subtask_analysis: Subtask Analysis
In xytangtang/ProcData: Process Data Analysis

Description Usage Arguments Value References See Also

subtask_analysis performs subtask identification procedure.

subtask_analysis(action_seqs, lambda = 0.3, n_subtask, rnn_dim = 20,
  n_epoch = 20, step_size = 0.001, batch_size = 1,
  optimizer_name = "rmsprop", index_valid = 0.2, verbose = FALSE,
  ...)

`action_seqs`	a list of action sequences
`lambda`	a number between 0 and 1
`n_subtask`	the desired number of subtasks or a vector of candidate number of subtasks
`rnn_dim`	latent dimension of RNN
`n_epoch`	the number of training epochs.
`step_size`	the learning rate of optimizer.
`batch_size`	the batch size used in training.
`optimizer_name`	a character string specifying the optimizer to be used for training. Availabel options are `"sgd"`, `"rmsprop"`, `"adadelta"`, and `"adam"`.
`index_valid`	proportion of sequences used as the validation set or a vector of indices specifying the validation set.
`verbose`	logical. If TRUE, training progress is printed.
`...`	additional arguments passed to `kmeans`

an object of class "subtask". It is a list containing

`action_seqs`	a list of action sequences
`entropy_seqs`	a list of entropy sequences
`seg_seqs`	a list of segment boundaries
`subtask_seqs`	a list of subtask sequences
`subtasks`	a vector of subtasks
`n_subtask`	the number of subtasks
`tot.withinss`	a vector of total within cluster sum of squares
`relative_cluster_profiles`	a `n_subtask` by `length(actions)` matrix. Each row gives the action frequency profile of each subtask relative to the overall action frequency profile
`loss_history`	a `n_epoch` by 2 matrix. The two columns contain the loss at the end of each epoch on the training set and the validation set, respectively.
`rnn_dim`	the latent dimension of the recurrent neural network
`model_fit`	a vector of class `"raw"`. It is the serialized version of the trained action prediction model.
`actions`	a vector of the actions in `action_seqs`.
`max_len`	maximum length of the action sequences.