H2O 3.14.0.7
REST API Reference
GET /3/About
Return information about this H2O cluster.
GET /3/Capabilities
List of all registered capabilities
GET /3/Capabilities/API
List of all registered Rest API capabilities
GET /3/Capabilities/Core
List registered core capabilities
GET /3/Cloud
Determine the status of the nodes in the H2O cloud.
HEAD /3/Cloud
Determine the status of the nodes in the H2O cloud.
GET /3/ComputeGram
Get weighted gram matrix
POST /3/CreateFrame
Create a synthetic H2O Frame with random data. You can specify the number of rows/columns, as well as column types: integer, real, boolean, time, string, categorical. The frame may also have a dedicated “response” column, and some of the entries in the dataset may be created as missing.
DELETE /3/DKV
Remove all keys from the H2O distributed K/V store.
DELETE /3/DKV/{key}
Remove an arbitrary key from the H2O distributed K/V store.
POST /3/DataInfoFrame
Test only
POST /3/DecryptionSetup
Install a decryption tool for parsing of encrypted data.
GET /3/DownloadDataset
Download dataset as a CSV.
GET /3/DownloadDataset.bin
Download dataset as a CSV.
GET /3/Find
Find a value within a Frame.
GET /3/Frames
Return all Frames in the H2O distributed K/V store.
DELETE /3/Frames
Delete all Frames from the H2O distributed K/V store.
GET /3/Frames/{frame_id}
Return the specified Frame.
DELETE /3/Frames/{frame_id}
Delete the specified Frame from the H2O distributed K/V store.
GET /3/Frames/{frame_id}/columns
Return all the columns from a Frame.
GET /3/Frames/{frame_id}/columns/{column}
Return the specified column from a Frame.
GET /3/Frames/{frame_id}/columns/{column}/domain
Return the domains for the specified categorical column (“null” if the column is not a categorical).
GET /3/Frames/{frame_id}/columns/{column}/summary
Return the summary metrics for a column, e.g. min, max, mean, sigma, percentiles, etc.
POST /3/Frames/{frame_id}/export
Export a Frame to the given path with optional overwrite.
GET /3/Frames/{frame_id}/export/{path}/overwrite/{force}
[DEPRECATED] Export a Frame to the given path with optional overwrite.
GET /3/Frames/{frame_id}/summary
Return a Frame, including the histograms, after forcing computation of rollups.
POST /3/GarbageCollect
Explicitly call System.gc().
GET /3/GetGLMRegPath
Get full regularization path
GET /3/ImportFiles
[DEPRECATED] Import raw data files into a single-column H2O Frame.
POST /3/ImportFiles
Import raw data files into a single-column H2O Frame.
GET /3/InitID
Issue a new session ID.
DELETE /3/InitID
End a session.
POST /3/Interaction
Create interactions between categorical columns.
GET /3/JStack
Report stack traces for all threads on all nodes.
GET /3/Jobs
Get a list of all the H2O Jobs (long-running actions).
GET /3/Jobs/{job_id}
Get the status of the given H2O Job (long-running action).
POST /3/Jobs/{job_id}/cancel
Cancel a running job.
GET /3/KillMinus3
Kill minus 3 on this node
POST /3/LogAndEcho
Save a message to the H2O logfile.
GET /3/Logs/nodes/{nodeidx}/files/{name}
Get named log file for a node.
POST /3/MakeGLMModel
Make a new GLM model based on existing one
GET /3/Metadata/endpoints
Return the list of (almost) all REST API endpoints.
GET /3/Metadata/endpoints/{path}
Return the REST API endpoint metadata, including documentation, for the endpoint specified by path or index.
GET /3/Metadata/schemaclasses/{classname}
Return the REST API schema metadata for specified schema class.
GET /3/Metadata/schemas
Return list of all REST API schemas.
GET /3/Metadata/schemas/{schemaname}
Return the REST API schema metadata for specified schema.
POST /3/MissingInserter
Insert missing values.
GET /3/ModelBuilders
Return the Model Builder metadata for all available algorithms.
POST /3/ModelBuilders/deeplearning
Train a DeepLearning model.
POST /3/ModelBuilders/deeplearning/parameters
Validate a set of DeepLearning model builder parameters.
POST /3/ModelBuilders/deepwater
Train a DeepWater model.
POST /3/ModelBuilders/deepwater/parameters
Validate a set of DeepWater model builder parameters.
POST /3/ModelBuilders/drf
Train a DRF model.
POST /3/ModelBuilders/drf/parameters
Validate a set of DRF model builder parameters.
POST /3/ModelBuilders/gbm
Train a GBM model.
POST /3/ModelBuilders/gbm/parameters
Validate a set of GBM model builder parameters.
POST /3/ModelBuilders/glm
Train a GLM model.
POST /3/ModelBuilders/glm/parameters
Validate a set of GLM model builder parameters.
POST /3/ModelBuilders/glrm
Train a GLRM model.
POST /3/ModelBuilders/glrm/parameters
Validate a set of GLRM model builder parameters.
POST /3/ModelBuilders/kmeans
Train a KMeans model.
POST /3/ModelBuilders/kmeans/parameters
Validate a set of KMeans model builder parameters.
POST /3/ModelBuilders/naivebayes
Train a NaiveBayes model.
POST /3/ModelBuilders/naivebayes/parameters
Validate a set of NaiveBayes model builder parameters.
POST /3/ModelBuilders/pca
Train a PCA model.
POST /3/ModelBuilders/pca/parameters
Validate a set of PCA model builder parameters.
POST /3/ModelBuilders/word2vec
Train a Word2Vec model.
POST /3/ModelBuilders/word2vec/parameters
Validate a set of Word2Vec model builder parameters.
POST /3/ModelBuilders/xgboost
Train a XGBoost model.
POST /3/ModelBuilders/xgboost/parameters
Validate a set of XGBoost model builder parameters.
GET /3/ModelBuilders/{algo}
Return the Model Builder metadata for the specified algorithm.
POST /3/ModelBuilders/{algo}/model_id
Return a new unique model_id for the specified algorithm.
GET /3/ModelMetrics
Return all the saved scoring metrics.
GET /3/ModelMetrics/frames/{frame}
Return the saved scoring metrics for the specified Frame.
GET /3/ModelMetrics/frames/{frame}/models/{model}
Return the saved scoring metrics for the specified Model and Frame.
DELETE /3/ModelMetrics/frames/{frame}/models/{model}
Return the saved scoring metrics for the specified Model and Frame.
GET /3/ModelMetrics/models/{model}
Return the saved scoring metrics for the specified Model.
GET /3/ModelMetrics/models/{model}/frames/{frame}
Return the saved scoring metrics for the specified Model and Frame.
DELETE /3/ModelMetrics/models/{model}/frames/{frame}
Return the saved scoring metrics for the specified Model and Frame.
POST /3/ModelMetrics/models/{model}/frames/{frame}
Return the scoring metrics for the specified Frame with the specified Model. If the Frame has already been scored with the Model then cached results will be returned; otherwise predictions for all rows in the Frame will be generated and the metrics will be returned.
POST /3/ModelMetrics/predictions_frame/{predictions_frame}/actuals_frame/{actuals_frame}
Create a ModelMetrics object from the predicted and actual values, and a domain for classification problems or a distribution family for regression problems.
GET /3/Models
Return all Models from the H2O distributed K/V store.
DELETE /3/Models
Delete all Models from the H2O distributed K/V store.
GET /3/Models.java/{model_id}
[DEPRECATED] Return the stream containing model implementation in Java code.
GET /3/Models.java/{model_id}/preview
Return potentially abridged model suitable for viewing in a browser (currently only used for java model code).
GET /3/Models/{model_id}
Return the specified Model from the H2O distributed K/V store, optionally with the list of compatible Frames.
DELETE /3/Models/{model_id}
Delete the specified Model from the H2O distributed K/V store.
GET /3/Models/{model_id}/mojo
Return the model in the MOJO format. This format can then be interpreted by gen_model.jar in order to perform prediction / scoring. Currently works for GBM and DRF algos only.
GET /3/NetworkTest
Run a network test to measure the performance of the cluster interconnect.
GET /3/NodePersistentStorage/categories/{category}/exists
Return true or false.
GET /3/NodePersistentStorage/categories/{category}/names/{name}/exists
Return true or false.
GET /3/NodePersistentStorage/configured
Return true or false.
POST /3/NodePersistentStorage/{category}
Store a value.
GET /3/NodePersistentStorage/{category}
Return all keys stored for a given category.
POST /3/NodePersistentStorage/{category}/{name}
Store a named value.
GET /3/NodePersistentStorage/{category}/{name}
Return value for a given name.
DELETE /3/NodePersistentStorage/{category}/{name}
Delete a key.
POST /3/Parse
Parse a raw byte-oriented Frame into a useful columnar data Frame.
POST /3/ParseSVMLight
Parse a raw byte-oriented Frame into a useful columnar data Frame.
POST /3/ParseSetup
Guess the parameters for parsing raw byte-oriented data into an H2O Frame.
POST /3/PartialDependence/
Create data for partial dependence plot(s) for the specified model and frame.
GET /3/PartialDependence/{name}
Fetch partial dependence data.
POST /3/Predictions/models/{model}/frames/{frame}
Score (generate predictions) for the specified Frame with the specified Model. Both the Frame of predictions and the metrics will be returned.
GET /3/Profiler
Report real-time profiling information for all nodes (sorted, aggregated stack traces).
POST /3/Shutdown
Shut down the cluster.
POST /3/SplitFrame
Split an H2O Frame.
GET /3/SteamMetrics
Get metrics for Steam from H2O.
GET /3/Timeline
Debugging tool that provides information on current communication between nodes.
GET /3/Typeahead/files
Typeahead hander for filename completion.
POST /3/UnlockKeys
Unlock all keys in the H2O distributed K/V store, to attempt to recover from a crash.
GET /3/WaterMeterCpuTicks/{nodeidx}
Return a CPU usage snapshot of all cores of all nodes in the H2O cluster.
GET /3/WaterMeterIo
Return IO usage snapshot of all nodes in the H2O cluster.
GET /3/WaterMeterIo/{nodeidx}
Return IO usage snapshot of all nodes in the H2O cluster.
GET /3/Word2VecSynonyms
Find synonyms using a word2vec model
GET /3/Word2VecTransform
Transform words to vectors using a word2vec model
POST /4/Frames/$simple
Create frame with random (uniformly distributed) data. You can specify how many columns of each type to make; and what the desired range for each column type.
POST /4/Predictions/models/{model}/frames/{frame}
Score (generate predictions) for the specified Frame with the specified Model. Both the Frame of predictions and the metrics will be returned.
GET /4/endpoints
Returns the list of all REST API (v4) endpoints.
GET /4/jobs/{job_id}
Retrieve information about the current state of a job.
GET /4/modelsinfo
Return basic information about all models available to train.
POST /4/sessions
Start a new Rapids session, and return the session id.
DELETE /4/sessions/{session_key}
Close the Rapids session.
POST /99/Assembly
Fit an assembly to an input frame
GET /99/Assembly.java/{assembly_id}/{pojo_name}
Generate a Java POJO from the Assembly
GET /99/AutoML
Return all the AutoML objects.
GET /99/AutoML/{automl_id}
Fetch the specified AutoML object.
POST /99/AutoMLBuilder
Start an AutoML build process.
POST /99/DCTTransformer
Row-by-row discrete cosine transforms in 1D, 2D and 3D.
POST /99/Grid/aggregator
Run grid search for Aggregator model.
POST /99/Grid/deeplearning
Run grid search for DeepLearning model.
POST /99/Grid/deepwater
Run grid search for DeepWater model.
POST /99/Grid/drf
Run grid search for DRF model.
POST /99/Grid/gbm
Run grid search for GBM model.
POST /99/Grid/glm
Run grid search for GLM model.
POST /99/Grid/glrm
Run grid search for GLRM model.
POST /99/Grid/kmeans
Run grid search for KMeans model.
POST /99/Grid/naivebayes
Run grid search for NaiveBayes model.
POST /99/Grid/pca
Run grid search for PCA model.
POST /99/Grid/stackedensemble
Run grid search for StackedEnsemble model.
POST /99/Grid/svd
Run grid search for SVD model.
POST /99/Grid/word2vec
Run grid search for Word2Vec model.
POST /99/Grid/xgboost
Run grid search for XGBoost model.
GET /99/Grids
Return all grids from H2O distributed K/V store.
GET /99/Grids/{grid_id}
Return the specified grid search result.
POST /99/ImportSQLTable
Import SQL table into an H2O Frame.
GET /99/Leaderboards
Return all the AutoML leaderboards.
GET /99/Leaderboards/{project_name}
Return the AutoML leaderboard for the given project.
POST /99/ModelBuilders/aggregator
Train a Aggregator model.
POST /99/ModelBuilders/aggregator/parameters
Validate a set of Aggregator model builder parameters.
POST /99/ModelBuilders/stackedensemble
Train a StackedEnsemble model.
POST /99/ModelBuilders/stackedensemble/parameters
Validate a set of StackedEnsemble model builder parameters.
POST /99/ModelBuilders/svd
Train a SVD model.
POST /99/ModelBuilders/svd/parameters
Validate a set of SVD model builder parameters.
POST /99/Models.bin/{model_id}
Import given binary model into H2O.
GET /99/Models.bin/{model_id}
Export given model.
GET /99/Models.mojo/{model_id}
Export given model as Mojo.
GET /99/Models/{model_id}/json
Export given model details in json format.
POST /99/Rapids
Execute an Rapids AstRoot.
GET /99/Rapids/help
Produce help for Rapids AstRoot language.
GET /99/Sample
Example of an experimental endpoint. Call via /EXPERIMENTAL/Sample. Experimental endpoints can change at any moment.
POST /99/Tabulate
Tabulate one column vs another.
