app.py

import pickle
import pandas as pd
import shap
from shap.plots._force_matplotlib import draw_additive_plot
import gradio as gr
import numpy as np
import matplotlib.pyplot as plt
# load the model from disk
loaded_model = pickle.load(open("heart_xgb.pkl", 'rb'))
# Setup SHAP
explainer = shap.Explainer(loaded_model) # PLEASE DO NOT CHANGE THIS.
# Create the main function for server
def main_func(age, sex, cp, trtbps, chol, fbs, restecg, thalachh, exng, oldpeak, slp, caa, thall):
    new_row = pd.DataFrame.from_dict({'age':age,'sex':sex,
              'cp':cp,'trtbps':trtbps,'chol':chol, 'fbs':fbs, 'restecg':restecg,
              'thalachh':thalachh, 'exng':exng, 'oldpeak':oldpeak, 'slp':slp, 'caa':caa, 'thall':thall}, orient = 'index').transpose()
   
    prob = loaded_model.predict_proba(new_row)
   
    shap_values = explainer(new_row)
    # plot = shap.force_plot(shap_values[0], matplotlib=True, figsize=(30,30), show=False)
    # plot = shap.plots.waterfall(shap_values[0], max_display=6, show=False)
    plot = shap.plots.bar(shap_values[0], max_display=6, order=shap.Explanation.abs, show_data='auto', show=False)
    plt.tight_layout()
    local_plot = plt.gcf()
    plt.close()
   
    return {"Leave": float(prob[0][0]), "Stay": 1-float(prob[0][0])}, local_plot
# Create the UI
title = "**Heart Attack Predictor & Interpreter** 🪐"
description1 = """
This app takes info from subjects and predicts their heart attack likelihood. Do not use for medical diagnosis.  
"""
description2 = """
To use the app, click on one of the examples, or adjust the values of the factors, and click on Analyze. 🤞
""" 
with gr.Blocks(title=title) as demo:
    gr.Markdown(f"## {title}")
#    gr.Markdown("""![marketing](file/marketing.jpg)""")
    gr.Markdown(description1)
    gr.Markdown("""---""")
    gr.Markdown(description2)
    gr.Markdown("""---""")
    age = gr.Slider(label="age score", minimum=15, maximum=90, value=40, step=5)
    sex = gr.Slider(label="sex score", minimum=0, maximum=1, value=1, step=1)
    cp = gr.Slider(label="cp score", minimum=1, maximum=5, value=4, step=1)
    trtbps = gr.Slider(label="trtbps Score", minimum=1, maximum=5, value=4, step=1)
    chol = gr.Slider(label="chol Score", minimum=1, maximum=5, value=4, step=1)
    fbs = gr.Slider(label="fbs Score", minimum=1, maximum=5, value=4, step=1)
    restecg = gr.Slider(label="restecg Score", minimum=1, maximum=5, value=4, step=1)
    thalachh = gr.Slider(label="thalachh Score", minimum=1, maximum=5, value=4, step=1)
    exng = gr.Slider(label="exng Score", minimum=1, maximum=5, value=4, step=1)
    oldpeak = gr.Slider(label="oldpeak Score", minimum=1, maximum=5, value=4, step=1)
    slp = gr.Slider(label="slp Score", minimum=1, maximum=5, value=4, step=1)
    caa = gr.Slider(label="caa Score", minimum=1, maximum=5, value=4, step=1)
    thall = gr.Slider(label="thall Score", minimum=1, maximum=5, value=4, step=1)
    submit_btn = gr.Button("Analyze")
    with gr.Column(visible=True) as output_col:
        label = gr.Label(label = "Predicted Label")
        local_plot = gr.Plot(label = 'Shap:')
    submit_btn.click(
        main_func,
        [age, sex, cp, trtbps, chol, fbs, restecg, thalachh, exng, oldpeak, slp, caa, thall],
        [label,local_plot], api_name="Employee_Turnover"
    )
   
    gr.Markdown("### Click on any of the examples below to see how it works:")
    gr.Examples([[24,0,4,4,5,4,4,5,5,1,2,3,4], [20,0,3,4,5,4,4,5,5,1,2,3,3]], [age, sex, cp, trtbps, chol, fbs, restecg, thalachh, exng, oldpeak, slp, caa, thall], [label,local_plot], main_func, cache_examples=True)
demo.launch()