LSTMCell¶

Defined in fynance.models.lstm

class LSTMCell(X, y=None, drop=None, x_type=None, y_type=None, bias=True, hidden_activation=nn.Tanh, hidden_state_size=None, memory_activation=nn.Tanh, memory_state_size=None, forget_activation=nn.Sigmoid, update_activation=nn.Sigmoid, output_activation=nn.Sigmoid)[source]

Bases: _LSTMCell

LSTM cell — public composable building block.

Implements the four LSTM gates (forget, input, candidate, output) without an output projection layer. Designed to be composed inside larger architectures (TCN, Transformers, encoder-decoders). For a standalone trainable model with output projection, use LongShortTermMemory.

Parameters:

Xint or array-like: Input dimension (int) or input data. When passing an int, y may be omitted.
yarray-like or int, optional: Output data or output dimension. Not required when using the cell as a building block.
hidden_state_sizeint, optional: Size of the hidden state. Defaults to the input size.
memory_state_sizeint, optional: Size of the cell state. Defaults to hidden state size.
dropfloat, optional: Dropout probability applied before each gate.
hidden_activation, memory_activationtorch.nn.Module, optional: Activations for hidden and cell state (default: Tanh for both).
forget_activation, update_activation, output_activation
torch.nn.Module, optional: Gate activations (default: Sigmoid for all three).

See also

LongShortTermMemory: full model with output projection and training.
fynance.models.gru.GRUCell: GRU variant.

Examples

>>> import torch
>>> from fynance.models.lstm import LSTMCell
>>> cell = LSTMCell(8, hidden_state_size=16)
>>> H = torch.zeros(4, 16)
>>> C = torch.zeros(4, 16)
>>> X = torch.randn(4, 8)
>>> H_new, C_new = cell(X, H, C)
>>> H_new.shape
torch.Size([4, 16])

load_model(path, load_optimizer=False)

Save the model with this weights and parameters.

Parameters:

pathstr or os.PathLike object: Path to load the model.
load_optimizerbool, optional: If True, then load also the optimizer.

save_model(path, save_optimizer=False)

Save the model with this weights and parameters.

Parameters:

pathstr or os.PathLike object: Path to save the model.
save_optimizerbool, optional: If True, then save also the optimizer.

set_data(X, y, x_type=None, y_type=None)

Set data inputs and outputs.

Coerces X and y to torch.Tensor and caches them as self.X / self.y. After the call the attributes self.T (number of observations), self.N (input columns) and self.M (output columns) are set.

Parameters:

X, yarray-like: Respectively input and output data. Accepted types: numpy.ndarray, torch.Tensor, pandas.DataFrame. Shapes must be (T, N) and (T, M) respectively.
x_type, y_typetorch.dtype, optional: Target dtypes for the resulting tensors. Default is None, which preserves the input dtype.

Returns:

BaseNeuralNet: self, to allow chaining.

Raises:

ValueError: If self.N / self.M were already set and X / y do not match, or if X and y have different lengths.

set_lr_scheduler(lr_scheduler, **kwargs)

Set dynamic learning rate.

Parameters:

lr_schedulertorch.optim.lr_scheduler._LRScheduler: Method from torch.optim.lr_scheduler to wrap self.optimizer, cf module torch.optim.lr_scheduler in PyTorch documentation [2].
**kwargs: Keyword arguments to pass to the learning rate scheduler.

References

[2]

https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate

set_optimizer(criterion, optimizer, params=None, **kwargs)

Set the optimizer object.

Set optimizer object with specified criterion as loss function and any kwargs as optional parameters.

Parameters:

criterionCallabletorch.nn.modules.loss: A loss function.
optimizertorch.optim.Optimizer: An optimizer algorithm.
paramsobject or iterable object: Layer of parameters to optimize or dicts defining parameter groups. If set to None then all parameters of model will be optimized. Default is None.
**kwargs: Keyword arguments of optimizer, cf PyTorch documentation [1].

Returns:

BaseNeuralNet: Self object model.

References

[1]

https://pytorch.org/docs/stable/optim.html

set_seed(seed_torch=None, seed_numpy=None)

Set seed for PyTorch and NumPy random number generator.

Parameters:

seed_torch, seed_numpybool or int, optional: If seed is an int \(0 < seed < 2^32\) set respectively PyTorch and NumPy seed with the number. Otherwise if is True then choose a random number, else doesn’t set seed.