Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 import pandas as pd
 import joblib
 from huggingface_hub import hf_hub_download
+import numpy as np
 
 # Download model and feature names from Hugging Face
 model_path = hf_hub_download(repo_id="alperugurcan/mercedes", filename="mercedes_model.joblib")
@@ -11,24 +12,54 @@ feature_names_path = hf_hub_download(repo_id="alperugurcan/mercedes", filename="
 model = joblib.load(model_path)
 feature_names = joblib.load(feature_names_path)
 
+def create_input_components():
+    # Create a more organized input interface
+    numeric_inputs = []
+    for i, name in enumerate(feature_names):
+        # Create a number input with a more descriptive label
+        input_component = gr.Number(
+            label=f"{name}",
+            value=0.0,  # default value
+            minimum=-1000,  # adjust these limits as needed
+            maximum=1000
+        )
+        numeric_inputs.append(input_component)
+    return numeric_inputs
+
 def predict(*features):
-    # Create a DataFrame with the input features
-    df = pd.DataFrame([features], columns=feature_names)
-    
-    # Make prediction
-    prediction = model.predict(df)[0]
-    return f"Predicted time: {prediction:.2f}"
+    try:
+        # Convert inputs to float and create DataFrame
+        features = [float(f) if f is not None else 0.0 for f in features]
+        df = pd.DataFrame([features], columns=feature_names)
+        
+        # Ensure all data types are float
+        df = df.astype(float)
+        
+        # Make prediction using booster directly
+        if hasattr(model, '_Booster'):
+            booster = model._Booster
+            prediction = booster.predict(df)[0]
+        else:
+            prediction = model.predict(df)[0]
+            
+        return f"Predicted manufacturing time: {prediction:.2f} seconds"
+    except Exception as e:
+        return f"Error in prediction: {str(e)}"
 
-# Create the interface
-inputs = [gr.Number(label=f"Feature {i+1}") for i in range(len(feature_names))]
-output = gr.Textbox(label="Prediction")
+# Create interface with organized inputs
+inputs = create_input_components()
+output = gr.Textbox(label="Prediction Result")
 
+# Create the interface
 interface = gr.Interface(
     fn=predict,
     inputs=inputs,
     outputs=output,
     title="Mercedes-Benz Manufacturing Time Prediction",
-    description="Enter feature values to predict manufacturing time"
+    description="Enter feature values to predict the manufacturing time. All features should be numerical values.",
+    examples=[[0.0] * len(feature_names)],  # Add an example with all zeros
+    cache_examples=True
 )
 
-interface.launch()
+# Launch with debugging enabled
+interface.launch(debug=True)