> ## Documentation Index
> Fetch the complete documentation index at: https://nixtlaverse.nixtla.io/llms.txt
> Use this file to discover all available pages before exploring further.

> TimeXer: Cross-series attention transformer for multivariate forecasting with patch-based processing and exogenous variable support for complex temporal patterns.

# TimeXer

<img src="https://mintcdn.com/nixtla/wOkzptAA8LlzXeB0/neuralforecast/imgs_models/timexer.png?fit=max&auto=format&n=wOkzptAA8LlzXeB0&q=85&s=64a056a3a9d7741b1fa7e86a47993f42" alt="Figure 1. Architecture of TimeXer." width="1994" height="914" data-path="neuralforecast/imgs_models/timexer.png" />

*Figure 1. Architecture of TimeXer.*

## 1. TimeXer

### `TimeXer`

```python theme={null}
TimeXer(
    h,
    input_size,
    n_series,
    futr_exog_list=None,
    hist_exog_list=None,
    stat_exog_list=None,
    cat_exog_list=None,
    categorical_cardinalities=None,
    cat_emb_dim="fastai",
    exclude_insample_y=False,
    patch_len=16,
    hidden_size=512,
    n_heads=8,
    e_layers=2,
    d_ff=2048,
    factor=1,
    dropout=0.1,
    use_norm=True,
    loss=MAE(),
    valid_loss=None,
    max_steps=1000,
    learning_rate=0.001,
    num_lr_decays=-1,
    early_stop_patience_steps=-1,
    val_monitor="ptl/val_loss",
    val_check_steps=100,
    batch_size=32,
    valid_batch_size=None,
    windows_batch_size=32,
    inference_windows_batch_size=32,
    start_padding_enabled=False,
    training_data_availability_threshold=0.0,
    step_size=1,
    scaler_type="identity",
    random_seed=1,
    drop_last_loader=False,
    alias=None,
    optimizer=None,
    optimizer_kwargs=None,
    lr_scheduler=None,
    lr_scheduler_kwargs=None,
    dataloader_kwargs=None,
    **trainer_kwargs
)
```

