in evaluation/utils.py [0:0]
def show_sample(sample, print_all_preds=False):
print("==" * 20)
for key in ["idx", "type", "level", "dataset"]:
if key in sample:
# capitalize
print("{}: {}".format(key[0].upper() + key[1:], sample[key]))
print("Question:", repr(sample["question"]))
if "code" in sample:
if print_all_preds:
for code in sample["code"]:
print("-" * 20)
print("code:", code)
print("Execution:", sample["report"])
else:
print("Solution:\n", sample["code"][0])
print("Execution:", sample["report"][0])
if "pred" in sample:
print("Prediction:", repr(sample["pred"][0]))
for key in ["gt", "score", "unit", "gt_cot"]:
if key in sample:
_key = key_map.get(key, key)
print("{}: {}".format(_key, repr(sample[key])))
print()