Update app.py

app.py

@@ -7,8 +7,46 @@ from PyPDF2 import PdfReader
 from collections import defaultdict
 
 # ========== TRANSCRIPT PARSING FUNCTIONS ==========
+def extract_courses_with_grade_levels(text):
+    grade_level_pattern = r"(Grade|Year)\s*[:]?\s*(\d+|Freshman|Sophomore|Junior|Senior)"
+    grade_match = re.search(grade_level_pattern, text, re.IGNORECASE)
+    current_grade_level = grade_match.group(2) if grade_match else "Unknown"
+
+    course_pattern = r"""
+        (?:^|\n)
+        (?: (Grade|Year)\s*[:]?\s*(\d+|Freshman|Sophomore|Junior|Senior)\s*[\n-]* )?
+        (
+            (?:[A-Z]{2,}\s?\d{3})
+            |
+            [A-Z][a-z]+(?:\s[A-Z][a-z]+)*
+        )
+        \s*
+        (?: [:\-]?\s* ([A-F][+-]?|\d{2,3}%)? )?
+    """
+
+    courses_by_grade = defaultdict(list)
+    current_grade = current_grade_level
+
+    for match in re.finditer(course_pattern, text, re.VERBOSE | re.MULTILINE):
+        grade_context, grade_level, course, grade = match.groups()
+
+        if grade_context:
+            current_grade = grade_level
+
+        if course:
+            course_info = {"course": course.strip()}
+            if grade:
+                course_info["grade"] = grade.strip()
+            courses_by_grade[current_grade].append(course_info)
+
+    return dict(courses_by_grade)
+
 def parse_transcript(file):
-    if file.name.endswith('.pdf'):
+    if file.name.endswith('.csv'):
+        df = pd.read_csv(file)
+    elif file.name.endswith('.xlsx'):
+        df = pd.read_excel(file)
+    elif file.name.endswith('.pdf'):
         text = ''
         reader = PdfReader(file)
         for page in reader.pages:
@@ -20,16 +58,17 @@ def parse_transcript(file):
         grade_match = re.search(r'(Grade|Year)[\s:]*(\d+|Freshman|Sophomore|Junior|Senior)', text, re.IGNORECASE)
         grade_level = grade_match.group(2) if grade_match else "Unknown"
 
-        # GPA extraction
+        # Enhanced GPA extraction
         gpa_data = {'weighted': "N/A", 'unweighted': "N/A"}
         gpa_patterns = [
             r'Weighted GPA[\s:]*(\d\.\d{1,2})',
             r'GPA \(Weighted\)[\s:]*(\d\.\d{1,2})',
+            r'Cumulative GPA \(Weighted\)[\s:]*(\d\.\d{1,2})',
             r'Unweighted GPA[\s:]*(\d\.\d{1,2})',
             r'GPA \(Unweighted\)[\s:]*(\d\.\d{1,2})',
+            r'Cumulative GPA \(Unweighted\)[\s:]*(\d\.\d{1,2})',
             r'GPA[\s:]*(\d\.\d{1,2})'
         ]
-        
         for pattern in gpa_patterns:
             for match in re.finditer(pattern, text, re.IGNORECASE):
                 gpa_value = match.group(1)
@@ -43,6 +82,8 @@ def parse_transcript(file):
                     if gpa_data['weighted'] == "N/A":
                         gpa_data['weighted'] = gpa_value
 
+        courses_by_grade = extract_courses_with_grade_levels(text)
+
         output_text = f"Grade Level: {grade_level}\n\n"
         if gpa_data['weighted'] != "N/A" or gpa_data['unweighted'] != "N/A":
             output_text += "GPA Information:\n"
@@ -53,12 +94,43 @@ def parse_transcript(file):
         else:
             output_text += "No GPA information found\n"
 
+        output_text += "\n(Courses not shown here)"
+
         return output_text, {
             "gpa": gpa_data,
-            "grade_level": grade_level
+            "grade_level": grade_level,
+            "courses": courses_by_grade
         }
     else:
-        return "Currently only PDF transcripts are supported", None
+        return "Unsupported file format", None
+
+    # For CSV/XLSX fallback
+    gpa = "N/A"
+    for col in ['GPA', 'Grade Point Average', 'Cumulative GPA']:
+        if col in df.columns:
+            gpa = df[col].iloc[0] if isinstance(df[col].iloc[0], (float, int)) else "N/A"
+            break
+
+    grade_level = "N/A"
+    for col in ['Grade Level', 'Grade', 'Class', 'Year']:
+        if col in df.columns:
+            grade_level = df[col].iloc[0]
+            break
+
+    courses = []
+    for col in ['Course', 'Subject', 'Course Name', 'Class']:
+        if col in df.columns:
+            courses = df[col].tolist()
+            break
+
+    output_text = f"Grade Level: {grade_level}\nGPA: {gpa}\n\nCourses:\n"
+    output_text += "\n".join(f"- {course}" for course in courses)
+
+    return output_text, {
+        "gpa": {"unweighted": gpa, "weighted": "N/A"},
+        "grade_level": grade_level,
+        "courses": courses
+    }
 