REST API Schema Reference
AboutEntryV3
name
string | Property name | Out |
value
string | Property value | Out |
AboutV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
entries
Iced[] | List of properties about this running H2O instance | Out |
AggregatorModelOutputV99
output_frame
Key | Aggregated Frame of Exemplars | In |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
AggregatorModelV99
model_id
Key | Model key | In/Out |
parameters
AggregatorParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
AggregatorOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
AggregatorParametersV99
transform
enum | Transformation of training data | In |
pca_method
enum | Method for computing PCA (Caution: GLRM is currently experimental and unstable) | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
k
int | Rank of matrix approximation | In/Out |
max_iterations
int | Maximum number of iterations for PCA | In/Out |
target_num_exemplars
int | Targeted number of exemplars | In/Out |
rel_tol_num_exemplars
double | Relative tolerance for number of exemplars (e.g, 0.5 is +/- 50%) | In/Out |
seed
long | RNG seed for initialization | In/Out |
use_all_factor_levels
boolean | Whether first factor level is included in each categorical expansion | In/Out |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
AggregatorV99
parameters
AggregatorParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
AssemblyKeyV3
name
string | Name (string representation) for this Key. | In/Out |
type
string | Name (string representation) for the type of Keyed this Key points to. | In/Out |
URL
string | URL for the resource that this Key points to, if one exists. | In/Out |
AssemblyV99
steps
string[] | A list of steps describing the assembly line. | In |
frame
Key | Input Frame for the assembly. | In |
pojo_name
string | The name of the file and generated class | In |
assembly_id
string | The key of the Assembly object to retrieve from the DKV. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
result
Key | Output of the assembly line. | Out |
assembly
Key | A Key to the fit Assembly data structure | Out |
AutoMLBuildControlV99
project_name
string | optional project name used to group models from multiple runs into a leaderboard; derived from the training data name if not specified | In |
loss
string | loss function | In |
stopping_criteria
RandomDiscreteValueSearchCriteria | stopping criteria for the search | In |
AutoMLBuildModelsV99
exclude_algos
enum[] | Prevent AutoML from trying these algos; ignored if you use the model_searches parameter | In |
model_searches
Grid[] | Optional model build parameter sets, including base hyperparameters and optional hyperparameter search | In |
AutoMLBuildSpecV99
build_control
AutoMLBuildControl | Specification of overall controls for the AutoML build process | In |
input_spec
AutoMLInput | Specification of the input data for the AutoML build process | In |
feature_engineering
AutoMLFeatureEngineering | Specification of the feature engineering for the AutoML build process | In |
build_models
AutoMLBuildModels | If present, specifies details of how to train models | In |
ensemble_parameters
AutoMLEnsembleParameters | If present, AutoML should build ensembles; more control over the process is optional | In |
job
Job | The AutoML Job key | Out |
AutoMLEnsembleParametersV99
(No fields)
AutoMLFeatureEngineeringV99
try_mutations
boolean | Try frame transformations | In |
AutoMLInputV99
training_path
ImportFiles | Path of training data to import and parse, in any form that H2O accepts, including local files or directories, s3, hdfs, etc. | In |
validation_path
ImportFiles | Path of validation data to import and parse, in any form that H2O accepts, including local files or directories, s3, hdfs, etc. | In |
leaderboard_path
ImportFiles | Path of test data (to create the leaderboard) to import and parse, in any form that H2O accepts, including local files or directories, s3, hdfs, etc. | In |
parse_setup
ParseSetup | Used to override default settings for training and test data parsing. | In |
training_frame
Key | ID of the training data frame. | In |
validation_frame
Key | ID of the validation data frame. | In |
leaderboard_frame
Key | ID of the leaderboard/test data frame. | In |
response_column
VecSpecifier | Response column | In |
fold_column
VecSpecifier | Fold column for cross-validation | In |
weights_column
VecSpecifier | Weights column, specifying row weights for model training | In |
ignored_columns
string[] | Names of columns to ignore for training | In |
AutoMLKeyV3
name
string | Name (string representation) for this Key. | In/Out |
type
string | Name (string representation) for the type of Keyed this Key points to. | In/Out |
URL
string | URL for the resource that this Key points to, if one exists. | In/Out |
AutoMLV99
automl_id
Key | Optional AutoML run ID; omitting this returns all runs | In |
project_name
string | Identifier for models that should be grouped together in the same leaderboard | In/Out |
training_frame
Key | ID of the actual training frame for this AutoML run after any automatic splitting | Out |
validation_frame
Key | ID of the actual validation frame for this AutoML run after any automatic splitting | Out |
leaderboard_frame
Key | ID of the actual leaderboard frame for this AutoML run after any automatic splitting | Out |
leaderboard
Leaderboard | The leaderboard for this project, potentially including models from other AutoML runs | Out |
leaderboard_table
TwoDimTable | The leaderboard for this project, potentially including models from other AutoML runs, for easy rendering | Out |
user_feedback
UserFeedback | User feedback for events from this AutoML run | Out |
user_feedback_table
TwoDimTable | User feedback for events from this AutoML run, for easy rendering | Out |
AutoMLsV99
project_name
string | Name of project of interest | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
auto_ml_runs
AutoML[] | AutoMLs | Out |
CapabilitiesV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
capabilities
Iced[] | List of H2O capabilities | Out |
CapabilityEntryV3
name
string | Extension name | Out |
CartesianSearchCriteriaV99
strategy
enum | Hyperparameter space search strategy. | In/Out |
CloudV3
skip_ticks
boolean | skip_ticks | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
version
string | version | Out |
branch_name
string | branch_name | Out |
build_number
string | build_number | Out |
build_age
string | build_age | Out |
build_too_old
boolean | build_too_old | Out |
node_idx
int | Node index number cloud status is collected from (zero-based) | Out |
cloud_name
string | cloud_name | Out |
cloud_size
int | cloud_size | Out |
cloud_uptime_millis
long | cloud_uptime_millis | Out |
cloud_healthy
boolean | cloud_healthy | Out |
bad_nodes
int | Nodes reporting unhealthy | Out |
consensus
boolean | Cloud voting is stable | Out |
locked
boolean | Cloud is accepting new members or not | Out |
is_client
boolean | Cloud is in client mode. | Out |
nodes
Iced[] | nodes | Out |
internal_security_enabled
boolean | internal_security_enabled | Out |
ClusteringModelBuilderSchema
parameters
Parameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
ClusteringModelParametersSchemaV3
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
k
int | The max. number of clusters. If estimate_k is disabled, the model will find k centroids, otherwise it will find up to k centroids. | In/Out |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
ColSpecifierV3
column_name
string | Name of the column | In/Out |
is_member_of_frames
string[] | List of fields which specify columns that must contain this column | In/Out |
ColV3
label
string | label | Out |
missing_count
long | missing | Out |
zero_count
long | zeros | Out |
positive_infinity_count
long | positive infinities | Out |
negative_infinity_count
long | negative infinities | Out |
mins
double[] | mins | Out |
maxs
double[] | maxs | Out |
mean
double | mean | Out |
sigma
double | sigma | Out |
type
string | datatype: {enum, string, int, real, time, uuid} | Out |
domain
string[] | domain; not-null for categorical columns only | Out |
domain_cardinality
int | cardinality of this column’s domain; not-null for categorical columns only | Out |
data
double[] | data | Out |
string_data
string[] | string data | Out |
precision
byte | decimal precision, -1 for all digits | Out |
histogram_bins
long[] | Histogram bins; null if not computed | Out |
histogram_base
double | Start of histogram bin zero | Out |
histogram_stride
double | Stride per bin | Out |
percentiles
double[] | Percentile values, matching the default percentiles | Out |
ColumnSpecsBase
name
string | Column Name | Out |
type
string | Column Type | Out |
format
string | Column Format (printf) | Out |
description
string | Column Description | Out |
ConfusionMatrixV3
CoxPHModelOutputV3
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
CoxPHModelV3
model_id
Key | Model key | In/Out |
parameters
CoxPHParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
CoxPHOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
CoxPHParametersV3
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
CoxPHV3
parameters
CoxPHParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
CreateFrameOriginalIV4
dest
Key | destination key | In |
rows
int | Number of rows | In |
cols
int | Number of data columns (in addition to the first response column) | In |
seed
long | Random number seed that determines the random values | In |
randomize
boolean | Whether frame should be randomized | In |
value
long | Constant value (for randomize=false) | In |
real_range
double | Range for real variables (-range … range) | In |
categorical_fraction
double | Fraction of categorical columns (for randomize=true) | In |
factors
int | Factor levels for categorical variables | In |
integer_fraction
double | Fraction of integer columns (for randomize=true) | In |
integer_range
int | Range for integer variables (-range … range) | In |
binary_fraction
double | Fraction of binary columns (for randomize=true) | In |
binary_ones_fraction
double | Fraction of 1’s in binary columns | In |
time_fraction
double | Fraction of date/time columns (for randomize=true) | In |
string_fraction
double | Fraction of string columns (for randomize=true) | In |
missing_fraction
double | Fraction of missing values | In |
has_response
boolean | Whether an additional response column should be generated | In |
response_factors
int | Number of factor levels of the first column (1=real, 2=binomial, N=multinomial) | In |
positive_response
boolean | For real-valued response variable: Whether the response should be positive only. | In |
_fields
string | Filter on the set of output fields: if you set _fields=”foo,bar,baz”, then only those fields will be included in the output; or you can specify _fields=”-goo,gee” to include all fields except goo and gee. If the result contains nested data structures, then you can refer to the fields within those structures as well. For example if you specify _fields=”foo(oof),bar(-rab)”, then only fields foo and bar will be included, and within foo there will be only field oof, whereas within bar all fields except rab will be reported. | In |
CreateFrameSimpleIV4
dest
Key | Id for the frame to be created. | In |
seed
long | Random number seed that determines the random values. | In |
nrows
int | Number of rows. | In |
ncols_real
int | Number of real-valued columns. Values in these columns will be uniformly distributed between real_lb and real_ub. | In |
ncols_int
int | Number of integer columns. | In |
ncols_enum
int | Number of enum (categorical) columns. | In |
ncols_bool
int | Number of boolean (binary) columns. | In |
ncols_str
int | Number of string columns. | In |
ncols_time
int | Number of time columns. | In |
real_lb
double | Lower bound for the range of the real-valued columns. | In |
real_ub
double | Upper bound for the range of the real-valued columns. | In |
int_lb
int | Lower bound for the range of integer columns. | In |
int_ub
int | Upper bound for the range of integer columns. | In |
enum_nlevels
int | Number of levels (categories) for the enum columns. | In |
bool_p
double | Fraction of ones in each boolean (binary) column. | In |
time_lb
long | Lower bound for the range of time columns (in ms since the epoch). | In |
time_ub
long | Upper bound for the range of time columns (in ms since the epoch). | In |
str_length
int | Length of generated strings in string columns. | In |
missing_fraction
double | Fraction of missing values. | In |
response_type
enum | Type of the response column to add. | In |
response_lb
double | Lower bound for the response variable (real/int/time types). | In |
response_ub
double | Upper bound for the response variable (real/int/time types). | In |
response_p
double | Frequency of 1s for the bool (binary) response column. | In |
response_nlevels
int | Number of categorical levels for the enum response column. | In |
_fields
string | Filter on the set of output fields: if you set _fields=”foo,bar,baz”, then only those fields will be included in the output; or you can specify _fields=”-goo,gee” to include all fields except goo and gee. If the result contains nested data structures, then you can refer to the fields within those structures as well. For example if you specify _fields=”foo(oof),bar(-rab)”, then only fields foo and bar will be included, and within foo there will be only field oof, whereas within bar all fields except rab will be reported. | In |
CreateFrameV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
dest
Key | destination key | In/Out |
rows
long | Number of rows | In/Out |
cols
int | Number of data columns (in addition to the first response column) | In/Out |
seed
long | Random number seed that determines the random values | In/Out |
seed_for_column_types
long | Random number seed for setting the column types | In/Out |
randomize
boolean | Whether frame should be randomized | In/Out |
value
long | Constant value (for randomize=false) | In/Out |
real_range
long | Range for real variables (-range … range) | In/Out |
categorical_fraction
double | Fraction of categorical columns (for randomize=true) | In/Out |
factors
int | Factor levels for categorical variables | In/Out |
integer_fraction
double | Fraction of integer columns (for randomize=true) | In/Out |
integer_range
long | Range for integer variables (-range … range) | In/Out |
binary_fraction
double | Fraction of binary columns (for randomize=true) | In/Out |
binary_ones_fraction
double | Fraction of 1’s in binary columns | In/Out |
time_fraction
double | Fraction of date/time columns (for randomize=true) | In/Out |
string_fraction
double | Fraction of string columns (for randomize=true) | In/Out |
missing_fraction
double | Fraction of missing values | In/Out |
has_response
boolean | Whether an additional response column should be generated | In/Out |
response_factors
int | Number of factor levels of the first column (1=real, 2=binomial, N=multinomial) | In/Out |
positive_response
boolean | For real-valued response variable: Whether the response should be positive only. | In/Out |
key
Key | Job Key | Out |
DCTTransformerV3
dataset
Key | Dataset | In |
destination_frame
Key | Destination Frame ID | In |
dimensions
int[] | Dimensions of the input array: Height, Width, Depth (Nx1x1 for 1D, NxMx1 for 2D) | In |
inverse
boolean | Whether to do the inverse transform | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
DRFModelOutputV3
variable_importances
TwoDimTable | Variable Importances | Out |
init_f
double | The Intercept term, the initial model function value to which trees make adjustments | Out |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
DRFModelV3
model_id
Key | Model key | In/Out |
parameters
DRFParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
DRFOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
DRFParametersV3
mtries
int | Number of variables randomly sampled as candidates at each split. If set to -1, defaults to sqrt{p} for classification and p/3 for regression (where p is the # of predictors | In |
binomial_double_trees
boolean | For binary classification: Build 2x as many trees (one per class) - can lead to higher accuracy. | In |
ntrees
int | Number of trees. | In |
max_depth
int | Maximum tree depth. | In |
min_rows
