Add K-Means customer segmentation application

Dockerfile

@@ -0,0 +1,28 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+FROM python:3.9
+
+# Set up a non-root user for security
+RUN useradd -m -u 1000 user
+USER user
+
+# Set the PATH for user's local installations
+ENV PATH="/home/user/.local/bin:$PATH"
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy requirements.txt and install dependencies
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# Copy all application files (including app.py, kmeans_model.joblib, scaler_model.joblib)
+COPY --chown=user . /app
+
+# Command to run your Flask app
+# Flask typically uses a WSGI server like Gunicorn or directly app.run() for simple cases.
+# For a simple Flask app to run, you can use:
+CMD ["python", "app.py"] # This assumes app.py has app.run(host="0.0.0.0", port=7860)
+
+# OR, if you want a more robust setup with Gunicorn (add gunicorn to requirements.txt):
+# CMD ["gunicorn", "app:app", "--bind", "0.0.0.0:7860"]

app.py

@@ -0,0 +1,51 @@
+from flask import Flask, request, jsonify
+import joblib
+import pandas as pd
+import numpy as np
+
+app = Flask(__name__)
+
+# Load the pre-trained model and scaler
+try:
+    kmeans_model = joblib.load("kmeans_model.joblib")
+    scaler_model = joblib.load("scaler_model.joblib")
+    print("Models loaded successfully!")
+except Exception as e:
+    print(f"Error loading models: {e}")
+    kmeans_model = None
+    scaler_model = None
+
+@app.route("/predict", methods=["POST"])
+def predict():
+    if kmeans_model is None or scaler_model is None:
+        return jsonify({"error": "Model not loaded. Please check deployment logs."}), 500
+
+    data = request.get_json(force=True)
+    
+    try:
+        # Extract features and ensure order
+        age = data.get("age")
+        annual_income = data.get("annual_income")
+        spending_score = data.get("spending_score")
+
+        if age is None or annual_income is None or spending_score is None:
+            return jsonify({"error": "Missing required input features (age, annual_income, spending_score)."}), 400
+
+        # Create a DataFrame for scaling
+        features_df = pd.DataFrame([[age, annual_income, spending_score]],
+                                   columns=['Age', 'Annual Income (k$)', 'Spending Score (1-100)'])
+
+        # Scale the input features using the loaded scaler
+        scaled_features = scaler_model.transform(features_df)
+
+        # Predict the cluster
+        prediction = kmeans_model.predict(scaled_features)
+        cluster_id = int(prediction[0]) # Convert numpy int to Python int
+
+        return jsonify({"cluster_id": cluster_id})
+
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+if __name__ == "__main__":
+    app.run(debug=True) # debug=True for local testing, set to False for deployment

requirements.txt

@@ -0,0 +1,4 @@
+pandas
+scikit-learn
+joblib
+flask # or fastapi, uvicorn