From 9d071f72c9d224e3b8fe4c8e31dc70774f8386dc Mon Sep 17 00:00:00 2001
From: yashgadhiya10 <ygadhiya@umd.edu>
Date: Wed, 20 Aug 2025 12:11:48 -0400
Subject: [PATCH 1/2] Created new dataset Uganda 2024

---
 datasets.py | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/datasets.py b/datasets.py
index 05ccec15..980bae59 100644
--- a/datasets.py
+++ b/datasets.py
@@ -635,6 +635,37 @@ def load_labels(self) -> pd.DataFrame:
         df[SUBSET] = train_val_test_split(df.index, 0.3, 0.3)
         return df
 
+class Uganda_NorthCEO2024(LabeledDataset):
+    def load_labels(self) -> pd.DataFrame:
+        raw_folder = raw_dir / "Uganda_North_2024"
+        df1 = pd.read_csv(
+            raw_folder
+            / "ceo-UNHCR-North-Uganda-Feb-2024---Feb-2025-(Set-1)-sample-data-2025-08-19.csv"
+        )
+        df2 = pd.read_csv(
+            raw_folder
+            / "ceo-UNHCR-North-Uganda-Feb-2024---Feb-2025-(Set-2)-sample-data-2025-08-19.csv"
+        )
+        df = pd.concat([df1, df2])
+
+        # Discard rows with no label
+        df = df[~df["Does this pixel contain active cropland?"].isna()].copy()
+        df[CLASS_PROB] = df["Does this pixel contain active cropland?"] == "Crop"
+        df[CLASS_PROB] = df[CLASS_PROB].astype(int)
+        df["num_labelers"] = 1
+        df = df.groupby([LON, LAT], as_index=False, sort=False).agg(
+            {
+                CLASS_PROB: "mean",
+                "num_labelers": "sum",
+                "plotid": join_unique,
+                "sampleid": join_unique,
+                "email": join_unique,
+            }
+        )
+        df[START], df[END] = date(2024, 1, 1), date(2025, 4, 30)
+        df[SUBSET] = train_val_test_split(df.index, 0.3, 0.3)
+        return df
+
 
 class Uganda_NorthCEO2021(LabeledDataset):
     def load_labels(self) -> pd.DataFrame:
@@ -1683,6 +1714,7 @@ def load_labels(self) -> pd.DataFrame:
     Uganda_NorthCEO2018(),
     UgandaNorthCorLabel2019(),
     Uganda_NorthCEO2023(),
+    Uganda_NorthCEO2024(),
 ]
 
 if __name__ == "__main__":

From ecd29e975a736c0008642b0f60abb5c50667613e Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 20 Aug 2025 16:15:02 +0000
Subject: [PATCH 2/2] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 datasets.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/datasets.py b/datasets.py
index 980bae59..3ace9c41 100644
--- a/datasets.py
+++ b/datasets.py
@@ -635,6 +635,7 @@ def load_labels(self) -> pd.DataFrame:
         df[SUBSET] = train_val_test_split(df.index, 0.3, 0.3)
         return df
 
+
 class Uganda_NorthCEO2024(LabeledDataset):
     def load_labels(self) -> pd.DataFrame:
         raw_folder = raw_dir / "Uganda_North_2024"