orion.primitives.tadgan.TadGAN

class orion.primitives.tadgan.TadGAN(layers_encoder, layers_generator, layers_critic_x, layers_critic_z, optimizer, input_shape=None, target_shape=None, latent_dim=20, learning_rate=0.005, epochs=50, batch_size=64, iterations_critic=5, shuffle=True, detailed_losses=False, verbose=True, **hyperparameters)[source]

TadGAN model for time series reconstruction.

Parameters
  • layers_encoder (list) – List containing layers of encoder.

  • layers_generator (list) – List containing layers of generator.

  • layers_critic_x (list) – List containing layers of critic_x.

  • layers_critic_z (list) – List containing layers of critic_z.

  • input_shape (tuple) – Optional. Tuple denoting the shape of an input sample.

  • latent_dim (int) – Optional. Integer denoting dimension of latent space. Default 20.

  • target_shape (tuple) – Optional. Tuple denoting the shape of an output sample.

  • encoder_input_shape (tuple) – Shape of encoder input.

  • generator_input_shape (tuple) – Shape of generator input.

  • critic_x_input_shape (tuple) – Shape of critic_x input.

  • critic_z_input_shape (tuple) – Shape of critic_z input.

  • optimizer (str) – String denoting the keras optimizer.

  • learning_rate (float) – Optional. Float denoting the learning rate of the optimizer. Default 0.005.

  • epochs (int) – Optional. Integer denoting the number of epochs. Default 50.

  • latent_dim – Optional. Integer denoting dimension of latent space. Default 20.

  • iterations_critic (int) – Optional. Integer denoting the number of critic training steps per one Generator/Encoder training step. Default 5.

  • shuffle (bool) – Whether to shuffle the dataset for each epoch. Default True.

  • verbose (int) – Verbosity mode where 0 = silent, 1 = progress bar, 2 = one line per epoch. Default 0.

  • detailed_losses (bool) – Whether to output all loss values in verbose mode. Default False.

  • **hyperparameters (dict) – Optional. Dictionary containing any additional inputs.

__init__(layers_encoder, layers_generator, layers_critic_x, layers_critic_z, optimizer, input_shape=None, target_shape=None, latent_dim=20, learning_rate=0.005, epochs=50, batch_size=64, iterations_critic=5, shuffle=True, detailed_losses=False, verbose=True, **hyperparameters)[source]

Initialize the TadGAN model.

Methods

__init__(layers_encoder, layers_generator, …)

Initialize the TadGAN model.

fit(X[, y])

Fit the TadGAN model.

predict(X[, y])

Predict using TadGAN model.