app.py

import gradio as gr
import joblib
import numpy as np
import pandas as pd
from huggingface_hub import hf_hub_download
from sklearn.preprocessing import StandardScaler, OneHotEncoder, LabelEncoder

# Load the trained model and scaler objects from file


REPO_ID = "Hemg/studentApp" # hugging face  repo ID
MoDEL_FILENAME = "stx.joblib" # model file name
SCALER_FILENAME ="scaler.joblib" # scaler file name

model = joblib.load(hf_hub_download(repo_id=REPO_ID, filename=MoDEL_FILENAME))

scaler = joblib.load(hf_hub_download(repo_id=REPO_ID, filename=SCALER_FILENAME))
 
def encode_categorical_columns(df):
    label_encoder = LabelEncoder()
    ordinal_columns = df.select_dtypes(include=['object']).columns

    for col in ordinal_columns:
        df[col] = label_encoder.fit_transform(df[col])

    nominal_columns = df.select_dtypes(include=['object']).columns.difference(ordinal_columns)
    df = pd.get_dummies(df, columns=nominal_columns, drop_first=True)

    return df

# Define the prediction function
def predict_performance(Hours_Studied,Previous_Scores,Extracurricular_Activities,Sleep_Hours,SampleQuestions_Practiced):
    # Prepare input data represents independent variables for house prediction
    input_data = [[Hours_Studied,Previous_Scores,Extracurricular_Activities,Sleep_Hours,SampleQuestions_Practiced]]

    # Get the feature names from the Gradio interface inputs
    feature_names = ['Hours_Studied','Previous_Scores','Extracurricular_Activities','Sleep_Hours','SampleQuestions_Practiced']
    # Create a Pandas DataFrame with the input data and feature names
    input_df = pd.DataFrame(input_data, columns=feature_names)

    input_df = pd.DataFrame(input_data, columns=feature_names)

  
    df = encode_categorical_columns(input_df)

    # Scale the input data using the loaded scaler
    scaled_input = scaler.transform(df)

    # Make predictions using the loaded model
    prediction = model.predict(scaled_input)[0]
    
    return f"Performance_Index: {prediction:,.2f}" 

# Create the Gradio app
iface = gr.Interface(
    fn=predict_performance,
    inputs=[
        gr.Slider(minimum=1, maximum=10, step=1, label="Hours_Studied",info="How many hours did you study last week?"),
        gr.Slider(minimum=40, maximum=100, step=1, label="Previous_Scores",info="What were your previous academic scores in your most recent exams or assessments?"),
        #gr.Slider(minimum=1, maximum=100, step=1, label="Extracurricular_Activities",info="Are you involved in any extracurricular activities outside of your regular coursework?"),
        gr.Radio(["Yes", "No"], label="Extracurricular_Activities",info="Are you involved in any extracurricular activities outside of your regular coursework?"),
        gr.Slider(minimum=3, maximum=10, step=1, label="Sleep_Hours",info="On average, how many hours of sleep do you get per night?"),
        gr.Slider(minimum=1, maximum=10, step=1, label="SampleQuestions_Practiced",info="Have you been practicing any sample questions or past exam papers as part of your study routine?")
    ],
    outputs="text",
    title="Student_performance_prediction",
    description="Predict Performance_Index"
)

# Run the app
if __name__ == "__main__":
    iface.launch(share=True)