Update app.py

app.py

@@ -1,9 +1,4 @@
-
-
-
-# app.py (for Hugging Face Spaces deployment)
-
-import streamlit as st
+import gradio as gr
 import pickle
 import numpy as np
 from sklearn.preprocessing import StandardScaler
@@ -15,35 +10,28 @@ def load_model():
     return model
 
 # Make predictions with the model
-def predict(model, new_data):
+def predict(model, feature1, feature2, feature3, feature4, feature5):
+    new_data = np.array([[feature1, feature2, feature3, feature4, feature5]])
     scaler = StandardScaler()
     new_data_scaled = scaler.fit_transform(new_data)  # Standardize the data
-    return model.predict(new_data_scaled)
+    return model.predict(new_data_scaled)[0]
 
-# Streamlit app UI
+# Gradio Interface
 def main():
-    st.title('Random Forest Prediction App')
-
-    st.write("This app uses a pre-trained Random Forest model to make predictions.")
-
-    # Input data
-    feature1 = st.number_input("Feature 1", min_value=0.0, max_value=10.0, value=5.0)
-    feature2 = st.number_input("Feature 2", min_value=0.0, max_value=10.0, value=3.0)
-    feature3 = st.number_input("Feature 3", min_value=0.0, max_value=10.0, value=7.0)
-    feature4 = st.number_input("Feature 4", min_value=0.0, max_value=10.0, value=6.0)
-    feature5 = st.number_input("Feature 5", min_value=0.0, max_value=10.0, value=4.0)
-
-    # Prepare input data
-    new_data = np.array([[feature1, feature2, feature3, feature4, feature5]])
-
-    # Load the model and make predictions
     model = load_model()
-    if st.button('Predict'):
-        if model:
-            predictions = predict(model, new_data)
-            st.write(f"Predictions: {predictions}")
-        else:
-            st.write("Model not loaded correctly.")
+    
+    inputs = [
+        gr.inputs.Slider(minimum=0, maximum=10, default=5, label="Feature 1"),
+        gr.inputs.Slider(minimum=0, maximum=10, default=3, label="Feature 2"),
+        gr.inputs.Slider(minimum=0, maximum=10, default=7, label="Feature 3"),
+        gr.inputs.Slider(minimum=0, maximum=10, default=6, label="Feature 4"),
+        gr.inputs.Slider(minimum=0, maximum=10, default=4, label="Feature 5")
+    ]
+    
+    output = gr.outputs.Textbox()
+    
+    gr.Interface(fn=lambda feature1, feature2, feature3, feature4, feature5: predict(model, feature1, feature2, feature3, feature4, feature5),
+                 inputs=inputs, outputs=output, live=True).launch()
 
 if __name__ == '__main__':
     main()