Update app.py

app.py

@@ -1,38 +1,41 @@
+# app.py
 import gradio as gr
 import pickle
 import numpy as np
 from sklearn.preprocessing import StandardScaler
 
-# 1) Load your model once at startup
-with open("rf_model.pkl", "rb") as f:
-    MODEL = pickle.load(f)
+# 1) Load your trained model (make sure rf_model.pkl is in the repo root)
+def load_model():
+    with open("rf_model.pkl", "rb") as f:
+        return pickle.load(f)
 
-# 2) A simple predict function
-def predict(f1, f2, f3, f4, f5):
-    X = np.array([[f1, f2, f3, f4, f5]])
-    X_scaled = StandardScaler().fit_transform(X)
-    return int(MODEL.predict(X_scaled)[0])
+# 2) Prediction function: takes five numeric inputs, scales them, returns class
+def predict(feature1, feature2, feature3, feature4, feature5):
+    model = load_model()
+    x = np.array([[feature1, feature2, feature3, feature4, feature5]])
+    # NOTE: We fit_transform here for demo; in prod you'd persist the scaler too.
+    x_scaled = StandardScaler().fit_transform(x)
+    return str(model.predict(x_scaled)[0])
 
-# 3) Build your Gradio interface
+# 3) Build the Gradio interface
 demo = gr.Interface(
     fn=predict,
     inputs=[
-        gr.Slider(0, 10, step=1, value=5, label="Feature 1"),
-        gr.Slider(0, 10, step=1, value=3, label="Feature 2"),
-        gr.Slider(0, 10, step=1, value=7, label="Feature 3"),
-        gr.Slider(0, 10, step=1, value=6, label="Feature 4"),
-        gr.Slider(0, 10, step=1, value=4, label="Feature 5"),
+        gr.Slider(0, 10, value=5, label="Feature 1"),
+        gr.Slider(0, 10, value=3, label="Feature 2"),
+        gr.Slider(0, 10, value=7, label="Feature 3"),
+        gr.Slider(0, 10, value=6, label="Feature 4"),
+        gr.Slider(0, 10, value=4, label="Feature 5"),
     ],
-    outputs=gr.Label(label="Prediction"),
+    outputs=gr.Textbox(label="Predicted Class"),
     title="TaskMaster Job Scheduler",
-    description="Enter five feature values to get a RandomForest prediction."
+    description="Enter five feature values to get a RandomForest prediction.",
 )
 
+# 4) Launch with SSR turned off for Spaces
 if __name__ == "__main__":
-    # This tells Gradio to bind to all interfaces, on port 7860,
-    # and to BLOCK the Python thread (so the container stays up).
     demo.launch(
         server_name="0.0.0.0",
         server_port=7860,
-        prevent_thread_lock=False
+        ssr_mode=False  # disable server-side rendering on the Space
     )