pytorch-forecasting

pytorch-forecasting copied to clipboard

Question: Predictions exported as pandas.DataFrame

1

Hi, I am new to `pytorch-forecasting`. I followed the TFT tutorial and have a question regarding the predictions output. After generating a set of raw predictions by `raw_predictions, x =...

eltoncyc

- PyTorch-Forecasting version: 0.10.1 - PyTorch version: 1.11.0 - Python version: 3.7 - Operating System: Windows - Pandas version: 1.3.5 ### Expected behavior I tried to use a TemporalFusionTransformer model...

JoMaCaCha

TFT Forecasting: How to handle multiple time series with varying length (time_idx). I have multiple time series with varying length, what is the elegant way to handle the forecasting problem using TFT

3

- PyTorch-Forecasting version: - PyTorch version: - Python version: - Operating System: ### Expected behavior I executed code ... in order to ... and expected to get result ... ###...

KeelyBRao

- PyTorch-Forecasting version: 0.10.1 - PyTorch version: 1.10.1 - Python version: 3.7.4 - Operating System: Ubuntu 20.04 ### Expected behavior I was using the `CompositeMetric` module by adding `SMAPE` and...

waihongON

Question about using lags or monthly categorical features for seasonality recognition

1

Hey there, I try to forecast monthly sales with the help of `DeepAR` and `TemporalFusionTransformer`. The data I use has monthly seasonality, and the seasonality is the same or at...

lch679

- PyTorch-Forecasting version: 0.10.1 - PyTorch version: 1.11.0 - Python version: 3.9 - Operating System: Windows ### Issue I tried tunning learning rate with "auto_lr_find", But encountered permission error for...

hannahyess

`.partial_dependency()` method of `BaseModel` and sub classes output a single value for probe value when using `QuantileLoss`. So for `k` probe values, `t` time steps predicted, it outputs a shape...

chrisaddy

PyTorch-Forecasting version: 0.9.2 PyTorch version: 1.12.0 PyTorch-Lightning: 1.5.10 Python version: 3.8.12 Operating System: Windows 10 I have a very big data set, which does not fully fit into one single...

eTuDpy

PyTorch-Forecasting version: current master branch PyTorch version: 1.9.0 Python version: 3.8 Hi, I'm using 1 year hourly data to train. Just a single target and time (and another const column...

processadd

- PyTorch-Forecasting version: 0.9.2 - PyTorch version: 1.10.1 - Python version: 3.9 - Operating System: Windows 10 Hello to everyone. Does anyone know how to compute the QuantileLoss in predictions...

IgnacioZH