Update app.py

app.py

@@ -12,30 +12,40 @@ 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
+# Most common X0 values with their frequencies
+FEATURE_OPTIONS = {
+    "z (Most Common - 360 cases)": "z",
+    "ak (349 cases)": "ak",
+    "y (324 cases)": "y",
+    "ay (313 cases)": "ay",
+    "t (306 cases)": "t",
+    "x (300 cases)": "x",
+    "o (269 cases)": "o",
+    "f (227 cases)": "f",
+    "n (195 cases)": "n",
+    "w (182 cases)": "w"
+}
 
-def predict(*features):
+# Default values for other features
+DEFAULT_VALUES = {name: 0.0 for name in feature_names}
+
+def predict(selected_option):
     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)
+        # Create a dictionary with all features set to default values
+        input_dict = DEFAULT_VALUES.copy()
+        
+        # Get the actual value from the selected option
+        selected_value = FEATURE_OPTIONS[selected_option]
         
-        # Ensure all data types are float
-        df = df.astype(float)
+        # Create dummy variable columns for X0
+        for val in set(FEATURE_OPTIONS.values()):
+            col_name = f'X0_{val}'
+            input_dict[col_name] = 1 if val == selected_value else 0
         
-        # Make prediction using booster directly
+        # Create DataFrame with all features
+        df = pd.DataFrame([input_dict])
+        
+        # Make prediction
         if hasattr(model, '_Booster'):
             booster = model._Booster
             prediction = booster.predict(df)[0]
@@ -46,20 +56,20 @@ def predict(*features):
     except Exception as e:
         return f"Error in prediction: {str(e)}"
 
-# Create interface with organized inputs
-inputs = create_input_components()
-output = gr.Textbox(label="Prediction Result")
-
-# Create the interface
+# Create interface with dropdown
 interface = gr.Interface(
     fn=predict,
-    inputs=inputs,
-    outputs=output,
-    title="Mercedes-Benz Manufacturing Time Prediction",
-    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
+    inputs=gr.Dropdown(
+        choices=list(FEATURE_OPTIONS.keys()),
+        label="Select Manufacturing Configuration (X0)",
+        value=list(FEATURE_OPTIONS.keys())[0]
+    ),
+    outputs=gr.Textbox(label="Prediction Result"),
+    title="Mercedes-Benz Manufacturing Time Predictor",
+    description="Select one of the most common manufacturing configurations to predict the production time. The options are sorted by frequency of occurrence in the training data.",
+    examples=[[list(FEATURE_OPTIONS.keys())[0]]],
+    cache_examples=True,
+    theme=gr.themes.Soft()
 )
 
-# Launch with debugging enabled
 interface.launch(debug=True)