double | Fewest allowed (weighted) observations in a leaf. | In |
nbins
int | For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the best point | In |
nbins_top_level
int | For numerical columns (real/int), build a histogram of (at most) this many bins at the root level, then decrease by factor of two per level | In |
nbins_cats
int | For categorical columns (factors), build a histogram of this many bins, then split at the best point. Higher values can lead to more overfitting. | In |
r2_stopping
double | r2_stopping is no longer supported and will be ignored if set - please use stopping_rounds, stopping_metric and stopping_tolerance instead. Previous version of H2O would stop making trees when the R^2 metric equals or exceeds this | In |
seed
long | Seed for pseudo random number generator (if applicable) | In |
build_tree_one_node
boolean | Run on one node only; no network overhead but fewer cpus used. Suitable for small datasets. | In |
sample_rate
double | Row sample rate per tree (from 0.0 to 1.0) | In |
sample_rate_per_class
double[] | A list of row sample rates per class (relative fraction for each class, from 0.0 to 1.0), for each tree | In |
col_sample_rate_per_tree
double | Column sample rate per tree (from 0.0 to 1.0) | In |
col_sample_rate_change_per_level
double | Relative change of the column sampling rate for every level (from 0.0 to 2.0) | In |
score_tree_interval
int | Score the model after every so many trees. Disabled if set to 0. | In |
min_split_improvement
double | Minimum relative improvement in squared error reduction for a split to happen | In |
histogram_type
enum | What type of histogram to use for finding optimal split points | In |
calibrate_model
boolean | Use Platt Scaling to calculate calibrated class probabilities. Calibration can provide more accurate estimates of class probabilities. | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
balance_classes
boolean | Balance training data class counts via over/under-sampling (for imbalanced data). | In/Out |
class_sampling_factors
float[] | 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. | In/Out |
max_after_balance_size
float | Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires balance_classes. | In/Out |
max_confusion_matrix_size
int | [Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs | In/Out |
max_hit_ratio_k
int | Max. number (top K) of predictions to use for hit ratio computation (for multi-class only, 0 to disable) | In/Out |
calibration_frame
Key | Calibration frame for Platt Scaling | In/Out |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
DRFV3
parameters
DRFParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
DStackTraceV3
node
string | Node name | Out |
time
long | Unix epoch time | Out |
thread_traces
string[] | One trace per thread | Out |
DataInfoFrameV3
frame
Key | input frame | In |
interactions
string[] | interactions | In |
use_all
boolean | use all factor levels | In |
standardize
boolean | standardize | In |
interactions_only
boolean | interactions only returned | In |
result
Key | output frame | Out |
DecryptionSetupV3
password
string | Key password | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
decrypt_tool_id
Key | Target key for the Decryption Tool | In/Out |
decrypt_impl
string | Implementation of the Decryption Tool | In/Out |
keystore_id
Key | Location of Java Keystore | In/Out |
keystore_type
string | Keystore type | In/Out |
key_alias
string | Key alias | In/Out |
cipher_spec
string | Specification of the cipher (and padding) | In/Out |
DecryptionToolKeyV3
name
string | Name (string representation) for this Key. | In/Out |
type
string | Name (string representation) for the type of Keyed this Key points to. | In/Out |
URL
string | URL for the resource that this Key points to, if one exists. | In/Out |
DeepLearningModelOutputV3
weights
Key[] | Frame keys for weight matrices | In |
biases
Key[] | Frame keys for bias vectors | In |
normmul
double[] | Normalization/Standardization multipliers for numeric predictors | Out |
normsub
double[] | Normalization/Standardization offsets for numeric predictors | Out |
normrespmul
double[] | Normalization/Standardization multipliers for numeric response | Out |
normrespsub
double[] | Normalization/Standardization offsets for numeric response | Out |
catoffsets
int[] | Categorical offsets for one-hot encoding | Out |
variable_importances
TwoDimTable | Variable Importances | Out |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
DeepLearningModelV3
model_id
Key | Model key | In/Out |
parameters
DeepLearningParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
DeepLearningModelOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
DeepLearningParametersV3
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
balance_classes
boolean | Balance training data class counts via over/under-sampling (for imbalanced data). | In/Out |
class_sampling_factors
float[] | 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. | In/Out |
max_after_balance_size
float | Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires balance_classes. | In/Out |
max_confusion_matrix_size
int | [Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs. | In/Out |
max_hit_ratio_k
int | Max. number (top K) of predictions to use for hit ratio computation (for multi-class only, 0 to disable). | In/Out |
activation
enum | Activation function. | In/Out |
hidden
int[] | Hidden layer sizes (e.g. [100, 100]). | In/Out |
epochs
double | How many times the dataset should be iterated (streamed), can be fractional. | In/Out |
train_samples_per_iteration
long | 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. | In/Out |
target_ratio_comm_to_comp
double | Target ratio of communication overhead to computation. Only for multi-node operation and train_samples_per_iteration = -2 (auto-tuning). | In/Out |
seed
long | Seed for random numbers (affects sampling) - Note: only reproducible when running single threaded. | In/Out |
adaptive_rate
boolean | Adaptive learning rate. | In/Out |
rho
double | Adaptive learning rate time decay factor (similarity to prior updates). | In/Out |
epsilon
double | Adaptive learning rate smoothing factor (to avoid divisions by zero and allow progress). | In/Out |
rate
double | Learning rate (higher => less stable, lower => slower convergence). | In/Out |
rate_annealing
double | Learning rate annealing: rate / (1 + rate_annealing * samples). | In/Out |
rate_decay
double | Learning rate decay factor between layers (N-th layer: rate * rate_decay ^ (n - 1). | In/Out |
momentum_start
double | Initial momentum at the beginning of training (try 0.5). | In/Out |
momentum_ramp
double | Number of training samples for which momentum increases. | In/Out |
momentum_stable
double | Final momentum after the ramp is over (try 0.99). | In/Out |
nesterov_accelerated_gradient
boolean | Use Nesterov accelerated gradient (recommended). | In/Out |
input_dropout_ratio
double | Input layer dropout ratio (can improve generalization, try 0.1 or 0.2). | In/Out |
hidden_dropout_ratios
double[] | Hidden layer dropout ratios (can improve generalization), specify one value per hidden layer, defaults to 0.5. | In/Out |
l1
double | L1 regularization (can add stability and improve generalization, causes many weights to become 0). | In/Out |
l2
double | L2 regularization (can add stability and improve generalization, causes many weights to be small. | In/Out |
max_w2
float | Constraint for squared sum of incoming weights per unit (e.g. for Rectifier). | In/Out |
initial_weight_distribution
enum | Initial weight distribution. | In/Out |
initial_weight_scale
double | Uniform: -value…value, Normal: stddev. | In/Out |
initial_weights
Key[] | A list of H2OFrame ids to initialize the weight matrices of this model with. | In/Out |
initial_biases
Key[] | A list of H2OFrame ids to initialize the bias vectors of this model with. | In/Out |
loss
enum | Loss function. | In/Out |
score_interval
double | Shortest time interval (in seconds) between model scoring. | In/Out |
score_training_samples
long | Number of training set samples for scoring (0 for all). | In/Out |
score_validation_samples
long | Number of validation set samples for scoring (0 for all). | In/Out |
score_duty_cycle
double | Maximum duty cycle fraction for scoring (lower: more training, higher: more scoring). | In/Out |
classification_stop
double | Stopping criterion for classification error fraction on training data (-1 to disable). | In/Out |
regression_stop
double | Stopping criterion for regression error (MSE) on training data (-1 to disable). | In/Out |
quiet_mode
boolean | Enable quiet mode for less output to standard output. | In/Out |
score_validation_sampling
enum | Method used to sample validation dataset for scoring. | In/Out |
overwrite_with_best_model
boolean | If enabled, override the final model with the best model found during training. | In/Out |
autoencoder
boolean | Auto-Encoder. | In/Out |
use_all_factor_levels
boolean | Use all factor levels of categorical variables. Otherwise, the first factor level is omitted (without loss of accuracy). Useful for variable importances and auto-enabled for autoencoder. | In/Out |
standardize
boolean | If enabled, automatically standardize the data. If disabled, the user must provide properly scaled input data. | In/Out |
diagnostics
boolean | Enable diagnostics for hidden layers. | In/Out |
variable_importances
boolean | Compute variable importances for input features (Gedeon method) - can be slow for large networks. | In/Out |
fast_mode
boolean | Enable fast mode (minor approximation in back-propagation). | In/Out |
force_load_balance
boolean | Force extra load balancing to increase training speed for small datasets (to keep all cores busy). | In/Out |
replicate_training_data
boolean | Replicate the entire training dataset onto every node for faster training on small datasets. | In/Out |
single_node_mode
boolean | Run on a single node for fine-tuning of model parameters. | In/Out |
shuffle_training_data
boolean | Enable shuffling of training data (recommended if training data is replicated and train_samples_per_iteration is close to #nodes x #rows, of if using balance_classes). | In/Out |
missing_values_handling
enum | Handling of missing values. Either MeanImputation or Skip. | In/Out |
sparse
boolean | Sparse data handling (more efficient for data with lots of 0 values). | In/Out |
col_major
boolean | id="deprecated-use-a-column-major-weight-matrix-for-input-layer-can-speed-up-forward-propagation-but-might-slow-down-backpropagation-">DEPRECATED Use a column major weight matrix for input layer. Can speed up forward propagation, but might slow down backpropagation.< | In/Out |
average_activation
double | Average activation for sparse auto-encoder. #Experimental | In/Out |
sparsity_beta
double | Sparsity regularization. #Experimental | In/Out |
max_categorical_features
int | Max. number of categorical features, enforced via hashing. #Experimental | In/Out |
reproducible
boolean | Force reproducibility on small data (will be slow - only uses 1 thread). | In/Out |
export_weights_and_biases
boolean | Whether to export Neural Network weights and biases to H2O Frames. | In/Out |
mini_batch_size
int | Mini-batch size (smaller leads to better fit, larger can speed up and generalize better). | In/Out |
elastic_averaging
boolean | Elastic averaging between compute nodes can improve distributed model convergence. #Experimental | In/Out |
elastic_averaging_moving_rate
double | Elastic averaging moving rate (only if elastic averaging is enabled). | In/Out |
elastic_averaging_regularization
double | Elastic averaging regularization strength (only if elastic averaging is enabled). | In/Out |
pretrained_autoencoder
Key | Pretrained autoencoder model to initialize this model with. | In/Out |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
DeepLearningV3
parameters
DeepLearningParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
DeepWaterModelOutputV3
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
DeepWaterModelV3
model_id
Key | Model key | In/Out |
parameters
DeepWaterParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
DeepWaterModelOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
DeepWaterParametersV3
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
problem_type
enum | Problem type, auto-detected by default. If set to image, the H2OFrame must contain a string column containing the path (URI or URL) to the images in the first column. If set to text, the H2OFrame must contain a string column containing the text in the first column. If set to dataset, Deep Water behaves just like any other H2O Model and builds a model on the provided H2OFrame (non-String columns). | In/Out |
activation
enum | Activation function. Only used if no user-defined network architecture file is provided, and only for problem_type=dataset. | In/Out |
hidden
int[] | Hidden layer sizes (e.g. [200, 200]). Only used if no user-defined network architecture file is provided, and only for problem_type=dataset. | In/Out |
input_dropout_ratio
double | Input layer dropout ratio (can improve generalization, try 0.1 or 0.2). | In/Out |
hidden_dropout_ratios
double[] | Hidden layer dropout ratios (can improve generalization), specify one value per hidden layer, defaults to 0.5. | In/Out |
max_confusion_matrix_size
int | [Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs. | In/Out |
sparse
boolean | Sparse data handling (more efficient for data with lots of 0 values). | In/Out |
max_hit_ratio_k
int | Max. number (top K) of predictions to use for hit ratio computation (for multi-class only, 0 to disable). | In/Out |
epochs
double | How many times the dataset should be iterated (streamed), can be fractional. | In/Out |
train_samples_per_iteration
long | 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. | In/Out |
target_ratio_comm_to_comp
double | Target ratio of communication overhead to computation. Only for multi-node operation and train_samples_per_iteration = -2 (auto-tuning). | In/Out |
seed
long | Seed for random numbers (affects sampling) - Note: only reproducible when running single threaded. | In/Out |
learning_rate
double | Learning rate (higher => less stable, lower => slower convergence). | In/Out |
learning_rate_annealing
double | Learning rate annealing: rate / (1 + rate_annealing * samples). | In/Out |
momentum_start
double | Initial momentum at the beginning of training (try 0.5). | In/Out |
momentum_ramp
double | Number of training samples for which momentum increases. | In/Out |
momentum_stable
double | Final momentum after the ramp is over (try 0.99). | In/Out |
score_interval
double | Shortest time interval (in seconds) between model scoring. | In/Out |
score_training_samples
long | Number of training set samples for scoring (0 for all). | In/Out |
score_validation_samples
long | Number of validation set samples for scoring (0 for all). | In/Out |
score_duty_cycle
double | Maximum duty cycle fraction for scoring (lower: more training, higher: more scoring). | In/Out |
classification_stop
double | Stopping criterion for classification error fraction on training data (-1 to disable). | In/Out |
regression_stop
double | Stopping criterion for regression error (MSE) on training data (-1 to disable). | In/Out |
quiet_mode
boolean | Enable quiet mode for less output to standard output. | In/Out |
overwrite_with_best_model
boolean | If enabled, override the final model with the best model found during training. | In/Out |
autoencoder
boolean | Auto-Encoder. | In/Out |
diagnostics
boolean | Enable diagnostics for hidden layers. | In/Out |
variable_importances
boolean | Compute variable importances for input features (Gedeon method) - can be slow for large networks. | In/Out |
replicate_training_data
boolean | Replicate the entire training dataset onto every node for faster training on small datasets. | In/Out |
single_node_mode
boolean | Run on a single node for fine-tuning of model parameters. | In/Out |
shuffle_training_data
boolean | Enable global shuffling of training data. | In/Out |
mini_batch_size
int | Mini-batch size (smaller leads to better fit, larger can speed up and generalize better). | In/Out |
clip_gradient
double | Clip gradients once their absolute value is larger than this value. | In/Out |
network
