Update app.py

app.py

@@ -2,15 +2,14 @@
 import sys
 import subprocess
 import importlib
+from datetime import datetime
 
-# List of required packages
 required_packages = {
     'gradio': 'gradio>=3.0',
     'pandas': 'pandas',
     'PyPDF2': 'PyPDF2',
     'transformers': 'transformers',
-    'pdfplumber': 'pdfplumber',
-    'typing_extensions': 'typing_extensions'
+    'pdfplumber': 'pdfplumber'
 }
 
 def check_and_install_packages():
@@ -23,12 +22,7 @@ def check_and_install_packages():
 
     if missing_packages:
         print(f"Missing packages: {', '.join(missing_packages)}")
-        print("Attempting to install...")
-        try:
-            subprocess.check_call([sys.executable, "-m", "pip", "install", *missing_packages])
-            print("Installation successful.")
-        except subprocess.CalledProcessError as e:
-            print(f"Failed to install packages. Error: {e}")
+        subprocess.check_call([sys.executable, "-m", "pip", "install", *missing_packages])
 
 check_and_install_packages()
 
@@ -59,6 +53,7 @@ class UniversalTranscriptParser:
         }
     
     def parse_transcript(self, text: str) -> Dict[str, Union[Dict, List[Dict]]]:
+        """Determine transcript type and parse accordingly"""
         transcript_type = self._identify_transcript_type(text)
         
         if transcript_type == 'homeschool':
@@ -69,6 +64,7 @@ class UniversalTranscriptParser:
             return self._parse_miami_dade(text)
     
     def _identify_transcript_type(self, text: str) -> str:
+        """Identify which type of transcript we're processing"""
         if re.search(r'Sample OFFICIAL HIGH SCHOOL TRANSCRIPT', text):
             return 'homeschool'
         elif re.search(r'DORAL ACADEMY HIGH SCHOOL', text):
@@ -76,22 +72,27 @@ class UniversalTranscriptParser:
         return 'miami_dade'
     
     def _parse_homeschool(self, text: str) -> Dict[str, Union[Dict, List[Dict]]]:
+        """Parse homeschool transcript format"""
         courses = []
         current_grade = None
         current_year = None
         
+        # Extract student info
         student_info = {}
         name_match = re.search(r'Student Name:\s*(.+)\s*SSN:', text)
         if name_match:
             student_info['name'] = name_match.group(1).strip()
         
+        # Process each line
         for line in text.split('\n'):
+            # Check for grade level header
             grade_match = re.match(r'^\|?\s*(\d+th Grade)\s*\|.*(\d{4}-\d{4})', line)
             if grade_match:
                 current_grade = grade_match.group(1)
                 current_year = grade_match.group(2)
                 continue
             
+            # Course line pattern
             course_match = re.match(
                 r'^\|?\s*([^\|]+?)\s*\|\s*([A-Z][+*]?)\s*\|\s*([^\|]+)\s*\|\s*(\d+\.?\d*)\s*\|\s*(\d+)',
                 line
@@ -99,6 +100,7 @@ class UniversalTranscriptParser:
             
             if course_match and current_grade:
                 course_name = course_match.group(1).strip()
+                # Clean course names that start with | or have extra spaces
                 course_name = re.sub(r'^\|?\s*', '', course_name)
                 
                 courses.append({
@@ -112,33 +114,40 @@ class UniversalTranscriptParser:
                     'transcript_type': 'homeschool'
                 })
         
+        # Extract GPA information from homeschool transcript
         gpa_data = {}
         gpa_match = re.search(r'Cum\. GPA\s*\|\s*([\d\.]+)', text)
         if gpa_match:
             gpa_data['unweighted'] = gpa_match.group(1)
-            gpa_data['weighted'] = gpa_match.group(1)
+            gpa_data['weighted'] = gpa_match.group(1)  # Homeschool often has same weighted/unweighted
         
         return {
             'student_info': student_info,
-            'courses': {'All': courses},
+            'courses': {'All': courses},  # Homeschool doesn't separate by grade in same way
             'gpa': gpa_data,
             'grade_level': current_grade.replace('th Grade', '') if current_grade else "Unknown"
         }
     
     def _parse_doral_academy(self, text: str) -> Dict[str, Union[Dict, List[Dict]]]:
+        """Parse Doral Academy specific format"""
         courses = []
+        
+        # Extract student info
         student_info = {}
         name_match = re.search(r'LEGAL NAME:\s*([^\n]+)', text)
         if name_match:
             student_info['name'] = name_match.group(1).strip()
         
