import gradio as gr import joblib import pandas as pd import numpy as np import os # Load all trained models models = { "Logistic Regression": joblib.load('logistic_regression_model.joblib'), "Random Forest": joblib.load('random_forest_model.joblib'), "Support Vector Machine (SVM)": joblib.load('svm_model.joblib'), "Decision Tree": joblib.load('decision_tree_model.joblib'), "XGBoost": joblib.load('xgboost_model.joblib'), "AdaBoost": joblib.load('adaboost_model.joblib') } # ← fixed: closing brace present # --- BACKGROUND MAPPINGS --- mappings = { "Gender": {"Male": 1, "Female": 0}, "YesNo": {"Yes": 1, "No": 0}, "Income": { "Below ₹3,00,000": 0, "₹3,00,001 - ₹5,00,000": 1, "₹5,00,001 - ₹8,00,000": 2, "₹8,00,001 - ₹12,00,000": 3, "Above ₹12,00,000": 4 }, "Grades": { "Below 50%": 0, "50% - 59.9%": 1, "60% - 69.9%": 2, "70% - 79.9%": 3, "80% - 89.9%": 4, "90% and above": 5 }, "Social_Category": {"General": 0, "OBC": 1, "SC": 2, "ST": 3, "EWS": 4}, "Domicile_Type": {"Urban": 0, "Semi-Urban": 1, "Rural": 2} } def predict_risk(model_name, gender, age, social_category, domicile_type, first_gen, disability_status, income_bracket, family_members, earning_members, scholarship, loan_status, class10, class12, cgpa, backlogs, year_backs): # 1. Select the model model = models[model_name] # 2. Convert text to numbers encoded_gender = mappings["Gender"].get(gender, 0) encoded_first_gen = mappings["YesNo"].get(first_gen, 0) encoded_disability = mappings["YesNo"].get(disability_status, 0) encoded_scholarship = mappings["YesNo"].get(scholarship, 0) encoded_loan = mappings["YesNo"].get(loan_status, 0) encoded_income = mappings["Income"].get(income_bracket, 0) encoded_class10 = mappings["Grades"].get(class10, 0) encoded_class12 = mappings["Grades"].get(class12, 0) encoded_social = mappings["Social_Category"].get(social_category, 0) encoded_domicile = mappings["Domicile_Type"].get(domicile_type, 0) # 3. Create the numeric DataFrame input_data = pd.DataFrame({ 'Gender_bin': [encoded_gender], 'Age': [age], 'Social_Category': [encoded_social], 'Domicile_Type': [encoded_domicile], 'First_Gen_bin': [encoded_first_gen], 'Disability_Status_bin': [encoded_disability], 'Income_ord': [encoded_income], 'Total_Family_Members': [family_members], 'Earning_Members': [earning_members], 'Scholarship_Status_bin': [encoded_scholarship], 'Education_Loan_Status_bin': [encoded_loan], 'Class10_ord': [encoded_class10], 'Class12_ord': [encoded_class12], 'Current_CGPA': [cgpa], 'Current_Backlogs': [backlogs], 'Year_Backs': [year_backs] }) # 4. Predict prediction = model.predict(input_data)[0] result = "At Risk" if prediction >= 2 else "Not At Risk" # 5. Calculate confidence try: probabilities = model.predict_proba(input_data) confidence = float(np.max(probabilities)) * 100 except: confidence = 85.0 return { "model_used": model_name, "prediction": result, "confidence": round(confidence, 2), "risk_score": float(prediction) } # Create Gradio interface iface = gr.Interface( fn=predict_risk, inputs=[ gr.Dropdown(list(models.keys()), label="Select Model", value="XGBoost"), gr.Dropdown(["Male", "Female"], label="Gender"), gr.Number(label="Age", minimum=17, maximum=30), gr.Dropdown(["General", "OBC", "SC", "ST", "EWS"], label="Social Category"), gr.Dropdown(["Urban", "Semi-Urban", "Rural"], label="Domicile Type"), gr.Dropdown(["Yes", "No"], label="First Generation"), gr.Dropdown(["Yes", "No"], label="Disability Status"), gr.Dropdown(["Below ₹3,00,000", "₹3,00,001 - ₹5,00,000", "₹5,00,001 - ₹8,00,000", "₹8,00,001 - ₹12,00,000", "Above ₹12,00,000"], label="Annual Family Income"), gr.Number(label="Total Family Members", minimum=1, maximum=15), gr.Number(label="Earning Members", minimum=0, maximum=10), gr.Dropdown(["Yes", "No"], label="Scholarship Status"), gr.Dropdown(["Yes", "No"], label="Education Loan Status"), gr.Dropdown(["Below 50%", "50% - 59.9%", "60% - 69.9%", "70% - 79.9%", "80% - 89.9%", "90% and above"], label="Class 10 Percentage"), gr.Dropdown(["Below 50%", "50% - 59.9%", "60% - 69.9%", "70% - 79.9%", "80% - 89.9%", "90% and above"], label="Class 12 Percentage"), gr.Number(label="Current CGPA", minimum=0, maximum=10, step=0.01), gr.Number(label="Current Backlogs", minimum=0, maximum=10), gr.Number(label="Year Backs", minimum=0, maximum=5) ], outputs=gr.JSON(label="Prediction Result"), title="SETU Student At-Risk Prediction", description="AI-powered student dropout risk assessment system with multiple ML models", api_name="predict" ) # ← fixed: closing parenthesis present if __name__ == "__main__": iface.launch()