Update app.py

app.py

@@ -1,219 +1,219 @@
-import sys
-import os
-import time
-import json
-import logging
-
-import joblib
-import numpy as np
-import pandas as pd
-
-from flask import Flask, request, jsonify
-from sklearn.pipeline import Pipeline
-
-from features.feature_builder import build_features
-from schemas.request_schema import PredictRequest
-
-
-# ======================
-# PATH SETUP
-# ======================
-BASE_DIR = os.path.dirname(os.path.abspath(__file__))
-sys.path.insert(0, BASE_DIR)
-
-
-# ======================
-# APP INIT
-# ======================
-app = Flask(__name__)
-
-
-# ======================
-# LOGGING
-# ======================
-logging.basicConfig(
-    level=logging.INFO,
-    format="%(asctime)s - %(levelname)s - %(message)s"
-)
-
-
-# ======================
-# SECURITY CONFIG
-# ======================
-API_KEY = os.getenv("FRAUD_API_KEY")
-MAX_REQUEST_SIZE = 10_000  # 10 KB
-RATE_LIMIT = 30
-RATE_LIMIT_WINDOW = 60  # seconds
-
-rate_limit_store = {}
-
-
-def is_rate_limited(client_ip: str) -> bool:
-    now = time.time()
-
-    if client_ip not in rate_limit_store:
-        rate_limit_store[client_ip] = []
-
-    rate_limit_store[client_ip] = [
-        t for t in rate_limit_store[client_ip]
-        if now - t < RATE_LIMIT_WINDOW
-    ]
-
-    if len(rate_limit_store[client_ip]) >= RATE_LIMIT:
-        return True
-
-    rate_limit_store[client_ip].append(now)
-    return False
-
-
-# ======================
-# GLOBAL API KEY GUARD
-# ======================
-@app.before_request
-def check_api_key():
-    # Health endpoint is public
-    if request.path == "/health":
-        return
-
-    # Skip static files if any
-    if request.path.startswith("/static"):
-        return
-
-    if not API_KEY:
-        logging.error("FRAUD_API_KEY environment variable not set")
-        return jsonify({"error": "Server misconfigured"}), 500
-
-    client_key = request.headers.get("X-API-KEY")
-    if not client_key or client_key != API_KEY:
-        return jsonify({"error": "Unauthorized"}), 401
-
-
-# ======================
-# LOAD MODEL & PREPROCESSOR
-# ======================
-MODEL_PATH = os.path.join(BASE_DIR, "models", "ensemble_model_enhanced.joblib")
-PREPROCESSOR_PATH = os.path.join(BASE_DIR, "models", "preprocessor_enhanced.joblib")
-
-if not os.path.exists(MODEL_PATH):
-    raise FileNotFoundError(f"Model tidak ditemukan: {MODEL_PATH}")
-
-if not os.path.exists(PREPROCESSOR_PATH):
-    raise FileNotFoundError(f"Preprocessor tidak ditemukan: {PREPROCESSOR_PATH}")
-
-model = joblib.load(MODEL_PATH)
-preprocessor = joblib.load(PREPROCESSOR_PATH)
-
-pipeline_model = Pipeline([
-    ("preprocess", preprocessor),
-    ("classifier", model)
-])
-
-THRESHOLD = 0.6
-
-
-# ======================
-# HEALTH CHECK
-# ======================
-@app.route("/health", methods=["GET"])
-def health():
-    return jsonify({
-        "status": "ok",
-        "model_loaded": model is not None,
-        "timestamp": time.time()
-    })
-
-
-# ======================
-# PREDICT
-# ======================
-@app.route("/predict", methods=["POST"])
-def predict():
-    start_time = time.time()
-
-    # ---------- REQUEST SIZE ----------
-    if request.content_length and request.content_length > MAX_REQUEST_SIZE:
-        return jsonify({"error": "Request too large"}), 413
-
-    # ---------- RATE LIMIT ----------
-    client_ip = request.remote_addr or "unknown"
-    if is_rate_limited(client_ip):
-        return jsonify({"error": "Too many requests"}), 429
-
-    # ---------- PARSE & VALIDATE ----------
-    try:
-        payload = request.get_json()
-        req = PredictRequest(**payload)
-        data = req.model_dump()
-        logging.info("Request valid: %s", data)
-    except Exception as e:
-        return jsonify({
-            "error": "Invalid request schema",