+        # Extract school year information
         year_pattern = re.compile(r'YEAR:\s*(\d{4}-\d{4})\s*GRADE LEVEL:\s*(\d{2})', re.MULTILINE)
         year_matches = year_pattern.finditer(text)
         
+        # Create mapping of grade levels to years
         grade_year_map = {}
         for match in year_matches:
             grade_year_map[match.group(2)] = match.group(1)
         
+        # Course pattern for Doral Academy
         course_pattern = re.compile(
             r'(\d)\s+(\d{7})\s+([^\n]+?)\s+([A-Z]{2})\s+([A-Z])\s+([A-Z])\s+([A-Z])\s+(\d\.\d{2})\s+(\d\.\d{2})',
             re.MULTILINE
@@ -166,6 +175,7 @@ class UniversalTranscriptParser:
             
             courses_by_grade[grade_level_num].append(course_info)
         
+        # Extract GPA information from Doral Academy transcript
         gpa_data = {}
         unweighted_match = re.search(r'Un-weighted GPA\s*([\d\.]+)', text)
         weighted_match = re.search(r'Weighted GPA\s*([\d\.]+)', text)
@@ -175,6 +185,7 @@ class UniversalTranscriptParser:
         if weighted_match:
             gpa_data['weighted'] = weighted_match.group(1)
         
+        # Extract current grade level
         grade_level = "12" if re.search(r'GRADE LEVEL:\s*12', text) else "Unknown"
         
         return {
@@ -185,14 +196,17 @@ class UniversalTranscriptParser:
         }
     
     def _parse_miami_dade(self, text: str) -> Dict[str, Union[Dict, List[Dict]]]:
+        """Parse standard Miami-Dade format"""
         courses = []
         courses_by_grade = defaultdict(list)
         
+        # Extract student info
         student_info = {}
         name_match = re.search(r'0783977 - ([^,]+),\s*([^\n]+)', text)
         if name_match:
             student_info['name'] = f"{name_match.group(2)} {name_match.group(1)}"
         
+        # Course pattern for Miami-Dade
         course_pattern = re.compile(
             r'([A-Z]-[A-Za-z\s&]+)\s*\|\s*(\d{4}-\d{4})\s*\|\s*(\d{2})\s*\|\s*([A-Z0-9]+)\s*\|\s*([^\|]+)\s*\|\s*([^\|]+)\s*\|\s*([^\|]+)\s*\|\s*([A-Z]?)\s*\|\s*([A-Z]?)\s*\|\s*([^\|]+)',
             re.MULTILINE
@@ -218,11 +232,13 @@ class UniversalTranscriptParser:
             
             courses_by_grade[match.group(3)].append(course_info)
         
+        # Extract GPA information
         gpa_data = {
             'weighted': extract_gpa(text, 'Weighted GPA'),
             'unweighted': extract_gpa(text, 'Un-weighted GPA')
         }
         
+        # Extract current grade level
         grade_level = re.search(r'Current Grade:\s*(\d+)', text).group(1) if re.search(r'Current Grade:\s*(\d+)', text) else "Unknown"
         
         return {
@@ -274,85 +290,16 @@ def parse_transcript(file):
         
         parsed_data = parser.parse_transcript(text)
         
