neuralforecast
neuralforecast copied to clipboard
Nixtla
Scalable and user friendly neural :brain: forecasting algorithms.
### Description Create several default config search spaces for auto models varying by dataset size. ### Use case _No response_
### Description Add tutorial for `StemGNN` model on traffic data. ### Link _No response_
**Describe the bug** I could not install neuralforecast in a new conda environment **To Reproduce** `conda create -n nixtla -c conda-forge python=3.8 # or 3.9 or 3.10` `conda activate nixtla`...
Distribution Losses are missing a protection of duplicated `level` and `quantiles` initialization, see: https://github.com/Nixtla/neuralforecast/blob/main/neuralforecast/losses/pytorch.py#L1050
Hello, my time series data has some large missing gaps, I was wondering if it is possible to remove the rows with missing value instead of applying data interpolation methods...
When I am using Tensorflow/Keras I compress my models as in this [guide](https://www.tensorflow.org/model_optimization/guide/pruning/pruning_with_keras#create_a_10x_smaller_model_from_combining_pruning_and_quantization), where I combine prune/quantize my model. Can I compress TFT or/and N-HiTs from neuralforecast? I tried with...
An epoch corresponds to a complete pass of the model through the training data, while a step refers to the Gradient Descent step performed on a data batch during training....
Thanks a lot for your continuous support so far! I have some follow-up questions. How do we extract the model objects' test loss and test forecasts? Is the final loss...
AutoNHITS.default_config is not a valid config if provided as argument since it uses 'input_size_multiplier', which is only translated to the necessary 'input_size' if config==None. This makes configs that are only...
I have some questions about AutoNBEATS and AutoNHITS, as mentioned below: 1. The forecaster can use this code snippet to generate the model fitted in sample values, but it gives...