Description Usage Arguments Value Examples
High Dimensional Changepoint Detection
1 2 3 4 5 6 | hdcd(x, delta = 0.1, lambda = NULL, lambda_min_ratio = 0.01,
lambda_grid_size = 10, gamma = NULL, method = c("nodewise_regression",
"summed_regression", "ratio_regression"), penalize_diagonal = F,
optimizer = c("line_search", "section_search"), control = NULL,
standardize = T, threshold = 1e-07, n_folds = 10, verbose = T,
parallel = T, FUN = NULL, ...)
|
x |
A n times p matrix or data frame. |
delta |
Numeric value between 0 and 0.5. This tuning parameter determines the minimal segment size proportional to the size of the dataset and hence an upper bound for the number of changepoints (roughly 1/δ). |
lambda |
Positive numeric value. This is the regularization parameter in the single Lasso fits. This value is ignored if FUN is not NULL. |
lambda_min_ratio |
Numeric value between 0 and 1. If the λ_max is determined internally this will pick λ_min = lambda_min_ratio * λ_max. |
lambda_grid_size |
Integer value determining the number of values between λ_min and λ_max to will be equally spaced on a logarithmic scale. |
gamma |
Numeric value or vector. If NULL the full solution path for gamma will be caluclated for every combination of λ and δ |
method |
Which estimator should be used? Possible choices are
This value is ignored if |
penalize_diagonal |
Boolean, should the diagonal elements of the precision matrix be penalized by λ? This value is ignored if FUN is not NULL. |
optimizer |
Which search technique should be used for performing individual splits in the binary segmentation alogrithm? Possible choices are
|
control |
A list with parameters that is accessed by the selected optimizer:
|
standardize |
Boolean. If TRUE the penalty parameter λ will be adjusted for every dimension in the single Lasso fits according to the standard deviation in the data. |
threshold |
The threshold for halting the iteration in
|
n_folds |
Number of folds. Test data will be selected equi-spaced, i.e. each n_fold-th observation. |
verbose |
Boolean. If TRUE additional information will be printed. |
parallel |
If TRUE and a parallel backend is registered, the cross-validation will be performed in parallel. |
FUN |
A loss function with formal arguments, |
... |
Supply additional arguments for a specific method (e.g. |
For a single fit a list with elements
A numeric list with the indices of the changepoints
The fully grown binary tree
For cross-validation a list with elements
#'
A numeric list with the indices of the changepoints
A multi-dimensional array with the cross-validation results
Best gamma value
Best lambda value
Best delta value
If only a single fit was performed a list with the found changepoints as well as the fully grown binary tree are returned. For cross-validation the a list with the found changepopints, the optimal parameter values and the full results is returned.
1 2 3 4 5 | dat <- SimulateFromModel(CreateModel(n_segments = 2,n = 100,p = 30, ChainNetwork))
## Not run:
hdcd(dat, 0.1, 0.1, 0.05, method = "summed_regression", verbose = T)
## End(Not run)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.