enum | Network architecture. | In/Out |
backend
enum | Deep Learning Backend. | In/Out |
image_shape
int[] | Width and height of image. | In/Out |
channels
int | Number of (color) channels. | In/Out |
gpu
boolean | Whether to use a GPU (if available). | In/Out |
device_id
int[] | Device IDs (which GPUs to use). | In/Out |
cache_data
boolean | Whether to cache the data in memory (automatically disabled if data size is too large). | In/Out |
network_definition_file
string | Path of file containing network definition (graph, architecture). | In/Out |
network_parameters_file
string | Path of file containing network (initial) parameters (weights, biases). | In/Out |
mean_image_file
string | Path of file containing the mean image data for data normalization. | In/Out |
export_native_parameters_prefix
string | Path (prefix) where to export the native model parameters after every iteration. | In/Out |
standardize
boolean | If enabled, automatically standardize the data. If disabled, the user must provide properly scaled input data. | In/Out |
balance_classes
boolean | Balance training data class counts via over/under-sampling (for imbalanced data). | In/Out |
class_sampling_factors
float[] | 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. | In/Out |
max_after_balance_size
float | Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires balance_classes. | In/Out |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
DeepWaterV3
parameters
DeepWaterParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
DownloadDataV3
frame_id
Key | Frame to download | In |
hex_string
boolean | Emit double values in a machine readable lossless format with Double.toHexString(). | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
csv
string | CSV Stream | Out |
filename
string | Suggested Filename | Out |
EndpointV4
url
string | Method+Url of the request; variable parts are enclosed in curly braces. For example: /4/schemas/{schema_name} | In |
description
string | Short description of the functionality provided by the endpoint. | In |
name
string | Unique name of the endpoint. These names can be used to look up the endpoint’s info via GET /4/endpoints/{name}. | In |
input_schema
string | Input schema. | In |
output_schema
string | Schema for the result returned by the endpoint. | In |
__schema
string | Url describing the schema of the current object. | In |
EndpointsListV4
endpoints
Route[] | List of endpoints in H2O REST API (v4). | In |
__schema
string | Url describing the schema of the current object. | In |
EventV3
date
string | Time when the event was recorded. Format is hh:mm:ss:ms | In |
nanos
long | Time in nanos | In |
type
enum | type of recorded event | In |
ExampleModelOutputV3
iterations
int | Iterations executed | In |
maxs
double[] | (No description available) | In |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
ExampleModelV3
model_id
Key | Model key | In/Out |
parameters
ExampleParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
ExampleOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
ExampleParametersV3
max_iterations
int | Maximum training iterations. | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
ExampleV3
parameters
ExampleParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
FieldMetadataV3
schema_name
string | Schema name for this field, if it is_schema, or the name of the enum, if it’s an enum. | In |
name
string | Field name in the Schema | Out |
type
string | Type for this field | Out |
is_schema
boolean | Type for this field is itself a Schema. | Out |
value
Polymorphic | Value for this field | Out |
help
string | A short help description to appear alongside the field in a UI | Out |
label
string | The label that should be displayed for the field if the name is insufficient | Out |
required
boolean | Is this field required, or is the default value generally sufficient? | Out |
level
enum | How important is this field? The web UI uses the level to do a slow reveal of the parameters | Out |
direction
enum | Is this field an input, output or inout? | Out |
is_inherited
boolean | Is the field inherited from the parent schema? | Out |
inherited_from
string | If this field is inherited from a class higher in the hierarchy which one? | Out |
is_gridable
boolean | Is the field gridable (i.e., it can be used in grid call) | Out |
values
string[] | For enum-type fields the allowed values are specified using the values annotation; this is used in UIs to tell the user the allowed values, and for validation | Out |
json
boolean | Should this field be rendered in the JSON representation? | Out |
is_member_of_frames
string[] | For Vec-type fields this is the set of other Vec-type fields which must contain mutually exclusive values; for example, for a SupervisedModel the response_column must be mutually exclusive with the weights_column | Out |
is_mutually_exclusive_with
string[] | For Vec-type fields this is the set of Frame-type fields which must contain the named column; for example, for a SupervisedModel the response_column must be in both the training_frame and (if it’s set) the validation_frame | Out |
FindV3
key
Frame | Frame to search | In |
column
string | Column, or null for all | In |
row
long | Starting row for search | In |
match
string | Value to search for; leave blank for a search for missing values | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
prev
long | previous row with matching value, or -1 | Out |
next
long | next row with matching value, or -1 | Out |
FrameBaseV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
frame_id
Key | Frame ID | In/Out |
byte_size
long | Total data size in bytes | Out |
is_text
boolean | Is this Frame raw unparsed data? | Out |
FrameKeyV3
name
string | Name (string representation) for this Key. | In/Out |
type
string | Name (string representation) for the type of Keyed this Key points to. | In/Out |
URL
string | URL for the resource that this Key points to, if one exists. | In/Out |
FrameSynopsisV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
frame_id
Key | Frame ID | In/Out |
rows
long | Number of rows in the Frame | Out |
columns
long | Number of columns in the Frame | Out |
byte_size
long | Total data size in bytes | Out |
is_text
boolean | Is this Frame raw unparsed data? | Out |
FrameV3
row_offset
long | Row offset to display | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
row_count
int | Number of rows to display | In/Out |
column_offset
int | Column offset to return | In/Out |
column_count
int | Number of columns to return | In/Out |
total_column_count
int | Total number of columns in the Frame | In/Out |
frame_id
Key | Frame ID | In/Out |
checksum
long | checksum | Out |
rows
long | Number of rows in the Frame | Out |
num_columns
long | Number of columns in the Frame | Out |
default_percentiles
double[] | Default percentiles, from 0 to 1 | Out |
columns
Vec[] | Columns in the Frame | Out |
compatible_models
string[] | Compatible models, if requested | Out |
chunk_summary
TwoDimTable | Chunk summary | Out |
distribution_summary
TwoDimTable | Distribution summary | Out |
byte_size
long | Total data size in bytes | Out |
is_text
boolean | Is this Frame raw unparsed data? | Out |
FramesV3
frame_id
Key | Name of Frame of interest | In |
column
string | Name of column of interest | In |
find_compatible_models
boolean | Find and return compatible models? | In |
path
string | File output path | In |
force
boolean | Overwrite existing file | In |
num_parts
int | Number of part files to use (1=single file,-1=automatic) | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
row_offset
long | Row offset to return | In/Out |
row_count
int | Number of rows to return | In/Out |
column_offset
int | Column offset to return | In/Out |
column_count
int | Number of columns to return | In/Out |
job
Job | Job for export file | Out |
frames
Iced[] | Frames | Out |
compatible_models
Model[] | Compatible models | Out |
domain
string[][] | Domains | Out |
GBMModelOutputV3
variable_importances
TwoDimTable | Variable Importances | Out |
init_f
double | The Intercept term, the initial model function value to which trees make adjustments | Out |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
GBMModelV3
model_id
Key | Model key | In/Out |
parameters
GBMParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
GBMOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
GBMParametersV3
learn_rate
double | Learning rate (from 0.0 to 1.0) | In |
learn_rate_annealing
double | Scale the learning rate by this factor after each tree (e.g., 0.99 or 0.999) | In |
col_sample_rate
double | Column sample rate (from 0.0 to 1.0) | In |
max_abs_leafnode_pred
double | Maximum absolute value of a leaf node prediction | In |
pred_noise_bandwidth
double | Bandwidth (sigma) of Gaussian multiplicative noise ~N(1,sigma) for tree node predictions | In |
ntrees
int | Number of trees. | In |
max_depth
int | Maximum tree depth. | In |
min_rows
double | Fewest allowed (weighted) observations in a leaf. | In |
nbins
int | For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the best point | In |
nbins_top_level
int | For numerical columns (real/int), build a histogram of (at most) this many bins at the root level, then decrease by factor of two per level | In |
nbins_cats
int | For categorical columns (factors), build a histogram of this many bins, then split at the best point. Higher values can lead to more overfitting. | In |
r2_stopping
double | r2_stopping is no longer supported and will be ignored if set - please use stopping_rounds, stopping_metric and stopping_tolerance instead. Previous version of H2O would stop making trees when the R^2 metric equals or exceeds this | In |
seed
long | Seed for pseudo random number generator (if applicable) | In |
build_tree_one_node
boolean | Run on one node only; no network overhead but fewer cpus used. Suitable for small datasets. | In |
sample_rate
double | Row sample rate per tree (from 0.0 to 1.0) | In |
sample_rate_per_class
double[] | A list of row sample rates per class (relative fraction for each class, from 0.0 to 1.0), for each tree | In |
col_sample_rate_per_tree
double | Column sample rate per tree (from 0.0 to 1.0) | In |
col_sample_rate_change_per_level
double | Relative change of the column sampling rate for every level (from 0.0 to 2.0) | In |
score_tree_interval
int | Score the model after every so many trees. Disabled if set to 0. | In |
min_split_improvement
double | Minimum relative improvement in squared error reduction for a split to happen | In |
histogram_type
enum | What type of histogram to use for finding optimal split points | In |
calibrate_model
boolean | Use Platt Scaling to calculate calibrated class probabilities. Calibration can provide more accurate estimates of class probabilities. | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
balance_classes
boolean | Balance training data class counts via over/under-sampling (for imbalanced data). | In/Out |
class_sampling_factors
float[] | 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. | In/Out |
max_after_balance_size
float | Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires balance_classes. | In/Out |
max_confusion_matrix_size
int | [Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs | In/Out |
max_hit_ratio_k
int | Max. number (top K) of predictions to use for hit ratio computation (for multi-class only, 0 to disable) | In/Out |
calibration_frame
Key | Calibration frame for Platt Scaling | In/Out |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
GBMV3
parameters
GBMParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
GLMModelOutputV3
coefficients_table
TwoDimTable | Table of Coefficients | In |
standardized_coefficient_magnitudes
TwoDimTable | Standardized Coefficient Magnitudes | In |
lambda_best
double | Lambda minimizing the objective value, only applicable with lambd search | In |
lambda_1se
double | Lambda best + 1 standard error. Only applicable with lambda search and cross-validation | In |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
GLMModelV3
model_id
Key | Model key | In/Out |
parameters
GLMParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
GLMOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
GLMParametersV3
seed
long | Seed for pseudo random number generator (if applicable) | In |
family
enum | Family. Use binomial for classification with logistic regression, others are for regression problems. | In |
tweedie_variance_power
double | Tweedie variance power | In |
tweedie_link_power
double | Tweedie link power | In |
solver
enum | AUTO will set the solver based on given data and the other parameters. IRLSM is fast on on problems with small number of predictors and for lambda-search with L1 penalty, L_BFGS scales better for datasets with many columns. Coordinate descent is experimental (beta). | In |
alpha
double[] | Distribution of regularization between the L1 (Lasso) and L2 (Ridge) penalties. A value of 1 for alpha represents Lasso regression, a value of 0 produces Ridge regression, and anything in between specifies the amount of mixing between the two. Default value of alpha is 0 when SOLVER = ‘L-BFGS’; 0.5 otherwise. | In |
lambda
double[] | Regularization strength | In |
lambda_search
boolean | Use lambda search starting at lambda max, given lambda is then interpreted as lambda min | In |
early_stopping
boolean | Stop early when there is no more relative improvement on train or validation (if provided) | In |
nlambdas
int | Number of lambdas to be used in a search. Default indicates: If alpha is zero, with lambda search set to True, the value of nlamdas is set to 30 (fewer lambdas are needed for ridge regression) otherwise it is set to 100. | In |
standardize
boolean | Standardize numeric columns to have zero mean and unit variance | In |
non_negative
boolean | Restrict coefficients (not intercept) to be non-negative | In |
max_iterations
int | Maximum number of iterations | In |
beta_epsilon
double | Converge if beta changes less (using L-infinity norm) than beta esilon, ONLY applies to IRLSM solver | In |
objective_epsilon
double | Converge if objective value changes less than this. Default indicates: If lambda_search is set to True the value of objective_epsilon is set to .0001. If the lambda_search is set to False and lambda is equal to zero, the value of objective_epsilon is set to .000001, for any other value of lambda the default value of objective_epsilon is set to .0001. | In |
gradient_epsilon
double | Converge if objective changes less (using L-infinity norm) than this, ONLY applies to L-BFGS solver. Default indicates: If lambda_search is set to False and lambda is equal to zero, the default value of gradient_epsilon is equal to .000001, otherwise the default value is .0001. If lambda_search is set to True, the conditional values above are 1E-8 and 1E-6 respectively. | In |
obj_reg
double | Likelihood divider in objective value computation, default is 1/nobs | In |
link
enum | (No description available) | In |
intercept
boolean | Include constant term in the model | In |
prior
double | Prior probability for y==1. To be used only for logistic regression iff the data has been sampled and the mean of response does not reflect reality. | In |
lambda_min_ratio
double | Minimum lambda used in lambda search, specified as a ratio of lambda_max. Default indicates: if the number of observations is greater than the number of variables then lambda_min_ratio is set to 0.0001; if the number of observations is less than the number of variables then lambda_min_ratio is set to 0.01. | In |
beta_constraints
Key | Beta constraints | In |
max_active_predictors
int | Maximum number of active predictors during computation. Use as a stopping criterion to prevent expensive model building with many predictors. Default indicates: If the IRLSM solver is used, the value of max_active_predictors is set to 7000 otherwise it is set to 100000000. | In |
interactions
string[] | A list of predictor column indices to interact. All pairwise combinations will be computed for the list. | In |
compute_p_values
boolean | Request p-values computation, p-values work only with IRLSM solver and no regularization | In |
remove_collinear_columns
boolean | In case of linearly dependent columns, remove some of the dependent columns | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
