Builds a feed-forward multilayer artificial neural network on an H2OFrame.
h2o.deeplearning( x, y, training_frame, model_id = NULL, validation_frame = NULL, nfolds = 0, keep_cross_validation_models = TRUE, keep_cross_validation_predictions = FALSE, keep_cross_validation_fold_assignment = FALSE, fold_assignment = c("AUTO", "Random", "Modulo", "Stratified"), fold_column = NULL, ignore_const_cols = TRUE, score_each_iteration = FALSE, weights_column = NULL, offset_column = NULL, balance_classes = FALSE, class_sampling_factors = NULL, max_after_balance_size = 5, checkpoint = NULL, pretrained_autoencoder = NULL, overwrite_with_best_model = TRUE, use_all_factor_levels = TRUE, standardize = TRUE, activation = c("Tanh", "TanhWithDropout", "Rectifier", "RectifierWithDropout", "Maxout", "MaxoutWithDropout"), hidden = c(200, 200), epochs = 10, train_samples_per_iteration = -2, target_ratio_comm_to_comp = 0.05, seed = -1, adaptive_rate = TRUE, rho = 0.99, epsilon = 1e-08, rate = 0.005, rate_annealing = 1e-06, rate_decay = 1, momentum_start = 0, momentum_ramp = 1e+06, momentum_stable = 0, nesterov_accelerated_gradient = TRUE, input_dropout_ratio = 0, hidden_dropout_ratios = NULL, l1 = 0, l2 = 0, max_w2 = 3.4028235e+38, initial_weight_distribution = c("UniformAdaptive", "Uniform", "Normal"), initial_weight_scale = 1, initial_weights = NULL, initial_biases = NULL, loss = c("Automatic", "CrossEntropy", "Quadratic", "Huber", "Absolute", "Quantile"), distribution = c("AUTO", "bernoulli", "multinomial", "gaussian", "poisson", "gamma", "tweedie", "laplace", "quantile", "huber"), quantile_alpha = 0.5, tweedie_power = 1.5, huber_alpha = 0.9, score_interval = 5, score_training_samples = 10000, score_validation_samples = 0, score_duty_cycle = 0.1, classification_stop = 0, regression_stop = 1e-06, stopping_rounds = 5, stopping_metric = c("AUTO", "deviance", "logloss", "MSE", "RMSE", "MAE", "RMSLE", "AUC", "AUCPR", "lift_top_group", "misclassification", "mean_per_class_error", "custom", "custom_increasing"), stopping_tolerance = 0, max_runtime_secs = 0, score_validation_sampling = c("Uniform", "Stratified"), diagnostics = TRUE, fast_mode = TRUE, force_load_balance = TRUE, variable_importances = TRUE, replicate_training_data = TRUE, single_node_mode = FALSE, shuffle_training_data = FALSE, missing_values_handling = c("MeanImputation", "Skip"), quiet_mode = FALSE, autoencoder = FALSE, sparse = FALSE, col_major = FALSE, average_activation = 0, sparsity_beta = 0, max_categorical_features = 2147483647, reproducible = FALSE, export_weights_and_biases = FALSE, mini_batch_size = 1, categorical_encoding = c("AUTO", "Enum", "OneHotInternal", "OneHotExplicit", "Binary", "Eigen", "LabelEncoder", "SortByResponse", "EnumLimited"), elastic_averaging = FALSE, elastic_averaging_moving_rate = 0.9, elastic_averaging_regularization = 0.001, export_checkpoints_dir = NULL, auc_type = c("AUTO", "NONE", "MACRO_OVR", "WEIGHTED_OVR", "MACRO_OVO", "WEIGHTED_OVO"), verbose = FALSE )
x | (Optional) A vector containing the names or indices of the predictor variables to use in building the model. If x is missing, then all columns except y are used. |
---|---|
y | The name or column index of the response variable in the data. The response must be either a numeric or a categorical/factor variable. If the response is numeric, then a regression model will be trained, otherwise it will train a classification model. |
training_frame | Id of the training data frame. |
model_id | Destination id for this model; auto-generated if not specified. |
validation_frame | Id of the validation data frame. |
nfolds | Number of folds for K-fold cross-validation (0 to disable or >= 2). Defaults to 0. |
keep_cross_validation_models |
|
keep_cross_validation_predictions |
|
keep_cross_validation_fold_assignment |
|
fold_assignment | Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified' option will stratify the folds based on the response variable, for classification problems. Must be one of: "AUTO", "Random", "Modulo", "Stratified". Defaults to AUTO. |
fold_column | Column with cross-validation fold index assignment per observation. |
ignore_const_cols |
|
score_each_iteration |
