torchts quick API |
|
---|---|
RNN model for time series forecasting |
|
MLP model for time series forecasting |
|
parsnip API |
|
General interface to recurrent neural network models |
|
Modules |
|
A configurable recurrent neural network model |
|
A configurable feed forward network (Multi-Layer Perceptron) with embedding |
|
Create multiple embeddings at once |
|
Shortcut to create linear layer with nonlinear activation function |
|
A shortcut to create a feed-forward block (MLP block) |
|
Data transformations |
|
Convert an object to tensor |
|
Create a time series dataset from a |
|
Create a torch dataset for time series data from a |
|
Quick shortcut to create a torch dataloader based on the given dataset |
|
Convert |
|
Metrics |
|
Mean absolute error |
|
Mean absolute percentage error |
|
Symmetric mean absolute percentage error |
|
Utils |
|
Check, if vector is categorical, i.e. if is logical, factor, character or integer |
|
Return size of categorical variables in the data.frame |
|
Propose the length of embedding vector for each embedded feature. |
|
Partially clear outcome variable in new data by overriding with NA values |
|
Set model device. |
|
Plot forecast vs ground truth |
|
Data |
|
Weather data from Polish "poles of extreme temperatures" in 2001-2020 |
|
A subset from M5 Walmart Challenge Dataset in one data frame |