Bases: <code>[BaseModel](#neuralforecast.common._base_model.BaseModel)</code>

TimeXer

**Parameters:**

| Name | Type | Description | Default |
| - | - | - | - |
| `h` | <code>[int](#int)</code> | Forecast horizon. | *required* |
| `input_size` | <code>[int](#int)</code> | autorregresive inputs size, y=\[1,2,3,4] input\_size=2 -> y\_\[t-2:t]=\[1,2]. | *required* |
| `n_series` | <code>[int](#int)</code> | number of time-series. | *required* |
| `futr_exog_list` | <code>str list</code> | future exogenous columns. | <code>None</code> |
| `hist_exog_list` | <code>str list</code> | historic exogenous columns. | <code>None</code> |
| `stat_exog_list` | <code>str list</code> | static exogenous columns. | <code>None</code> |
| `cat_exog_list` | <code>str list</code> | exogenous columns (from `hist_exog_list` / `stat_exog_list`) to embed instead of scale. | <code>None</code> |
| `categorical_cardinalities` | <code>[dict](#dict)</code> | mapping from each categorical column to its number of distinct categories. | <code>None</code> |
| `cat_emb_dim` | <code>[str](#str) or [int](#int)</code> | categorical embedding size strategy ('fastai', 'sqrt', 'half') or an explicit integer. | <code>'fastai'</code> |
| `patch_len` | <code>[int](#int)</code> | length of patches. | <code>16</code> |
| `hidden_size` | <code>[int](#int)</code> | dimension of the model. | <code>512</code> |
| `n_heads` | <code>[int](#int)</code> | number of heads. | <code>8</code> |
| `e_layers` | <code>[int](#int)</code> | number of encoder layers. | <code>2</code> |
| `d_ff` | <code>[int](#int)</code> | dimension of fully-connected layer. | <code>2048</code> |
| `factor` | <code>[int](#int)</code> | attention factor. | <code>1</code> |
| `dropout` | <code>[float](#float)</code> | dropout rate. | <code>0.1</code> |
| `use_norm` | <code>[bool](#bool)</code> | whether to normalize or not. | <code>True</code> |
| `loss` | <code>PyTorch module</code> | instantiated train loss class from [losses collection](./losses.pytorch.html). | <code>[MAE](#neuralforecast.losses.pytorch.MAE)()</code> |
| `valid_loss` | <code>PyTorch module</code> | instantiated valid loss class from [losses collection](./losses.pytorch.html). | <code>None</code> |
| `max_steps` | <code>[int](#int)</code> | maximum number of training steps. | <code>1000</code> |
| `learning_rate` | <code>[float](#float)</code> | Learning rate between (0, 1). | <code>0.001</code> |
| `num_lr_decays` | <code>[int](#int)</code> | Number of learning rate decays, evenly distributed across max\_steps. | <code>-1</code> |
| `early_stop_patience_steps` | <code>[int](#int)</code> | Number of validation iterations before early stopping. | <code>-1</code> |
| `val_monitor` | <code>[str](#str)</code> | metric to monitor for early stopping. Valid options: "ptl/val\_loss", "valid\_loss", "train\_loss". Default: "ptl/val\_loss". | <code>'ptl/val\_loss'</code> |
| `val_check_steps` | <code>[int](#int)</code> | Number of training steps between every validation loss check. | <code>100</code> |
| `batch_size` | <code>[int](#int)</code> | number of different series in each batch. | <code>32</code> |
| `valid_batch_size` | <code>[int](#int)</code> | number of different series in each validation and test batch, if None uses batch\_size. | <code>None</code> |
| `windows_batch_size` | <code>[int](#int)</code> | number of windows in each batch. | <code>32</code> |
| `inference_windows_batch_size` | <code>[int](#int)</code> | number of windows to sample in each inference batch, -1 uses all. | <code>32</code> |
| `start_padding_enabled` | <code>[bool](#bool)</code> | if True, the model will pad the time series with zeros at the beginning, by input size. | <code>False</code> |
| `training_data_availability_threshold` | <code>[Union](#Union)\[[float](#float), [List](#List)\[[float](#float)]]</code> | minimum fraction of valid data points required for training windows. Single float applies to both insample and outsample; list of two floats specifies \[insample\_fraction, outsample\_fraction]. Default 0.0 allows windows with only 1 valid data point (current behavior). | <code>0.0</code> |
| `step_size` | <code>[int](#int)</code> | step size between each window of temporal data. | <code>1</code> |
| `scaler_type` | <code>[str](#str)</code> | type of scaler for temporal inputs normalization see [temporal scalers](https://github.com/Nixtla/neuralforecast/blob/main/neuralforecast/common/_scalers.py). | <code>'identity'</code> |
| `random_seed` | <code>[int](#int)</code> | random\_seed for pytorch initializer and numpy generators. | <code>1</code> |
| `drop_last_loader` | <code>[bool](#bool)</code> | if True `TimeSeriesDataLoader` drops last non-full batch. | <code>False</code> |
| `alias` | <code>[str](#str)</code> | optional, Custom name of the model. | <code>None</code> |
| `optimizer` | <code>Subclass of 'torch.optim.Optimizer'</code> | optional, user specified optimizer instead of the default choice (Adam). | <code>None</code> |
| `optimizer_kwargs` | <code>[dict](#dict)</code> | optional, list of parameters used by the user specified `optimizer`. | <code>None</code> |
| `lr_scheduler` | <code>Subclass of 'torch.optim.lr\_scheduler.LRScheduler'</code> | optional, user specified lr\_scheduler instead of the default choice (StepLR). | <code>None</code> |
| `lr_scheduler_kwargs` | <code>[dict](#dict)</code> | optional, list of parameters used by the user specified `lr_scheduler`. | <code>None</code> |
| `dataloader_kwargs` | <code>[dict](#dict)</code> | optional, list of parameters passed into the PyTorch Lightning dataloader by the `TimeSeriesDataLoader`. | <code>None</code> |
| `**trainer_kwargs` | <code>[int](#int)</code> | keyword trainer arguments inherited from [PyTorch Lightning's trainer](https://pytorch-lightning.readthedocs.io/en/stable/api/pytorch_lightning.trainer.trainer.Trainer.html?highlight=trainer). | <code>{}</code> |

<details class="references" open markdown="1">
  <summary>References</summary>

  * [Yuxuan Wang, Haixu Wu, Jiaxiang Dong, Guo Qin, Haoran Zhang, Yong Liu, Yunzhong Qiu, Jianmin Wang, Mingsheng Long. "TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables"](https://arxiv.org/abs/2402.19072)
</details>

