ValueError: Wrong number of items passed 0, placement implies 1

Question

I'm trying to run this code and cannot understand the issue I am facing.

This code is working just fine:

model = joblib.load(MODEL_PATH)

But this does not:

model = XGBRegressor()
model.load_model(MODEL_PATH)
model.predict(df[features])

I get this error:

ValueError: Wrong number of items passed 0, placement implies 1