missing_values_handling
enum | Handling of missing values. Either MeanImputation or Skip. | In/Out |
balance_classes
boolean | Balance training data class counts via over/under-sampling (for imbalanced data). | In/Out |
class_sampling_factors
float[] | 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. | In/Out |
max_after_balance_size
float | Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires balance_classes. | In/Out |
max_confusion_matrix_size
int | [Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs | In/Out |
max_hit_ratio_k
int | Maximum number (top K) of predictions to use for hit ratio computation (for multi-class only, 0 to disable) | In/Out |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
GLMRegularizationPathV3
model
Key | source model | In |
lambdas
double[] | Computed lambda values | In |
explained_deviance_train
double[] | explained deviance on the training set | In |
explained_deviance_valid
double[] | explained deviance on the validation set | In |
coefficients
double[][] | coefficients for all lambdas | In |
coefficients_std
double[][] | standardized coefficients for all lambdas | In |
coefficient_names
string[] | coefficient names | In |
GLMV3
parameters
GLMParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
GLRMModelOutputV3
iterations
int | Number of iterations executed | In |
updates
int | Number of updates executed | In |
objective
double | Current value of the objective function | In |
avg_change_obj
double | Average change in objective value on final iteration | In |
step_size
double | Final step size | In |
archetypes
TwoDimTable | Mapping from lower dimensional k-space to training features (Y) | In |
singular_vals
double[] | Singular values of XY matrix | In |
eigenvectors
TwoDimTable | Eigenvectors of XY matrix | In |
representation_name
string | Frame key name for X matrix | In |
importance
TwoDimTable | Standard deviation and importance of each principal component | In |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
GLRMModelV3
model_id
Key | Model key | In/Out |
parameters
GLRMParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
GLRMOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
GLRMParametersV3
transform
enum | Transformation of training data | In |
k
int | Rank of matrix approximation | In |
loss
enum | Numeric loss function | In |
multi_loss
enum | Categorical loss function | In |
loss_by_col
enum[] | Loss function by column (override) | In |
loss_by_col_idx
int[] | Loss function by column index (override) | In |
period
int | Length of period (only used with periodic loss function) | In |
regularization_x
enum | Regularization function for X matrix | In |
regularization_y
enum | Regularization function for Y matrix | In |
gamma_x
double | Regularization weight on X matrix | In |
gamma_y
double | Regularization weight on Y matrix | In |
max_iterations
int | Maximum number of iterations | In |
max_updates
int | Maximum number of updates, defaults to 2*max_iterations | In |
init_step_size
double | Initial step size | In |
min_step_size
double | Minimum step size | In |
seed
long | RNG seed for initialization | In |
init
enum | Initialization mode | In |
svd_method
enum | Method for computing SVD during initialization (Caution: Randomized is currently experimental and unstable) | In |
user_y
Key | User-specified initial Y | In |
user_x
Key | User-specified initial X | In |
loading_name
string | Frame key to save resulting X | In |
expand_user_y
boolean | Expand categorical columns in user-specified initial Y | In |
impute_original
boolean | Reconstruct original training data by reversing transform | In |
recover_svd
boolean | Recover singular values and eigenvectors of XY | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
GLRMV3
parameters
GLRMParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
GarbageCollectV3
(No fields)
GramV3
X
Key | source data | In |
W
VecSpecifier | weight vector | In |
use_all_factor_levels
boolean | use all factor levels when doing 1-hot encoding | In |
standardize
boolean | standardize data | In |
skip_missing
boolean | skip missing values | In |
destination_frame
Key | Destination key for the resulting matrix. | Out |
GrepModelOutputV3
matches
string[] | Matching strings | In |
offsets
long[] | Byte offsets of matches | In |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
GrepModelV3
model_id
Key | Model key | In/Out |
parameters
GrepParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
GrepOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
GrepParametersV3
regex
string | regex | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
GrepV3
parameters
GrepParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
GridKeyV3
name
string | Name (string representation) for this Key. | In/Out |
type
string | Name (string representation) for the type of Keyed this Key points to. | In/Out |
URL
string | URL for the resource that this Key points to, if one exists. | In/Out |
GridSchemaV99
grid_id
Key | Grid id | In |
model_ids
Key[] | Model IDs built by a grid search | In |
sort_by
string | Model performance metric to sort by. Examples: logloss, residual_deviance, mse, rmse, mae,rmsle, auc, r2, f1, recall, precision, accuracy, mcc, err, err_count, lift_top_group, max_per_class_error | In/Out |
decreasing
boolean | Specify whether sort order should be decreasing. | In/Out |
hyper_names
string[] | Used hyper parameters. | Out |
failed_params
Parameters[] | List of failed parameters | Out |
failure_details
string[] | List of detailed failure messages | Out |
failure_stack_traces
string[] | List of detailed failure stack traces | Out |
failed_raw_params
string[][] | List of raw parameters causing model building failure | Out |
training_metrics
ModelMetrics[] | Training model metrics for the returned models; only returned if sort_by is set | Out |
validation_metrics
ModelMetrics[] | Validation model metrics for the returned models; only returned if sort_by is set | Out |
cross_validation_metrics
ModelMetrics[] | Cross validation model metrics for the returned models; only returned if sort_by is set | Out |
cross_validation_metrics_summary
TwoDimTable[] | Cross validation model metrics summary for the returned models; only returned if sort_by is set | Out |
summary_table
TwoDimTable | Summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
GridSearchSchema
parameters
Parameters | Basic model builder parameters. | In |
hyper_parameters
Map | Grid search parameters. | In/Out |
grid_id
Key | Destination id for this grid; auto-generated if not specified. | In/Out |
search_criteria
HyperSpaceSearchCriteria | Hyperparameter search criteria, including strategy and early stopping directives. If it is not given, exhaustive Cartesian is used. | In/Out |
total_models
int | Number of all models generated by grid search. | Out |
job
Job | Job Key. | Out |
GridsV99
H2OErrorV3
timestamp
long | Milliseconds since the epoch for the time that this H2OError instance was created. Generally this is a short time since the underlying error ocurred. | Out |
error_url
string | Error url | Out |
msg
string | Message intended for the end user (a data scientist). | Out |
dev_msg
string | Potentially more detailed message intended for a developer (e.g. a front end engineer or someone designing a language binding). | Out |
http_status
int | HTTP status code for this error. | Out |
values
Map | Any values that are relevant to reporting or handling this error. Examples are a key name if the error is on a key, or a field name and object name if it’s on a specific field. | Out |
exception_type
string | Exception type, if any. | Out |
exception_msg
string | Raw exception message, if any. | Out |
stacktrace
string[] | Stacktrace, if any. | Out |
H2OModelBuilderErrorV3
parameters
Parameters | Model builder parameters. | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
timestamp
long | Milliseconds since the epoch for the time that this H2OError instance was created. Generally this is a short time since the underlying error ocurred. | Out |
error_url
string | Error url | Out |
msg
string | Message intended for the end user (a data scientist). | Out |
dev_msg
string | Potentially more detailed message intended for a developer (e.g. a front end engineer or someone designing a language binding). | Out |
http_status
int | HTTP status code for this error. | Out |
values
Map | Any values that are relevant to reporting or handling this error. Examples are a key name if the error is on a key, or a field name and object name if it’s on a specific field. | Out |
exception_type
string | Exception type, if any. | Out |
exception_msg
string | Raw exception message, if any. | Out |
stacktrace
string[] | Stacktrace, if any. | Out |
HeartBeatEvent
sends
int | number of sent heartbeats | In |
recvs
int | number of received heartbeats | In |
date
string | Time when the event was recorded. Format is hh:mm:ss:ms | In |
nanos
long | Time in nanos | In |
type
enum | type of recorded event | In |
HyperSpaceSearchCriteriaV99
strategy
enum | Hyperparameter space search strategy. | In/Out |
IOEvent
io_flavor
string | flavor of the recorded io (ice/hdfs/…) | In |
node
string | node where this io event happened | In |
data
string | data info | In |
date
string | Time when the event was recorded. Format is hh:mm:ss:ms | In |
nanos
long | Time in nanos | In |
type
enum | type of recorded event | In |
ImportFilesV3
path
string | path | In |
pattern
string | pattern | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
files
string[] | files | Out |
destination_frames
string[] | names | Out |
fails
string[] | fails | Out |
dels
string[] | dels | Out |
ImportSQLTableV99
connection_url
string | connection_url | In |
table
string | table | In |
select_query
string | select_query | In |
username
string | username | In |
password
string | password | In |
columns
string | columns | In |
optimize
boolean | optimize | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
InitIDV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
session_key
string | Session ID | In/Out |
InputSchemaV4
_fields
string | Filter on the set of output fields: if you set _fields=”foo,bar,baz”, then only those fields will be included in the output; or you can specify _fields=”-goo,gee” to include all fields except goo and gee. If the result contains nested data structures, then you can refer to the fields within those structures as well. For example if you specify _fields=”foo(oof),bar(-rab)”, then only fields foo and bar will be included, and within foo there will be only field oof, whereas within bar all fields except rab will be reported. | In |
InteractionV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
dest
Key | destination key | In/Out |
source_frame
Key | Input data frame | In/Out |
factor_columns
string[] | Factor columns | In/Out |
pairwise
boolean | Whether to create pairwise quadratic interactions between factors (otherwise create one higher-order interaction). Only applicable if there are 3 or more factors. | In/Out |
max_factors
int | Max. number of factor levels in pair-wise interaction terms (if enforced, one extra catch-all factor will be made) | In/Out |
min_occurrence
int | Min. occurrence threshold for factor levels in pair-wise interaction terms | In/Out |
IoStatsEntry
backend
string | Back end type | Out |
store_count
long | Number of store events | Out |
store_bytes
long | Cumulative stored bytes | Out |
delete_count
long | Number of delete events | Out |
load_count
long | Number of load events | Out |
load_bytes
long | Cumulative loaded bytes | Out |
JStackV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
traces
DStackTrace[] | Stacktraces | Out |
JobIV4
job_id
string | Id of the job to fetch. | In |
_fields
string | Filter on the set of output fields: if you set _fields=”foo,bar,baz”, then only those fields will be included in the output; or you can specify _fields=”-goo,gee” to include all fields except goo and gee. If the result contains nested data structures, then you can refer to the fields within those structures as well. For example if you specify _fields=”foo(oof),bar(-rab)”, then only fields foo and bar will be included, and within foo there will be only field oof, whereas within bar all fields except rab will be reported. | In |
JobKeyV3
name
string | Name (string representation) for this Key. | In/Out |
type
string | Name (string representation) for the type of Keyed this Key points to. | In/Out |
URL
string | URL for the resource that this Key points to, if one exists. | In/Out |
JobV3
key
Key | Job Key | In |
description
string | Job description | In |
dest
Key | destination key | In/Out |
status
string | job status | Out |
progress
float | progress, from 0 to 1 | Out |
progress_msg
string | current progress status description | Out |
start_time
long | Start time | Out |
msec
long | Runtime in milliseconds | Out |
warnings
string[] | exception | Out |
exception
string | exception | Out |
stacktrace
string | stacktrace | Out |
ready_for_view
boolean | ready for view | Out |
JobV4
job_id
string | Job id | In |
status
enum | Job status | In |
progress
float | Current progress, a number going from 0 to 1 | In |
progress_msg
string | Current progress status description | In |
start_time
long | Start time | In |
duration
long | Runtime in milliseconds | In |
target_id
string | Id of the target object (being created by this Job) | In |
target_type
string | Type of the target: Frame, Model, etc. | In |
exception
string | Exception message, if an exception occurred | In |
stacktrace
string | Stacktrace | In |
__schema
string | Url describing the schema of the current object. | In |
JobsV3
job_id
Key | Optional Job identifier | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
jobs
Job[] | jobs | Out |
KMeansModelOutputV3
centers
TwoDimTable | Cluster Centers[k][features] | In |
centers_std
TwoDimTable | Cluster Centers[k][features] on Standardized Data | In |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
KMeansModelV3
model_id
Key | Model key | In/Out |
parameters
KMeansParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
KMeansOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
KMeansParametersV3
user_points
Key | This option allows you to specify a dataframe, where each row represents an initial cluster center. The user-specified points must have the same number of columns as the training observations. The number of rows must equal the number of clusters | In |
max_iterations
int | Maximum training iterations (if estimate_k is enabled, then this is for each inner Lloyds iteration) | In |
standardize
boolean | Standardize columns before computing distances | In |
seed
long | RNG Seed | In |
init
enum | Initialization mode | In |
estimate_k
boolean | Whether to estimate the number of clusters (<=k) iteratively and deterministically. | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
k
int | The max. number of clusters. If estimate_k is disabled, the model will find k centroids, otherwise it will find up to k centroids. | In/Out |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
KMeansV3
parameters
KMeansParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
KeyV3
name
string | Name (string representation) for this Key. | In/Out |
type
string | Name (string representation) for the type of Keyed this Key points to. | In/Out |
URL
string | URL for the resource that this Key points to, if one exists. | In/Out |
KillMinus3V3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
LeaderboardKeyV3
name
string | Name (string representation) for this Key. | In/Out |
type
string | Name (string representation) for the type of Keyed this Key points to. | In/Out |
URL
string | URL for the resource that this Key points to, if one exists. | In/Out |
LeaderboardV99
project_name
string | Identifier for models that should be grouped together in the leaderboard | In/Out |
sort_metric
string | Metric used to sort this leaderboard | In/Out |
sort_decreasing
boolean | Metric direction used in the sort | In/Out |
models
Key[] | List of models for this leaderboard, sorted by metric so that the best is first | Out |
sort_metrics
double[] | Sort metrics for the models in this leaderboard, in the same order as the models | Out |
LeaderboardsV99
project_name