-        output_text = f"Student Transcript Summary\n{'='*40}\n"
-        
-        if 'student_info' in parsed_data and 'name' in parsed_data['student_info']:
-            output_text += f"Student: {parsed_data['student_info']['name']}\n"
-        
-        output_text += f"Current Grade Level: {parsed_data.get('grade_level', 'Unknown')}\n"
-        
-        if 'gpa' in parsed_data:
-            gpa = parsed_data['gpa']
-            output_text += f"Weighted GPA: {gpa.get('weighted', 'N/A')}\n"
-            output_text += f"Unweighted GPA: {gpa.get('unweighted', 'N/A')}\n\n"
-        
-        output_text += "Course History:\n{'='*40}\n"
-        
-        if 'courses' in parsed_data:
-            courses_by_grade = parsed_data['courses']
-            
-            def grade_sort_key(grade):
-                try:
-                    num = int(re.search(r'\d+', grade).group())
-                    return num
-                except (AttributeError, ValueError):
-                    return float('inf')
-            
-            grades_sorted = sorted(courses_by_grade.keys(), key=grade_sort_key)
-            
-            for grade in grades_sorted:
-                output_text += f"\nGrade {grade}:\n{'-'*30}\n"
-                for course in courses_by_grade[grade]:
-                    output_text += f"- {course.get('name', 'Unnamed Course')}"
-                    if 'grade' in course and course['grade']:
-                        output_text += f" (Grade: {course['grade']})"
-                    if 'credits' in course:
-                        output_text += f" | Credits: {course['credits']}"
-                    if 'school_year' in course:
-                        output_text += f" | Year: {course['school_year']}"
-                    output_text += "\n"
+        # Only show GPA in the output
+        output_text = f"Transcript Processed Successfully!\n\n"
+        output_text += f"GPA Information:\n"
+        output_text += f"- Weighted: {parsed_data['gpa'].get('weighted', 'N/A')}\n"
+        output_text += f"- Unweighted: {parsed_data['gpa'].get('unweighted', 'N/A')}"
         
         return output_text, parsed_data
     else:
         return "Unsupported file format (PDF only for transcript parsing)", None
 
-def transcript_display(transcript_dict):
-    if not transcript_dict or "courses" not in transcript_dict:
-        return "No course information available"
-    
-    display = "### Detailed Course History\n"
-    courses_by_grade = transcript_dict["courses"]
-    
-    if isinstance(courses_by_grade, dict):
-        def grade_sort_key(grade):
-            try:
-                num = int(re.search(r'\d+', grade).group())
-                return num
-            except (AttributeError, ValueError):
-                return float('inf')
-        
-        grades_sorted = sorted(courses_by_grade.keys(), key=grade_sort_key)
-        
-        for grade in grades_sorted:
-            display += f"\n**Grade {grade}**\n"
-            for course in courses_by_grade[grade]:
-                display += f"- {course.get('name', 'Unnamed Course')}"
-                if 'grade' in course and course['grade']:
-                    display += f" (Grade: {course['grade']})"
-                if 'credits' in course:
-                    display += f" | Credits: {course['credits']}"
-                if 'school_year' in course:
-                    display += f" | Year: {course['school_year']}"
-                display += "\n"
-    
-    if 'gpa' in transcript_dict:
-        gpa = transcript_dict['gpa']
-        display += "\n**GPA Information**\n"
-        display += f"- Unweighted: {gpa.get('unweighted', 'N/A')}\n"
-        display += f"- Weighted: {gpa.get('weighted', 'N/A')}\n"
-    
-    return display
-
 # ========== LEARNING STYLE QUIZ ==========
 learning_style_questions = [
     "When you study for a test, you prefer to:",
@@ -421,16 +368,20 @@ def learning_style_quiz(*answers):
     max_score = max(scores.values())
     total_questions = len(learning_style_questions)
     
+    # Calculate percentages
     percentages = {style: (score/total_questions)*100 for style, score in scores.items()}
     
+    # Sort styles by score (descending)
     sorted_styles = sorted(scores.items(), key=lambda x: x[1], reverse=True)
     
+    # Prepare detailed results
     result = "Your Learning Style Results:\n\n"
     for style, score in sorted_styles:
         result += f"{style}: {score}/{total_questions} ({percentages[style]:.1f}%)\n"
     
     result += "\n"
     
+    # Determine primary and secondary styles
     primary_styles = [style for style, score in scores.items() if score == max_score]
     
     if len(primary_styles) == 1:
@@ -453,7 +404,7 @@ def learning_style_quiz(*answers):
             result += "- Create summaries in your own words\n"
             result += "- Read textbooks and articles\n"
             result += "- Make lists to organize information\n"
-        else:
+        else:  # Kinesthetic
             result += "Tips for Kinesthetic Learners:\n"
             result += "- Use hands-on activities\n"
             result += "- Take frequent movement breaks\n"
@@ -469,6 +420,7 @@ def learning_style_quiz(*answers):
 def save_profile(name, age, interests, transcript, learning_style, 
                 movie, movie_reason, show, show_reason, 
                 book, book_reason, character, character_reason, blog):
+    # Convert age to int if it's a numpy number (from gradio Number input)
     age = int(age) if age else 0
     
