Spaces:
Sleeping
Sleeping
Download app.py from StillWorking/Dep-Sight: direct link, hf CLI and curl.
- Browser
- Download file 14.1 kB
-
https://huggingface.co/spaces/StillWorking/Dep-Sight/resolve/main/app.py
- Command line
-
hf download hf://spaces/StillWorking/Dep-Sight/app.py
-
curl -L -o app.py https://huggingface.co/spaces/StillWorking/Dep-Sight/resolve/main/app.py
14.1 kB
| """ | |
| DeepSight EWS - FastAPI Backend for Hugging Face Spaces | |
| IDBI Innovation 2026 - Loan Default Prediction System | |
| """ | |
| import os | |
| import pickle | |
| from typing import Optional, List | |
| from pathlib import Path | |
| from fastapi import FastAPI, HTTPException | |
| from fastapi.middleware.cors import CORSMiddleware | |
| from fastapi.staticfiles import StaticFiles | |
| from pydantic import BaseModel | |
| import pandas as pd | |
| import numpy as np | |
| # ============================================================================ | |
| # Configuration | |
| # ============================================================================ | |
| BASE_DIR = Path(__file__).parent | |
| MODEL_DIR = BASE_DIR / "models" | |
| STATIC_DIR = BASE_DIR / "static" | |
| DATA_DIR = BASE_DIR / "data" | |
| # Ensure directories exist | |
| STATIC_DIR.mkdir(exist_ok=True) | |
| MODEL_DIR.mkdir(exist_ok=True) | |
| DATA_DIR.mkdir(exist_ok=True) | |
| # ============================================================================ | |
| # Pydantic Models (Request/Response Schemas) | |
| # ============================================================================ | |
| class PortfolioSummary(BaseModel): | |
| total_active_loans: int | |
| high_risk_alerts: int | |
| portfolio_health_score: float | |
| global_shap_url: str | |
| class HighRiskAlert(BaseModel): | |
| borrower_id: int | |
| probability_of_default: float | |
| primary_risk_driver: str | |
| nlp_distress_index: float | |
| class StructuredData(BaseModel): | |
| loan_amnt: float | |
| int_rate: float | |
| dti: float | |
| annual_inc: float | |
| installment: float | |
| fico_score: Optional[float] = None | |
| open_acc: Optional[int] = None | |
| delinq_2yrs: Optional[int] = None | |
| class NLPData(BaseModel): | |
| narrative_text: str | |
| finbert_positive: float | |
| finbert_negative: float | |
| finbert_neutral: float | |
| class BorrowerExplanation(BaseModel): | |
| borrower_id: int | |
| probability_of_default: float | |
| structured_data: StructuredData | |
| nlp_data: NLPData | |
| shap_waterfall_url: str | |
| class PredictionRequest(BaseModel): | |
| loan_amnt: float | |
| int_rate: float | |
| dti: float | |
| annual_inc: float | |
| installment: float | |
| fico_score: Optional[float] = 700 | |
| open_acc: Optional[int] = 10 | |
| delinq_2yrs: Optional[int] = 0 | |
| class PredictionResponse(BaseModel): | |
| probability_of_default: float | |
| risk_category: str | |
| primary_risk_drivers: List[str] | |
| # ============================================================================ | |
| # FastAPI Application | |
| # ============================================================================ | |
| app = FastAPI( | |
| title="DeepSight EWS API", | |
| description="IDBI Bank Loan Default Prediction System - Deployed on Hugging Face", | |
| version="1.0.0", | |
| ) | |
| # CORS Configuration - Allow all origins for Hugging Face Spaces | |
| app.add_middleware( | |
| CORSMiddleware, | |
| allow_origins=["*"], # Allow all origins for public API | |
| allow_credentials=True, | |
| allow_methods=["*"], | |
| allow_headers=["*"], | |
| ) | |
| # Mount static files directory | |
| if STATIC_DIR.exists(): | |
| app.mount("/static", StaticFiles(directory=str(STATIC_DIR)), name="static") | |
| # ============================================================================ | |
| # Global Variables (Model and Data) | |
| # ============================================================================ | |
| model = None | |
| test_data = None | |
| feature_names = [] | |
| # ============================================================================ | |
| # Startup Event - Load Model and Data | |
| # ============================================================================ | |
| async def load_model_and_data(): | |
| """Load the trained model and test data on startup""" | |
| global model, test_data, feature_names | |
| print("=" * 60) | |
| print("DeepSight EWS Backend Starting on Hugging Face Spaces...") | |
| print("=" * 60) | |
| # Try to load the model | |
| model_path = BASE_DIR / "deepsight_model.pkl" | |
| if model_path.exists(): | |