string | Name of project of interest | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
leaderboards
Leaderboard[] | Leaderboards | Out |
ListRequestV4
__schema
string | Url describing the schema of the current object. | In |
LogAndEchoV3
message
string | Message to be Logged and Echoed | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
LogsV3
nodeidx
string | Identifier of the node to get logs from. It can be either node index starting from (0-based), where -1 means current node, or IP and port. | In |
name
string | Which specific log file to read from the log file directory. If left unspecified, the system chooses a default for you. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
log
string | Content of log file | Out |
MakeGLMModelV3
model
Key | source model | In |
dest
Key | destination key | In |
names
string[] | coefficient names | In |
beta
double[] | new glm coefficients | In |
threshold
float | decision threshold for label-generation | In |
MetadataV3
num
int | Number for specifying an endpoint | In |
http_method
string | HTTP method (GET, POST, DELETE) if fetching by path | In |
path
string | Path for specifying an endpoint | In |
classname
string | Class name, for fetching docs for a schema (DEPRECATED) | In |
schemaname
string | Schema name (e.g., DocsV1), for fetching docs for a schema | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
routes
Route[] | List of endpoint routes | Out |
schemas
SchemaMetadata[] | List of schemas | Out |
markdown
string | Table of Contents Markdown | Out |
MissingInserterV3
dataset
Key | dataset | In |
fraction
double | Fraction of data to replace with a missing value | In |
seed
long | Seed | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
ModelBuilderSchema
parameters
Parameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
ModelBuilderV3
parameters
Parameters | Model builder parameters. | Out |
messages
ValidationMessage[] | Info, warning and error messages; NOTE: can be appended to while the Job is running | Out |
error_count
int | Count of error messages | Out |
ModelBuildersV3
algo
string | Algo of ModelBuilder of interest | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
model_builders
Map | ModelBuilders | Out |
ModelExportV3
model_id
Key | Name of Model of interest | In |
dir
string | Destination file (hdfs, s3, local) | In |
force
boolean | Overwrite destination file in case it exists or throw exception if set to false. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
ModelIdV3
model_id
string | Model ID | Out |
ModelImportV3
model_id
Key | Save imported model under given key into DKV. | In |
dir
string | Source directory (hdfs, s3, local) containing serialized model | In |
force
boolean | Override existing model in case it exists or throw exception if set to false | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
ModelInfoV4
algo
string | Algorithm name, such as ‘gbm’, ‘deeplearning’, etc. | In |
maturity
string | Development status of the algorithm: alpha, beta, or stable. | In |
have_pojo
boolean | Does the model support generation of POJOs? | In |
have_mojo
boolean | Does the model support generation of MOJOs? | In |
mojo_version
string | Mojo version number for this algorithm. | In |
__schema
string | Url describing the schema of the current object. | In |
ModelKeyV3
name
string | Name (string representation) for this Key. | In/Out |
type
string | Name (string representation) for the type of Keyed this Key points to. | In/Out |
URL
string | URL for the resource that this Key points to, if one exists. | In/Out |
ModelMetricsAutoEncoderV3
nobs
long | Number of observations. | In |
model
Key | The model used for this scoring run. | In/Out |
model_checksum
long | The checksum for the model used for this scoring run. | In/Out |
frame
Key | The frame used for this scoring run. | In/Out |
frame_checksum
long | The checksum for the frame used for this scoring run. | In/Out |
description
string | Optional description for this scoring run (to note out-of-bag, sampled data, etc.) | Out |
model_category
enum | The category (e.g., Clustering) for the model used for this scoring run. | Out |
scoring_time
long | The time in mS since the epoch for the start of this scoring run. | Out |
predictions
Frame | Predictions Frame. | Out |
MSE
double | The Mean Squared Error of the prediction for this scoring run. | Out |
RMSE
double | The Root Mean Squared Error of the prediction for this scoring run. | Out |
ModelMetricsBaseV3
nobs
long | Number of observations. | In |
model
Key | The model used for this scoring run. | In/Out |
model_checksum
long | The checksum for the model used for this scoring run. | In/Out |
frame
Key | The frame used for this scoring run. | In/Out |
frame_checksum
long | The checksum for the frame used for this scoring run. | In/Out |
description
string | Optional description for this scoring run (to note out-of-bag, sampled data, etc.) | Out |
model_category
enum | The category (e.g., Clustering) for the model used for this scoring run. | Out |
scoring_time
long | The time in mS since the epoch for the start of this scoring run. | Out |
predictions
Frame | Predictions Frame. | Out |
MSE
double | The Mean Squared Error of the prediction for this scoring run. | Out |
RMSE
double | The Root Mean Squared Error of the prediction for this scoring run. | Out |
ModelMetricsBinomialGLMV3
nobs
long | Number of observations. | In |
model
Key | The model used for this scoring run. | In/Out |
model_checksum
long | The checksum for the model used for this scoring run. | In/Out |
frame
Key | The frame used for this scoring run. | In/Out |
frame_checksum
long | The checksum for the frame used for this scoring run. | In/Out |
residual_deviance
double | residual deviance | Out |
null_deviance
double | null deviance | Out |
AIC
double | AIC | Out |
null_degrees_of_freedom
long | null DOF | Out |
residual_degrees_of_freedom
long | residual DOF | Out |
r2
double | The R^2 for this scoring run. | Out |
logloss
double | The logarithmic loss for this scoring run. | Out |
AUC
double | The AUC for this scoring run. | Out |
Gini
double | The Gini score for this scoring run. | Out |
mean_per_class_error
double | The mean misclassification error per class. | Out |
domain
string[] | The class labels of the response. | Out |
thresholds_and_metric_scores
TwoDimTable | The Metrics for various thresholds. | Out |
max_criteria_and_metric_scores
TwoDimTable | The Metrics for various criteria. | Out |
gains_lift_table
TwoDimTable | Gains and Lift table. | Out |
description
string | Optional description for this scoring run (to note out-of-bag, sampled data, etc.) | Out |
model_category
enum | The category (e.g., Clustering) for the model used for this scoring run. | Out |
scoring_time
long | The time in mS since the epoch for the start of this scoring run. | Out |
predictions
Frame | Predictions Frame. | Out |
MSE
double | The Mean Squared Error of the prediction for this scoring run. | Out |
RMSE
double | The Root Mean Squared Error of the prediction for this scoring run. | Out |
ModelMetricsBinomialV3
nobs
long | Number of observations. | In |
model
Key | The model used for this scoring run. | In/Out |
model_checksum
long | The checksum for the model used for this scoring run. | In/Out |
frame
Key | The frame used for this scoring run. | In/Out |
frame_checksum
long | The checksum for the frame used for this scoring run. | In/Out |
r2
double | The R^2 for this scoring run. | Out |
logloss
double | The logarithmic loss for this scoring run. | Out |
AUC
double | The AUC for this scoring run. | Out |
Gini
double | The Gini score for this scoring run. | Out |
mean_per_class_error
double | The mean misclassification error per class. | Out |
domain
string[] | The class labels of the response. | Out |
thresholds_and_metric_scores
TwoDimTable | The Metrics for various thresholds. | Out |
max_criteria_and_metric_scores
TwoDimTable | The Metrics for various criteria. | Out |
gains_lift_table
TwoDimTable | Gains and Lift table. | Out |
description
string | Optional description for this scoring run (to note out-of-bag, sampled data, etc.) | Out |
model_category
enum | The category (e.g., Clustering) for the model used for this scoring run. | Out |
scoring_time
long | The time in mS since the epoch for the start of this scoring run. | Out |
predictions
Frame | Predictions Frame. | Out |
MSE
double | The Mean Squared Error of the prediction for this scoring run. | Out |
RMSE
double | The Root Mean Squared Error of the prediction for this scoring run. | Out |
ModelMetricsClusteringV3
tot_withinss
double | Within Cluster Sum of Square Error | In |
totss
double | Total Sum of Square Error to Grand Mean | In |
betweenss
double | Between Cluster Sum of Square Error | In |
centroid_stats
TwoDimTable | Centroid Statistics | In |
nobs
long | Number of observations. | In |
model
Key | The model used for this scoring run. | In/Out |
model_checksum
long | The checksum for the model used for this scoring run. | In/Out |
frame
Key | The frame used for this scoring run. | In/Out |
frame_checksum
long | The checksum for the frame used for this scoring run. | In/Out |
description
string | Optional description for this scoring run (to note out-of-bag, sampled data, etc.) | Out |
model_category
enum | The category (e.g., Clustering) for the model used for this scoring run. | Out |
scoring_time
long | The time in mS since the epoch for the start of this scoring run. | Out |
predictions
Frame | Predictions Frame. | Out |
MSE
double | The Mean Squared Error of the prediction for this scoring run. | Out |
RMSE
double | The Root Mean Squared Error of the prediction for this scoring run. | Out |
ModelMetricsGLRMV99
numerr
double | Sum of Squared Error (Numeric Cols) | In |
caterr
double | Misclassification Error (Categorical Cols) | In |
numcnt
long | Number of Non-Missing Numeric Values | In |
catcnt
long | Number of Non-Missing Categorical Values | In |
nobs
long | Number of observations. | In |
model
Key | The model used for this scoring run. | In/Out |
model_checksum
long | The checksum for the model used for this scoring run. | In/Out |
frame
Key | The frame used for this scoring run. | In/Out |
frame_checksum
long | The checksum for the frame used for this scoring run. | In/Out |
description
string | Optional description for this scoring run (to note out-of-bag, sampled data, etc.) | Out |
model_category
enum | The category (e.g., Clustering) for the model used for this scoring run. | Out |
scoring_time
long | The time in mS since the epoch for the start of this scoring run. | Out |
predictions
Frame | Predictions Frame. | Out |
MSE
double | The Mean Squared Error of the prediction for this scoring run. | Out |
RMSE
double | The Root Mean Squared Error of the prediction for this scoring run. | Out |
ModelMetricsListSchemaV3
model
Key | Key of Model of interest (optional) | In |
frame
Key | Key of Frame of interest (optional) | In |
reconstruction_error
boolean | Compute reconstruction error (optional, only for Deep Learning AutoEncoder models) | In |
reconstruction_error_per_feature
boolean | Compute reconstruction error per feature (optional, only for Deep Learning AutoEncoder models) | In |
deep_features_hidden_layer
int | Extract Deep Features for given hidden layer (optional, only for Deep Learning models) | In |
deep_features_hidden_layer_name
string | Extract Deep Features for given hidden layer by name (optional, only for Deep Water models) | In |
reconstruct_train
boolean | Reconstruct original training frame (optional, only for GLRM models) | In |
project_archetypes
boolean | Project GLRM archetypes back into original feature space (optional, only for GLRM models) | In |
reverse_transform
boolean | Reverse transformation applied during training to model output (optional, only for GLRM models) | In |
leaf_node_assignment
boolean | Return the leaf node assignment (optional, only for DRF/GBM models) | In |
exemplar_index
int | Retrieve all members for a given exemplar (optional, only for Aggregator models) | In |
deviances
boolean | Compute the deviances per row (optional, only for classification or regression models) | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
predictions_frame
Key | Key of predictions frame, if predictions are requested (optional) | In/Out |
deviances_frame
Key | Key for the frame containing per-observation deviances (optional) | In/Out |
model_metrics
ModelMetrics[] | ModelMetrics | Out |
ModelMetricsMakerSchemaV3
predictions_frame
string | Predictions Frame. | In/Out |
actuals_frame
string | Actuals Frame. | In/Out |
domain
string[] | Domain (for classification). | In/Out |
distribution
enum | Distribution (for regression). | In/Out |
model_metrics
ModelMetrics | Model Metrics. | Out |
ModelMetricsMultinomialGLMV3
nobs
long | Number of observations. | In |
model
Key | The model used for this scoring run. | In/Out |
model_checksum
long | The checksum for the model used for this scoring run. | In/Out |
frame
Key | The frame used for this scoring run. | In/Out |
frame_checksum
long | The checksum for the frame used for this scoring run. | In/Out |
residual_deviance
double | residual deviance | Out |
null_deviance
double | null deviance | Out |
AIC
double | AIC | Out |
null_degrees_of_freedom
long | null DOF | Out |
residual_degrees_of_freedom
long | residual DOF | Out |
r2
double | The R^2 for this scoring run. | Out |
hit_ratio_table
TwoDimTable | The hit ratio table for this scoring run. | Out |
cm
ConfusionMatrix | The ConfusionMatrix object for this scoring run. | Out |
logloss
double | The logarithmic loss for this scoring run. | Out |
mean_per_class_error
double | The mean misclassification error per class. | Out |
description
string | Optional description for this scoring run (to note out-of-bag, sampled data, etc.) | Out |
model_category
enum | The category (e.g., Clustering) for the model used for this scoring run. | Out |
scoring_time
long | The time in mS since the epoch for the start of this scoring run. | Out |
predictions
Frame | Predictions Frame. | Out |
MSE
double | The Mean Squared Error of the prediction for this scoring run. | Out |
RMSE
double | The Root Mean Squared Error of the prediction for this scoring run. | Out |
ModelMetricsMultinomialV3
nobs
long | Number of observations. | In |
model
Key | The model used for this scoring run. | In/Out |
model_checksum
long | The checksum for the model used for this scoring run. | In/Out |
frame
Key | The frame used for this scoring run. | In/Out |
frame_checksum
long | The checksum for the frame used for this scoring run. | In/Out |
r2
double | The R^2 for this scoring run. | Out |
hit_ratio_table
TwoDimTable | The hit ratio table for this scoring run. | Out |
cm
ConfusionMatrix | The ConfusionMatrix object for this scoring run. | Out |
logloss
double | The logarithmic loss for this scoring run. | Out |
mean_per_class_error
double | The mean misclassification error per class. | Out |
description
string | Optional description for this scoring run (to note out-of-bag, sampled data, etc.) | Out |
model_category
enum | The category (e.g., Clustering) for the model used for this scoring run. | Out |
scoring_time
long | The time in mS since the epoch for the start of this scoring run. | Out |
predictions
Frame | Predictions Frame. | Out |
MSE
double | The Mean Squared Error of the prediction for this scoring run. | Out |
RMSE
double | The Root Mean Squared Error of the prediction for this scoring run. | Out |
ModelMetricsPCAV3
nobs
long | Number of observations. | In |
model
Key | The model used for this scoring run. | In/Out |
model_checksum
long | The checksum for the model used for this scoring run. | In/Out |
frame
Key | The frame used for this scoring run. | In/Out |
frame_checksum
long | The checksum for the frame used for this scoring run. | In/Out |
description
string | Optional description for this scoring run (to note out-of-bag, sampled data, etc.) | Out |
model_category
enum | The category (e.g., Clustering) for the model used for this scoring run. | Out |
scoring_time
long | The time in mS since the epoch for the start of this scoring run. | Out |
predictions
Frame | Predictions Frame. | Out |
MSE
double | The Mean Squared Error of the prediction for this scoring run. | Out |
RMSE
double | The Root Mean Squared Error of the prediction for this scoring run. | Out |