     favorites = {
@@ -501,8 +453,9 @@ def save_profile(name, age, interests, transcript, learning_style,
 **Age:** {age}  
 **Interests:** {interests}  
 **Learning Style:** {learning_style}  
-#### Transcript:
-{transcript_display(transcript)}
+#### GPA Information:
+- Weighted: {transcript['gpa'].get('weighted', 'N/A')}
+- Unweighted: {transcript['gpa'].get('unweighted', 'N/A')}
 #### Favorites:
 - Movie: {favorites['movie']} ({favorites['movie_reason']})
 - Show: {favorites['show']} ({favorites['show_reason']})
@@ -528,107 +481,96 @@ def generate_response(message, history):
     if not profile:
         return "Please complete and save your profile first using the previous tabs."
     
+    # Get profile data
     learning_style = profile.get("learning_style", "")
-    grade_level = profile.get("transcript", {}).get("grade_level", "unknown")
-    gpa = profile.get("transcript", {}).get("gpa", {})
-    interests = profile.get("interests", "")
-    courses = profile.get("transcript", {}).get("courses", {})
+    transcript = profile.get("transcript", {})
+    gpa = transcript.get("gpa", {})
+    courses = []
     
+    # Flatten all courses from all grades
+    if 'courses' in transcript:
+        if isinstance(transcript['courses'], dict):
+            for grade_courses in transcript['courses'].values():
+                courses.extend(grade_courses)
+        elif isinstance(transcript['courses'], list):
+            courses = transcript['courses']
+    
+    # Common responses
     greetings = ["hi", "hello", "hey"]
     study_help = ["study", "learn", "prepare", "exam"]
-    grade_help = ["grade", "gpa", "score"]
-    interest_help = ["interest", "hobby", "passion"]
-    course_help = ["courses", "classes", "transcript", "schedule"]
+    grade_help = ["gpa", "grade point average", "grades"]
+    course_help = ["courses", "classes", "subjects"]
     
     if any(greet in message.lower() for greet in greetings):
         return f"Hello {profile.get('name', 'there')}! How can I help you today?"
     
+    elif any(word in message.lower() for word in grade_help):
+        return (f"Your GPA information:\n"
+               f"- Weighted: {gpa.get('weighted', 'N/A')}\n"
+               f"- Unweighted: {gpa.get('unweighted', 'N/A')}")
+    
     elif any(word in message.lower() for word in study_help):
+        # Analyze course performance to give personalized advice
+        strong_subjects = [c['name'] for c in courses if 'grade' in c and c['grade'] in ['A', 'A+', 'B+']]
+        weak_subjects = [c['name'] for c in courses if 'grade' in c and c['grade'] in ['D', 'F']]
+        
+        response = "Here are some personalized study tips:\n"
+        
+        if strong_subjects:
+            response += f"\nYou're doing well in: {', '.join(strong_subjects[:3])}\n"
+            response += "→ Keep up the good work in these areas!\n"
+        
+        if weak_subjects:
+            response += f"\nYou might want to focus more on: {', '.join(weak_subjects[:3])}\n"
+            response += "→ Consider getting extra help or tutoring\n"
+        
+        # Add learning style specific tips
         if "Visual" in learning_style:
-            response = ("Based on your visual learning style, I recommend:\n"
-                       "- Creating mind maps or diagrams\n"
-                       "- Using color-coded notes\n"
-                       "- Watching educational videos")
+            response += "\nVisual Learner Tip: Try creating diagrams or mind maps\n"
         elif "Auditory" in learning_style:
-            response = ("Based on your auditory learning style, I recommend:\n"
-                       "- Recording lectures and listening to them\n"
-                       "- Participating in study groups\n"
-                       "- Explaining concepts out loud")
+            response += "\nAuditory Learner Tip: Record yourself explaining concepts\n"
         elif "Reading/Writing" in learning_style:
-            response = ("Based on your reading/writing learning style, I recommend:\n"
-                       "- Writing detailed notes\n"
-                       "- Creating summaries in your own words\n"
-                       "- Reading textbooks and articles")
+            response += "\nReading/Writing Tip: Write summaries in your own words\n"
         elif "Kinesthetic" in learning_style:
-            response = ("Based on your kinesthetic learning style, I recommend:\n"
-                       "- Hands-on practice\n"
-                       "- Creating physical models\n"
-                       "- Taking frequent movement breaks")
-        else:
-            response = ("Here are some general study tips:\n"
-                       "- Break study sessions into 25-minute chunks\n"
-                       "- Review material regularly\n"
-                       "- Teach concepts to someone else")
+            response += "\nKinesthetic Tip: Use physical objects to demonstrate concepts\n"
         
