import gradio as gr import pandas as pd import json import os import re from PyPDF2 import PdfReader from collections import defaultdict # ========== NER MODEL HANDLING FOR SPACES ========== try: from transformers import pipeline ner_pipeline = pipeline("ner", model="dslim/bert-base-NER") except ImportError: ner_pipeline = None print("NER model not available - continuing without it") except Exception as e: ner_pipeline = None print(f"Could not load NER model: {e}") # ========== TRANSCRIPT PARSING ========== def extract_gpa(text, gpa_type): pattern = rf'{gpa_type}\s*([\d\.]+)' match = re.search(pattern, text) return match.group(1) if match else "N/A" def extract_courses_from_table(text): course_pattern = re.compile( r'(\d{4}-\d{4})\s*' # School year r'\|?\s*(\d+)\s*' # Grade level r'\|?\s*([A-Z0-9]+)\s*' # Course code r'\|?\s*([^\|]+?)\s*' # Course name (captures until next pipe) r'(?:\|\s*[^\|]*){2}' # Skip Term and DstNumber r'\|\s*([A-FW]?)\s*' # Grade (FG column) r'(?:\|\s*[^\|]*)' # Skip Incl column r'\|\s*([\d\.]+|inProgress)' # Credits ) courses_by_grade = defaultdict(list) for match in re.finditer(course_pattern, text): year_range, grade_level, course_code, course_name, grade, credits = match.groups() course_name = course_name.strip() if 'DE:' in course_name: course_name = course_name.replace('DE:', 'Dual Enrollment:') if 'AP' in course_name: course_name = course_name.replace('AP', 'AP ') course_info = { 'name': f"{course_code} {course_name}", 'year': year_range, 'credits': credits } if grade and grade.strip(): course_info['grade'] = grade.strip() courses_by_grade[grade_level].append(course_info) return courses_by_grade def parse_transcript(file): if file.name.endswith('.pdf'): text = '' reader = PdfReader(file) for page in reader.pages: text += page.extract_text() + '\n' gpa_data = { 'weighted': extract_gpa(text, 'Weighted GPA'), 'unweighted': extract_gpa(text, 'Un-weighted GPA') } grade_match = re.search(r'Current Grade:\s*(\d+)', text) grade_level = grade_match.group(1) if grade_match else "Unknown" courses_by_grade = extract_courses_from_table(text) output_text = f"Student Transcript Summary\n{'='*40}\n" output_text += f"Current Grade Level: {grade_level}\n" output_text += f"Weighted GPA: {gpa_data['weighted']}\n" output_text += f"Unweighted GPA: {gpa_data['unweighted']}\n\n" output_text += "Course History:\n{'='*40}\n" for grade in sorted(courses_by_grade.keys(), key=int): output_text += f"\nGrade {grade}:\n{'-'*30}\n" for course in courses_by_grade[grade]: output_text += f"- {course['name']}" if 'grade' in course and course['grade']: output_text += f" (Grade: {course['grade']})" if 'credits' in course: output_text += f" | Credits: {course['credits']}" output_text += f" | Year: {course['year']}\n" return output_text, { "gpa": gpa_data, "grade_level": grade_level, "courses": dict(courses_by_grade) } else: return "Unsupported file format (PDF only for transcript parsing)", None # ========== LEARNING STYLE QUIZ ========== learning_style_questions = [ "When you study for a test, you prefer to:", "When you need directions to a new place, you prefer:", "When you learn a new skill, you prefer to:", "When you're trying to concentrate, you:", "When you meet new people, you remember them by:", "When you're assembling furniture or a gadget, you:", "When choosing a restaurant, you rely most on:", "When you're in a waiting room, you typically:", "When giving someone instructions, you tend to:", "When you're trying to recall information, you:", "When you're at a museum or exhibit, you:", "When you're learning a new language, you prefer:", "When you're taking notes in class, you:", "When you're explaining something complex, you:", "When you're at a party, you enjoy:", "When you're trying to remember a phone number, you:", "When you're relaxing, you prefer to:", "When you're learning to use new software, you:", "When you're giving a presentation, you rely on:", "When you're solving a difficult problem, you:" ] learning_style_options = [ ["Read the textbook (Reading/Writing)", "Listen to lectures (Auditory)", "Use diagrams/charts (Visual)", "Practice problems (Kinesthetic)"], ["Look at a map (Visual)", "Have someone tell you (Auditory)", "Write down directions (Reading/Writing)", "Try walking/driving there (Kinesthetic)"], ["Read instructions (Reading/Writing)", "Have someone show you (Visual)", "Listen to explanations (Auditory)", "Try it yourself (Kinesthetic)"], ["Need quiet (Reading/Writing)", "Need background noise (Auditory)", "Need to move around (Kinesthetic)", "Need visual stimulation (Visual)"], ["Their face (Visual)", "Their name (Auditory)", "What you talked about (Reading/Writing)", "What you did together (Kinesthetic)"], ["Read the instructions carefully (Reading/Writing)", "Look at the diagrams (Visual)", "Ask someone to explain (Auditory)", "Start