app.py

from huggingface_hub import hf_hub_download
import pickle
import gradio as gr
import numpy as np

# Download the model from Hugging Face Hub
model_path = hf_hub_download(repo_id="suryadev1/knn", filename="knn_model_pc.pkl")

# Load the model
with open(model_path, 'rb') as f:
    knn = pickle.load(f)

# Define the prediction function
def predict(input_data):
    # Convert input_data to numpy array
    input_data = np.array(input_data).reshape(1, -1)
    # Make predictions
    predictions = knn.predict([[0.2,0.03,0.0,1.0,0.0]])
    return predictions[0]

# Create Gradio interface
# Adjust the input components based on the number of features your model expects
input_components = [gr.inputs.Number(label=f"Feature {i+1}") for i in range(4)]
output_component = gr.outputs.Textbox(label="Prediction")

iface = gr.Interface(
    fn=predict,
    inputs=input_components,
    outputs=output_component,
    title="KNN Model Prediction",
    description="Enter values for each feature to get a prediction."
)

# Launch the interface
iface.launch()