> ## Documentation Index
> Fetch the complete documentation index at: https://nixtla-old-docs.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# PatchTST
The PatchTST model is an efficient Transformer-based model for
multivariate time series forecasting.
It is based on two key components: - segmentation of time series into
windows (patches) which are served as input tokens to Transformer -
channel-independence. where each channel contains a single univariate
time series.
**References** - [Nie, Y., Nguyen, N. H., Sinthong, P., &
Kalagnanam, J. (2022). “A Time Series is Worth 64 Words: Long-term
Forecasting with
Transformers”](https://arxiv.org/pdf/2211.14730.pdf) Figure 1. PatchTST.
## 1. Backbone
### Auxiliary Functions
***
source
### get\_activation\_fn
> ```text theme={null}
> get_activation_fn (activation)
> ```
***
source
### Transpose
> ```text theme={null}
> Transpose (*dims, contiguous=False)
> ```
*Transpose*
### Positional Encoding
***
source
### positional\_encoding
> ```text theme={null}
> positional_encoding (pe, learn_pe, q_len, hidden_size)
> ```
***
source
### Coord1dPosEncoding
> ```text theme={null}
> Coord1dPosEncoding (q_len, exponential=False, normalize=True)
> ```
***
source
### Coord2dPosEncoding
> ```text theme={null}
> Coord2dPosEncoding (q_len, hidden_size, exponential=False,
> normalize=True, eps=0.001)
> ```
***
source
### PositionalEncoding
> ```text theme={null}
> PositionalEncoding (q_len, hidden_size, normalize=True)
> ```
### Encoder
***
source
### TSTEncoderLayer
> ```text theme={null}
> TSTEncoderLayer (q_len, hidden_size, n_heads, d_k=None, d_v=None,
> linear_hidden_size=256, store_attn=False,
> norm='BatchNorm', attn_dropout=0, dropout=0.0,
> bias=True, activation='gelu', res_attention=False,
> pre_norm=False)
> ```
*TSTEncoderLayer*
***
source
### TSTEncoder
> ```text theme={null}
> TSTEncoder (q_len, hidden_size, n_heads, d_k=None, d_v=None,
> linear_hidden_size=None, norm='BatchNorm', attn_dropout=0.0,
> dropout=0.0, activation='gelu', res_attention=False,
> n_layers=1, pre_norm=False, store_attn=False)
> ```
*TSTEncoder*
***
source
### TSTiEncoder
> ```text theme={null}
> TSTiEncoder (c_in, patch_num, patch_len, max_seq_len=1024, n_layers=3,
> hidden_size=128, n_heads=16, d_k=None, d_v=None,
> linear_hidden_size=256, norm='BatchNorm', attn_dropout=0.0,
> dropout=0.0, act='gelu', store_attn=False,
> key_padding_mask='auto', padding_var=None, attn_mask=None,
> res_attention=True, pre_norm=False, pe='zeros',
> learn_pe=True)
> ```
*TSTiEncoder*
***
source
### Flatten\_Head
> ```text theme={null}
> Flatten_Head (individual, n_vars, nf, h, c_out, head_dropout=0)
> ```
*Flatten\_Head*
***
source
### PatchTST\_backbone
> ```text theme={null}
> PatchTST_backbone (c_in:int, c_out:int, input_size:int, h:int,
> patch_len:int, stride:int,
> max_seq_len:Optional[int]=1024, n_layers:int=3,
> hidden_size=128, n_heads=16, d_k:Optional[int]=None,
> d_v:Optional[int]=None, linear_hidden_size:int=256,
> norm:str='BatchNorm', attn_dropout:float=0.0,
> dropout:float=0.0, act:str='gelu',
> key_padding_mask:str='auto',
> padding_var:Optional[int]=None,
> attn_mask:Optional[torch.Tensor]=None,
> res_attention:bool=True, pre_norm:bool=False,
> store_attn:bool=False, pe:str='zeros',
> learn_pe:bool=True, fc_dropout:float=0.0,
> head_dropout=0, padding_patch=None,
> pretrain_head:bool=False, head_type='flatten',
> individual=False, revin=True, affine=True,
> subtract_last=False)
> ```
*PatchTST\_backbone*
## 2. Model
***
source
### PatchTST
> ```text theme={null}
> PatchTST (h, input_size, stat_exog_list=None, hist_exog_list=None,
> futr_exog_list=None, exclude_insample_y=False,
> encoder_layers:int=3, n_heads:int=16, hidden_size:int=128,
> linear_hidden_size:int=256, dropout:float=0.2,
> fc_dropout:float=0.2, head_dropout:float=0.0,
> attn_dropout:float=0.0, patch_len:int=16, stride:int=8,
> revin:bool=True, revin_affine:bool=False,
> revin_subtract_last:bool=True, activation:str='gelu',
> res_attention:bool=True, batch_normalization:bool=False,
> learn_pos_embed:bool=True, loss=MAE(), valid_loss=None,
> max_steps:int=5000, learning_rate:float=0.0001,
> num_lr_decays:int=-1, early_stop_patience_steps:int=-1,
> val_check_steps:int=100, batch_size:int=32,
> valid_batch_size:Optional[int]=None, windows_batch_size=1024,
> inference_windows_batch_size:int=1024,
> start_padding_enabled=False, step_size:int=1,
> scaler_type:str='identity', random_seed:int=1,
> drop_last_loader:bool=False, alias:Optional[str]=None,
> optimizer=None, optimizer_kwargs=None, lr_scheduler=None,
> lr_scheduler_kwargs=None, dataloader_kwargs=None,
> **trainer_kwargs)
> ```
\*PatchTST
The PatchTST model is an efficient Transformer-based model for
multivariate time series forecasting.
