Update app.py

app.py

@@ -1,42 +1,44 @@
-import gradio as gr
-import pandas as pd
-import joblib
+import os
+import pickle
+import numpy as np
+from flask import Flask, request, jsonify
+
+app = Flask(__name__)
 
 # Load model
-model = joblib.load("predictive_model_smote.pkl")
-
-def predict_failure(type_value, air_temp, process_temp, rotational_speed, torque, tool_wear):
-    
-    # Create dataframe (same order as training)
-    input_data = pd.DataFrame([{
-        "Type": type_value,
-        "Air temperature [K]": air_temp,
-        "Process temperature [K]": process_temp,
-        "Rotational speed [rpm]": rotational_speed,
-        "Torque [Nm]": torque,
-        "Tool wear [min]": tool_wear
-    }])
-    
-    prediction = model.predict(input_data)[0]
-    
-    if prediction == 1:
-        return "⚠️ Machine Failure Likely"
-    else:
-        return "✅ Machine Working Normally"
-
-interface = gr.Interface(
-    fn=predict_failure,
-    inputs=[
-        gr.Dropdown(["L", "M", "H"], label="Type"),
-        gr.Number(label="Air Temperature (K)"),
-        gr.Number(label="Process Temperature (K)"),
-        gr.Number(label="Rotational Speed (rpm)"),
-        gr.Number(label="Torque (Nm)"),
-        gr.Number(label="Tool Wear (min)")
-    ],
-    outputs="text",
-    title="Predictive Maintenance Model",
-    description="Enter machine parameters to predict failure."
-)
-
-interface.launch()
+MODEL_PATH = "predictive_model_smote.pkl"
+
+with open(MODEL_PATH, "rb") as f:
+    model = pickle.load(f)
+
+@app.route("/")
+def home():
+    return {"message": "Predictive Maintenance API is running"}
+
+@app.route("/predict", methods=["POST"])
+def predict():
+    try:
+        data = request.json
+        
+        # Expected input features in correct order
+        features = [
+            data["Air temperature [K]"],
+            data["Process temperature [K]"],
+            data["Rotational speed [rpm]"],
+            data["Torque [Nm]"],
+            data["Tool wear [min]"]
+        ]
+
+        features_array = np.array([features])
+        prediction = model.predict(features_array)[0]
+
+        return jsonify({
+            "prediction": int(prediction)
+        })
+
+    except Exception as e:
+        return jsonify({"error": str(e)})
+
+if __name__ == "__main__":
+    port = int(os.environ.get("PORT", 7860))
+    app.run(host="0.0.0.0", port=port)