# Naive forecast¶

To compute the rMAE and the MASE, a naive forecast is employed. The naive forecast can be built by three methods:

1. Considering daily seasonality and assuming that the prices from one day to the other do not change.
2. Considering weekly seasonality and assuming that the prices from one week to the other do not change
3. Considering different seasonality dependening on the day of the week: daily seasonality for Tuesday to Friday and weekly seasonality for Saturday to Monday.
epftoolbox.evaluation.naive_forecast(p_real, m=None, n_prices_day=24)[source]

Function to buil the naive forecast for electricity price forecasting

The function is used to compute the accuracy metrics MASE and RMAE

Parameters: p_real (pandas.DataFrame) – Dataframe containing the real prices. It must be of shape $$(n_\mathrm{prices}, 1)$$, m (int, optional) – Index that specifies the seasonality in the naive forecast. It can be 'D' for daily seasonality, 'W' for weekly seasonality, or None for the standard naive forecast in electricity price forecasting, i.e. daily seasonality for Tuesday to Friday and weekly seasonality for Saturday to Monday. n_prices_day (int, optional) – Number of prices in a day. Usually this value is 24 for most day-ahead markets Dataframe containing the predictions of the naive forecast. pandas.DataFrame