question_analyzer.py

import requests
import json
import pandas as pd
from typing import List, Dict, Any

class QuestionAnalyzer:
    def __init__(self, api_url: str = "https://agents-course-unit4-scoring.hf.space"):
        self.api_url = api_url
        self.questions_url = f"{api_url}/questions"
        self.questions_data = None
    
    def fetch_questions(self) -> bool:
        """
        Recupera le domande dal server e le salva nell'istanza
        Returns: True se il fetch è andato a buon fine, False altrimenti
        """
        print(f"Fetching questions from: {self.questions_url}")
        try:
            response = requests.get(self.questions_url, timeout=15)
            response.raise_for_status()
            self.questions_data = response.json()
            
            if not self.questions_data:
                print("❌ Questions list is empty.")
                return False
                
            print(f"✅ Successfully fetched {len(self.questions_data)} questions.")
            return True
            
        except requests.exceptions.RequestException as e:
            print(f"❌ Error fetching questions: {e}")
            return False
        except json.JSONDecodeError as e:
            print(f"❌ Error decoding JSON response: {e}")
            return False
        except Exception as e:
            print(f"❌ Unexpected error: {e}")
            return False
    
    def analyze_structure(self) -> None:
        """Analizza la struttura delle domande"""
        if not self.questions_data:
            print("❌ No questions data available. Run fetch_questions() first.")
            return
        
        print("\n" + "="*50)
        print("QUESTION STRUCTURE ANALYSIS")
        print("="*50)
        
        # Analisi generale
        print(f"📊 Total questions: {len(self.questions_data)}")
        
        if len(self.questions_data) > 0:
            # Analizza il primo elemento per capire la struttura
            first_question = self.questions_data[0]
            print(f"\n🔍 Keys in each question: {list(first_question.keys())}")
            
            # Mostra il primo esempio completo
            print(f"\n📝 First question example:")
            for key, value in first_question.items():
                if isinstance(value, str) and len(value) > 100:
                    print(f"  {key}: {value[:100]}...")
                else:
                    print(f"  {key}: {value}")
    
    def show_sample_questions(self, n: int = 5) -> None:
        """Mostra n domande di esempio"""
        if not self.questions_data:
            print("❌ No questions data available. Run fetch_questions() first.")
            return
            
        print(f"\n" + "="*50)
        print(f"SAMPLE QUESTIONS (showing first {min(n, len(self.questions_data))})")
        print("="*50)
        
        for i, question in enumerate(self.questions_data[:n]):
            print(f"\n--- Question {i+1} ---")
            task_id = question.get('task_id', 'N/A')
            question_text = question.get('question', 'N/A')
            
            print(f"Task ID: {task_id}")
            print(f"Question: {question_text[:200]}{'...' if len(question_text) > 200 else ''}")
            
            # Mostra altri campi se presenti
            for key, value in question.items():
                if key not in ['task_id', 'question']:
                    if isinstance(value, str) and len(value) > 50:
                        print(f"{key}: {value[:50]}...")
                    else:
                        print(f"{key}: {value}")
    
    def create_summary_dataframe(self) -> pd.DataFrame:
        """Crea un DataFrame riassuntivo delle domande"""
        if not self.questions_data:
            print("❌ No questions data available. Run fetch_questions() first.")
            return pd.DataFrame()
        
        summary_data = []
        for question in self.questions_data:
            summary_row = {
                'task_id': question.get('task_id', 'N/A'),
                'question_length': len(question.get('question', '')),
                'question_preview': question.get('question', '')[:100] + '...' if len(question.get('question', '')) > 100 else question.get('question', ''),
            }
            
            # Aggiungi altri campi se presenti
            for key, value in question.items():
                if key not in ['task_id', 'question']:
                    summary_row[key] = value
            
            summary_data.append(summary_row)
        
        return pd.DataFrame(summary_data)
    
    def save_questions_to_file(self, filename: str = "questions_data.json") -> bool:
        """Salva le domande in un file JSON locale"""
        if not self.questions_data:
            print("❌ No questions data available. Run fetch_questions() first.")
            return False
        
        try:
            with open(filename, 'w', encoding='utf-8') as f:
                json.dump(self.questions_data, f, indent=2, ensure_ascii=False)
            print(f"✅ Questions saved to {filename}")
            return True
        except Exception as e:
            print(f"❌ Error saving questions: {e}")
            return False


def main():
    """Funzione principale per testare il QuestionAnalyzer"""
    print("🚀 Starting Question Analysis...")
    
    # Crea l'analyzer
    analyzer = QuestionAnalyzer()
    
    # Fetch delle domande
    if not analyzer.fetch_questions():
        print("❌ Failed to fetch questions. Exiting.")
        return
    
    # Analizza la struttura
    analyzer.analyze_structure()
    
    # Mostra domande di esempio
    analyzer.show_sample_questions(3)
    
    # Crea e mostra DataFrame riassuntivo
    df = analyzer.create_summary_dataframe()
    if not df.empty:
        print(f"\n" + "="*50)
        print("SUMMARY DATAFRAME")
        print("="*50)
        print(df.head(10))
    
    # Salva le domande localmente
    analyzer.save_questions_to_file()
    
    print(f"\n✅ Analysis complete!")


if __name__ == "__main__":
    main()