app.py

import gradio as gr
import pandas as pd 
import numpy as np 


import pickle
with open("linear_regression_model.pkl", "rb") as file:
    lin_reg = pickle.load(file)

# define the input module 
inputs = [
    gr.components.Number(label="Longitude"),
    gr.components.Number(label="Latitude"),
    gr.components.Number(label="Housing Median Age"),
    gr.components.Number(label="Total Rooms"),
    gr.components.Number(label="Total Bedrooms"),
    gr.components.Number(label="Population"),
    gr.components.Number(label="Households"),
    gr.components.Number(label="Median Income")
]

# define the output module 
outputs = gr.components.Textbox(label = 'Output')


# define the backend function 
from sklearn.preprocessing import MinMaxScaler
def predict_price(longitude, latitude, housing_median_age, total_rooms, total_bedrooms, population, households, median_income):
    features = pd.DataFrame({
        'longitude': [longitude],
        'latitude': [latitude],
        'housing_median_age': [housing_median_age],
        'total_rooms': [total_rooms],
        'total_bedrooms': [total_bedrooms],
        'population': [population],
        'households': [households],
        'median_income': [median_income]
    })

    scaler = MinMaxScaler() ## define the transformer
    # load your scaler from the training dataset 

    features=scaler.fit_transform(features)
    linear_regression_prediction = lin_reg.predict(features)[0]
    #decision_tree_prediction = tree_reg.predict(features)[0]

    return linear_regression_prediction

interface = gr.Interface(fn=predict_price, inputs=inputs, outputs=outputs).launch(debug=True)