It is based on two key components: - segmentation of time series into
windows (patches) which are served as input tokens to Transformer -
channel-independence, where each channel contains a single univariate
time series.
**Parameters:** `h`: int, Forecast horizon. `input_size`: int,
autorregresive inputs size, y=\[1,2,3,4] input\_size=2 ->
y\_\[t-2:t]=\[1,2]. `stat_exog_list`: str list, static exogenous
columns. `hist_exog_list`: str list, historic exogenous columns.
`futr_exog_list`: str list, future exogenous columns.
`exclude_insample_y`: bool=False, the model skips the autoregressive
features y\[t-input\_size:t] if True. `encoder_layers`: int, number
of layers for encoder. `n_heads`: int=16, number of multi-head’s
attention. `hidden_size`: int=128, units of embeddings and
encoders. `linear_hidden_size`: int=256, units of linear layer.
`dropout`: float=0.1, dropout rate for residual connection.
`fc_dropout`: float=0.1, dropout rate for linear layer.
`head_dropout`: float=0.1, dropout rate for Flatten head layer.
`attn_dropout`: float=0.1, dropout rate for attention layer.
`patch_len`: int=32, length of patch. Note: patch\_len = min(patch\_len,
input\_size + stride). `stride`: int=16, stride of patch.
`revin`: bool=True, bool to use RevIn. `revin_affine`: bool=False,
bool to use affine in RevIn. `revin_subtract_last`: bool=False, bool
to use substract last in RevIn. `activation`: str=‘ReLU’, activation
from \[‘gelu’,‘relu’]. `res_attention`: bool=False, bool to use
residual attention. `batch_normalization`: bool=False, bool to use
batch normalization. `learn_pos_embed`: bool=True, bool to learn
positional embedding. `loss`: PyTorch module, instantiated train
loss class from [losses
collection](https://nixtla.github.io/neuralforecast/losses.pytorch.html).
`valid_loss`: PyTorch module=`loss`, instantiated valid loss class from
[losses
collection](https://nixtla.github.io/neuralforecast/losses.pytorch.html).
`max_steps`: int=1000, maximum number of training steps.
`learning_rate`: float=1e-3, Learning rate between (0, 1).
`num_lr_decays`: int=-1, Number of learning rate decays, evenly
distributed across max\_steps. `early_stop_patience_steps`: int=-1,
Number of validation iterations before early stopping.
`val_check_steps`: int=100, Number of training steps between every
validation loss check. `batch_size`: int=32, number of different
series in each batch. `valid_batch_size`: int=None, number of
different series in each validation and test batch, if None uses
batch\_size. `windows_batch_size`: int=1024, number of windows to
sample in each training batch, default uses all.
`inference_windows_batch_size`: int=1024, number of windows to sample in
each inference batch. `start_padding_enabled`: bool=False, if True,
the model will pad the time series with zeros at the beginning, by input
size. `step_size`: int=1, step size between each window of temporal
data. `scaler_type`: str=‘identity’, type of scaler for temporal
inputs normalization see [temporal
scalers](https://nixtla.github.io/neuralforecast/common.scalers.html).
`random_seed`: int, random\_seed for pytorch initializer and numpy
generators. `drop_last_loader`: bool=False, if True
`TimeSeriesDataLoader` drops last non-full batch. `alias`: str,
optional, Custom name of the model. `optimizer`: Subclass of
‘torch.optim.Optimizer’, optional, user specified optimizer instead of
the default choice (Adam). `optimizer_kwargs`: dict, optional, list
of parameters used by the user specified `optimizer`.
`lr_scheduler`: Subclass of ‘torch.optim.lr\_scheduler.LRScheduler’,
optional, user specified lr\_scheduler instead of the default choice
(StepLR). `lr_scheduler_kwargs`: dict, optional, list of parameters
used by the user specified `lr_scheduler`. \
`dataloader_kwargs`: dict, optional, list of parameters passed into the
PyTorch Lightning dataloader by the `TimeSeriesDataLoader`.
`**trainer_kwargs`: int, keyword trainer arguments inherited from
[PyTorch Lighning’s
trainer](https://pytorch-lightning.readthedocs.io/en/stable/api/pytorch_lightning.trainer.trainer.Trainer.html?highlight=trainer).
