# app.py - FINAL PROFESSIONAL version with input validation and guardrails

import gradio as gr
import joblib
import pandas as pd
import os
import subprocess

# --- STEP 1: Download the Model Files from the Hub (same as before) ---
MODEL_URL = "https://huggingface.co/szili2011/ai-house-price-predictor/resolve/main/housing_model.joblib"
COLUMNS_URL = "https://huggingface.co/szili2011/ai-house-price-predictor/resolve/main/model_columns.joblib"
MODEL_LOCAL_PATH = "housing_model.joblib"
COLUMNS_LOCAL_PATH = "model_columns.joblib"

if not os.path.exists(MODEL_LOCAL_PATH):
    print("--- Downloading Model Files ---")
    subprocess.run(["wget", "-O", MODEL_LOCAL_PATH, MODEL_URL])
    subprocess.run(["wget", "-O", COLUMNS_LOCAL_PATH, COLUMNS_URL])
    print("--- Download Complete ---")

# --- STEP 2: Load the Now-Local Model and Columns (same as before) ---
try:
    print(f"Loading model from local path: '{MODEL_LOCAL_PATH}'")
    model = joblib.load(MODEL_LOCAL_PATH)
    print(f"Loading columns from local path: '{COLUMNS_LOCAL_PATH}'")
    model_columns = joblib.load(COLUMNS_LOCAL_PATH)
    print("✅ Model and columns loaded successfully.")
    model_loaded_successfully = True
except Exception as e:
    print(f"❌ CRITICAL ERROR during model loading: {e}")
    model_loaded_successfully = False


# --- This is the core prediction function with the new validation logic ---
def predict_price(sqft, bedrooms, house_age, condition, year_sold, interest_rate, region, sub_type, style, has_garage, has_pool):
    if not model_loaded_successfully:
        raise gr.Error("Model is not loaded. Please check the Space logs for errors.")

    # --- NEW: Input Validation Guardrails ---
    # Before we do anything, we check if the user's inputs are reasonable.
    # If not, we stop and send back a helpful error message.
    if not (300 <= sqft <= 30000):
        raise gr.Error(f"Input Error: Square Footage must be between 300 and 30,000. You entered {sqft}.")
    if not (1 <= bedrooms <= 20):
        raise gr.Error(f"Input Error: Number of Bedrooms must be between 1 and 20. You entered {bedrooms}.")
    if not (0 <= house_age <= 200):
        raise gr.Error(f"Input Error: House Age must be between 0 and 200. You entered {house_age}.")
    if not (2000 <= year_sold <= 2030):
        raise gr.Error(f"Input Error: Year Sold must be between 2000 and 2030. You entered {year_sold}.")
    if not (0 <= interest_rate <= 25):
        raise gr.Error(f"Input Error: Interest Rate must be between 0 and 25. You entered {interest_rate}.")

    # If all checks pass, we proceed with the prediction.
    input_data = {
        'SquareFootage': sqft, 'Bedrooms': bedrooms, 'HouseAge': house_age,
        'PropertyCondition': condition, 'HasGarage': has_garage, 'HasPool': has_pool,
        'YearSold': year_sold, 'InterestRate': interest_rate,
        'Region': region, 'SubType': sub_type, 'ArchitecturalStyle': style
    }
    input_df = pd.DataFrame([input_data])
    
    input_processed = pd.get_dummies(input_df)
    final_input = input_processed.reindex(columns=model_columns, fill_value=0)
    
    predicted_price = model.predict(final_input)[0]
    
    return f"${predicted_price:,.0f}"

# --- Create the Gradio Interface with better UI limits ---
demo = gr.Interface(
    fn=predict_price,
    inputs=[
        # --- NEW: Added minimum and maximum values to the UI components ---
        gr.Number(label="Square Footage", value=2500, minimum=300, maximum=30000),
        gr.Number(label="Bedrooms", value=4, minimum=1, maximum=20),
        gr.Number(label="House Age (years)", value=15, minimum=0, maximum=200),
        gr.Slider(label="Property Condition", minimum=1, maximum=10, step=1, value=8),
        gr.Number(label="Year Sold", value=2024, minimum=2000, maximum=2030),
        gr.Number(label="Interest Rate (%)", value=5.5, minimum=0, maximum=25),
        gr.Radio(['Sunbelt', 'Pacific Northwest', 'Rust Belt', 'New England', 'Mountain West'], label="Region", value="Sunbelt"),
        gr.Radio(['Urban', 'Suburban', 'Rural', 'Historic District'], label="Sub-Type", value="Suburban"),
        gr.Radio(['Modern', 'Ranch', 'Colonial', 'Craftsman', 'Victorian'], label="Architectural Style", value="Colonial"),
        gr.Checkbox(label="Has Garage?", value=True),
        gr.Checkbox(label="Has Pool?", value=False)
    ],
    outputs=gr.Textbox(label="Predicted Price"),
    title="AI House Price Predictor",
    description="Describe a property, and our AI will estimate its market value. This AI was trained on a 9.2GB simulated dataset and is hosted on Hugging Face."
)

# Launch the app
demo.launch()