From f752cf5a4855b515adf7486cd5d99503252a4086 Mon Sep 17 00:00:00 2001
From: Haoran Pan <167847254+TPLin22@users.noreply.github.com>
Date: Wed, 2 Apr 2025 19:52:54 +0800
Subject: [PATCH] fix: replace func "len()" in ensemble test code to support
 various data type (#739)

* replace len with def get_length

* update get_length implementation
---
 .../data_science/ensemble/eval_tests/ensemble_test.txt   | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/rdagent/components/coder/data_science/ensemble/eval_tests/ensemble_test.txt b/rdagent/components/coder/data_science/ensemble/eval_tests/ensemble_test.txt
index 58943f2f..5b6237dd 100644
--- a/rdagent/components/coder/data_science/ensemble/eval_tests/ensemble_test.txt
+++ b/rdagent/components/coder/data_science/ensemble/eval_tests/ensemble_test.txt
@@ -34,6 +34,9 @@ def print_preds_info(model_name, data_type, preds):
         else:
             print(f"Unknown prediction type: {type(preds)}")
 
+def get_length(data):
+    return data.shape[0] if hasattr(data, 'shape') else len(data)
+
 X, y, test_X, test_ids = load_data()
 X, y, test_X = feat_eng(X, y, test_X)
 train_X, val_X, train_y, val_y = train_test_split(X, y, test_size=0.2, random_state=42)
@@ -109,9 +112,9 @@ assert isinstance(final_pred, pred_type), (
 
 # Check shape
 if isinstance(final_pred, (list, np.ndarray, pd.DataFrame, torch.Tensor, tf.Tensor)):
-    assert len(final_pred) == len(test_X), (
-        f"Wrong output sample size: len(final_pred)={len(final_pred)} "
-        f"vs. len(test_X)={len(test_X)}"
+    assert get_length(final_pred) == get_length(test_X), (
+        f"Wrong output sample size: get_length(final_pred)={get_length(final_pred)} "
+        f"vs. get_length(test_X)={get_length(test_X)}"
     )
 
 # check scores.csv