Spaces:
Sleeping
Sleeping
Download app.py from SetuEduTech/setu_v2: direct link, hf CLI and curl.
- Browser
- Download file 5.39 kB
-
https://huggingface.co/spaces/SetuEduTech/setu_v2/resolve/main/app.py
- Command line
-
hf download hf://spaces/SetuEduTech/setu_v2/app.py
-
curl -L -o app.py https://huggingface.co/spaces/SetuEduTech/setu_v2/resolve/main/app.py
5.39 kB
| import gradio as gr | |
| import joblib | |
| import pandas as pd | |
| import numpy as np | |
| # 1. Load preprocessing tools | |
| preprocessor = joblib.load('preprocessor.joblib') | |
| label_encoder = joblib.load('label_encoder.joblib') | |
| # 2. 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') | |
| } | |
| 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, | |
| stress, burnout, depression | |
| ): | |
| """ | |
| Takes raw input values, applies the same preprocessing as the notebook, | |
| and returns the predicted risk label together with the model's confidence. | |
| """ | |
| # 3. Build a DataFrame with exactly the column names used during training. | |
| # 'Sl. no' is irrelevant, set to a dummy value. | |
| input_data = pd.DataFrame({ | |
| 'Sl. no': [0], | |
| 'Gender': [gender], | |
| 'Age in years': [age], | |
| 'Social Category': [social_category], | |
| 'Domicile Type': [domicile_type], | |
| 'Are you a First-Generation College Student': [first_gen], | |
| 'Disability Status': [disability_status], | |
| 'Annual Family Income Bracket': [income_bracket], | |
| 'Total Family Members': [family_members], | |
| 'Earning Members in Family Count': [earning_members], | |
| 'Scholarship / Fee-Waiver Status': [scholarship], | |
| 'Do you have an Education Loan?': [loan_status], | |
| '10th Board Percentage/Grade Equivalent': [class10], | |
| '12th Board / Diploma Percentage / Grade Equivalent': [class12], | |
| 'Current Cumulative Grade Point Average (CGPA)': [cgpa], | |
| 'Current Backlog Count': [backlogs], | |
| 'Stress and Anxiety Levels': [stress], | |
| 'Burnout (Mental Exhaustion)': [burnout], | |
| 'Depression/ Emotional Well being': [depression] | |
| }) | |
| # 4. Preprocess (scale, encode) exactly as in training | |
| X_preprocessed = preprocessor.transform(input_data) | |
| # 5. Predict | |
| model = models[model_name] | |
| y_encoded = model.predict(X_preprocessed)[0] # 0 or 1 | |
| label = label_encoder.inverse_transform([y_encoded])[0] # 'at-risk' or 'not at-risk' | |
| result = "At Risk" if label == "at-risk" else "Not At Risk" | |
| # 6. Confidence (probability of the predicted class) | |
| try: | |
| proba = model.predict_proba(X_preprocessed)[0] | |
| # index of the predicted class | |
| confidence = float(proba[y_encoded]) * 100 | |
| except AttributeError: | |
| confidence = 85.0 # fallback if model doesn't support predict_proba | |
| return { | |
| "model_used": model_name, | |
| "prediction": result, | |
| "confidence": round(confidence, 2) | |
| } | |
| # 7. Build the Gradio interface with correct dropdown choices | |
| # (make sure these match the actual values in your training dataset) | |
| 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 ₹1,00,000", | |
| "₹1,00,000 - ₹3,00,000", | |
| "₹3,00,001 - ₹5,00,000", | |
| "₹5,00,001 - ₹8,00,000", | |
| "₹8,00,001 - ₹12,00,000", | |
| "₹12,00,001 - ₹15,00,000", | |
| "Above ₹15,00,000" | |
| ], | |
| label="Annual Family Income Bracket" | |
| ), | |
| 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="Stress and Anxiety Levels", minimum=1, maximum=5), | |
| gr.Number(label="Burnout (Mental Exhaustion)", minimum=1, maximum=5), | |
| gr.Number(label="Depression/ Emotional Well being", minimum=1, 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" | |
| ) | |
| if __name__ == "__main__": | |
| iface.launch() |