Add StandardScaler object for feature scaling

- Introduced a new StandardScaler instance saved as scaler.pkl.
- This scaler standardizes features by removing the mean and scaling to unit variance.
- The scaler is configured with default parameters: with_mean=True, with_std=True, and copy=True.
- This change is essential for preprocessing data before model training to ensure consistent feature scaling.

app.py

@@ -0,0 +1,18 @@
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
+
+# Load your model
+model = joblib.load("knn_diabetes_model.pkl")
+
+app = Flask(__name__)
+
+@app.route("/predict", methods=["POST"])
+def predict():
+    data = request.json  # expects JSON with same feature names as training
+    df = pd.DataFrame(data)
+    predictions = model.predict(df)
+    return jsonify(predictions.tolist())
+
+if __name__ == "__main__":
+    app.run(debug=True)