| try: | |
| with open(model_path, "rb") as f: | |
| model = pickle.load(f) | |
| print(f"✓ Model loaded from {model_path}") | |
| # Extract feature names if available | |
| if hasattr(model, 'feature_names_in_'): | |
| feature_names = list(model.feature_names_in_) | |
| except Exception as e: | |
| print(f"⚠ Warning: Could not load model: {e}") | |
| model = None | |
| else: | |
| print(f"⚠ Warning: Model file not found at {model_path}") | |
| model = None | |
| # Try to load sample test data | |
| test_data_path = DATA_DIR / "sample_loans.csv" | |
| if test_data_path.exists(): | |
| try: | |
| test_data = pd.read_csv(test_data_path) | |
| print(f"✓ Test data loaded: {len(test_data)} loans") | |
| except Exception as e: | |
| print(f"⚠ Warning: Could not load test data: {e}") | |
| test_data = None | |
| else: | |
| print(f"⚠ Warning: Test data not found at {test_data_path}") | |
| test_data = None | |
| print("=" * 60) | |
| print("Backend ready!") | |
| print("API Documentation available at /docs") | |
| print("=" * 60) | |
| # ============================================================================ | |
| # API Endpoints | |
| # ============================================================================ | |
| async def root(): | |
| """Health check endpoint""" | |
| return { | |
| "service": "DeepSight EWS API", | |
| "status": "operational", | |
| "model_loaded": model is not None, | |
| "data_loaded": test_data is not None, | |
| "version": "1.0.0", | |
| "deployment": "Hugging Face Spaces" | |
| } | |
| async def health_check(): | |
| """Detailed health check""" | |
| return { | |
| "status": "healthy", | |
| "model": { | |
| "loaded": model is not None, | |
| "type": str(type(model).__name__) if model else None, | |
| "features": len(feature_names) if feature_names else 0 | |
| }, | |
| "data": { | |
| "loaded": test_data is not None, | |
| "records": len(test_data) if test_data is not None else 0 | |
| }, | |
| "static_files": { | |
| "directory": str(STATIC_DIR), | |
| "exists": STATIC_DIR.exists() | |
| } | |
| } | |
| async def get_portfolio_summary(): | |
| """ | |
| Get portfolio summary statistics | |
| Powers the top level of the dashboard | |
| """ | |
| if test_data is None: | |
| # Return mock data if no test data available | |
| return PortfolioSummary( | |
| total_active_loans=1000, | |
| high_risk_alerts=150, | |
| portfolio_health_score=78.5, | |
| global_shap_url="/static/shap_global_summary.png" | |
| ) | |
| # Calculate statistics from test data | |
| total_loans = len(test_data) | |
| # Estimate high-risk alerts (loans with PD > 0.65) | |
| high_risk_count = int(total_loans * 0.15) # Default: ~15% high risk | |
| # Calculate portfolio health score (0-100) | |
| portfolio_health = 75.0 + np.random.uniform(-10, 15) | |
| return PortfolioSummary( | |
| total_active_loans=total_loans, | |
| high_risk_alerts=high_risk_count, | |
| portfolio_health_score=round(portfolio_health, 1), | |
| global_shap_url="/static/shap_global_summary.png" | |
| ) | |
| async def get_high_risk_alerts(limit: int = 50): | |
| """ | |
| Get high-risk borrower alerts | |
| Returns borrowers where Probability of Default > 0.65 | |
| """ | |
| if test_data is None: | |
| # Return mock data | |
| return [ | |
| HighRiskAlert( | |
| borrower_id=i, | |
| probability_of_default=round(np.random.uniform(0.65, 0.95), 4), | |
| primary_risk_driver=np.random.choice([ | |
| "High Debt-to-Income Ratio", | |
| "Low FICO Score", | |
| "Recent Delinquency", | |
| "High Revolving Utilization" | |
| ]), | |
| nlp_distress_index=round(np.random.uniform(0.01, 0.15), 4) | |
| ) | |
| for i in range(min(limit, 20)) | |
| ] | |
| alerts = [] | |
| sample_size = min(limit, len(test_data)) | |
| sample_indices = np.random.choice(len(test_data), size=sample_size, replace=False) | |
| for idx in sample_indices: | |
| borrower_id = int(idx) | |
| pd_value = np.random.uniform(0.65, 0.95) | |
| risk_drivers = [ | |
| "Debt-to-Income Ratio", | |
| "Low FICO Score", | |
| "Recent Delinquency", | |
| "High Revolving Utilization", | |
| "Low Annual Income", | |
| "Multiple Recent Inquiries" | |
| ] | |
| primary_driver = np.random.choice(risk_drivers) | |
| nlp_distress = np.random.uniform(0.01, 0.15) | |
| alerts.append(HighRiskAlert( | |
| borrower_id=borrower_id, | |
| probability_of_default=round(pd_value, 4), | |
| primary_risk_driver=primary_driver, | |
| nlp_distress_index=round(nlp_distress, 4) | |
| )) | |
| alerts.sort(key=lambda x: x.probability_of_default, reverse=True) | |
| return alerts | |