-            "detail": str(e)
-        }), 422
-
-    # ---------- BUSINESS VALIDATION ----------
-    amount = data.get("amount", 0)
-    location = data.get("location", -1)
-
-    if amount <= 0 or amount > 100_000_000:
-        return jsonify({"error": "Invalid amount value"}), 400
-
-    if location < 0:
-        return jsonify({"error": "Invalid location value"}), 400
-
-    # ---------- FEATURE BUILD ----------
-    try:
-        X_df = build_features(data)
-        logging.info("Feature DF: %s", X_df.to_dict(orient="records"))
-    except Exception as e:
-        logging.error(f"Feature building error: {e}")
-        return jsonify({
-            "error": "Feature building error",
-            "detail": str(e)
-        }), 500
-
-    # ---------- PREDICT ----------
-    try:
-        X = preprocessor.transform(X_df)
-        fraud_prob = model.predict_proba(X)[0][1]
-    except Exception as e:
-        logging.error(f"Prediction error: {e}")
-        return jsonify({
-            "error": "Preprocessing or prediction error",
-            "detail": str(e)
-        }), 500
-
-    # ---------- DECISION ----------
-    is_fraud = fraud_prob >= THRESHOLD
-
-    if fraud_prob >= 0.85:
-        decision = "BLOCK"
-    elif fraud_prob >= THRESHOLD:
-        decision = "REVIEW"
-    else:
-        decision = "ALLOW"
-
-    latency_ms = round((time.time() - start_time) * 1000, 2)
-
-    # ---------- STRUCTURED LOG ----------
-    logging.info({
-        "event": "fraud_decision",
-        "fraud_probability": float(fraud_prob),
-        "decision": decision,
-        "threshold": THRESHOLD,
-        "latency_ms": latency_ms
-    })
-
-    return jsonify({
-        "fraud_probability": round(float(fraud_prob), 4),
-        "is_fraud": bool(is_fraud),
-        "decision": decision,
-        "latency_ms": latency_ms
-    })
-
-
-# ======================
-# RUN SERVER
-# ======================
-if __name__ == "__main__":
-    app.run(debug=True, port=5001)
+import sys
+import os
+import time
+import json
+import logging
+
+import joblib
+import numpy as np
+import pandas as pd
+
+from flask import Flask, request, jsonify
+from sklearn.pipeline import Pipeline
+
+from features.feature_builder import build_features
+from schemas.request_schema import PredictRequest
+
+
+# ======================
+# PATH SETUP
+# ======================
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, BASE_DIR)
+
+
+# ======================
+# APP INIT
+# ======================
+app = Flask(__name__)
+
+
+# ======================
+# LOGGING
+# ======================
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s"
+)
+
+
+# ======================
+# SECURITY CONFIG
+# ======================
+API_KEY = os.getenv("FRAUD_API_KEY")
+MAX_REQUEST_SIZE = 10_000  # 10 KB
+RATE_LIMIT = 30
+RATE_LIMIT_WINDOW = 60  # seconds
+
+rate_limit_store = {}
+
+
+def is_rate_limited(client_ip: str) -> bool:
+    now = time.time()
+
+    if client_ip not in rate_limit_store:
+        rate_limit_store[client_ip] = []
+
+    rate_limit_store[client_ip] = [
+        t for t in rate_limit_store[client_ip]
+        if now - t < RATE_LIMIT_WINDOW
+    ]
+
+    if len(rate_limit_store[client_ip]) >= RATE_LIMIT:
+        return True
+
+    rate_limit_store[client_ip].append(now)
+    return False
+
+
+# ======================
+# GLOBAL API KEY GUARD
+# ======================
+@app.before_request
+def check_api_key():
+    # Health endpoint is public
+    # if request.path == "/health":
+    #     return
+
+    # # Skip static files if any
+    # if request.path.startswith("/static"):
+    #     return
+
+    # if not API_KEY:
+    #     logging.error("FRAUD_API_KEY environment variable not set")
+    #     return jsonify({"error": "Server misconfigured"}), 500
+
+    # client_key = request.headers.get("X-API-KEY")
+    # if not client_key or client_key != API_KEY:
+    #     return jsonify({"error": "Unauthorized"}), 401
+
+
+# ======================
+# LOAD MODEL & PREPROCESSOR
+# ======================
+MODEL_PATH = os.path.join(BASE_DIR, "models", "ensemble_model_enhanced.joblib")
+PREPROCESSOR_PATH = os.path.join(BASE_DIR, "models", "preprocessor_enhanced.joblib")
+
+if not os.path.exists(MODEL_PATH):
+    raise FileNotFoundError(f"Model tidak ditemukan: {MODEL_PATH}")
+
+if not os.path.exists(PREPROCESSOR_PATH):
+    raise FileNotFoundError(f"Preprocessor tidak ditemukan: {PREPROCESSOR_PATH}")
+
+model = joblib.load(MODEL_PATH)
+preprocessor = joblib.load(PREPROCESSOR_PATH)
+
+pipeline_model = Pipeline([
+    ("preprocess", preprocessor),
+    ("classifier", model)
+])
+
+THRESHOLD = 0.6
+
+
+# ======================
+# HEALTH CHECK
+# ======================
+@app.route("/health", methods=["GET"])
+def health():
+    return jsonify({
+        "status": "ok",
+        "model_loaded": model is not None,
+        "timestamp": time.time()
+    })
+
+
+# ======================
+# PREDICT
+# ======================
+@app.route("/predict", methods=["POST"])
+def predict():
+    start_time = time.time()
+
+    # ---------- REQUEST SIZE ----------
+    if request.content_length and request.content_length > MAX_REQUEST_SIZE:
+        return jsonify({"error": "Request too large"}), 413
+
+    # ---------- RATE LIMIT ----------
+    client_ip = request.remote_addr or "unknown"
+    if is_rate_limited(client_ip):
+        return jsonify({"error": "Too many requests"}), 429
+
+    # ---------- PARSE & VALIDATE ----------
+    try:
+        payload = request.get_json()
+        req = PredictRequest(**payload)
+        data = req.model_dump()
+        logging.info("Request valid: %s", data)
+    except Exception as e:
+        return jsonify({
+            "error": "Invalid request schema",
+            "detail": str(e)
+        }), 422
+
+    # ---------- BUSINESS VALIDATION ----------
+    amount = data.get("amount", 0)
+    location = data.get("location", -1)
+
+    if amount <= 0 or amount > 100_000_000:
+        return jsonify({"error": "Invalid amount value"}), 400
+
+    if location < 0:
+        return jsonify({"error": "Invalid location value"}), 400
+
+    # ---------- FEATURE BUILD ----------
+    try:
+        X_df = build_features(data)
+        logging.info("Feature DF: %s", X_df.to_dict(orient="records"))
+    except Exception as e:
+        logging.error(f"Feature building error: {e}")
+        return jsonify({
+            "error": "Feature building error",
+            "detail": str(e)
+        }), 500
+
+    # ---------- PREDICT ----------
+    try:
+        X = preprocessor.transform(X_df)
+        fraud_prob = model.predict_proba(X)[0][1]
+    except Exception as e:
+        logging.error(f"Prediction error: {e}")
+        return jsonify({
+            "error": "Preprocessing or prediction error",
+            "detail": str(e)
+        }), 500
+
+    # ---------- DECISION ----------
+    is_fraud = fraud_prob >= THRESHOLD
+
+    if fraud_prob >= 0.85:
+        decision = "BLOCK"
+    elif fraud_prob >= THRESHOLD:
+        decision = "REVIEW"
+    else:
+        decision = "ALLOW"
+
+    latency_ms = round((time.time() - start_time) * 1000, 2)
+
+    # ---------- STRUCTURED LOG ----------
+    logging.info({
+        "event": "fraud_decision",
+        "fraud_probability": float(fraud_prob),
+        "decision": decision,
+        "threshold": THRESHOLD,
+        "latency_ms": latency_ms
+    })
+
+    return jsonify({
+        "fraud_probability": round(float(fraud_prob), 4),
+        "is_fraud": bool(is_fraud),
+        "decision": decision,
+        "latency_ms": latency_ms
+    })
+
+
+# ======================
+# RUN SERVER
+# ======================
+if __name__ == "__main__":
+    app.run(debug=True, port=5001)