From 68bd8ac79b33e48942316b26f253db644b6763ad Mon Sep 17 00:00:00 2001
From: Daniel Buades Marcos <daniel.buades@clinia.com>
Date: Sun, 8 Dec 2024 03:18:35 +0100
Subject: [PATCH] fix(publichealth-qa):  ignore rows with `None` values in
 `question` or `answer` (#1565)

---
 mteb/tasks/Retrieval/multilingual/PublicHealthQARetrieval.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mteb/tasks/Retrieval/multilingual/PublicHealthQARetrieval.py b/mteb/tasks/Retrieval/multilingual/PublicHealthQARetrieval.py
index c22d15afc..6f7d188b7 100644
--- a/mteb/tasks/Retrieval/multilingual/PublicHealthQARetrieval.py
+++ b/mteb/tasks/Retrieval/multilingual/PublicHealthQARetrieval.py
@@ -43,6 +43,9 @@ def _load_publichealthqa_data(
         answer_ids = {answer: _id for _id, answer in enumerate(set(data["answer"]))}
 
         for row in data:
+            if row["question"] is None or row["answer"] is None:
+                # There are some questions and answers that are None in the original dataset, specifically in the Arabic subset.
+                continue
             question = row["question"]
             answer = row["answer"]
             query_id = f"Q{question_ids[question]}"