import gradio as gr
import pickle
import numpy as np
import os

# Class for loading model and predicting
class CropYieldModel:
    def __init__(self, model_path):
        if not os.path.exists(model_path):
            raise FileNotFoundError(f"Model file not found at {model_path}")
        with open(model_path, 'rb') as file:
            self.model = pickle.load(file)

    def predict(self, feature1, feature2, feature3):
        try:
            # Prepare input features
            features = np.array([[feature1, feature2, feature3]])
            prediction = self.model.predict(features)
            return f"Predicted Crop Yield: {float(prediction[0]):.2f}"
        except Exception as e:
            return f"Prediction failed: {str(e)}"

# Load model
model_path = 'model/crop_yield_model.pkl'  # Adjust the path if needed
predictor = CropYieldModel(model_path)

# Gradio Interface
demo = gr.Interface(
    fn=predictor.predict,
    inputs=[
        gr.Number(label="Feature 1"),
        gr.Number(label="Feature 2"),
        gr.Number(label="Feature 3")
    ],
    outputs=gr.Textbox(label="Prediction Result"),
    title="Crop Yield Prediction",
    description="Enter the values for the features to predict crop yield."
)

if __name__ == "__main__":
    demo.launch()