dsipts.models.LinearTS module

class dsipts.models.LinearTS.moving_avg(kernel_size, stride)

Bases: Module

Moving average block to highlight the trend of time series

Initialize internal Module state, shared by both nn.Module and ScriptModule.

__init__(kernel_size, stride)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class dsipts.models.LinearTS.series_decomp(kernel_size)

Bases: Module

Series decomposition block

Initialize internal Module state, shared by both nn.Module and ScriptModule.

__init__(kernel_size)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class dsipts.models.LinearTS.LinearTS(past_steps, future_steps, past_channels, future_channels, embs, cat_emb_dim, kernel_size, sum_emb, out_channels, hidden_size, dropout_rate=0.1, activation='torch.nn.ReLU', kind='linear', use_bn=False, persistence_weight=0.0, loss_type='l1', quantiles=[], n_classes=0, optim=None, optim_config=None, scheduler_config=None, simple=False, **kwargs)

Bases: Base

Linear model from https://github.com/cure-lab/LTSF-Linear/blob/main/run_longExp.py

Parameters:

• past_steps (int) – number of past datapoints used

• future_steps (int) – number of future lag to predict

• past_channels (int) – number of numeric past variables, must be >0

• future_channels (int) – number of future numeric variables

• embs (List[int]) – list of the initial dimension of the categorical variables

• cat_emb_dim (int) – final dimension of each categorical variable

• kernel_size (int) – kernel dimension for initial moving average

• sum_emb (bool) – if true the contribution of each embedding will be summed-up otherwise stacked

• out_channels (int) – number of output channels

• hidden_size (int) – hidden size of the lienar block

• dropout_rate (float, optional) – dropout rate in Dropout layers. Default 0.1

• activation (str, optional) – activation fuction function pytorch. Default torch.nn.ReLU

• kind (str, optional) – one among linear, dlinear (de-trending), nlinear (differential). Defaults to ‘linear’.

• use_bn (bool, optional) – if true BN layers will be added and dropouts will be removed. Default False

• quantiles (List[int], optional) – we can use quantile loss il len(quantiles) = 0 (usually 0.1,0.5, 0.9) or L1loss in case len(quantiles)==0. Defaults to [].

• persistence_weight (float) – weight controlling the divergence from persistence model. Default 0

• loss_type (str, optional) – this model uses custom losses or l1 or mse. Custom losses can be linear_penalization or exponential_penalization. Default l1,

• n_classes (int) – number of classes (0 in regression)

• optim (str, optional) – if not None it expects a pytorch optim method. Defaults to None that is mapped to Adam.

• optim_config (dict, optional) – configuration for Adam optimizer. Defaults to None.

• scheduler_config (dict, optional) – configuration for stepLR scheduler. Defaults to None.

• simple (bool, optional) – if simple, the model used is the same that the one illustrated in the paper, otherwise it is a more complicated one with the same idea

handle_multivariate = True

handle_future_covariates = True

handle_categorical_variables = True

handle_quantile_loss = True

description = 'Can   handle multivariate output \nCan   handle future covariates\nCan   handle categorical covariates\nCan   handle Quantile loss function\n THE SIMPLE IMPLEMENTATION DOES NOT USE CATEGORICAL NOR FUTURE VARIABLES'

__init__(past_steps, future_steps, past_channels, future_channels, embs, cat_emb_dim, kernel_size, sum_emb, out_channels, hidden_size, dropout_rate=0.1, activation='torch.nn.ReLU', kind='linear', use_bn=False, persistence_weight=0.0, loss_type='l1', quantiles=[], n_classes=0, optim=None, optim_config=None, scheduler_config=None, simple=False, **kwargs)

Linear model from https://github.com/cure-lab/LTSF-Linear/blob/main/run_longExp.py

Parameters:

• past_steps (int) – number of past datapoints used

• future_steps (int) – number of future lag to predict

• past_channels (int) – number of numeric past variables, must be >0

• future_channels (int) – number of future numeric variables

• embs (List[int]) – list of the initial dimension of the categorical variables

• cat_emb_dim (int) – final dimension of each categorical variable

• kernel_size (int) – kernel dimension for initial moving average

• sum_emb (bool) – if true the contribution of each embedding will be summed-up otherwise stacked

• out_channels (int) – number of output channels

• hidden_size (int) – hidden size of the lienar block

• dropout_rate (float, optional) – dropout rate in Dropout layers. Default 0.1

• activation (str, optional) – activation fuction function pytorch. Default torch.nn.ReLU

• kind (str, optional) – one among linear, dlinear (de-trending), nlinear (differential). Defaults to ‘linear’.

• use_bn (bool, optional) – if true BN layers will be added and dropouts will be removed. Default False

• quantiles (List[int], optional) – we can use quantile loss il len(quantiles) = 0 (usually 0.1,0.5, 0.9) or L1loss in case len(quantiles)==0. Defaults to [].

• persistence_weight (float) – weight controlling the divergence from persistence model. Default 0

• loss_type (str, optional) – this model uses custom losses or l1 or mse. Custom losses can be linear_penalization or exponential_penalization. Default l1,

• n_classes (int) – number of classes (0 in regression)

• optim (str, optional) – if not None it expects a pytorch optim method. Defaults to None that is mapped to Adam.

• optim_config (dict, optional) – configuration for Adam optimizer. Defaults to None.

• scheduler_config (dict, optional) – configuration for stepLR scheduler. Defaults to None.

• simple (bool, optional) – if simple, the model used is the same that the one illustrated in the paper, otherwise it is a more complicated one with the same idea

forward(batch)

Forlward method used during the training loop

Parameters:

batch (dict) – the batch structure. The keys are: y : the target variable(s). This is always present x_num_past: the numerical past variables. This is always present x_num_future: the numerical future variables x_cat_past: the categorical past variables x_cat_future: the categorical future variables idx_target: index of target features in the past array

Returns:

output of the mode;

Return type:

torch.tensor