search

kdgutier / esrnn_torch

MIT License
156 stars 44 forks source link

application for time series data with trend #26

Closed ramdhan1989 closed 3 years ago

ramdhan1989 commented 3 years ago

Hi, I am trying to use this package for air passenger dataset the result as follow : image

is it good to use this package for this typical dataset (with seasonal and trend) ?

my model is look like this : model = ESRNN(max_epochs=250, freq_of_test=5, batch_size=1, learning_rate=1e-3, per_series_lr_multip=0.8, lr_scheduler_step_size=10, lr_decay=0.1, gradient_clipping_threshold=50, rnn_weight_decay=0.0, level_variability_penalty=100, testing_percentile=0, training_percentile=100, ensemble=False, max_periods=25, seasonality=[12], input_size=12, output_size=40, cell_type='LSTM', state_hsize=40, dilations=[[1], [6]], add_nl_layer=False, random_seed=1, device='cuda')

Is there any advice to tune the model in order to get good result ?

thank you

kdgutier commented 3 years ago

If there is a clear seasonality for example in your case a seasonality of [12] is reasonable. I recommend you to use the hyperopt library for hyperparameter selection (https://anaconda.org/conda-forge/hyperopt). Good luck!