Update app.py

app.py

@@ -1,36 +1,29 @@
-# app.py
 import gradio as gr
 import pickle
 import numpy as np
 from sklearn.preprocessing import StandardScaler
 
-MODEL_PATH = "rf_model.pkl"
+# Load model once at startup
+with open("rf_model.pkl", "rb") as f:
+    MODEL = pickle.load(f)
 
-def load_model():
-    with open(MODEL_PATH, "rb") as f:
-        return pickle.load(f)
-
-def predict(feature1, feature2, feature3, feature4, feature5):
-    model = load_model()
-    raw = np.array([[feature1, feature2, feature3, feature4, feature5]])
-    # Standardize features (must match training preprocessing)
-    scaler = StandardScaler()
-    scaled = scaler.fit_transform(raw)
-    return int(model.predict(scaled)[0])
+def predict(f1, f2, f3, f4, f5):
+    arr = np.array([[f1, f2, f3, f4, f5]])
+    scaled = StandardScaler().fit_transform(arr)
+    return str(MODEL.predict(scaled)[0])
 
 with gr.Blocks() as demo:
-    gr.Markdown("## 🐨 Random Forest Prediction App\nMove the sliders and click **Predict**")
+    gr.Markdown("## 🐨 TaskMaster Job Scheduler")
     with gr.Row():
-        f1 = gr.Slider(0, 10, value=5, label="Feature 1")
-        f2 = gr.Slider(0, 10, value=3, label="Feature 2")
+        f1 = gr.Slider(0, 10, value=5, label="Feature 1")
+        f2 = gr.Slider(0, 10, value=3, label="Feature 2")
     with gr.Row():
-        f3 = gr.Slider(0, 10, value=7, label="Feature 3")
-        f4 = gr.Slider(0, 10, value=6, label="Feature 4")
-    f5 = gr.Slider(0, 10, value=4, label="Feature 5")
+        f3 = gr.Slider(0, 10, value=7, label="Feature 3")
+        f4 = gr.Slider(0, 10, value=6, label="Feature 4")
+    f5 = gr.Slider(0, 10, value=4, label="Feature 5")
     btn = gr.Button("Predict")
     out = gr.Textbox(label="Prediction")
-
     btn.click(fn=predict, inputs=[f1, f2, f3, f4, f5], outputs=out)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()  # no server_name/port flags needed on Spaces