import gradio as gr
import numpy as np
from joblib import dump, load
# Load the model from disk
loaded_logistic_regression_model = load("logistic_regression_model.joblib")

print("Model loaded successfully")



def predict_survival(Pclass, Sex, Age, SibSp, Parch, Fare, HasCabin, Embarked):
    # Convert inputs to the correct format
    Sex = 1 if Sex == 'male' else 0
    HasCabin = 0 if HasCabin == 'No' else 1
    Embarked = {'S': 2, 'C': 0, 'Q': 1}.get(Embarked, 2)
    
    # Create a numpy array from the inputs
    input_data = np.array([[Pclass, Sex, Age, SibSp, Parch, Fare, HasCabin, Embarked]])
    
    # Use the model to make a prediction
    prediction = loaded_logistic_regression_model.predict(input_data)
    
    # Convert the prediction to a human-readable result
    result = "Survived" if prediction[0] == 1 else "Did Not Survive"
    return result

# Define the Gradio interface
iface = gr.Interface(
    fn=predict_survival,
    inputs=[
        gr.Dropdown(choices=[1, 2, 3], label="Pclass"),
        gr.Radio(choices=["male", "female"], label="Sex"),
        gr.Number(label="Age"),
        gr.Number(label="SibSp"),
        gr.Number(label="Parch"),
        gr.Number(label="Fare"),
        gr.Radio(choices=["Yes", "No"], label="Has Cabin"),
        gr.Dropdown(choices=["S", "C", "Q"], label="Embarked"),
    ],
    outputs="text",
    title="Titanic Survival Prediction",
    description="Predict whether a passenger on the Titanic would have survived."
)

# Launch the interface
iface.launch()