Generalized low rank decomposition of an H2O data frame

Source: R/glrm.R

Builds a generalized low rank decomposition of an H2O data frame

h2o.glrm(
  training_frame,
  cols = NULL,
  model_id = NULL,
  validation_frame = NULL,
  ignore_const_cols = TRUE,
  score_each_iteration = FALSE,
  representation_name = NULL,
  loading_name = NULL,
  transform = c("NONE", "STANDARDIZE", "NORMALIZE", "DEMEAN", "DESCALE"),
  k = 1,
  loss = c("Quadratic", "Absolute", "Huber", "Poisson", "Hinge", "Logistic", "Periodic"),
  loss_by_col = c("Quadratic", "Absolute", "Huber", "Poisson", "Hinge", "Logistic",
    "Periodic", "Categorical", "Ordinal"),
  loss_by_col_idx = NULL,
  multi_loss = c("Categorical", "Ordinal"),
  period = 1,
  regularization_x = c("None", "Quadratic", "L2", "L1", "NonNegative", "OneSparse",
    "UnitOneSparse", "Simplex"),
  regularization_y = c("None", "Quadratic", "L2", "L1", "NonNegative", "OneSparse",
    "UnitOneSparse", "Simplex"),
  gamma_x = 0,
  gamma_y = 0,
  max_iterations = 1000,
  max_updates = 2000,
  init_step_size = 1,
  min_step_size = 1e-04,
  seed = -1,
  init = c("Random", "SVD", "PlusPlus", "User"),
  svd_method = c("GramSVD", "Power", "Randomized"),
  user_y = NULL,
  user_x = NULL,
  expand_user_y = TRUE,
  impute_original = FALSE,
  recover_svd = FALSE,
  max_runtime_secs = 0,
  export_checkpoints_dir = NULL
)

Arguments

training_frame

Id of the training data frame.
cols

(Optional) A vector containing the data columns on which k-means operates.
model_id

Destination id for this model; auto-generated if not specified.
validation_frame

Id of the validation data frame.
ignore_const_cols

Logical. Ignore constant columns. Defaults to TRUE.
score_each_iteration

Logical. Whether to score during each iteration of model training. Defaults to FALSE.
representation_name

Frame key to save resulting X
loading_name

[Deprecated] Use representation_name instead. Frame key to save resulting X.
transform

Transformation of training data Must be one of: "NONE", "STANDARDIZE", "NORMALIZE", "DEMEAN", "DESCALE". Defaults to NONE.
k

Rank of matrix approximation Defaults to 1.
loss

Numeric loss function Must be one of: "Quadratic", "Absolute", "Huber", "Poisson", "Hinge", "Logistic", "Periodic". Defaults to Quadratic.
loss_by_col

Loss function by column (override) Must be one of: "Quadratic", "Absolute", "Huber", "Poisson", "Hinge", "Logistic", "Periodic", "Categorical", "Ordinal".
loss_by_col_idx

Loss function by column index (override)
multi_loss

Categorical loss function Must be one of: "Categorical", "Ordinal". Defaults to Categorical.
period

Length of period (only used with periodic loss function) Defaults to 1.
regularization_x

Regularization function for X matrix Must be one of: "None", "Quadratic", "L2", "L1", "NonNegative", "OneSparse", "UnitOneSparse", "Simplex". Defaults to None.
regularization_y

Regularization function for Y matrix Must be one of: "None", "Quadratic", "L2", "L1", "NonNegative", "OneSparse", "UnitOneSparse", "Simplex". Defaults to None.
gamma_x

Regularization weight on X matrix Defaults to 0.
gamma_y

Regularization weight on Y matrix Defaults to 0.
max_iterations

Maximum number of iterations Defaults to 1000.
max_updates

Maximum number of updates, defaults to 2*max_iterations Defaults to 2000.
init_step_size

Initial step size Defaults to 1.
min_step_size

Minimum step size Defaults to 0.0001.
seed

Seed for random numbers (affects certain parts of the algo that are stochastic and those might or might not be enabled by default). Defaults to -1 (time-based random number).
init

Initialization mode Must be one of: "Random", "SVD", "PlusPlus", "User". Defaults to PlusPlus.
svd_method

Method for computing SVD during initialization (Caution: Randomized is currently experimental and unstable) Must be one of: "GramSVD", "Power", "Randomized". Defaults to Randomized.
user_y

User-specified initial Y
user_x

User-specified initial X
expand_user_y

Logical. Expand categorical columns in user-specified initial Y Defaults to TRUE.
impute_original

Logical. Reconstruct original training data by reversing transform Defaults to FALSE.
recover_svd

Logical. Recover singular values and eigenvectors of XY Defaults to FALSE.
max_runtime_secs

Maximum allowed runtime in seconds for model training. Use 0 to disable. Defaults to 0.
export_checkpoints_dir

Automatically export generated models to this directory.

Value

an object of class H2ODimReductionModel.

References

M. Udell, C. Horn, R. Zadeh, S. Boyd (2014). Generalized Low Rank Models[https://arxiv.org/abs/1410.0342]. Unpublished manuscript, Stanford Electrical Engineering Department. N. Halko, P.G. Martinsson, J.A. Tropp. Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions[https://arxiv.org/abs/0909.4061]. SIAM Rev., Survey and Review section, Vol. 53, num. 2, pp. 217-288, June 2011.

See also

h2o.kmeans, h2o.svd, h2o.prcomp

Examples

if (FALSE) {
library(h2o)
h2o.init()
australia_path <- system.file("extdata", "australia.csv", package = "h2o")
australia <- h2o.uploadFile(path = australia_path)
h2o.glrm(training_frame = australia, k = 5, loss = "Quadratic", regularization_x = "L1",
         gamma_x = 0.5, gamma_y = 0, max_iterations = 1000)
}