import gradio as gr
import matplotlib.pyplot as plt
import shap
import hopsworks
import pandas as pd
import joblib

# Assuming you have your model and data defined elsewhere
project = hopsworks.login(
    project="SonyaStern_Lab1",
    api_key_value="c9StuuVQPoMUeXWe.jB2XeWcI8poKUN59W13MxAbMemzY7SChOnX151GtTFNhysBBUPMRuEp5IK7SE3i1",
)
mr = project.get_model_registry()
model = mr.get_model("diabetes_model", version=1)
model_dir = model.download()
model = joblib.load(model_dir + "/diabetes_model.pkl")
rf_model = model.steps[-1][1]  # Load your model
df = pd.DataFrame(
    [[20, 20, 30, 40]],
    columns=["age", "bmi", "hba1c_level", "blood_glucose_level"],
)


def generate_plots():
    # Create the first plot as before
    fig1, ax1 = plt.subplots()
    ax1.plot([1, 2, 3], [4, 5, 6])
    ax1.set_title("Plot 1")

    # Generate the SHAP waterfall plot for fig2
    fig2 = shap.plots.waterfall(
        shap.Explanation(
            values=shap.Explainer(rf_model).shap_values(df)[1][0],
            base_values=shap.Explainer(rf_model).expected_value[1],
        )
    )

    return fig1, fig2


with gr.Blocks() as demo:
    with gr.Row():
        gr.Plot(generate_plots()[0])  # Display first plot in the first row

    with gr.Row():
        gr.Plot(generate_plots()[1])  # Display SHAP waterfall plot in the second row

demo.launch()