putting pieces together (Kinesthetic)"], ["Online photos of the food (Visual)", "Recommendations from friends (Auditory)", "Reading the menu online (Reading/Writing)", "Remembering how it felt to eat there (Kinesthetic)"], ["Read magazines (Reading/Writing)", "Listen to music (Auditory)", "Watch TV (Visual)", "Fidget or move around (Kinesthetic)"], ["Write them down (Reading/Writing)", "Explain verbally (Auditory)", "Demonstrate (Visual)", "Guide them physically (Kinesthetic)"], ["See written words in your mind (Visual)", "Hear the information in your head (Auditory)", "Write it down to remember (Reading/Writing)", "Associate it with physical actions (Kinesthetic)"], ["Read all the descriptions (Reading/Writing)", "Listen to audio guides (Auditory)", "Look at the displays (Visual)", "Touch interactive exhibits (Kinesthetic)"], ["Study grammar rules (Reading/Writing)", "Listen to native speakers (Auditory)", "Use flashcards with images (Visual)", "Practice conversations (Kinesthetic)"], ["Write detailed paragraphs (Reading/Writing)", "Record the lecture (Auditory)", "Draw diagrams and charts (Visual)", "Doodle while listening (Kinesthetic)"], ["Write detailed steps (Reading/Writing)", "Explain verbally with examples (Auditory)", "Draw diagrams (Visual)", "Use physical objects to demonstrate (Kinesthetic)"], ["Conversations with people (Auditory)", "Watching others or the environment (Visual)", "Writing notes or texting (Reading/Writing)", "Dancing or physical activities (Kinesthetic)"], ["See the numbers in your head (Visual)", "Say them aloud (Auditory)", "Write them down (Reading/Writing)", "Dial them on a keypad (Kinesthetic)"], ["Read a book (Reading/Writing)", "Listen to music (Auditory)", "Watch TV/movies (Visual)", "Do something physical (Kinesthetic)"], ["Read the manual (Reading/Writing)", "Ask someone to show you (Visual)", "Call tech support (Auditory)", "Experiment with the software (Kinesthetic)"], ["Detailed notes (Reading/Writing)", "Verbal explanations (Auditory)", "Visual slides (Visual)", "Physical demonstrations (Kinesthetic)"], ["Write out possible solutions (Reading/Writing)", "Talk through it with someone (Auditory)", "Draw diagrams (Visual)", "Build a model or prototype (Kinesthetic)"] ] def learning_style_quiz(*answers): scores = { "Visual": 0, "Auditory": 0, "Reading/Writing": 0, "Kinesthetic": 0 } for i, answer in enumerate(answers): if answer == learning_style_options[i][0]: scores["Reading/Writing"] += 1 elif answer == learning_style_options[i][1]: scores["Auditory"] += 1 elif answer == learning_style_options[i][2]: scores["Visual"] += 1 elif answer == learning_style_options[i][3]: scores["Kinesthetic"] += 1 max_score = max(scores.values()) total_questions = len(learning_style_questions) percentages = {style: (score/total_questions)*100 for style, score in scores.items()} sorted_styles = sorted(scores.items(), key=lambda x: x[1], reverse=True) 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" primary_styles = [style for style, score in scores.items() if score == max_score] if len(primary_styles) == 1: result += f"Your primary learning style is: {primary_styles[0]}\n\n" if primary_styles[0] == "Visual": result += "Tips for Visual Learners:\n" result += "- Use color coding in your notes\n" result += "- Create mind maps and diagrams\n" result += "- Watch educational videos\n" result += "- Use flashcards with images\n" elif primary_styles[0] == "Auditory": result += "Tips for Auditory Learners:\n" result += "- Record lectures and listen to them\n" result += "- Participate in study groups\n" result += "- Explain concepts out loud to yourself\n" result += "- Use rhymes or songs to remember information\n" elif primary_styles[0] == "Reading/Writing": result += "Tips for Reading/Writing Learners:\n" result += "- Write detailed notes\n" result += "- Create summaries in your own words\n" result += "- Read textbooks and articles\n" result += "- Make lists to organize information\n" else: result += "Tips for Kinesthetic Learners:\n" result += "- Use hands-on activities\n" result += "- Take frequent movement breaks\n" result += "- Create physical models\n" result += "- Associate information with physical actions\n" else: result += f"You have multiple strong learning styles: {', '.join(primary_styles)}\n\n" result += "You may benefit from combining different learning approaches.