Gerald Woo

Hi! If you guys are still interested in this work, please do check out our official implementation with experiments: https://github.com/salesforce/ETSformer, do check our paper for the updated benchmark (same as...

Hey, thanks for your interest in our work, could you provide more information on this error (the full error log) and the dimensions of the data you are working with?...

@lostella Thanks for getting back, the issue doesn't seem to arise from the QuantileForecast object. The dependency on forecasts in ```extract_past_data``` seems to only be to get the date index....

In fact, one more thing is that while MASE and MSIS may not have been defined for multivariate time series, the straightforward extension would be to calculate the seasonal error...

Sorry, I just realised that ```MultivariateEvaluator.get_metrics_per_ts``` is not meant to be used in this manner. It seems like ```get_metrics_per_ts``` has a precondition, that the time series and forecasts should be...

Perhaps a ```keep_dims``` option would be useful, I can imagine some methods which would like to process each dimension individually (multivariate extension of TFT)

Hi, thanks for the interest. Could you elaborate more about what your difficulties are? (1) What is not the same? (2) Where do you want to print it? The datasets...

Hi, thanks for your interest in our work, one easy workaround to get univariate output variables will be to mask the unwanted dimensions in the output forecast.

Hi guys, sorry for the late reply. The makefile is just calling this command ```python -m experiments.forecast --config_path=${config} build_experiment``` to generate the command files. You can run the python script...

Hey, thanks for the interest in our work, unfortunately I do not have the bandwidth to do so. You could try copy and pasting the model code into the Autoformer...