epftoolbox

epftoolbox copied to clipboard

A keras error will occur when running dnn-related examples

3

```bash cd examples python3 optimizing_hyperparameters_dnn.py ``` ```text Traceback (most recent call last): File "/workspace/epftoolbox/examples/optimizing_hyperparameters_dnn.py", line 56, in hyperparameter_optimizer(path_datasets_folder=path_datasets_folder, File "/workspace/epftoolbox/epftoolbox/models/_dnn_hyperopt.py", line 320, in hyperparameter_optimizer fmin(fmin_objective, space=space, algo=tpe.suggest, max_evals=max_evals, trials=trials, verbose=False)...

zh0ngtian

In _lear.py the `1H` notations used in lines 193-194, trigger several deprecation warnings. According to the related documentation ([here](https://pandas.pydata.org/docs/reference/api/pandas.DatetimeIndex.round.html#pandas.DatetimeIndex.round) and [here](https://pandas.pydata.org/docs/user_guide/timeseries.html#timeseries-offset-aliases)) should be replaced with "1h". I have tested the...

sbudai

DM statistic calculated incorrectly

1

Hi, I had a doubt on the way the DM test is calculated? https://epftoolbox.readthedocs.io/en/latest/modules/statest/dm.html This disagrees with other sources: - https://real-statistics.com/time-series-analysis/forecasting-accuracy/diebold-mariano-test/ - https://www.lem.sssup.it/phd/documents/Lesson19.pdf

namiyousef

Different data sets than yours or shorter timespan of DE

1

Hi, I am trying to run your code with my own data set and it always produces errors. I have data with Date in correct format as `index`, `Price` column,...

luboshanus

Not able to reproduce LEAR forecasts stored in epftoolbox/forecasts/

2

Dear @jeslago, as a first step before using your package for research purposes I tried to reproduce the BE forecasts [here](https://github.com/jeslago/epftoolbox/tree/master/forecasts) obtained with LEAR. To do so I've kept it...

aleszani

LEAR bug: exogeneous used at D-2, should be D-7

2

In file _lear.py, line 240, function build_and_split_XY(): There is for past_day in [1,2]: Should be: for past_day in [1,7]:

MichalJarema

Hyperparameter for Germany

3

Hi, I tried to replicate the forecast for the day ahead electricity prices for Germany, but the sMAPEs are too high, contrasting with the markets, like PJM, BE, and NP....

rderayati

ValueError with the LEAR model when using scikit-learn 1.1.0 or newer

1

Hi, Starting from version 1.1.0, scikit-learn class LassoLarsIC takes the keyword argument noise_variance. This causes an error with LEAR model if the calibration window is set to a relatively small...

ikonentj

DM test with score instead of forecasts

1

Hi, would you accept a PR for a DM-test version that accepts `scores_1`, `scores_2` as inputs instead of the original prices and point forecasts? That way, the DM test could...

simon-hirsch

Hi, I would like to use this package on Python `3.11.2`, `3.12` and `3.13`. I would like to know if is possible to remove the `3.11.0` limitation on the `setup.py`....

nyckmaia