ModelMetricsRegressionGLMV3
nobs
long | Number of observations. | In |
model
Key | The model used for this scoring run. | In/Out |
model_checksum
long | The checksum for the model used for this scoring run. | In/Out |
frame
Key | The frame used for this scoring run. | In/Out |
frame_checksum
long | The checksum for the frame used for this scoring run. | In/Out |
residual_deviance
double | residual deviance | Out |
null_deviance
double | null deviance | Out |
AIC
double | AIC | Out |
null_degrees_of_freedom
long | null DOF | Out |
residual_degrees_of_freedom
long | residual DOF | Out |
r2
double | The R^2 for this scoring run. | Out |
mean_residual_deviance
double | The mean residual deviance for this scoring run. | Out |
mae
double | The mean absolute error for this scoring run. | Out |
rmsle
double | The root mean squared log error for this scoring run. | Out |
description
string | Optional description for this scoring run (to note out-of-bag, sampled data, etc.) | Out |
model_category
enum | The category (e.g., Clustering) for the model used for this scoring run. | Out |
scoring_time
long | The time in mS since the epoch for the start of this scoring run. | Out |
predictions
Frame | Predictions Frame. | Out |
MSE
double | The Mean Squared Error of the prediction for this scoring run. | Out |
RMSE
double | The Root Mean Squared Error of the prediction for this scoring run. | Out |
ModelMetricsRegressionV3
nobs
long | Number of observations. | In |
model
Key | The model used for this scoring run. | In/Out |
model_checksum
long | The checksum for the model used for this scoring run. | In/Out |
frame
Key | The frame used for this scoring run. | In/Out |
frame_checksum
long | The checksum for the frame used for this scoring run. | In/Out |
r2
double | The R^2 for this scoring run. | Out |
mean_residual_deviance
double | The mean residual deviance for this scoring run. | Out |
mae
double | The mean absolute error for this scoring run. | Out |
rmsle
double | The root mean squared log error for this scoring run. | Out |
description
string | Optional description for this scoring run (to note out-of-bag, sampled data, etc.) | Out |
model_category
enum | The category (e.g., Clustering) for the model used for this scoring run. | Out |
scoring_time
long | The time in mS since the epoch for the start of this scoring run. | Out |
predictions
Frame | Predictions Frame. | Out |
MSE
double | The Mean Squared Error of the prediction for this scoring run. | Out |
RMSE
double | The Root Mean Squared Error of the prediction for this scoring run. | Out |
ModelMetricsSVDV99
nobs
long | Number of observations. | In |
model
Key | The model used for this scoring run. | In/Out |
model_checksum
long | The checksum for the model used for this scoring run. | In/Out |
frame
Key | The frame used for this scoring run. | In/Out |
frame_checksum
long | The checksum for the frame used for this scoring run. | In/Out |
description
string | Optional description for this scoring run (to note out-of-bag, sampled data, etc.) | Out |
model_category
enum | The category (e.g., Clustering) for the model used for this scoring run. | Out |
scoring_time
long | The time in mS since the epoch for the start of this scoring run. | Out |
predictions
Frame | Predictions Frame. | Out |
MSE
double | The Mean Squared Error of the prediction for this scoring run. | Out |
RMSE
double | The Root Mean Squared Error of the prediction for this scoring run. | Out |
ModelOutputSchemaV3
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
ModelParameterSchemaV3
is_member_of_frames
string[] | For Vec-type fields this is the set of other Vec-type fields which must contain mutually exclusive values; for example, for a SupervisedModel the response_column must be mutually exclusive with the weights_column | In |
is_mutually_exclusive_with
string[] | For Vec-type fields this is the set of Frame-type fields which must contain the named column; for example, for a SupervisedModel the response_column must be in both the training_frame and (if it’s set) the validation_frame | In |
name
string | name in the JSON, e.g. “lambda” | Out |
label
string | [DEPRECATED] same as name. | Out |
help
string | help for the UI, e.g. “regularization multiplier, typically used for foo bar baz etc.” | Out |
required
boolean | the field is required | Out |
type
string | Java type, e.g. “double” | Out |
default_value
Polymorphic | default value, e.g. 1 | Out |
actual_value
Polymorphic | actual value as set by the user and / or modified by the ModelBuilder, e.g., 10 | Out |
level
string | the importance of the parameter, used by the UI, e.g. “critical”, “extended” or “expert” | Out |
values
string[] | list of valid values for use by the front-end | Out |
gridable
boolean | Parameter can be used in grid call | Out |
ModelParametersSchemaV3
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
ModelSchemaBaseV3
model_id
Key | Model key | In/Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
ModelSchemaV3
model_id
Key | Model key | In/Out |
parameters
Parameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
Output | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
ModelSynopsisV3
model_id
Key | Model key | In/Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
ModelsInfoV4
models
ModelBuilder[] | Generic information about each model supported in H2O. | In |
__schema
string | Url describing the schema of the current object. | In |
ModelsV3
model_id
Key | Name of Model of interest | In |
preview
boolean | Return potentially abridged model suitable for viewing in a browser | In |
find_compatible_frames
boolean | Find and return compatible frames? | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
models
Model[] | Models | Out |
compatible_frames
Frame[] | Compatible frames | Out |
NaiveBayesModelOutputV3
levels
string[] | Categorical levels of the response | In |
apriori
TwoDimTable | A-priori probabilities of the response | In |
pcond
TwoDimTable[] | Conditional probabilities of the predictors | In |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
NaiveBayesModelV3
model_id
Key | Model key | In/Out |
parameters
NaiveBayesParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
NaiveBayesOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
NaiveBayesParametersV3
laplace
double | Laplace smoothing parameter | In |
min_sdev
double | Min. standard deviation to use for observations with not enough data | In |
eps_sdev
double | Cutoff below which standard deviation is replaced with min_sdev | In |
min_prob
double | Min. probability to use for observations with not enough data | In |
eps_prob
double | Cutoff below which probability is replaced with min_prob | In |
compute_metrics
boolean | Compute metrics on training data | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
balance_classes
boolean | Balance training data class counts via over/under-sampling (for imbalanced data). | In/Out |
class_sampling_factors
float[] | 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. | In/Out |
max_after_balance_size
float | Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires balance_classes. | In/Out |
max_confusion_matrix_size
int | [Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs | In/Out |
max_hit_ratio_k
int | Max. number (top K) of predictions to use for hit ratio computation (for multi-class only, 0 to disable) | In/Out |
seed
long | Seed for pseudo random number generator (only used for cross-validation and fold_assignment=”Random” or “AUTO”) | In/Out |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
NaiveBayesV3
parameters
NaiveBayesParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
NetworkBenchV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
results
TwoDimTable[] | NetworkBenchResults | Out |
NetworkEvent
is_send
boolean | Boolean flag distinguishing between sends (true) and receives(false) | In |
protocol
string | network protocol (UDP/TCP) | In |
msg_type
string | UDP type (exec,ack, ackack,… | In |
from
string | Sending node | In |
to
string | Receiving node | In |
data
string | Pretty print of the first few bytes of the msg payload. Contains class name for tasks. | In |
date
string | Time when the event was recorded. Format is hh:mm:ss:ms | In |
nanos
long | Time in nanos | In |
type
enum | type of recorded event | In |
NetworkTestV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
microseconds_collective
double[] | Collective broadcast/reduce times in microseconds (for each message size) | Out |
bandwidths_collective
double[] | Collective bandwidths in Bytes/sec (for each message size, for each node) | Out |
microseconds
double[][] | Round-trip times in microseconds (for each message size, for each node) | Out |
bandwidths
double[][] | Bi-directional bandwidths in Bytes/sec (for each message size, for each node) | Out |
nodes
string[] | Nodes | Out |
table
TwoDimTable | NetworkTestResults | Out |
NodePersistentStorageEntryV3
category
string | Category name | Out |
name
string | Key name | Out |
size
long | Size in bytes of value | Out |
timestamp_millis
long | Epoch time in milliseconds of when the value was written | Out |
NodePersistentStorageV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
category
string | Category name | In/Out |
name
string | Key name | In/Out |
value
string | Value | In/Out |
configured
boolean | Configured | Out |
exists
boolean | Exists | Out |
entries
Iced[] | List of entries | Out |
NodeV3
h2o
string | IP | Out |
ip_port
string | IP address and port in the form a.b.c.d:e | Out |
healthy
boolean | (now-last_ping)<HeartbeatThread.TIMEOUT | Out |
last_ping
long | Time (in msec) of last ping | Out |
pid
int | PID | Out |
num_cpus
int | num_cpus | Out |
cpus_allowed
int | cpus_allowed | Out |
nthreads
int | nthreads | Out |
sys_load
float | System load; average #runnables/#cores | Out |
my_cpu_pct
int | System CPU percentage used by this H2O process in last interval | Out |
sys_cpu_pct
int | System CPU percentage used by everything in last interval | Out |
mem_value_size
long | Data on Node memory | Out |
pojo_mem
long | Temp (non Data) memory | Out |
free_mem
long | Free heap | Out |
max_mem
long | Maximum memory size for node | Out |
swap_mem
long | Size of data on node’s disk | Out |
num_keys
int | id="local-keys">local keys< | Out |
free_disk
long | Free disk | Out |
max_disk
long | Max disk | Out |
rpcs_active
int | Active Remote Procedure Calls | Out |
fjthrds
short[] | F/J Thread count, by priority | Out |
fjqueue
short[] | F/J Task count, by priority | Out |
tcps_active
int | Open TCP connections | Out |
open_fds
int | Open File Descripters | Out |
gflops
double | Linpack GFlops | Out |
mem_bw
double | Memory Bandwidth | Out |
OutputSchemaV4
__schema
string | Url describing the schema of the current object. | In |
PCAModelOutputV3
importance
TwoDimTable | Standard deviation and importance of each principal component | In |
eigenvectors
TwoDimTable | Principal components matrix | In |
objective
double | Final value of GLRM squared loss function | In |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
PCAModelV3
model_id
Key | Model key | In/Out |
parameters
PCAParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
PCAOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
PCAParametersV3
transform
enum | Transformation of training data | In |
pca_method
enum | Method for computing PCA (Caution: GLRM is currently experimental and unstable) | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
k
int | Rank of matrix approximation | In/Out |
max_iterations
int | Maximum training iterations | In/Out |
seed
long | RNG seed for initialization | In/Out |
use_all_factor_levels
boolean | Whether first factor level is included in each categorical expansion | In/Out |
compute_metrics
boolean | Whether to compute metrics on the training data | In/Out |
impute_missing
boolean | Whether to impute missing entries with the column mean | In/Out |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
PCAV3
parameters
PCAParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
ParseSVMLightV3
destination_frame
Key | Final frame name | In |
source_frames
Key[] | Source frames | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
ParseSetupV3
decrypt_tool
Key | Key-reference to an initialized instance of a Decryption Tool | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
source_frames
Key[] | Source frames | In/Out |
parse_type
enum | Parser type | In/Out |
separator
byte | Field separator | In/Out |
single_quotes
boolean | Single quotes | In/Out |
check_header
int | Check header: 0 means guess, +1 means 1st line is header not data, -1 means 1st line is data not header | In/Out |
column_names
string[] | Column names | In/Out |
column_types
string[] | Value types for columns | In/Out |
na_strings
string[][] | NA strings for columns | In/Out |
column_name_filter
string | Regex for names of columns to return | In/Out |
column_offset
int | Column offset to return | In/Out |
column_count
int | Number of columns to return | In/Out |
total_filtered_column_count
int | Total number of columns we would return with no column pagination | In/Out |
destination_frame
string | Suggested name | Out |
header_lines
long | Number of header lines found | Out |
number_columns
int | Number of columns | Out |
data
string[][] | Sample data | Out |
warnings
string[] | Warnings | Out |
chunk_size
int | Size of individual parse tasks | Out |
ParseV3
destination_frame
Key | Final frame name | In |
source_frames
Key[] | Source frames | In |
parse_type
enum | Parser type | In |
separator
byte | Field separator | In |
single_quotes
boolean | Single Quotes | In |
check_header
int | Check header: 0 means guess, +1 means 1st line is header not data, -1 means 1st line is data not header | In |
number_columns
int | Number of columns | In |
column_names
string[] | Column names | In |
column_types
string[] | Value types for columns | In |
domains
string[][] | Domains for categorical columns | In |
na_strings
string[][] | NA strings for columns | In |
chunk_size
int | Size of individual parse tasks | In |
delete_on_done
boolean | Delete input key after parse | In |
blocking
boolean | Block until the parse completes (as opposed to returning early and requiring polling | In |
decrypt_tool
Key | Key-reference to an initialized instance of a Decryption Tool | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
job
Job | Parse job | Out |
rows
long | Rows | Out |
PartialDependenceKeyV3
name
string | Name (string representation) for this Key. | In/Out |
type
string | Name (string representation) for the type of Keyed this Key points to. | In/Out |
URL
string | URL for the resource that this Key points to, if one exists. | In/Out |
PartialDependenceV3
destination_key
Key | Key to store the destination | In |
model_id
Key | Model | In/Out |
frame_id
Key | Frame | In/Out |
cols
string[] | Column(s) | In/Out |
nbins
int | Number of bins | In/Out |
partial_dependence_data
TwoDimTable[] | Partial Dependence Data | Out |
ProfilerNodeEntryV3
stacktrace
string | Stack trace | Out |
count
int | Profile Count | Out |
ProfilerNodeV3
node_name
string | Node names | Out |
timestamp
long | Timestamp (millis since epoch) | Out |
entries
Iced[] | Profile entry list | Out |
ProfilerV3
depth
int | Stack trace depth | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
nodes
Iced[] | (No description available) | Out |
QuantileParametersV3
probs
double[] | Probabilities for quantiles | In |
combine_method
enum | How to combine quantiles for even sample sizes | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
QuantileV3
parameters
QuantileParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
RandomDiscreteValueSearchCriteriaV99
seed
long | Seed for random number generator; set to a value other than -1 for reproducibility. | In/Out |
max_models
int | Maximum number of models to build (optional). | In/Out |
max_runtime_secs
double | Maximum time to spend building models (optional). | In/Out |
stopping_rounds
int | 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) | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
strategy
enum | Hyperparameter space search strategy. | In/Out |
RapidsExpressionV3
name
string | (Class) name of the language construct | In |
pattern
string | Code fragment pattern. | In |
