Create app.py

app.py

@@ -0,0 +1,97 @@
+import gradio as gr
+import pandas as pd
+import PyPDF2
+import json
+import re
+
+# Parse uploaded transcript file
+def parse_transcript(file):
+    if file.name.endswith('.csv'):
+        df = pd.read_csv(file.name)
+    elif file.name.endswith(('.xls', '.xlsx')):
+        df = pd.read_excel(file.name)
+    elif file.name.endswith('.pdf'):
+        reader = PyPDF2.PdfReader(file)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text() or ""
+        df = pd.DataFrame({'Transcript_Text': [text]})
+    else:
+        raise ValueError("Unsupported file format. Use .csv, .xlsx, or .pdf")
+    return df
+
+# Extract student info
+def extract_transcript_info(df):
+    transcript_text = df['Transcript_Text'].iloc[0] if 'Transcript_Text' in df.columns else ''
+    info = {}
+    gpa_match = re.search(r'(GPA|Grade Point Average)[^\d]*(\d+\.\d+)', transcript_text, re.IGNORECASE)
+    if gpa_match:
+        info['GPA'] = gpa_match.group(2)
+    grade_match = re.search(r'Grade:?\s*(\d{1,2})', transcript_text, re.IGNORECASE)
+    if grade_match:
+        info['Grade_Level'] = grade_match.group(1)
+    courses = re.findall(r'(?i)\b([A-Z][a-zA-Z\s&/]+)\s+(\d{1,3})\b', transcript_text)
+    if courses:
+        info['Courses'] = list(set([c[0].strip() for c in courses]))
+    return info
+
+# Learning style questions
+def learning_style_quiz(q1, q2, q3):
+    scores = {'visual': 0, 'auditory': 0, 'reading/writing': 0, 'kinesthetic': 0}
+    mapping = [q1, q2, q3]
+    for answer in mapping:
+        scores[answer] += 1
+    best = max(scores, key=scores.get)
+    return best.capitalize()
+
+# Save all answers into profile
+def save_profile(file, q1, q2, q3, about_me, blog_text, blog_opt_in):
+    df = parse_transcript(file)
+    transcript_info = extract_transcript_info(df)
+    learning_type = learning_style_quiz(q1, q2, q3)
+
+    if not blog_opt_in and blog_text.strip() == "":
+        blog_text = "[User chose to skip this section]"
+
+    profile = {
+        "transcript": df.to_dict(orient='records'),
+        "transcript_info": transcript_info,
+        "learning_style": learning_type,
+        "about_me": about_me,
+        "blog": blog_text
+    }
+
+    with open("student_profile.json", "w") as f:
+        json.dump(profile, f, indent=4)
+
+    return f"✅ Profile saved! Your learning style is: {learning_type}"
+
+# Build Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 🎓 Personalized AI Student Assistant")
+
+    with gr.Row():
+        file = gr.File(label="📄 Upload Your Transcript (.csv, .xlsx, .pdf)")
+
+    with gr.Column():
+        gr.Markdown("### 🧠 Learning Style Discovery")
+        q1 = gr.Radio(["visual", "auditory", "reading/writing", "kinesthetic"], label="1. How do you prefer to learn new topics?")
+        q2 = gr.Radio(["visual", "auditory", "reading/writing", "kinesthetic"], label="2. How do you remember lists best?")
+        q3 = gr.Radio(["visual", "auditory", "reading/writing", "kinesthetic"], label="3. Favorite way to study?")
+
+    with gr.Column():
+        gr.Markdown("### ❤️ About You")
+        about_me = gr.Textbox(lines=6, label="Answer a few questions: \n1. What’s a fun fact about you? \n2. Favorite music/artist? \n3. Your dream job?")
+
+        blog_opt_in = gr.Checkbox(label="I want to write a personal blog for better personalization")
+        blog_text = gr.Textbox(lines=5, label="✍️ Optional: Write a mini blog about your life", visible=True)
+
+    submit = gr.Button("📥 Save My Profile")
+    output = gr.Textbox(label="Status")
+
+    submit.click(fn=save_profile,
+                 inputs=[file, q1, q2, q3, about_me, blog_text, blog_opt_in],
+                 outputs=[output])
+
+if __name__ == '__main__':
+    demo.launch()