|
weights_column | Column with observation weights. Giving some observation a weight of zero is equivalent to excluding it from the dataset; giving an observation a relative weight of 2 is equivalent to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row observation weights and do not increase the size of the data frame. This is typically the number of times a row is repeated, but non-integer values are supported as well. During training, rows with higher weights matter more, due to the larger loss function pre-factor. If you set weight = 0 for a row, the returned prediction frame at that row is zero and this is incorrect. To get an accurate prediction, remove all rows with weight == 0. |
offset_column | Offset column. This will be added to the combination of columns before applying the link function. |
balance_classes |
|
class_sampling_factors | Desired over/under-sampling ratios per class (in lexicographic order). If not specified, sampling factors will be automatically computed to obtain class balance during training. Requires balance_classes. |
max_after_balance_size | Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires balance_classes. Defaults to 5.0. |
checkpoint | Model checkpoint to resume training with. |
pretrained_autoencoder | Pretrained autoencoder model to initialize this model with. |
overwrite_with_best_model |
|
use_all_factor_levels |
|
standardize |
|
activation | Activation function. Must be one of: "Tanh", "TanhWithDropout", "Rectifier", "RectifierWithDropout", "Maxout", "MaxoutWithDropout". Defaults to Rectifier. |
hidden | Hidden layer sizes (e.g. [100, 100]). Defaults to c(200, 200). |
epochs | How many times the dataset should be iterated (streamed), can be fractional. Defaults to 10. |
train_samples_per_iteration | Number of training samples (globally) per MapReduce iteration. Special values are 0: one epoch, -1: all available data (e.g., replicated training data), -2: automatic. Defaults to -2. |
target_ratio_comm_to_comp | Target ratio of communication overhead to computation. Only for multi-node operation and train_samples_per_iteration = -2 (auto-tuning). Defaults to 0.05. |
seed | Seed for random numbers (affects certain parts of the algo that are stochastic and those might or might not be enabled by default). Note: only reproducible when running single threaded. Defaults to -1 (time-based random number). |
adaptive_rate |
|
rho | Adaptive learning rate time decay factor (similarity to prior updates). Defaults to 0.99. |
epsilon | Adaptive learning rate smoothing factor (to avoid divisions by zero and allow progress). Defaults to 1e-08. |
rate | Learning rate (higher => less stable, lower => slower convergence). Defaults to 0.005. |
rate_annealing | Learning rate annealing: rate / (1 + rate_annealing * samples). Defaults to 1e-06. |
rate_decay | Learning rate decay factor between layers (N-th layer: rate * rate_decay ^ (n - 1). Defaults to 1. |
momentum_start | Initial momentum at the beginning of training (try 0.5). Defaults to 0. |
momentum_ramp | Number of training samples for which momentum increases. Defaults to 1000000. |
momentum_stable | Final momentum after the ramp is over (try 0.99). Defaults to 0. |
nesterov_accelerated_gradient |
|
input_dropout_ratio | Input layer dropout ratio (can improve generalization, try 0.1 or 0.2). Defaults to 0. |
hidden_dropout_ratios | Hidden layer dropout ratios (can improve generalization), specify one value per hidden layer, defaults to 0.5. |
l1 | L1 regularization (can add stability and improve generalization, causes many weights to become 0). Defaults to 0. |
l2 | L2 regularization (can add stability and improve generalization, causes many weights to be small. Defaults to 0. |
max_w2 | Constraint for squared sum of incoming weights per unit (e.g. for Rectifier). Defaults to 3.4028235e+38. |
initial_weight_distribution | Initial weight distribution. Must be one of: "UniformAdaptive", "Uniform", "Normal". Defaults to UniformAdaptive. |
initial_weight_scale | Uniform: -value...value, Normal: stddev. Defaults to 1. |
initial_weights | A list of H2OFrame ids to initialize the weight matrices of this model with. |
