From 0699af2b5036c0a77b0cc740958621c87198a918 Mon Sep 17 00:00:00 2001
From: Jonah Gilbert <jonahmgilbert1@gmail.com>
Date: Mon, 13 Mar 2023 11:20:30 -0500
Subject: [PATCH 1/2] Include US territories in damages

---
 src/dscim/preprocessing/preprocessing.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/src/dscim/preprocessing/preprocessing.py b/src/dscim/preprocessing/preprocessing.py
index 7752bfc5..2a8fa8ab 100644
--- a/src/dscim/preprocessing/preprocessing.py
+++ b/src/dscim/preprocessing/preprocessing.py
@@ -257,7 +257,8 @@ def subset_USA_reduced_damages(
             f"{input_path}/{sector}/{recipe}_{reduction}_eta{eta}.zarr",
         )
 
-    subset = ds.sel(region=[i for i in ds.region.values if "USA" in i])
+    US_territories = ["USA", "XBK", "GUM", "XHO", "XJV", "XJA", "XKR", "XMW", "XNV", "MNP", "XPL", "PRI", "VIR", "XWK"]
+    subset = ds.sel(region=[i for i in ds.region.values if any(j in i for j in US_territories)])
 
     for var in subset.variables:
         subset[var].encoding.clear()
@@ -285,7 +286,8 @@ def subset_USA_ssp_econ(
         consolidated=True,
     )
 
-    zarr = zarr.sel(region=[i for i in zarr.region.values if "USA" in i])
+    US_territories = ["USA", "XBK", "GUM", "XHO", "XJV", "XJA", "XKR", "XMW", "XNV", "MNP", "XPL", "PRI", "VIR", "XWK"]
+    zarr = zarr.sel(region=[i for i in zarr.region.values if any(j in i for j in US_territories)])
 
     for var in zarr.variables:
         zarr[var].encoding.clear()

From 66d2828f7123b9315dee9f6b781a8e39e308dd28 Mon Sep 17 00:00:00 2001
From: Jonah Gilbert <jonahmgilbert1@gmail.com>
Date: Mon, 13 Mar 2023 11:28:15 -0500
Subject: [PATCH 2/2] Update changelog + black

---
 CHANGELOG.md                             |  1 +
 src/dscim/preprocessing/preprocessing.py | 42 +++++++++++++++++++++---
 2 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 180ded48..32972c10 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 - Add functions used for producing RFF weights. ([PR #66](https://github.com/ClimateImpactLab/dscim/pull/66), [@davidrzhdu](https://github.com/davidrzhdu))
 ### Changed
+- Included US territories in damages and economic variable subsetting. ([PR #78](https://github.com/ClimateImpactLab/dscim/pull/78), [@JMGilbert](https://github.com/JMGilbert))
 - Changed format of `eta_rhos` to allow for multiple values of `rho` for the same `eta`. ([PR #65](https://github.com/ClimateImpactLab/dscim/pull/65), [@JMGilbert](https://github.com/JMGilbert))
 - Remove diagnostics module. ([PR #60](https://github.com/ClimateImpactLab/dscim/pull/60), [@JMGilbert](https://github.com/JMGilbert))
 - Remove old/unnecessary files. ([PR #57](https://github.com/ClimateImpactLab/dscim/pull/57), [@JMGilbert](https://github.com/JMGilbert))
diff --git a/src/dscim/preprocessing/preprocessing.py b/src/dscim/preprocessing/preprocessing.py
index 2a8fa8ab..67fb2eec 100644
--- a/src/dscim/preprocessing/preprocessing.py
+++ b/src/dscim/preprocessing/preprocessing.py
@@ -257,8 +257,25 @@ def subset_USA_reduced_damages(
             f"{input_path}/{sector}/{recipe}_{reduction}_eta{eta}.zarr",
         )
 
-    US_territories = ["USA", "XBK", "GUM", "XHO", "XJV", "XJA", "XKR", "XMW", "XNV", "MNP", "XPL", "PRI", "VIR", "XWK"]
-    subset = ds.sel(region=[i for i in ds.region.values if any(j in i for j in US_territories)])
+    US_territories = [
+        "USA",
+        "XBK",
+        "GUM",
+        "XHO",
+        "XJV",
+        "XJA",
+        "XKR",
+        "XMW",
+        "XNV",
+        "MNP",
+        "XPL",
+        "PRI",
+        "VIR",
+        "XWK",
+    ]
+    subset = ds.sel(
+        region=[i for i in ds.region.values if any(j in i for j in US_territories)]
+    )
 
     for var in subset.variables:
         subset[var].encoding.clear()
@@ -286,8 +303,25 @@ def subset_USA_ssp_econ(
         consolidated=True,
     )
 
-    US_territories = ["USA", "XBK", "GUM", "XHO", "XJV", "XJA", "XKR", "XMW", "XNV", "MNP", "XPL", "PRI", "VIR", "XWK"]
-    zarr = zarr.sel(region=[i for i in zarr.region.values if any(j in i for j in US_territories)])
+    US_territories = [
+        "USA",
+        "XBK",
+        "GUM",
+        "XHO",
+        "XJV",
+        "XJA",
+        "XKR",
+        "XMW",
+        "XNV",
+        "MNP",
+        "XPL",
+        "PRI",
+        "VIR",
+        "XWK",
+    ]
+    zarr = zarr.sel(
+        region=[i for i in zarr.region.values if any(j in i for j in US_territories)]
+    )
 
     for var in zarr.variables:
         zarr[var].encoding.clear()