\n" return result # ========== PROFILE MANAGEMENT ========== def save_profile(name, age, interests, transcript, learning_style, movie, movie_reason, show, show_reason, book, book_reason, character, character_reason, blog): age = int(age) if age else 0 favorites = { "movie": movie, "movie_reason": movie_reason, "show": show, "show_reason": show_reason, "book": book, "book_reason": book_reason, "character": character, "character_reason": character_reason } data = { "name": name, "age": age, "interests": interests, "transcript": transcript, "learning_style": learning_style, "favorites": favorites, "blog": blog } os.makedirs("student_profiles", exist_ok=True) json_path = os.path.join("student_profiles", f"{name.replace(' ', '_')}_profile.json") with open(json_path, "w") as f: json.dump(data, f, indent=2) markdown_summary = f"""### Student Profile: {name} **Age:** {age} **Interests:** {interests} **Learning Style:** {learning_style} #### Transcript: {transcript_display(transcript)} #### Favorites: - Movie: {favorites['movie']} ({favorites['movie_reason']}) - Show: {favorites['show']} ({favorites['show_reason']}) - Book: {favorites['book']} ({favorites['book_reason']}) - Character: {favorites['character']} ({favorites['character_reason']}) #### Blog: {blog if blog else "_No blog provided_"} """ return markdown_summary 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): for grade in sorted(courses_by_grade.keys(), key=int): display += f"\n**Grade {grade}**\n" for course in courses_by_grade[grade]: display += f"- {course['name']}" if 'grade' in course and course['grade']: display += f" (Grade: {course['grade']})" if 'credits' in course: display += f" | Credits: {course['credits']}" display += f" | Year: {course['year']}\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 def load_profile(): if not os.path.exists("student_profiles"): return {} files = [f for f in os.listdir("student_profiles") if f.endswith('.json')] if files: with open(os.path.join("student_profiles", files[0]), "r") as f: return json.load(f) return {} def generate_response(message, history): profile = load_profile() if not profile: return "Please complete and save your profile first using the previous tabs." 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", {}) 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"] 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 study_help): 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") 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") 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") 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") 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" for grade in sorted(courses.keys(), key=int): response += f"\nGrade {grade}:\n" for course in courses[grade]: response += f"- {course['name']}" if 'grade' in course: response += f" (Grade: {course['grade']})" response += "\n" 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!") 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!") # ========== GRADIO INTERFACE ========== with gr.Blocks() as app: with gr.Tab("Step 1: Upload Transcript"): gr.Markdown("### Upload your transcript (PDF recommended for best results)") transcript_file = gr.File(label="Transcript file", file_types=[".pdf"]) transcript_output = gr.Textbox(label="Transcript Results", lines=20) transcript_data = gr.State() transcript_file.change( fn=parse_transcript, inputs=transcript_file, outputs=[transcript_output, transcript_data] ) with gr.Tab("Step 2: Learning Style Quiz"): gr.Markdown("### Learning Style Quiz (20 Questions)") quiz_components = [] for i, (question, options) in enumerate(zip(learning_style_questions, learning_style_options)): quiz_components.append(gr.Radio(options, label=f"{i+1}. {question}")) learning_output = gr.Textbox(label="Your Learning Style", lines=15) gr.Button("Submit Quiz").click( fn=learning_style_quiz, inputs=quiz_components, outputs=learning_output ) with gr.Tab("Step 3: Personal Questions"): name = gr.Textbox(label="What's your name?") age = gr.Number(label="How old are you?", precision=0) interests = gr.Textbox(label="What are your interests?") movie = gr.Textbox(label="Favorite movie?") movie_reason = gr.Textbox(label="Why do you like that movie?") show = gr.Textbox(label="Favorite TV show?") show_reason = gr.Textbox(label="Why do you like that show?") book = gr.Textbox(label="Favorite book?") book_reason = gr.Textbox(label="Why do you like that book?") character = gr.Textbox(label="Favorite character?") character_reason = gr.Textbox(label="Why do you like that character?") blog_checkbox = gr.Checkbox(label="Do you want to write a blog?", value=False) blog_text = gr.Textbox(label="Write your blog here", visible=False, lines=5) blog_checkbox.change(lambda x: gr.update(visible=x), inputs=blog_checkbox, outputs=blog_text) with gr.Tab("Step 4: Save & Review"): output_summary = gr.Markdown() save_btn = gr.Button("Save Profile") save_btn.click( fn=save_profile, inputs=[name, age, interests, transcript_data, learning_output, movie, movie_reason, show, show_reason, book, book_reason, character, character_reason, blog_text], outputs=output_summary ) with gr.Tab("🤖 AI Teaching Assistant"): gr.Markdown("## Your Personalized Learning Assistant") 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?" ] ) app.launch()