fix: do not impute isProteinCoding (opentargets#902)

* fix: fix col names for imputation * fix: fix v1 * fix: test
thehyve · Nov 5, 2024 · 6ec0d45 · 6ec0d45
1 parent 2af1074
commit 6ec0d45
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 2 deletions.
diff --git a/src/gentropy/dataset/l2g_feature_matrix.py b/src/gentropy/dataset/l2g_feature_matrix.py
@@ -143,7 +143,10 @@ def fill_na(
         Returns:
             L2GFeatureMatrix: L2G feature matrix dataset
         """
-        cols_to_impute = ["proteinGeneCount500kb", "geneCount500kb", "isProteinCoding"]
+        cols_to_impute = [
+            "proteinGeneCount500kb",
+            "geneCount500kb",
+        ]
         for col in cols_to_impute:
             if col not in self._df.columns:
                 continue

diff --git a/tests/gentropy/dataset/test_l2g_feature_matrix.py b/tests/gentropy/dataset/test_l2g_feature_matrix.py
@@ -228,7 +228,7 @@ def test_fill_na(spark: SparkSession) -> None:
                 "geneId": "gene3",
                 "proteinGeneCount500kb": 3.5,
                 "geneCount500kb": 9.0,
-                "isProteinCoding": 1.0,
+                "isProteinCoding": 0.0,
                 "anotherFeature": 0.0,
             },
         ],