Update app.py

app.py

@@ -1,40 +1,78 @@
 from fastapi import FastAPI, HTTPException, Header
-from pydantic import BaseModel
-import pandas as pd, os, joblib, time, requests
+import pandas as pd
+import os
+import joblib
+import time
+import requests
 from huggingface_hub import hf_hub_download
 from prometheus_client import Counter, Histogram, Gauge, generate_latest
 
-app = FastAPI()
+print("🚀 Starting FastAPI application...")
 
-API_KEY = os.getenv("API_KEY")
+app = FastAPI(title="Loan Approval API", version="1.0")
+
+# Environment variables
+API_KEY = os.getenv("API_KEY", "test-key-123")
 HF_MODEL_REPO = os.getenv("HF_MODEL_REPO")
 PROM_PUSHGATEWAY = os.getenv("PROM_PUSHGATEWAY")
 
+print(f"API_KEY: {'Set' if API_KEY else 'Not set'}")
+print(f"HF_MODEL_REPO: {HF_MODEL_REPO}")
+
 # Prometheus metrics
 REQS = Counter("pred_requests_total", "Total prediction requests")
 LAT = Histogram("pred_request_latency_seconds", "Request latency")
 LATEST = Gauge("latest_prediction", "Last predicted value")
 
-# Load model and preprocessing artifacts
-try:
-    m = hf_hub_download(repo_id=HF_MODEL_REPO, filename="best_model.joblib")
-    e = hf_hub_download(repo_id=HF_MODEL_REPO, filename="models/encoders.joblib")
-    s = hf_hub_download(repo_id=HF_MODEL_REPO, filename="models/scaler.joblib")
-    f = hf_hub_download(repo_id=HF_MODEL_REPO, filename="models/feature_columns.joblib")
-
-    model = joblib.load(m)
-    encoders = joblib.load(e)
-    scaler = joblib.load(s)
-    feature_columns = joblib.load(f)
-    loaded = True
-except Exception as ex:
-    print("Model load error:", ex)
+# Global variables
+model = None
+encoders = {}
+scaler = None
+feature_columns = []
+categorical_columns = []
+boolean_columns = []
+loaded = False
+
+# Load model on startup
+if not HF_MODEL_REPO:
+    print("⚠️  WARNING: HF_MODEL_REPO not set. Using mock mode.")
     loaded = False
+else:
+    try:
+        print(f" Downloading model from {HF_MODEL_REPO}...")
+        
+        m = hf_hub_download(repo_id=HF_MODEL_REPO, filename="best_model.joblib")
+        e = hf_hub_download(repo_id=HF_MODEL_REPO, filename="models/encoders.joblib")
+        s = hf_hub_download(repo_id=HF_MODEL_REPO, filename="models/scaler.joblib")
+        f = hf_hub_download(repo_id=HF_MODEL_REPO, filename="models/feature_columns.joblib")
+        c = hf_hub_download(repo_id=HF_MODEL_REPO, filename="models/categorical_columns.joblib")
+        b = hf_hub_download(repo_id=HF_MODEL_REPO, filename="models/boolean_columns.joblib")
+
+        print(" Loading artifacts...")
+        model = joblib.load(m)
+        encoders = joblib.load(e)
+        scaler = joblib.load(s)
+        feature_columns = joblib.load(f)
+        categorical_columns = joblib.load(c)
+        boolean_columns = joblib.load(b)
+        loaded = True
+        
+        print(" Model loaded successfully!")
+        print(f"   Features: {len(feature_columns)}")
+    except Exception as ex:
+        print(f" Model load error: {ex}")
+        loaded = False
+
+print(" FastAPI app initialized")
 
 
 @app.get("/")
 def health():
-    return {"status": "ok", "model_loaded": loaded, "features": feature_columns}
+    return {
+        "status": "ok",
+        "model_loaded": loaded,
+        "features": feature_columns if loaded else []
+    }
 
 
 @app.post("/predict")
@@ -45,26 +83,56 @@ def predict(payload: dict, x_api_key: str = Header(None)):
     if not loaded:
         raise HTTPException(status_code=503, detail="Model not loaded")
 
-    # Convert input dict to DataFrame and reindex to match training columns
-    df = pd.DataFrame([payload]).reindex(columns=feature_columns, fill_value=0)
-
-    # Scale numeric values
-    df_scaled = scaler.transform(df)
-    start = time.time()
-    pred = model.predict(df_scaled)[0]
-    LAT.observe(time.time() - start)
-    REQS.inc()
-    LATEST.set(pred)
-
-    if PROM_PUSHGATEWAY:
-        try:
-            requests.post(f"{PROM_PUSHGATEWAY}/metrics/job/loan_model", data=generate_latest())
-        except Exception:
-            pass
-
-    return {"prediction": int(pred), "used_features": feature_columns}
+    try:
+        df = pd.DataFrame([payload])
+        
+        for col in feature_columns:
+            if col not in df.columns:
+                df[col] = 0
+        
+        for col in boolean_columns:
+            if col in df.columns:
+                if df[col].dtype == bool:
+                    df[col] = df[col].astype(int)
+                elif df[col].dtype == 'object':
+                    df[col] = df[col].map({
+                        'True': 1, 'true': 1, True: 1, 1: 1,
+                        'False': 0, 'false': 0, False: 0, 0: 0
+                    }).fillna(0).astype(int)
+        
+        for col in categorical_columns:
+            if col in df.columns and col in encoders:
+                try:
+                    df[col] = encoders[col].transform(df[col])
+                except:
+                    df[col] = 0
+        
+        df = df[feature_columns]
+        df_scaled = scaler.transform(df)
+        
+        start = time.time()
+        pred = model.predict(df_scaled)[0]
+        latency = time.time() - start
+        
+        LAT.observe(latency)
+        REQS.inc()
+        LATEST.set(pred)
+
+        if PROM_PUSHGATEWAY:
+            try:
+                requests.post(f"{PROM_PUSHGATEWAY}/metrics/job/loan_model", data=generate_latest(), timeout=2)
+            except:
+                pass
+
+        return {
+            "prediction": int(pred),
+            "prediction_label": "Approved" if pred == 1 else "Rejected",
+            "latency_seconds": round(latency, 4)
+        }
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
 
 
 @app.get("/metrics")
 def metrics():
-    return generate_latest()
+    return generate_latest()