Update app.py

app.py

@@ -1,6 +1,8 @@
 import os
 import gradio as gr
 import requests
+import string
+import warnings
 import pandas as pd
 from huggingface_hub import login
 import re
@@ -9,6 +11,7 @@ from groq import Groq
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+
 # --- Basic Agent Definition ---
 class BasicAgent:
     def __init__(self):
@@ -100,7 +103,71 @@ class BasicAgent:
             return self.solve_riddle(question)
         return self.query_groq(question)
 
+def question_scorer(model_answer: str, ground_truth: str) -> bool:
+    def normalize_str(input_str, remove_punct=True) -> str:
+        no_spaces = re.sub(r"\s", "", input_str)
+        if remove_punct:
+            translator = str.maketrans("", "", string.punctuation)
+            return no_spaces.lower().translate(translator)
+        else:
+            return no_spaces.lower()
+
+    def normalize_number_str(number_str: str) -> float | None:
+        for char in ["$", "%", ","]:
+            number_str = number_str.replace(char, "")
+        try:
+            return float(number_str)
+        except ValueError:
+            print(f"String '{number_str}' cannot be normalized to number.")
+            return None
+
+    def split_string(s: str, char_list: list[str] = [",", ";"]) -> list[str]:
+        pattern = f"[{''.join(map(re.escape, char_list))}]"
+        return [elem.strip() for elem in re.split(pattern, s)]
+
+    def is_float(val) -> bool:
+        try:
+            float(val)
+            return True
+        except ValueError:
+            return False
+
+    if model_answer is None:
+        model_answer = "None"
+
+    # Case 1: Ground truth is numeric
+    if is_float(ground_truth):
+        print(f"Evaluating '{model_answer}' as a number.")
+        normalized = normalize_number_str(model_answer)
+        return normalized == float(ground_truth) if normalized is not None else False
+
+    # Case 2: Ground truth is a list
+    elif any(char in ground_truth for char in [",", ";"]):
+        print(f"Evaluating '{model_answer}' as a comma/semicolon-separated list.")
+        gt_elems = split_string(ground_truth)
+        ma_elems = split_string(model_answer)
+
+        if len(gt_elems) != len(ma_elems):
+            warnings.warn("Answer lists have different lengths, returning False.", UserWarning)
+            return False
+
+        for ma_elem, gt_elem in zip(ma_elems, gt_elems):
+            if is_float(gt_elem):
+                normalized = normalize_number_str(ma_elem)
+                if normalized != float(gt_elem):
+                    return False
+            else:
+                if normalize_str(ma_elem, remove_punct=False) != normalize_str(gt_elem, remove_punct=False):
+                    return False
+        return True
+
+    # Case 3: Ground truth is a plain string
+    else:
+        print(f"Evaluating '{model_answer}' as a string.")
+        return normalize_str(model_answer) == normalize_str(ground_truth)
 
+   print(question_scorer("FINAL ANSWER: right", ))  
+    
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
     if profile:
@@ -143,10 +210,10 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
         except Exception as e:
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
-
+    
     if not answers_payload:
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
-
+    print(question_scorer("FINAL ANSWER: right",submitted_answer))
     submission_data = {
         "username": username.strip(),
         "agent_code": agent_code,