 # ========== LEARNING STYLE QUIZ ==========
 learning_style_questions = [
@@ -66,7 +138,22 @@ learning_style_questions = [
     "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 meet new people, you remember them by:",
+    "When you're relaxing, you prefer to:",
+    "When you're explaining something to someone, you:",
+    "When you're trying to remember something, you:",
+    "When you're in a classroom, you learn best when:",
+    "When you're trying to solve a problem, you:",
+    "When you're taking notes, you:",
+    "When you're learning new software, you prefer to:",
+    "When you're at a museum, you spend the most time:",
+    "When you're assembling furniture, you:",
+    "When you're learning new vocabulary, you:",
+    "When you're giving a presentation, you prefer:",
+    "When you're at a party, you enjoy:",
+    "When you're taking a break from studying, you:",
+    "When you're learning dance moves, you:",
+    "When you're choosing a book, you prefer:"
 ]
 
 learning_style_options = [
@@ -74,7 +161,22 @@ learning_style_options = [
     ["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)"]
+    ["Their face (Visual)", "Their name (Auditory)", "What you talked about (Reading/Writing)", "What you did together (Kinesthetic)"],
+    ["Read (Reading/Writing)", "Listen to music (Auditory)", "Watch TV (Visual)", "Do something active (Kinesthetic)"],
+    ["Write it down (Reading/Writing)", "Tell them verbally (Auditory)", "Show them (Visual)", "Demonstrate physically (Kinesthetic)"],
+    ["See it written down (Visual)", "Say it out loud (Auditory)", "Write it down (Reading/Writing)", "Do it physically (Kinesthetic)"],
+    ["Reading materials (Reading/Writing)", "Listening to lectures (Auditory)", "Seeing diagrams (Visual)", "Doing hands-on activities (Kinesthetic)"],
+    ["Write down steps (Reading/Writing)", "Talk through it (Auditory)", "Draw diagrams (Visual)", "Try different approaches (Kinesthetic)"],
+    ["Write detailed notes (Reading/Writing)", "Record lectures (Auditory)", "Draw mind maps (Visual)", "Take minimal notes (Kinesthetic)"],
+    ["Read the manual (Reading/Writing)", "Have someone explain it (Auditory)", "Watch tutorial videos (Visual)", "Just start using it (Kinesthetic)"],
+    ["Reading descriptions (Reading/Writing)", "Listening to audio guides (Auditory)", "Looking at exhibits (Visual)", "Interactive displays (Kinesthetic)"],
+    ["Read instructions first (Reading/Writing)", "Ask someone to help (Auditory)", "Look at diagrams (Visual)", "Start assembling (Kinesthetic)"],
+    ["Write them repeatedly (Reading/Writing)", "Say them repeatedly (Auditory)", "Use flashcards (Visual)", "Use them in conversation (Kinesthetic)"],
+    ["Having detailed notes (Reading/Writing)", "Speaking freely (Auditory)", "Using visual aids (Visual)", "Demonstrating something (Kinesthetic)"],
+    ["Conversations (Auditory)", "People-watching (Visual)", "Dancing/games (Kinesthetic)", "Reading about people (Reading/Writing)"],
+    ["Read for fun (Reading/Writing)", "Listen to music (Auditory)", "Watch videos (Visual)", "Exercise (Kinesthetic)"],
+    ["Watch demonstrations (Visual)", "Listen to instructions (Auditory)", "Read choreography (Reading/Writing)", "Try the moves (Kinesthetic)"],
+    ["Text-heavy books (Reading/Writing)", "Audiobooks (Auditory)", "Books with pictures (Visual)", "Interactive books (Kinesthetic)"]
 ]
 
 def learning_style_quiz(*answers):
@@ -85,39 +187,36 @@ def learning_style_quiz(*answers):
         "Kinesthetic": 0
     }
     
+    # Map each answer to a learning style
     for i, answer in enumerate(answers):
-        if answer == learning_style_options[i][0]:
+        if answer in learning_style_options[i][0]:
             scores["Reading/Writing"] += 1
-        elif answer == learning_style_options[i][1]:
+        elif answer in learning_style_options[i][1]:
             scores["Auditory"] += 1
-        elif answer == learning_style_options[i][2]:
+        elif answer in learning_style_options[i][2]:
             scores["Visual"] += 1
-        elif answer == learning_style_options[i][3]:
+        elif answer in learning_style_options[i][3]:
             scores["Kinesthetic"] += 1
     
