# import spaces

# @spaces.G

import gradio as gr
import pandas as pd
import joblib

# Load the trained model once, when the app starts
random_forest = joblib.load(r"C:\Users\USER\OneDrive\Desktop\Webfala\titanic_demo\models\forest_model.joblib")

#PILLAR 1: THE FUNCTION
def predict_survival(name, Pclass,Sex, Age, SibSp, PaCh, Fare):
    input_data = pd.DataFrame({
        'Pclass': [Pclass],
        'Sex': [Sex],
        'Age': [Age],
        'SibSp': [SibSp],
        'PaCh': [PaCh],
        'Fare': [Fare],
    })

    prediction = random_forest.predict(input_data)[0]
    probabilities = random_forest.predict_proba(input_data)[0]

    if prediction == 0:
        result = f"Woo {name.title()}, you Died"
    else:
        result = f'Congratulations! {name.title()}, you survived!'

    #gr.Label expects a dict of {class name: probalility}
    probs = {"Died": float(probabilities[0]), "Survived": float(probabilities[1])}
    return result, probs

    # PILLAR 2: THE INPUITS (one per function parameter, same order)
inputs = [
    gr.Textbox(label="Name", placeholder="e.g Rhoda Innocent"),
    gr.Radio([1, 2, 3], label="Passenger Class ( 1 = First)", value = 3),
    gr.Radio([("Male", 0), ("Female", 1)], label="Sex", value = 0),
    gr.Slider(0, 80, value=30, step=1, label="Age"),
    gr.Number(label="Siblings/Spouses aboard", value=0, precision=0),
    gr.Number(label="Parents/Children aboard", value=0, precision=0),
    gr.Number(label="Fare paid ($)", value=30),
]

# PILLAR 3: THE OUTPUTS (one per returned value, same order)
outputs = [
    gr.Textbox(label="Prediction"),
    gr.Label(label="Probability"), 
]

#Write the three pillars together
demo = gr.Interface(
    fn=predict_survival,
    inputs=inputs,
    outputs=outputs,
    title="Titanic Survival Predictor",
    description="Enter a passenger's details and see if our random forest thinks they'd survive.",
    examples=[
        ["Musa Adamu", 3, 0, 20, 0, 0, 8],
        ["Tomi Jesu", 1, 1, 17, 0, 1, 150],
    ],
)

demo.launch()