Initial commit

modules/test_analyzer.py

@@ -0,0 +1,130 @@
+from pathlib import Path
+import PyPDF2
+from typing import Dict, List, Optional
+from pydantic import BaseModel
+from modules.pdf_utils import PDFUtils
+
+class TestAnalysis(BaseModel):
+    overall_score: float
+    section_scores: Dict[str, float]
+    feedback: str
+    recommendations: List[str]
+    detailed_analysis: Optional[Dict] = None
+
+class TestAnalyzer:
+    def __init__(self, api_key: str):
+        self.api_key = api_key
+
+    def extract_text_from_pdf(self, pdf_file: Path) -> str:
+        """
+        Extract text content from a PDF file
+        """
+        if not pdf_file.exists():
+            raise FileNotFoundError(f"PDF file not found: {pdf_file}")
+
+        text = ""
+        with open(pdf_file, 'rb') as file:
+            pdf_reader = PyPDF2.PdfReader(file)
+            for page in pdf_reader.pages:
+                text += page.extract_text() + "\n"
+
+        return text
+
+    def analyze_test(self, pdf_content: str, marks_data: Dict, mode: str = 'detailed') -> TestAnalysis:
+        """
+        Analyze a test and generate feedback based on marks data
+        """
+        # Calculate overall score
+        total_marks = sum(marks_data.values())
+        max_marks = len(marks_data) * 100  # Assuming each question is out of 100
+        overall_score = (total_marks / max_marks) * 100
+
+        # Calculate section scores (group by first part of question number)
+        section_scores = {}
+        for question, marks in marks_data.items():
+            section = question.split('.')[0]
+            if section not in section_scores:
+                section_scores[section] = []
+            section_scores[section].append(marks)
+
+        # Calculate average for each section
+        for section, marks in section_scores.items():
+            section_scores[section] = sum(marks) / len(marks)
+
+        # Generate feedback
+        feedback = self._generate_feedback(overall_score, section_scores)
+        
+        # Generate recommendations
+        recommendations = self._generate_recommendations(section_scores)
+
+        # Create detailed analysis if requested
+        detailed_analysis = None
+        if mode == 'detailed':
+            detailed_analysis = {
+                'question_analysis': self._analyze_questions(pdf_content, marks_data),
+                'strengths': self._identify_strengths(section_scores),
+                'weaknesses': self._identify_weaknesses(section_scores)
+            }
+
+        return TestAnalysis(
+            overall_score=overall_score,
+            section_scores=section_scores,
+            feedback=feedback,
+            recommendations=recommendations,
+            detailed_analysis=detailed_analysis
+        )
+
+    def _generate_feedback(self, overall_score: float, section_scores: Dict[str, float]) -> str:
+        """
+        Generate feedback based on overall score and section scores
+        """
+        if overall_score >= 90:
+            return "Excellent performance! You have demonstrated a strong understanding of the material."
+        elif overall_score >= 80:
+            return "Very good performance. You have a solid grasp of most concepts."
+        elif overall_score >= 70:
+            return "Good performance. You understand the main concepts but could improve in some areas."
+        elif overall_score >= 60:
+            return "Satisfactory performance. You have a basic understanding but need to work on several areas."
+        else:
+            return "Needs improvement. Focus on understanding the fundamental concepts better."
+
+    def _generate_recommendations(self, section_scores: Dict[str, float]) -> List[str]:
+        """
+        Generate recommendations based on section scores
+        """
+        recommendations = []
+        for section, score in section_scores.items():
+            if score < 70:
+                recommendations.append(f"Focus on improving your understanding of Section {section}")
+            elif score < 80:
+                recommendations.append(f"Review Section {section} to strengthen your knowledge")
+        
+        if not recommendations:
+            recommendations.append("Continue practicing to maintain your strong performance")
+        
+        return recommendations
+
+    def _analyze_questions(self, pdf_content: str, marks_data: Dict) -> Dict:
+        """
+        Analyze individual questions
+        """
+        question_analysis = {}
+        for question, marks in marks_data.items():
+            question_analysis[question] = {
+                'score': marks,
+                'performance': 'excellent' if marks >= 90 else 'good' if marks >= 70 else 'needs_improvement'
+            }
+        return question_analysis
+
+    def _identify_strengths(self, section_scores: Dict[str, float]) -> List[str]:
+        """
+        Identify strong sections
+        """
+        return [f"Section {section}" for section, score in section_scores.items() if score >= 80]
+
+    def _identify_weaknesses(self, section_scores: Dict[str, float]) -> List[str]:
+        """
+        Identify weak sections
+        """
+        return [f"Section {section}" for section, score in section_scores.items() if score < 70]