+    # Get the highest score(s)
     max_score = max(scores.values())
     dominant_styles = [style for style, score in scores.items() if score == max_score]
     
+    # Generate result
     if len(dominant_styles) == 1:
-        return f"Your primary learning style is: {dominant_styles[0]}"
+        result = f"Your primary learning style is: {dominant_styles[0]}"
     else:
-        return f"You have multiple strong learning styles: {', '.join(dominant_styles)}"
-
-# ========== PROFILE MANAGEMENT ==========
-def save_profile(name, age, interests, transcript, learning_style, 
-                movie, movie_reason, show, show_reason, 
-                book, book_reason, character, character_reason, blog):
-    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
-    }
+        result = f"You have multiple strong learning styles: {', '.join(dominant_styles)}"
     
+    # Add detailed breakdown
+    result += "\n\nDetailed Scores:\n"
+    for style, score in sorted(scores.items(), key=lambda x: x[1], reverse=True):
+        result += f"{style}: {score}/20\n"
+    
+    return result
+
+# ========== SAVE STUDENT PROFILE FUNCTION ==========
+def save_profile(name, age, interests, transcript, learning_style, favorites, blog):
     data = {
         "name": name,
         "age": age,
@@ -127,36 +226,60 @@ def save_profile(name, age, interests, transcript, 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)
-    
-    return "Profile saved successfully!"
 
-def load_profile():
-    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 {}
+    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:
+        return "No transcript uploaded."
+    if isinstance(transcript_dict, dict) and all(isinstance(v, list) for v in transcript_dict.values()):
+        display = ""
+        for grade_level, courses in transcript_dict.items():
+            display += f"\n**Grade {grade_level}**\n"
+            for course in courses:
+                display += f"- {course['course']}"
+                if 'grade' in course:
+                    display += f" (Grade: {course['grade']})"
+                display += "\n"
+        return display
+    return "\n".join([f"- {course}" for course in transcript_dict["courses"]] +
+                     [f"Grade Level: {transcript_dict['grade_level']}", f"GPA: {transcript_dict['gpa']}"])
 
 # ========== GRADIO INTERFACE ==========
 with gr.Blocks() as app:
-    # Profile tabs
     with gr.Tab("Step 1: Upload Transcript"):
-        transcript_file = gr.File(label="Upload your transcript (PDF)")
+        transcript_file = gr.File(label="Upload your transcript (CSV, Excel, or PDF)")
         transcript_output = gr.Textbox(label="Transcript Output")
         transcript_data = gr.State()
-        transcript_file.change(parse_transcript, inputs=transcript_file, outputs=[transcript_output, transcript_data])
+        transcript_file.change(fn=parse_transcript, inputs=transcript_file, outputs=[transcript_output, transcript_data])
 
     with gr.Tab("Step 2: Learning Style Quiz"):
+        gr.Markdown("### Complete this 20-question quiz to determine your learning style")
         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}"))
+            quiz_components.append(
+                gr.Radio(choices=options, label=f"{i+1}. {question}")
+            )
         
-        learning_output = gr.Textbox(label="Learning Style Result")
+        learning_output = gr.Textbox(label="Learning Style Result", lines=5)
         gr.Button("Submit Quiz").click(
             learning_style_quiz,
             inputs=quiz_components,
@@ -177,18 +300,30 @@ with gr.Blocks() as app:
         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)
+        blog_checkbox.change(fn=lambda x: gr.update(visible=x), inputs=blog_checkbox, outputs=blog_text)
 
-    with gr.Tab("Step 4: Save Profile"):
+    with gr.Tab("Step 4: Save & Review"):
+        output_summary = gr.Markdown()
         save_btn = gr.Button("Save Profile")
-        save_output = gr.Textbox(label="Save Status")
-        
-        save_btn.click(
-            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=save_output
-        )
+
+        def gather_and_save(name, age, interests, movie, movie_reason, show, show_reason,
+                          book, book_reason, character, character_reason, blog, transcript, learning_style):
+            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,
+            }
+            return save_profile(name, age, interests, transcript, learning_style, favorites, blog)
+
+        save_btn.click(fn=gather_and_save,
+                     inputs=[name, age, interests, movie, movie_reason, show, show_reason,
+                            book, book_reason, character, character_reason, blog_text,
+                            transcript_data, learning_output],
+                     outputs=output_summary)
 
 app.launch()