app.py

import numpy as np
import pandas as pd
import statsmodels.api as sm
from sklearn.preprocessing import StandardScaler
import gradio as gr
import pickle

with open ("scaled_obj.pkl", "rb") as f:
  sc_object = pickle.load(f)

with open ("scaled_model.pkl", "rb") as f:
  lin_model_object = pickle.load(f)

def fn_predict(Total_Revenue,Operating_Cost,Total_Assets,Total_Liabilities,Stock_Price,Market_Cap,EBITDA,RD_Expenses,Number_of_Employees):
  df = np.array([[Total_Revenue,Operating_Cost,Total_Assets,Total_Liabilities,Stock_Price,Market_Cap,EBITDA,RD_Expenses,Number_of_Employees]])
  scaled_new_data = sc_object.transform(df)

  predictions = lin_model_object.predict(scaled_new_data)
  return predictions

# Define Gradio interface
iface = gr.Interface(
    fn=fn_predict,
    inputs=[
        gr.Number(label="Total Revenue"),
        gr.Number(label="Operating Cost"),
        gr.Number(label="Total Assets"),
        gr.Number(label="Total Liabilities"),
        gr.Number(label="Stock Price"),
        gr.Number(label="Market Cap"),
        gr.Number(label="EBITDA"),
        gr.Number(label="R&D Expenses"),
        gr.Number(label="Number of Employees")
    ],
    outputs=gr.Textbox(),
    css="styles.css"
)

# Launch the application
iface.launch()