> ## 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.

# iTransformer

The iTransformer model simply takes the Transformer architecture but it
applies the attention and feed-forward network on the inverted
dimensions. This means that time points of each individual series are
embedded into tokens. That way, the attention mechanisms learn
multivariate correlation and the feed-forward network learns non-linear
relationships.

**References** - [Yong Liu, Tengge Hu, Haoran Zhang, Haixu Wu, Shiyu
Wang, Lintao Ma, Mingsheng Long. “iTransformer: Inverted Transformers
Are Effective for Time Series
Forecasting”](https://arxiv.org/abs/2310.06625)

<figure>
  <img src="https://mintlify.s3.us-west-1.amazonaws.com/nixtla-old-docs/neuralforecast/imgs_models/itransformer.png" alt="Figure 1. Architecture of iTransformer." />

  <figcaption aria-hidden="true">Figure 1. Architecture of
  iTransformer.</figcaption>
</figure>

# 1. Model

***

<a href="https://github.com/Nixtla/neuralforecast/blob/main/neuralforecast/models/itransformer.py#L24" target="_blank" style={{ float: "right", fontSize: "smaller" }}>source</a>

### iTransformer

> ```text theme={null}
>  iTransformer (h, input_size, n_series, futr_exog_list=None,
>                hist_exog_list=None, stat_exog_list=None,
>                exclude_insample_y=False, hidden_size:int=512,
>                n_heads:int=8, e_layers:int=2, d_layers:int=1,
>                d_ff:int=2048, factor:int=1, dropout:float=0.1,
>                use_norm:bool=True, loss=MAE(), valid_loss=None,
>                max_steps:int=1000, learning_rate:float=0.001,
>                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=32,
>                inference_windows_batch_size=32,
>                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)
> ```

\*iTransformer

**Parameters:**<br /> `h`: int, Forecast horizon. <br /> `input_size`: int,
autorregresive inputs size, y=\[1,2,3,4] input\_size=2 ->
y\_\[t-2:t]=\[1,2].<br /> `n_series`: int, number of time-series.<br />
`futr_exog_list`: str list, future exogenous columns.<br />
`hist_exog_list`: str list, historic exogenous columns.<br />
`stat_exog_list`: str list, static exogenous columns.<br />
`exclude_insample_y`: bool=False, the model skips the autoregressive
features y\[t-input\_size:t] if True.<br />\
`hidden_size`: int, dimension of the model.<br /> `n_heads`: int, number
of heads.<br /> `e_layers`: int, number of encoder layers.<br /> `d_layers`:
int, number of decoder layers.<br /> `d_ff`: int, dimension of
fully-connected layer.<br /> `factor`: int, attention factor.<br />
`dropout`: float, dropout rate.<br /> `use_norm`: bool, whether to
normalize or not.<br /> `loss`: PyTorch module, instantiated train loss
class from [losses
collection](https://nixtla.github.io/neuralforecast/losses.pytorch.html).<br />
`valid_loss`: PyTorch module=`loss`, instantiated valid loss class from
[losses
collection](https://nixtla.github.io/neuralforecast/losses.pytorch.html).<br />
`max_steps`: int=1000, maximum number of training steps.<br />
`learning_rate`: float=1e-3, Learning rate between (0, 1).<br />
`num_lr_decays`: int=-1, Number of learning rate decays, evenly
distributed across max\_steps.<br /> `early_stop_patience_steps`: int=-1,
Number of validation iterations before early stopping.<br />
`val_check_steps`: int=100, Number of training steps between every
validation loss check.<br /> `batch_size`: int=32, number of different
series in each batch.<br /> `valid_batch_size`: int=None, number of
different series in each validation and test batch, if None uses
batch\_size.<br /> `windows_batch_size`: int=32, number of windows to
sample in each training batch, default uses all.<br />
`inference_windows_batch_size`: int=32, number of windows to sample in
each inference batch, -1 uses all.<br /> `start_padding_enabled`:
bool=False, if True, the model will pad the time series with zeros at
the beginning, by input size.<br /> `step_size`: int=1, step size between
each window of temporal data.<br /> `scaler_type`: str=‘identity’, type of
scaler for temporal inputs normalization see [temporal
scalers](https://nixtla.github.io/neuralforecast/common.scalers.html).<br />
`random_seed`: int=1, random\_seed for pytorch initializer and numpy
generators.<br /> `drop_last_loader`: bool=False, if True
`TimeSeriesDataLoader` drops last non-full batch.<br /> `alias`: str,
optional, Custom name of the model.<br /> `optimizer`: Subclass of
‘torch.optim.Optimizer’, optional, user specified optimizer instead of
the default choice (Adam).<br /> `optimizer_kwargs`: dict, optional, list
of parameters used by the user specified `optimizer`.<br />
`lr_scheduler`: Subclass of ‘torch.optim.lr\_scheduler.LRScheduler’,
optional, user specified lr\_scheduler instead of the default choice
(StepLR).<br /> `lr_scheduler_kwargs`: dict, optional, list of parameters
used by the user specified `lr_scheduler`.<br /> `dataloader_kwargs`:
dict, optional, list of parameters passed into the PyTorch Lightning
dataloader by the `TimeSeriesDataLoader`. <br /> `**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).<br />