#### `TimeXer.fit`

```python theme={null}
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:**

| Name | Type | Description | Default |
| - | - | - | - |
| `dataset` | <code>[TimeSeriesDataset](#TimeSeriesDataset)</code> | NeuralForecast's `TimeSeriesDataset`, see [documentation](./tsdataset.html). | *required* |
| `val_size` | <code>[int](#int)</code> | Validation size for temporal cross-validation. | <code>0</code> |
| `random_seed` | <code>[int](#int)</code> | Random seed for pytorch initializer and numpy generators, overwrites model.**init**'s. | <code>None</code> |
| `test_size` | <code>[int](#int)</code> | Test size for temporal cross-validation. | <code>0</code> |

**Returns:**

| Type | Description |
| - | - |
| None | |

#### `TimeXer.predict`

```python theme={null}
predict(
    dataset,
    test_size=None,
    step_size=1,
    random_seed=None,
    quantiles=None,
    h=None,
    explainer_config=None,
    **data_module_kwargs
)
```

Predict.

Neural network prediction with PL's `Trainer` execution of `predict_step`.

**Parameters:**

| Name | Type | Description | Default |
| - | - | - | - |
| `dataset` | <code>[TimeSeriesDataset](#TimeSeriesDataset)</code> | NeuralForecast's `TimeSeriesDataset`, see [documentation](./tsdataset.html). | *required* |
| `test_size` | <code>[int](#int)</code> | Test size for temporal cross-validation. | <code>None</code> |
| `step_size` | <code>[int](#int)</code> | Step size between each window. | <code>1</code> |
| `random_seed` | <code>[int](#int)</code> | Random seed for pytorch initializer and numpy generators, overwrites model.**init**'s. | <code>None</code> |
| `quantiles` | <code>[list](#list)</code> | Target quantiles to predict. | <code>None</code> |
| `h` | <code>[int](#int)</code> | Prediction horizon, if None, uses the model's fitted horizon. Defaults to None. | <code>None</code> |
| `explainer_config` | <code>[dict](#dict)</code> | configuration for explanations. | <code>None</code> |
| `**data_module_kwargs` | <code>[dict](#dict)</code> | PL's TimeSeriesDataModule args, see [documentation](https://pytorch-lightning.readthedocs.io/en/1.6.1/extensions/datamodules.html#using-a-datamodule). | <code>{}</code> |

**Returns:**

| Type | Description |
| - | - |
| None | |

### Usage example

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

from neuralforecast import NeuralForecast
from neuralforecast.models import TimeXer
from neuralforecast.losses.pytorch import MAE, MSE
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]] # 132 train
Y_test_df = AirPassengersPanel[AirPassengersPanel.ds>=AirPassengersPanel['ds'].values[-12]].reset_index(drop=True) # 12 test

model = TimeXer(h=12,
                input_size=24,
                n_series=2,
                stat_exog_list=['airline1'],
                patch_len=12,
                hidden_size=128,
                n_heads=16,
                e_layers=2,
                d_ff=256,
                factor=1,
                dropout=0.1,
                use_norm=True,
                loss=MSE(),
                valid_loss=MAE(),
                early_stop_patience_steps=3,
                batch_size=32)

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['TimeXer'], 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()
```

## 2. Auxiliary Functions

### `FlattenHead`

```python theme={null}
FlattenHead(n_vars, nf, target_window, head_dropout=0)
```

Bases: <code>[Module](#torch.nn.Module)</code>

### `Encoder`

```python theme={null}
Encoder(layers, norm_layer=None, projection=None)
```

Bases: <code>[Module](#torch.nn.Module)</code>

### `EncoderLayer`

```python theme={null}
EncoderLayer(
    self_attention,
    cross_attention,
    d_model,
    d_ff=None,
    dropout=0.1,
    activation="relu",
)
```

Bases: <code>[Module](#torch.nn.Module)</code>

### `EnEmbedding`

```python theme={null}
EnEmbedding(n_vars, d_model, patch_len, dropout)
```

Bases: <code>[Module](#torch.nn.Module)</code>


## Related topics

- [NN Modules](/neuralforecast/common.modules.html.md)
- [Forecasting Models](/neuralforecast/docs/capabilities/overview.html.md)
- [Automatic Forecasting](/neuralforecast/models.html.md)
- [Time-LLM](/neuralforecast/models.timellm.html.md)
- [TimesNet](/neuralforecast/models.timesnet.html.md)