import gradio as gr
import joblib
import numpy as np
import pandas as pd
from huggingface_hub import hf_hub_download

# Load the trained model and scaler objects from file


REPO_ID = "Hemg/marketforecast" # hugging face  repo ID
MoDEL_FILENAME = "market.joblib" # model file name
SCALER_FILENAME ="marketscaler.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))
 
# model = joblib.load('D:\gradioapp\X.joblib')
# scaler = joblib.load('D:\gradioapp\Xx.joblib')

# Define the prediction function
def predict_enrol(Year, Instagram_Advertising, Facebook_Advertising, Event_Expenses, 
                 Internet_Expenses, Facebook_Enroll, Instagram_Enroll, Internet_Enroll,
                 Recommendation, Total_Expenses):
    # Prepare input data
    input_data = [[Year, Instagram_Advertising, Facebook_Advertising, Event_Expenses,
                  Internet_Expenses, Facebook_Enroll, Instagram_Enroll, Internet_Enroll,
                  Recommendation,  Total_Expenses]]

    # Get the feature names from the Gradio interface inputs
    feature_names = ["Year", "Instagram Advertising", "Facebook Advertising", 
                    "Event Expenses", "Internet Expenses", "Facebook Enroll",
                    "Instagram Enroll", "Internet Enroll", "Recommendation",
                     "Total Expenses"]
    # Create a Pandas DataFrame with the input data and feature names
    input_df = pd.DataFrame(input_data, columns=feature_names)

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

    # Make predictions using the loaded model
    prediction = model.predict(scaled_input)[0]
    
    return f"Predicted House Price: ${prediction:,.2f}" # Price is our dependent variable

# Create the Gradio app
iface = gr.Interface(
    fn=predict_enrol,
    inputs=[
        gr.Number(label="Year"),
        gr.Number(label="Instagram Advertising"),
        gr.Number(label="Facebook Advertising"),
        gr.Number(label="Event Expenses"),
        gr.Number(label="Internet Expenses"),
        gr.Number(label="Facebook Enroll"),
        gr.Number(label="Instagram Enroll"),
        gr.Number(label="Internet Enroll"),
        gr.Number(label="Recommendation"),
        gr.Number(label="Total Enroll"),
       
    ],
    outputs="text",
    title="marketforecast",
    description="Predict market"
)

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