TimesNet

TimesNet: 2D-variation modeling with Inception blocks for capturing intraperiod and interperiod temporal patterns in univariate time series forecasting.

The TimesNet univariate model tackles the challenge of modeling multiple intraperiod and interperiod temporal variations.

The architecture has the following distinctive features: - An embedding layer that maps the input sequence into a latent space. - Transformation of 1D time seires into 2D tensors, based on periods found by FFT. - A convolutional Inception block that captures temporal variations at different scales and between periods.

References

• Haixu Wu and Tengge Hu and Yong Liu and Hang Zhou and Jianmin Wang and Mingsheng Long. TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis - Based on the implementation in https://github.com/thuml/Time-Series-Library (license: https://github.com/thuml/Time-Series-Library/blob/main/LICENSE)

Figure 1. TimesNet Architecture.

1. TimesNet

TimesNet

TimesNet(
    h,
    input_size,
    stat_exog_list=None,
    hist_exog_list=None,
    futr_exog_list=None,
    exclude_insample_y=False,
    hidden_size=64,
    dropout=0.1,
    conv_hidden_size=64,
    top_k=5,
    num_kernels=6,
    encoder_layers=2,
    loss=MAE(),
    valid_loss=None,
    max_steps=1000,
    learning_rate=0.0001,
    num_lr_decays=-1,
    early_stop_patience_steps=-1,
    val_check_steps=100,
    batch_size=32,
    valid_batch_size=None,
    windows_batch_size=64,
    inference_windows_batch_size=256,
    start_padding_enabled=False,
    training_data_availability_threshold=0.0,
    step_size=1,
    scaler_type="standard",
    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: BaseModel

TimesNet

The TimesNet univariate model tackles the challenge of modeling multiple intraperiod and interperiod temporal variations.

Parameters:

Name	Type	Description	Default
h	int	Forecast horizon.	required
input_size	int	Length of input window (lags).	required
stat_exog_list	list of str	optional (default=None), Static exogenous columns.	None
hist_exog_list	list of str	optional (default=None), Historic exogenous columns.	None
futr_exog_list	list of str	optional (default=None), Future exogenous columns.	None
exclude_insample_y	bool	The model skips the autoregressive features y[t-input_size:t] if True.	False
hidden_size	int	Size of embedding for embedding and encoders.	64
dropout	float	Dropout for embeddings.	0.1
conv_hidden_size	int	Channels of the Inception block.	64
top_k	int	Number of periods.	5
num_kernels	int	Number of kernels for the Inception block.	6
encoder_layers	int	Number of encoder layers.	2
loss	PyTorch module	Instantiated train loss class from losses collection.	MAE()
valid_loss	PyTorch module	Instantiated validation loss class from losses collection.	None
max_steps	int	Maximum number of training steps.	1000
learning_rate	float	Learning rate.	0.0001
num_lr_decays	int	Number of learning rate decays, evenly distributed across max_steps. If -1, no learning rate decay is performed.	-1
early_stop_patience_steps	int	Number of validation iterations before early stopping. If -1, no early stopping is performed.	-1
val_check_steps	int	Number of training steps between every validation loss check.	100
batch_size	int	Number of different series in each batch.	32
valid_batch_size	int	Number of different series in each validation and test batch, if None uses batch_size.	None
windows_batch_size	int	Number of windows to sample in each training batch.	64
inference_windows_batch_size	int	Number of windows to sample in each inference batch.	256
start_padding_enabled	bool	If True, the model will pad the time series with zeros at the beginning by input size.	False
training_data_availability_threshold	Union[float, List[float]]	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).	0.0
step_size	int	Step size between each window of temporal data.	1
scaler_type	str	Type of scaler for temporal inputs normalization see temporal scalers.	‘standard’
random_seed	int	Random_seed for pytorch initializer and numpy generators.	1
drop_last_loader	bool	If True TimeSeriesDataLoader drops last non-full batch.	False
alias	str	optional (default=None), Custom name of the model.	None
optimizer	Subclass of ‘torch.optim.Optimizer’	optional (default=None), User specified optimizer instead of the default choice (Adam).	None
optimizer_kwargs	dict	optional (defualt=None), List of parameters used by the user specified optimizer.	None
lr_scheduler	Subclass of ‘torch.optim.lr_scheduler.LRScheduler’	optional, user specified lr_scheduler instead of the default choice (StepLR).	None
lr_scheduler_kwargs	dict	optional, list of parameters used by the user specified lr_scheduler.	None
dataloader_kwargs	dict	optional (default=None), List of parameters passed into the PyTorch Lightning dataloader by the TimeSeriesDataLoader.	None
**trainer_kwargs	int	keyword trainer arguments inherited from PyTorch Lighning’s trainer.

TimesNet.fit

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.

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	TimeSeriesDataset	NeuralForecast’s TimeSeriesDataset, see documentation.	required
val_size	int	Validation size for temporal cross-validation.	0
random_seed	int	Random seed for pytorch initializer and numpy generators, overwrites model.init’s.	None
test_size	int	Test size for temporal cross-validation.	0

Returns:

Type	Description
None

TimesNet.predict

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	TimeSeriesDataset	NeuralForecast’s TimeSeriesDataset, see documentation.	required
test_size	int	Test size for temporal cross-validation.	None
step_size	int	Step size between each window.	1
random_seed	int	Random seed for pytorch initializer and numpy generators, overwrites model.init’s.	None
quantiles	list	Target quantiles to predict.	None
h	int	Prediction horizon, if None, uses the model’s fitted horizon. Defaults to None.	None
explainer_config	dict	configuration for explanations.	None
**data_module_kwargs	dict	PL’s TimeSeriesDataModule args, see documentation.

Returns:

Type	Description
None

Usage Example

import pandas as pd
import matplotlib.pyplot as plt

from neuralforecast import NeuralForecast
from neuralforecast.losses.pytorch import DistributionLoss
from neuralforecast.utils import AirPassengersPanel, AirPassengersStatic

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 = TimesNet(h=12,
                 input_size=24,
                 hidden_size = 16,
                 conv_hidden_size = 32,
                 loss=DistributionLoss(distribution='Normal', level=[80, 90]),
                 scaler_type='standard',
                 learning_rate=1e-3,
                 max_steps=100,
                 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['TimesNet-median'], c='blue', label='median')
    plt.fill_between(x=plot_df['ds'][-12:], 
                    y1=plot_df['TimesNet-lo-90'][-12:].values, 
                    y2=plot_df['TimesNet-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['TimesNet'], c='blue', label='Forecast')
    plt.legend()
    plt.grid()

2. Auxiliary Functions

Inception_Block_V1

Inception_Block_V1(in_channels, out_channels, num_kernels=6, init_weight=True)

Bases: Module

Inception_Block_V1

TimesBlock

TimesBlock(input_size, h, k, hidden_size, conv_hidden_size, num_kernels)

Bases: Module

TimesBlock

FFT_for_Period

FFT_for_Period(x, k=2)