import gradio as gr
import joblib
import numpy as np

# Load the scaler and models
scaler = joblib.load('scaler.joblib')
models = {
    "processing": joblib.load('svm_model_processing.joblib'),
    "perception": joblib.load('svm_model_perception.joblib'),
    "input": joblib.load('svm_model_input.joblib'),
    "understanding": joblib.load('svm_model_understanding.joblib'),
}

# Define the prediction function
def predict(user_input):
    # Ensure the input is in the same order as your model expects
    user_input_array = np.array(user_input).reshape(1, -1)

    # Scale the input using the saved scaler
    user_input_scaled = scaler.transform(user_input_array)

    # Predict outcomes for all target variables
    predictions = {}
    for target, model in models.items():
        prediction = model.predict(user_input_scaled)
        predictions[target] = prediction[0]

    return predictions

# Define Gradio interface
interface = gr.Interface(fn=predict, 
                         inputs=gr.inputs.Dataframe(type="numpy", row_count=1, col_count=12, col_labels=['course overview', 'reading file', 'abstract materiale', 'concrete material', 'visual materials', 'self-assessment', 'exercises submit', 'quiz submitted', 'playing', 'paused', 'unstarted', 'buffering']),
                         outputs=gr.outputs.JSON(),
                         live=True)

# Launch the interface
interface.launch()