**References:** -[Nie, Y., Nguyen, N. H., Sinthong, P., &
Kalagnanam, J. (2022). “A Time Series is Worth 64 Words: Long-term
Forecasting with Transformers”](https://arxiv.org/pdf/2211.14730.pdf)\*
***
### PatchTST.fit
> ```text theme={null}
> PatchTST.fit (dataset, val_size=0, test_size=0, random_seed=None,
> distributed_config=None)
> ```
\*Fit.
The `fit` method, optimizes the neural network’s weights using the
initialization parameters (`learning_rate`, `windows_batch_size`, …) and
the `loss` function as defined during the initialization. Within `fit`
we use a PyTorch Lightning `Trainer` that inherits the initialization’s
`self.trainer_kwargs`, to customize its inputs, see [PL’s trainer
arguments](https://pytorch-lightning.readthedocs.io/en/stable/api/pytorch_lightning.trainer.trainer.Trainer.html?highlight=trainer).
The method is designed to be compatible with SKLearn-like classes and in
particular to be compatible with the StatsForecast library.
By default the `model` is not saving training checkpoints to protect
disk memory, to get them change `enable_checkpointing=True` in
`__init__`.
**Parameters:** `dataset`: NeuralForecast’s
[`TimeSeriesDataset`](https://nixtlaverse.nixtla.io/neuralforecast/tsdataset.html#timeseriesdataset),
see
[documentation](https://nixtla.github.io/neuralforecast/tsdataset.html).
`val_size`: int, validation size for temporal cross-validation.
`random_seed`: int=None, random\_seed for pytorch initializer and numpy
generators, overwrites model.\_\_init\_\_’s. `test_size`: int, test
size for temporal cross-validation. \*
***
### PatchTST.predict
> ```text theme={null}
> PatchTST.predict (dataset, test_size=None, step_size=1, random_seed=None,
> quantiles=None, **data_module_kwargs)
> ```
\*Predict.
Neural network prediction with PL’s `Trainer` execution of
`predict_step`.
**Parameters:** `dataset`: NeuralForecast’s
[`TimeSeriesDataset`](https://nixtlaverse.nixtla.io/neuralforecast/tsdataset.html#timeseriesdataset),
see
[documentation](https://nixtla.github.io/neuralforecast/tsdataset.html).
`test_size`: int=None, test size for temporal cross-validation.
`step_size`: int=1, Step size between each window. `random_seed`:
int=None, random\_seed for pytorch initializer and numpy generators,
overwrites model.\_\_init\_\_’s. `quantiles`: list of floats,
optional (default=None), target quantiles to predict.
`**data_module_kwargs`: PL’s TimeSeriesDataModule args, see
[documentation](https://pytorch-lightning.readthedocs.io/en/1.6.1/extensions/datamodules.html#using-a-datamodule).\*
## Usage example
```python theme={null}
import pandas as pd
import matplotlib.pyplot as plt
from neuralforecast import NeuralForecast
from neuralforecast.models import PatchTST
from neuralforecast.losses.pytorch import DistributionLoss
from neuralforecast.utils import AirPassengersPanel, AirPassengersStatic, augment_calendar_df
AirPassengersPanel, calendar_cols = augment_calendar_df(df=AirPassengersPanel, freq='M')
Y_train_df = AirPassengersPanel[AirPassengersPanel.ds=AirPassengersPanel['ds'].values[-12]].reset_index(drop=True) # 12 test
model = PatchTST(h=12,
input_size=104,
patch_len=24,
stride=24,
revin=False,
hidden_size=16,
n_heads=4,
scaler_type='robust',
loss=DistributionLoss(distribution='StudentT', level=[80, 90]),
learning_rate=1e-3,
max_steps=500,
val_check_steps=50,
early_stop_patience_steps=2)
nf = NeuralForecast(
models=[model],
freq='ME'
)
nf.fit(df=Y_train_df, static_df=AirPassengersStatic, val_size=12)
forecasts = nf.predict(futr_df=Y_test_df)
Y_hat_df = forecasts.reset_index(drop=False).drop(columns=['unique_id','ds'])
plot_df = pd.concat([Y_test_df, Y_hat_df], axis=1)
plot_df = pd.concat([Y_train_df, plot_df])
if model.loss.is_distribution_output:
plot_df = plot_df[plot_df.unique_id=='Airline1'].drop('unique_id', axis=1)
plt.plot(plot_df['ds'], plot_df['y'], c='black', label='True')
plt.plot(plot_df['ds'], plot_df['PatchTST-median'], c='blue', label='median')
plt.fill_between(x=plot_df['ds'][-12:],
y1=plot_df['PatchTST-lo-90'][-12:].values,
y2=plot_df['PatchTST-hi-90'][-12:].values,
alpha=0.4, label='level 90')
plt.grid()
plt.legend()
plt.plot()
else:
plot_df = plot_df[plot_df.unique_id=='Airline1'].drop('unique_id', axis=1)
plt.plot(plot_df['ds'], plot_df['y'], c='black', label='True')
plt.plot(plot_df['ds'], plot_df['PatchTST'], c='blue', label='Forecast')
plt.legend()
plt.grid()
```
