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("classroom_xgb.pkl", 'rb'))

# Setup SHAP
explainer = shap.Explainer(loaded_model) # PLEASE DO NOT CHANGE THIS.

# Create the main function for server
def main_func(Target, Admission_Grade, 2nd_Sem_Grades, Previous_Qualification_Grade, 1st_Sem_Grades, Course, 2nd_Sem_Units_Approved, Age_at_Enrollment):
    new_row = pd.DataFrame.from_dict({'Target':Target,'Admission_Grade':Admission_Grade,
              '2nd_Sem_Grades':2nd_Sem_Grades,'Previous_Qualification_Grade':Previous_Qualification_Grade,'1st_Sem_Grades':1st_Sem_Grades,
              'Course':Course,'2nd_Sem_Units_Approved':2nd_Sem_Units_Approved,'Age_at_Enrollment':Age_at_Enrollment},
                                      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 {"Dropout": float(prob[0][0]), "Graduate": 1-float(prob[0][0])}, local_plot

# Create the UI
title = "**Student Graduation Predictor & Interpreter** 🪐"
description1 = """This app takes info from subjects and predicts their graduation likelihood."""

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(description1)
    gr.Markdown("""---""")
    gr.Markdown(description2)
    gr.Markdown("""---""")
    with gr.Row():
        with gr.Column():
        Target = gr.Number(label="Target Score", value=40)
        Admission_Grade = gr.Slider(label="AdmissionGrade Score", minimum=0, maximum=1, value=1, step=1)
        2nd_Sem_Grades = gr.Slider(label="PreviousQualificationGrade Score", minimum=1, maximum=5, value=4, step=1)
        Previous_Qualification_Grade = gr.Slider(label="CurricularUnits1stSemGrade Score", minimum=1, maximum=5, value=4, step=1) 
        1st_Sem_Grades = gr.Slider(label="Course Score", minimum=1, maximum=5, value=4, step=1)
        Course = gr.Slider(label="Course", minimum=1, maximum=5, value=4, step=1)
        2nd_Sem_Units_Approved = gr.Slider(label="2nd_Sem_Units_Approved", minimum=1, maximum=5, value=4, step=1)
        Age_at_Enrollment = gr.Slider(label="AgeAtEnrollment 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,
        [Target, Admission_Grade, 2nd_Sem_Grades, Previous_Qualification_Grade, 1st_Sem_Grades, Course, 2nd_Sem_Units_Approved, Age_at_Enrollment],
        [label,local_plot], api_name="Graduation_Predictor"
    )
    
    gr.Markdown("### Click on any of the examples below to see how it works:")
    gr.Examples([['Graduate',119.6,13.000000,122.0,9773,5,18], [Target, Admission_Grade, 2nd_Sem_Grades, Previous_Qualification_Grade, 1st_Sem_Grades, Course, 2nd_Sem_Units_Approved, Age_at_Enrollment]
                 , [label,local_plot], main_func, cache_examples=True)

demo.launch()