Detect duplicates in participant_id column

wonkyconn/tests/test_workflow.py

@@ -0,0 +1,35 @@
+from argparse import Namespace
+from pathlib import Path
+
+import pandas as pd
+import pytest
+
+from wonkyconn.workflow import load_data_frame
+
+
+def test_load_data_frame(tmp_path: Path) -> None:
+    # Create a sample phenotypes file
+    phenotypes_path = tmp_path / "phenotypes.tsv"
+    phenotypes_path.write_text("participant_id\tage\tgender\nsub-01\t25\tM\nsub-02\t30\tF\nsub-03\t35\tM\n")
+
+    # Load the data frame
+    data_frame = load_data_frame(Namespace(phenotypes=str(phenotypes_path)))
+
+    # Check that the data frame has the expected shape and columns
+    row_count, _ = data_frame.shape
+    assert row_count == 3
+    assert list(data_frame.reset_index().columns) == ["participant_id", "age", "gender"]
+
+    data_frame = data_frame.reset_index()
+
+    # Check that we throw an error for missing columns
+    for missing_column in data_frame.columns:
+        data_frame.drop(columns=missing_column).to_csv(phenotypes_path, sep="\t", index=False)
+        with pytest.raises(ValueError, match=missing_column):
+            load_data_frame(Namespace(phenotypes=str(phenotypes_path)))
+
+    # Check that we throw an error for duplicate participant_id entries
+    data_frame = pd.concat([data_frame, data_frame.iloc[0:1]])  # Add a duplicate row
+    data_frame.to_csv(phenotypes_path, sep="\t", index=False)
+    with pytest.raises(ValueError, match="duplicate"):
+        load_data_frame(Namespace(phenotypes=str(phenotypes_path)))

wonkyconn/workflow.py

@@ -239,8 +239,8 @@ def make_record(
 
     # age / sex predictability metrics
     try:
-        ages = seg_data_frame["age"].to_numpy()
-        genders = seg_data_frame["gender"].to_numpy()
+        ages: npt.NDArray[np.float64] = seg_data_frame["age"].to_numpy()
+        genders: npt.NDArray[np.str_] = seg_data_frame["gender"].to_numpy()
 
         scores = age_sex_scores(
             connectivity_matrices,
@@ -292,6 +292,8 @@ def load_data_frame(args: argparse.Namespace) -> pd.DataFrame:
         index_col="participant_id",
         dtype={"participant_id": str},
     )
+    if data_frame.index.has_duplicates:
+        raise ValueError("Phenotypes file has duplicate participant_id entries")
     if "gender" not in data_frame.columns:
         raise ValueError('Phenotypes file is missing the "gender" column')
     if "age" not in data_frame.columns: