberSuffix> <StreetNamePreDirectional>south</StreetNamePreDirectional> <StreetName>Scott</StreetName> <StreetNamePostType>Dr</StreetNamePostType></AddressString>
+  <AddressString><AddressNumber>123</AddressNumber> <AddressNumberSuffix>A</AddressNumberSuffix> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>Main</StreetName> <StreetNamePostType>St</StreetNamePostType></AddressString>
+  <AddressString><AddressNumber>123</AddressNumber> <AddressNumberSuffix>a</AddressNumberSuffix> <StreetNamePreDirectional>East</StreetNamePreDirectional> <StreetName>Steven</StreetName> <StreetNamePostType>Run</StreetNamePostType></AddressString>
+  <AddressString><AddressNumber>3011</AddressNumber> <AddressNumberSuffix>a</AddressNumberSuffix> <StreetName>Main</StreetName> <StreetNamePostType>St</StreetNamePostType></AddressString>
+  <AddressString><AddressNumber>3892</AddressNumber> <AddressNumberSuffix>#</AddressNumberSuffix> <AddressNumberSuffix>3</AddressNumberSuffix> <StreetName>Scott</StreetName> <StreetNamePostType>Lane</StreetNamePostType></AddressString>
+  <AddressString><AddressNumber>435</AddressNumber> <AddressNumberSuffix>1/2</AddressNumberSuffix> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>100</StreetName> <StreetNamePostDirectional>W</StreetNamePostDirectional></AddressString>
 </AddressCollection>

From d6d43bc7f1853276e9f830d4a7e5945aa0b1d6ee Mon Sep 17 00:00:00 2001
From: Scott Davis <stdavis@utah.gov>
Date: Mon, 18 Aug 2025 13:41:13 -0600
Subject: [PATCH 2/2] remove duplicate

---
 training/labeled.xml | 1 -
 1 file changed, 1 deletion(-)

diff --git a/training/labeled.xml b/training/labeled.xml
index e32b84f..19f6a86 100644
--- a/training/labeled.xml
+++ b/training/labeled.xml
@@ -1572,7 +1572,6 @@
   <AddressString><AddressNumber>123</AddressNumber> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>Main</StreetName> <StreetNamePostType>St</StreetNamePostType> <PlaceName>City</PlaceName> <PlaceName>of</PlaceName> <PlaceName>Holladay</PlaceName></AddressString>
   <AddressString><AddressNumber>4447</AddressNumber> <StreetNamePreDirectional>E</StreetNamePreDirectional> <StreetName>Harvest</StreetName> <StreetName>Crop</StreetName> <StreetNamePostType>Dr,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
   <AddressString><AddressNumber>4086</AddressNumber> <StreetNamePreDirectional>E</StreetNamePreDirectional> <StreetName>Gazelle</StreetName> <StreetNamePostType>Run,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
-  <AddressString><AddressNumber>123</AddressNumber> <StreetNamePreDirectional>S</StreetNamePreDirectional> <StreetName>Main</StreetName> <StreetNamePostType>St</StreetNamePostType> <PlaceName>City</PlaceName> <PlaceName>of</PlaceName> <PlaceName>Holladay</PlaceName></AddressString>
   <AddressString><AddressNumber>7260</AddressNumber> <StreetNamePreDirectional>N</StreetNamePreDirectional> <StreetName>Silver</StreetName> <StreetName>Spring</StreetName> <StreetNamePostType>Way,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
   <AddressString><AddressNumber>3999</AddressNumber> <StreetNamePreDirectional>E</StreetNamePreDirectional> <StreetName>Gazelle</StreetName> <StreetNamePostType>Run,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>
   <AddressString><AddressNumber>8223</AddressNumber> <StreetNamePreDirectional>N</StreetNamePreDirectional> <StreetName>Gallio</StreetName> <StreetNamePostType>Ave,</StreetNamePostType> <PlaceName>Eagle</PlaceName> <PlaceName>Mountain</PlaceName></AddressString>