initial_biases | A list of H2OFrame ids to initialize the bias vectors of this model with. |
loss | Loss function. Must be one of: "Automatic", "CrossEntropy", "Quadratic", "Huber", "Absolute", "Quantile". Defaults to Automatic. |
distribution | Distribution function Must be one of: "AUTO", "bernoulli", "multinomial", "gaussian", "poisson", "gamma", "tweedie", "laplace", "quantile", "huber". Defaults to AUTO. |
quantile_alpha | Desired quantile for Quantile regression, must be between 0 and 1. Defaults to 0.5. |
tweedie_power | Tweedie power for Tweedie regression, must be between 1 and 2. Defaults to 1.5. |
huber_alpha | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). Defaults to 0.9. |
score_interval | Shortest time interval (in seconds) between model scoring. Defaults to 5. |
score_training_samples | Number of training set samples for scoring (0 for all). Defaults to 10000. |
score_validation_samples | Number of validation set samples for scoring (0 for all). Defaults to 0. |
score_duty_cycle | Maximum duty cycle fraction for scoring (lower: more training, higher: more scoring). Defaults to 0.1. |
classification_stop | Stopping criterion for classification error fraction on training data (-1 to disable). Defaults to 0. |
regression_stop | Stopping criterion for regression error (MSE) on training data (-1 to disable). Defaults to 1e-06. |
stopping_rounds | Early stopping based on convergence of stopping_metric. Stop if simple moving average of length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0 to disable) Defaults to 5. |
stopping_metric | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression and anonomaly_score for Isolation Forest). Note that custom and custom_increasing can only be used in GBM and DRF with the Python client. Must be one of: "AUTO", "deviance", "logloss", "MSE", "RMSE", "MAE", "RMSLE", "AUC", "AUCPR", "lift_top_group", "misclassification", "mean_per_class_error", "custom", "custom_increasing". Defaults to AUTO. |
stopping_tolerance | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) Defaults to 0. |
max_runtime_secs | Maximum allowed runtime in seconds for model training. Use 0 to disable. Defaults to 0. |
score_validation_sampling | Method used to sample validation dataset for scoring. Must be one of: "Uniform", "Stratified". Defaults to Uniform. |
diagnostics |
|
fast_mode |
|
force_load_balance |
|
variable_importances |
|
replicate_training_data |
|
single_node_mode |
|
shuffle_training_data |
|
missing_values_handling | Handling of missing values. Either MeanImputation or Skip. Must be one of: "MeanImputation", "Skip". Defaults to MeanImputation. |
quiet_mode |
|
autoencoder |
|
sparse |
|
col_major |
|
average_activation | Average activation for sparse auto-encoder. #Experimental Defaults to 0. |
sparsity_beta | Sparsity regularization. #Experimental Defaults to 0. |
max_categorical_features | Max. number of categorical features, enforced via hashing. #Experimental Defaults to 2147483647. |
reproducible |
|
export_weights_and_biases |
|
mini_batch_size | Mini-batch size (smaller leads to better fit, larger can speed up and generalize better). Defaults to 1. |
categorical_encoding | Encoding scheme for categorical features Must be one of: "AUTO", "Enum", "OneHotInternal", "OneHotExplicit", "Binary", "Eigen", "LabelEncoder", "SortByResponse", "EnumLimited". Defaults to AUTO. |
elastic_averaging |
|
elastic_averaging_moving_rate | Elastic averaging moving rate (only if elastic averaging is enabled). Defaults to 0.9. |
elastic_averaging_regularization | Elastic averaging regularization strength (only if elastic averaging is enabled). Defaults to 0.001. |
export_checkpoints_dir | Automatically export generated models to this directory. |
auc_type | Set default multinomial AUC type. Must be one of: "AUTO", "NONE", "MACRO_OVR", "WEIGHTED_OVR", "MACRO_OVO", "WEIGHTED_OVO". Defaults to AUTO. |
verbose |
|
predict.H2OModel
for prediction
# NOT RUN { library(h2o) h2o.init() iris_hf <- as.h2o(iris) iris_dl <- h2o.deeplearning(x = 1:4, y = 5, training_frame = iris_hf, seed=123456) # now make a prediction predictions <- h2o.predict(iris_dl, iris_hf) # }