         return response
     
-    elif any(word in message.lower() for word in grade_help):
-        return (f"Your GPA information:\n"
-               f"- Unweighted: {gpa.get('unweighted', 'N/A')}\n"
-               f"- Weighted: {gpa.get('weighted', 'N/A')}\n\n"
-               "To improve your grades, try:\n"
-               "- Setting specific goals\n"
-               "- Meeting with teachers\n"
-               "- Developing a study schedule")
-    
-    elif any(word in message.lower() for word in interest_help):
-        return (f"I see you're interested in: {interests}\n\n"
-               "You might want to:\n"
-               "- Find clubs or activities related to these interests\n"
-               "- Explore career paths that align with them")
-    
     elif any(word in message.lower() for word in course_help):
-        response = "Here's a summary of your courses:\n"
-        if isinstance(courses, dict):
-            def grade_sort_key(grade):
-                try:
-                    num = int(re.search(r'\d+', grade).group())
-                    return num
-                except (AttributeError, ValueError):
-                    return float('inf')
-            
-            grades_sorted = sorted(courses.keys(), key=grade_sort_key)
-            
-            for grade in grades_sorted:
-                response += f"\nGrade {grade}:\n"
-                for course in courses[grade]:
-                    response += f"- {course.get('name', 'Unnamed Course')}"
-                    if 'grade' in course:
-                        response += f" (Grade: {course['grade']})"
-                    response += "\n"
-        else:
-            response += "No detailed course information available."
+        if not courses:
+            return "No course information available."
+        
+        # Group by subject area
+        subjects = defaultdict(list)
+        for course in courses:
+            if 'name' in course:
+                # Extract first word as subject area
+                subject = course['name'].split()[0]
+                subjects[subject].append(course)
+        
+        response = "Your course subjects:\n"
+        for subject, subject_courses in subjects.items():
+            response += f"\n{subject} ({len(subject_courses)} courses)"
+        
         return response
     
     elif "help" in message.lower():
         return ("I can help with:\n"
-               "- Study tips based on your learning style\n"
-               "- GPA and grade information\n"
-               "- Course history and schedules\n"
-               "- General academic advice\n\n"
-               "Try asking about study strategies or your grades!")
+               "- Your GPA information\n"
+               "- Personalized study tips\n"
+               "- Course information\n"
+               "- Learning style recommendations")
     
     else:
         return ("I'm your personalized teaching assistant. "
-               "I can help with study tips, grade information, and academic advice. "
-               "Try asking about how to study for your classes!")
+               "Ask me about your GPA, courses, or study tips!")
 
 # ========== GRADIO INTERFACE ==========
 with gr.Blocks() as app:
     with gr.Tab("Step 1: Upload Transcript"):
         gr.Markdown("### Upload your transcript (PDF recommended)")
         transcript_file = gr.File(label="Transcript file", file_types=[".pdf"])
-        transcript_output = gr.Textbox(label="Transcript Results", lines=20)
+        transcript_output = gr.Textbox(label="Transcript Results", lines=5)
         transcript_data = gr.State()
         transcript_file.change(
             fn=parse_transcript,
@@ -681,13 +623,12 @@ with gr.Blocks() as app:
         chatbot = gr.ChatInterface(
             fn=generate_response,
             examples=[
-                "How should I study for my next test?",
-                "What's my GPA information?",
-                "Show me my course history",
-                "How can I improve my grades?"
+                "What's my GPA?",
+                "How should I study for my classes?",
+                "What subjects am I taking?"
             ]
         )
 
-# ========== RUN APPLICATION ==========
 if __name__ == "__main__":
-    app.launch()
+    app.launch()
+