**References**<br /> - [Yong Liu, Tengge Hu, Haoran Zhang, Haixu Wu, Shiyu
Wang, Lintao Ma, Mingsheng Long. “iTransformer: Inverted Transformers
Are Effective for Time Series
Forecasting”](https://arxiv.org/abs/2310.06625)\*

***

### iTransformer.fit

> ```text theme={null}
>  iTransformer.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:**<br /> `dataset`: NeuralForecast’s
[`TimeSeriesDataset`](https://nixtlaverse.nixtla.io/neuralforecast/tsdataset.html#timeseriesdataset),
see
[documentation](https://nixtla.github.io/neuralforecast/tsdataset.html).<br />
`val_size`: int, validation size for temporal cross-validation.<br />
`random_seed`: int=None, random\_seed for pytorch initializer and numpy
generators, overwrites model.\_\_init\_\_’s.<br /> `test_size`: int, test
size for temporal cross-validation.<br />\*

***

### iTransformer.predict

> ```text theme={null}
>  iTransformer.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:**<br /> `dataset`: NeuralForecast’s
[`TimeSeriesDataset`](https://nixtlaverse.nixtla.io/neuralforecast/tsdataset.html#timeseriesdataset),
see
[documentation](https://nixtla.github.io/neuralforecast/tsdataset.html).<br />
`test_size`: int=None, test size for temporal cross-validation.<br />
`step_size`: int=1, Step size between each window.<br /> `random_seed`:
int=None, random\_seed for pytorch initializer and numpy generators,
overwrites model.\_\_init\_\_’s.<br /> `quantiles`: list of floats,
optional (default=None), target quantiles to predict. <br />
`**data_module_kwargs`: PL’s TimeSeriesDataModule args, see
[documentation](https://pytorch-lightning.readthedocs.io/en/1.6.1/extensions/datamodules.html#using-a-datamodule).\*

# 2. Usage example

```python theme={null}
import pandas as pd
import matplotlib.pyplot as plt

from neuralforecast import NeuralForecast
from neuralforecast.models import iTransformer
from neuralforecast.utils import AirPassengersPanel, AirPassengersStatic
from neuralforecast.losses.pytorch import MSE

Y_train_df = AirPassengersPanel[AirPassengersPanel.ds<AirPassengersPanel['ds'].values[-12]].reset_index(drop=True) # 132 train
Y_test_df = AirPassengersPanel[AirPassengersPanel.ds>=AirPassengersPanel['ds'].values[-12]].reset_index(drop=True) # 12 test

model = iTransformer(h=12,
                     input_size=24,
                     n_series=2,
                     hidden_size=128,
                     n_heads=2,
                     e_layers=2,
                     d_layers=1,
                     d_ff=4,
                     factor=1,
                     dropout=0.1,
                     use_norm=True,
                     loss=MSE(),
                     valid_loss=MAE(),
                     early_stop_patience_steps=3,
                     batch_size=32,
                     max_steps=100)

fcst = NeuralForecast(models=[model], freq='ME')
fcst.fit(df=Y_train_df, static_df=AirPassengersStatic, val_size=12)
forecasts = fcst.predict(futr_df=Y_test_df)

# Plot predictions
fig, ax = plt.subplots(1, 1, figsize = (20, 7))
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])

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['iTransformer'], c='blue', label='Forecast')
ax.set_title('AirPassengers Forecast', fontsize=22)
ax.set_ylabel('Monthly Passengers', fontsize=20)
ax.set_xlabel('Year', fontsize=20)
ax.legend(prop={'size': 15})
ax.grid()
```