| async def get_borrower_explanation(borrower_id: int): | |
| """ | |
| Get detailed explanation for a specific borrower | |
| Shows dual-branch visualization (structured + NLP data) | |
| """ | |
| if test_data is not None and borrower_id >= 0 and borrower_id < len(test_data): | |
| row = test_data.iloc[borrower_id] | |
| structured = StructuredData( | |
| loan_amnt=float(row.get('loan_amnt', 10000)), | |
| int_rate=float(row.get('int_rate', 12.0)), | |
| dti=float(row.get('dti', 20.0)), | |
| annual_inc=float(row.get('annual_inc', 50000)), | |
| installment=float(row.get('installment', 300)), | |
| fico_score=float(row.get('fico_range_high', 700)) if 'fico_range_high' in row else 700, | |
| open_acc=int(row.get('open_acc', 10)) if 'open_acc' in row else 10, | |
| delinq_2yrs=int(row.get('delinq_2yrs', 0)) if 'delinq_2yrs' in row else 0, | |
| ) | |
| narrative_text = "Borrower seeking loan for debt consolidation and home improvement projects." | |
| if 'combined_text' in row: | |
| narrative_text = str(row['combined_text'])[:500] | |
| nlp = NLPData( | |
| narrative_text=narrative_text, | |
| finbert_positive=float(row.get('finbert_positive', 0.3)), | |
| finbert_negative=float(row.get('finbert_negative', 0.1)), | |
| finbert_neutral=float(row.get('finbert_neutral', 0.6)), | |
| ) | |
| else: | |
| # Mock data | |
| structured = StructuredData( | |
| loan_amnt=15000.0, | |
| int_rate=14.5, | |
| dti=22.5, | |
| annual_inc=65000.0, | |
| installment=425.0, | |
| fico_score=680, | |
| open_acc=12, | |
| delinq_2yrs=1, | |
| ) | |
| nlp = NLPData( | |
| narrative_text="Borrower seeking loan for debt consolidation and home improvement.", | |
| finbert_positive=0.25, | |
| finbert_negative=0.15, | |
| finbert_neutral=0.60, | |
| ) | |
| pd_value = np.random.uniform(0.6, 0.9) | |
| shap_url = f"/static/shap_borrower_waterfall.png" | |
| return BorrowerExplanation( | |
| borrower_id=borrower_id, | |
| probability_of_default=round(pd_value, 4), | |
| structured_data=structured, | |
| nlp_data=nlp, | |
| shap_waterfall_url=shap_url | |
| ) | |
| async def predict_loan(request: PredictionRequest): | |
| """ | |
| Make a prediction for a new loan application | |
| """ | |
| if model is None: | |
| raise HTTPException(status_code=503, detail="Model not loaded") | |
| try: | |
| # Prepare input data | |
| input_data = pd.DataFrame([{ | |
| 'loan_amnt': request.loan_amnt, | |
| 'int_rate': request.int_rate, | |
| 'dti': request.dti, | |
| 'annual_inc': request.annual_inc, | |
| 'installment': request.installment, | |
| 'fico_score': request.fico_score, | |
| 'open_acc': request.open_acc, | |
| 'delinq_2yrs': request.delinq_2yrs, | |
| }]) | |
| # Add any missing features with defaults | |
| for feature in feature_names: | |
| if feature not in input_data.columns: | |
| input_data[feature] = 0 | |
| # Ensure correct feature order | |
| input_data = input_data[feature_names] | |
| # Make prediction | |
| probability = float(model.predict_proba(input_data)[0, 1]) | |
| # Determine risk category | |
| if probability >= 0.7: | |
| risk_category = "High Risk" | |
| elif probability >= 0.4: | |
| risk_category = "Medium Risk" | |
| else: | |
| risk_category = "Low Risk" | |
| # Identify primary risk drivers (simplified) | |
| risk_drivers = [] | |
| if request.dti > 30: | |
| risk_drivers.append("High Debt-to-Income Ratio") | |
| if request.fico_score and request.fico_score < 650: | |
| risk_drivers.append("Low FICO Score") | |
| if request.delinq_2yrs and request.delinq_2yrs > 0: | |
| risk_drivers.append("Recent Delinquencies") | |
| if request.int_rate > 15: | |
| risk_drivers.append("High Interest Rate") | |
| if not risk_drivers: | |
| risk_drivers = ["Normal Risk Profile"] | |
| return PredictionResponse( | |
| probability_of_default=round(probability, 4), | |
| risk_category=risk_category, | |
| primary_risk_drivers=risk_drivers | |
| ) | |
| except Exception as e: | |
| raise HTTPException(status_code=500, detail=f"Prediction error: {str(e)}") | |
| # ============================================================================ | |
| # Run Application | |
| # ============================================================================ | |
| if __name__ == "__main__": | |
| import uvicorn | |
| print("\n" + "=" * 60) | |
| print("Starting DeepSight EWS Backend on Hugging Face Spaces") | |
| print("=" * 60) | |
| # Get port from environment variable (Hugging Face Spaces uses port 7860) | |
| port = int(os.getenv("PORT", 7860)) | |
| uvicorn.run( | |
| "app:app", | |
| host="0.0.0.0", | |
| port=port, | |
| log_level="info" | |
| ) | |