Update app.py

app.py

@@ -1,66 +1,59 @@
-import gradio as gr
-import pandas as pd
-import pickle
-
-# Load trained model and preprocessor
-with open("rfr.pkl", "rb") as f:
-    model = pickle.load(f)
-
-with open("prepocessor.pkl", "rb") as f:
-    preprocessor = pickle.load(f)
-
-# Final features (everything except sellingprice)
-input_features = [
-    "year", "make", "model", "trim", "body", "transmission", "vin", 
-    "state", "condition", "odometer", "color", "interior", "seller", 
-    "mmr", "Year", "Month", "Day", "Quarter"
-]
-
-def predict_price(year, make, model_name, trim, body, transmission, vin,
-                  state, condition, odometer, color, interior, seller, mmr,
-                  Year, Month, Day, Quarter):
-    
-    # Create DataFrame
-    df = pd.DataFrame([[
-        year, make, model_name, trim, body, transmission, vin,
-        state, condition, odometer, color, interior, seller, mmr,
-        Year, Month, Day, Quarter
-    ]], columns=input_features)
-
-    # Preprocess
-    X_processed = preprocessor.transform(df)
-
-    # Predict
-    prediction = model.predict(X_processed)[0]
-    return f"💰 Estimated Selling Price: ${prediction:,.2f}"
-
-# Gradio UI
-demo = gr.Interface(
-    fn=predict_price,
-    inputs=[
-        gr.Number(label="year"),
-        gr.Textbox(label="make"),
-        gr.Textbox(label="model"),
-        gr.Textbox(label="trim"),
-        gr.Textbox(label="body"),
-        gr.Dropdown(choices=["automatic", "manual"], label="transmission"),
-        gr.Textbox(label="vin"),
-        gr.Textbox(label="state"),
-        gr.Number(label="condition"),
-        gr.Number(label="odometer"),
-        gr.Textbox(label="color"),
-        gr.Textbox(label="interior"),
-        gr.Textbox(label="seller"),
-        gr.Number(label="mmr"),
-        gr.Number(label="Year"),
-        gr.Number(label="Month"),
-        gr.Number(label="Day"),
-        gr.Number(label="Quarter"),
-    ],
-    outputs=gr.Textbox(label="Prediction"),
-    title="🚗 Car Price Prediction",
-    description="Enter car details to predict the estimated selling price."
-)
-
-if __name__ == "__main__":
-    demo.launch()
+import gradio as gr
+import pickle as pkl
+import pandas as pd
+
+# === Load Preprocessor and Model ===
+preprocessor = pkl.load(open("prepocessr.pkl", "rb"))
+model = pkl.load(open("rfrc.pkl", "rb"))
+
+# === Define Prediction Function ===
+def predict(make, model_car, year, trim, body, transmission, state, condition, odometer, color, interior, mmr):
+    # Put inputs into a DataFrame with the same column names as training
+    input_df = pd.DataFrame([{
+        "make": make,
+        "model": model_car,
+        "year": year,
+        "trim": trim,
+        "body": body,
+        "transmission": transmission,
+        "state": state,
+        "condition": condition,
+        "odometer": odometer,
+        "color": color,
+        "interior": interior,
+        "mmr": mmr
+    }])
+
+    # Apply preprocessing
+    X_proc = preprocessor.transform(input_df)
+
+    # Predict with model
+    prediction = model.predict(X_proc)[0]
+
+    return f"Predicted Selling Price: ${prediction:,.2f}"
+
+# === Gradio Interface ===
+iface = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Textbox(label="Make"),
+        gr.Textbox(label="Model"),
+        gr.Number(label="Year"),
+        gr.Textbox(label="Trim"),
+        gr.Textbox(label="Body"),
+        gr.Textbox(label="Transmission"),
+        gr.Textbox(label="State"),
+        gr.Number(label="Condition"),
+        gr.Number(label="Odometer"),
+        gr.Textbox(label="Color"),
+        gr.Textbox(label="Interior"),
+        gr.Number(label="MMR"),
+    ],
+    outputs=gr.Textbox(label="Prediction"),
+    title="Car Price Prediction App",
+    description="Enter car details to predict the selling price."
+)
+
+# Launch app
+if __name__ == "__main__":
+    iface.launch()