description
string | Description of the functionality provided by this language construct. | In |
RapidsFrameV3
ast
string | A Rapids AstRoot expression | In |
session_id
string | Session key | In |
id
string | [DEPRECATED] Key name to assign Frame results | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
key
Key | Frame result | Out |
num_rows
long | Rows in Frame result | Out |
num_cols
int | Columns in Frame result | Out |
RapidsFunctionV3
ast
string | A Rapids AstRoot expression | In |
session_id
string | Session key | In |
id
string | [DEPRECATED] Key name to assign Frame results | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
funstr
string | Function result | Out |
RapidsHelpV3
expressions
Iced[] | Description of the rapids language. | Out |
RapidsNumberV3
ast
string | A Rapids AstRoot expression | In |
session_id
string | Session key | In |
id
string | [DEPRECATED] Key name to assign Frame results | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
scalar
double | Number result | Out |
RapidsNumbersV3
ast
string | A Rapids AstRoot expression | In |
session_id
string | Session key | In |
id
string | [DEPRECATED] Key name to assign Frame results | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
scalar
double[] | Number array result | Out |
RapidsSchemaV3
ast
string | A Rapids AstRoot expression | In |
session_id
string | Session key | In |
id
string | [DEPRECATED] Key name to assign Frame results | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
RapidsStringV3
ast
string | A Rapids AstRoot expression | In |
session_id
string | Session key | In |
id
string | [DEPRECATED] Key name to assign Frame results | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
string
string | String result | Out |
RapidsStringsV3
ast
string | A Rapids AstRoot expression | In |
session_id
string | Session key | In |
id
string | [DEPRECATED] Key name to assign Frame results | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
string
string[] | String array result | Out |
RapidsV99
ast
string | An Abstract Syntax Tree. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
error
string | Parsing error, if any | Out |
scalar
double | Scalar result | Out |
funstr
string | Function result | Out |
string
string | String result | Out |
key
Key | Result key | Out |
num_rows
long | Rows in Frame result | Out |
num_cols
int | Columns in Frame result | Out |
RemoveAllV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
RemoveV3
key
Key | Object to be removed. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
RequestSchemaV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
RouteV3
http_method
string | (No description available) | Out |
url_pattern
string | (No description available) | Out |
summary
string | (No description available) | Out |
api_name
string | (No description available) | Out |
handler_class
string | (No description available) | Out |
handler_method
string | (No description available) | Out |
input_schema
string | (No description available) | Out |
output_schema
string | (No description available) | Out |
path_params
string[] | (No description available) | Out |
markdown
string | (No description available) | Out |
SVDModelOutputV99
v_key
Key | Frame key of right singular vectors | In |
d
double[] | Singular values | In |
u_key
Key | Frame key of left singular vectors | In |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
SVDModelV99
model_id
Key | Model key | In/Out |
parameters
SVDParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
SVDOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
SVDParametersV99
transform
enum | Transformation of training data | In |
svd_method
enum | Method for computing SVD (Caution: Randomized is currently experimental and unstable) | In |
nv
int | Number of right singular vectors | In |
max_iterations
int | Maximum iterations | In |
seed
long | RNG seed for k-means++ initialization | In |
keep_u
boolean | Save left singular vectors? | In |
u_name
string | Frame key to save left singular vectors | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
use_all_factor_levels
boolean | Whether first factor level is included in each categorical expansion | In/Out |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
SVDV99
parameters
SVDParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
SchemaMetadataV3
version
int | Version number of the Schema. | In |
name
string | Simple name of the Schema. NOTE: the schema_names form a single namespace. | In |
superclass
string | Simple name of the superclass of the Schema. NOTE: the schema_names form a single namespace. | In |
type
string | Simple name of H2O type that this Schema represents. Must not be changed after creation (treat as final). | In |
label
string | [DEPRECATED] This field is always the same as name. | Out |
fields
FieldMetadata[] | All the public fields of the schema | Out |
markdown
string | Documentation for the schema in Markdown format with GitHub extensions | Out |
SchemaV3
(No fields)
SessionIdV4
session_key
string | Session ID | In |
__schema
string | Url describing the schema of the current object. | In |
SharedTreeModelOutputV3
variable_importances
TwoDimTable | Variable Importances | Out |
init_f
double | The Intercept term, the initial model function value to which trees make adjustments | Out |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
SharedTreeModelV3
model_id
Key | Model key | In/Out |
parameters
Parameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
Output | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
SharedTreeParametersV3
ntrees
int | Number of trees. | In |
max_depth
int | Maximum tree depth. | In |
min_rows
double | Fewest allowed (weighted) observations in a leaf. | In |
nbins
int | For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the best point | In |
nbins_top_level
int | For numerical columns (real/int), build a histogram of (at most) this many bins at the root level, then decrease by factor of two per level | In |
nbins_cats
int | For categorical columns (factors), build a histogram of this many bins, then split at the best point. Higher values can lead to more overfitting. | In |
r2_stopping
double | r2_stopping is no longer supported and will be ignored if set - please use stopping_rounds, stopping_metric and stopping_tolerance instead. Previous version of H2O would stop making trees when the R^2 metric equals or exceeds this | In |
seed
long | Seed for pseudo random number generator (if applicable) | In |
build_tree_one_node
boolean | Run on one node only; no network overhead but fewer cpus used. Suitable for small datasets. | In |
sample_rate
double | Row sample rate per tree (from 0.0 to 1.0) | In |
sample_rate_per_class
double[] | A list of row sample rates per class (relative fraction for each class, from 0.0 to 1.0), for each tree | In |
col_sample_rate_per_tree
double | Column sample rate per tree (from 0.0 to 1.0) | In |
col_sample_rate_change_per_level
double | Relative change of the column sampling rate for every level (from 0.0 to 2.0) | In |
score_tree_interval
int | Score the model after every so many trees. Disabled if set to 0. | In |
min_split_improvement
double | Minimum relative improvement in squared error reduction for a split to happen | In |
histogram_type
enum | What type of histogram to use for finding optimal split points | In |
calibrate_model
boolean | Use Platt Scaling to calculate calibrated class probabilities. Calibration can provide more accurate estimates of class probabilities. | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
balance_classes
boolean | Balance training data class counts via over/under-sampling (for imbalanced data). | In/Out |
class_sampling_factors
float[] | 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. | In/Out |
max_after_balance_size
float | Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires balance_classes. | In/Out |
max_confusion_matrix_size
int | [Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs | In/Out |
max_hit_ratio_k
int | Max. number (top K) of predictions to use for hit ratio computation (for multi-class only, 0 to disable) | In/Out |
calibration_frame
Key | Calibration frame for Platt Scaling | In/Out |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
SharedTreeV3
parameters
Parameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
ShutdownV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
SplitFrameV3
key
Key | Job Key | In |
dataset
Key | Dataset | In |
ratios
double[] | Split ratios - resulting number of split is ratios.length+1 | In |
destination_frames
Key[] | Destination keys for each output frame split. | In/Out |
StackedEnsembleModelOutputV99
metalearner
Key | Model which combines the base_models into a stacked ensemble. | Out |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
StackedEnsembleModelV99
model_id
Key | Model key | In/Out |
parameters
StackedEnsembleParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
StackedEnsembleOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
StackedEnsembleParametersV99
base_models
Key[] | List of model ids which we can stack together. Models must have been cross-validated using nfolds > 1, and folds must be identical across models. | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
StackedEnsembleV99
parameters
StackedEnsembleParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
SteamMetricsV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
version
long | Steam metrics API version | Out |
idle_millis
long | Number of milliseconds that the cluster has been idle | Out |
StreamingSchema
(No fields)
TabulateV3
dataset
Key | Dataset | In |
nbins_predictor
int | Number of bins for predictor column | In |
nbins_response
int | Number of bins for response column | In |
predictor
VecSpecifier | Predictor | In/Out |
response
VecSpecifier | Response | In/Out |
weight
VecSpecifier | Observation weights (optional) | In/Out |
count_table
TwoDimTable | Counts table | Out |
response_table
TwoDimTable | Response table | Out |
TimelineV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
now
long | Current time in millis. | Out |
self
string | This node | Out |
events
Iced[] | recorded timeline events | Out |
TreeStatsV3
min_depth
int | minDepth | In |
max_depth
int | maxDepth | In |
mean_depth
float | meanDepth | In |
min_leaves
int | minLeaves | In |
max_leaves
int | maxLeaves | In |
mean_leaves
float | meanLeaves | In |
TwoDimTableV3
name
string | Table Name | Out |
description
string | Table Description | Out |
columns
Iced[] | Column Specification | Out |
rowcount
int | Number of Rows | Out |
data
Polymorphic[][] | Table Data (col-major) | Out |
TypeaheadV3
src
string | training_frame | In |
limit
int | limit | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
matches
string[] | matches | Out |
UnlockKeysV3
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
UserFeedbackEventV99
timestamp
long | Timestamp for this event, in milliseconds since Jan 1, 1970 | Out |
level
enum | Importance of this feedback event | Out |
stage
enum | Stage of the AutoML process for this feedback event | Out |
message
string | User message for this event | Out |
UserFeedbackV99
automl_id
Key | The AutoML ID for these events | In/Out |
feedback_events
UserFeedbackEvent[] | (No description available) | Out |
ValidationMessageV3
message_type
string | Type of validation message (ERROR, WARN, INFO, HIDE) | Out |
field_name
string | Field to which the message applies | Out |
message
string | Message text | Out |
VarImpV3
varimp
float[] | Variable importance of individual variables | Out |
names
string[] | Names of variables | Out |
WaterMeterCpuTicksV3
nodeidx
int | Index of node to query ticks for (0-based) | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
cpu_ticks
long[][] | array of tick counts per core | Out |
WaterMeterIoV3
nodeidx
int | Index of node to query ticks for (0-based) | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
persist_stats
Iced[] | array of IO info | Out |
Word2VecModelOutputV3
epochs
int | Number of epochs executed | In |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
Word2VecModelV3
model_id
Key | Model key | In/Out |
parameters
Word2VecParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
Word2VecOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
Word2VecParametersV3
vec_size
int | Set size of word vectors | In |
window_size
int | Set max skip length between words | In |
sent_sample_rate
float | Set threshold for occurrence of words. Those that appear with higher frequency in the training data
will be randomly down-sampled; useful range is (0, 1e-5) | In |
norm_model
enum | Use Hierarchical Softmax | In |
epochs
int | Number of training iterations to run | In |
min_word_freq
int | This will discard words that appear less than times | In |
init_learning_rate
float | Set the starting learning rate | In |
word_model
enum | Use the Skip-Gram model | In |
pre_trained
Key | Id of a data frame that contains a pre-trained (external) word2vec model | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
Word2VecSynonymsV3
model
Key | Source word2vec Model | In |
word
string | Target word to find synonyms for | In |
count
int | Number of synonyms | In |
synonyms
string[] | Synonymous words | In |
scores
double[] | Similarity scores | In |
Word2VecTransformV3
model
Key | Source word2vec Model | In |
words_frame
Key | Words Frame | In |
aggregate_method
enum | Method of aggregating word-vector sequences into a single vector | In |
vectors_frame
Key | Word Vectors Frame | Out |
Word2VecV3
parameters
Word2VecParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |
XGBoostModelOutputV3
variable_importances
TwoDimTable | Variable Importances | Out |
names
string[] | Column names | Out |
domains
string[][] | Domains for categorical columns | Out |
cross_validation_models
Key[] | Cross-validation models (model ids) | Out |
cross_validation_predictions
Key[] | Cross-validation predictions, one per cv model (deprecated, use cross_validation_holdout_predictions_frame_id instead) | Out |
cross_validation_holdout_predictions_frame_id
Key | Cross-validation holdout predictions (full out-of-sample predictions on training data) | Out |
cross_validation_fold_assignment_frame_id
Key | Cross-validation fold assignment (each row is assigned to one holdout fold) | Out |
model_category
enum | Category of the model (e.g., Binomial) | Out |
model_summary
TwoDimTable | Model summary | Out |
scoring_history
TwoDimTable | Scoring history | Out |
training_metrics
ModelMetrics | Training data model metrics | Out |
validation_metrics
ModelMetrics | Validation data model metrics | Out |
cross_validation_metrics
ModelMetrics | Cross-validation model metrics | Out |
cross_validation_metrics_summary
TwoDimTable | Cross-validation model metrics summary | Out |
status
string | Job status | Out |
start_time
long | Start time in milliseconds | Out |
end_time
long | End time in milliseconds | Out |
run_time
long | Runtime in milliseconds | Out |
help
Map | Help information for output fields | Out |
XGBoostModelV3
model_id
Key | Model key | In/Out |
parameters
XGBoostParameters | The build parameters for the model (e.g. K for KMeans). | Out |
output
XGBoostOutput | The build output for the model (e.g. the cluster centers for KMeans). | Out |
compatible_frames
string[] | Compatible frames, if requested | Out |
checksum
long | Checksum for all the things that go into building the Model. | Out |
algo
string | The algo name for this Model. | Out |
algo_full_name
string | The pretty algo name for this Model (e.g., Generalized Linear Model, rather than GLM). | Out |
response_column_name
string | The response column name for this Model (if applicable). Is null otherwise. | Out |
data_frame
Key | The Model’s training frame key | Out |
timestamp
long | Timestamp for when this model was completed | Out |
XGBoostParametersV3
ntrees
int | (same as n_estimators) Number of trees. | In |
n_estimators
int | (same as ntrees) Number of trees. | In |
max_depth
int | Maximum tree depth. | In |
min_rows
double | (same as min_child_weight) Fewest allowed (weighted) observations in a leaf. | In |
min_child_weight
double | (same as min_rows) Fewest allowed (weighted) observations in a leaf. | In |
learn_rate
double | (same as eta) Learning rate (from 0.0 to 1.0) | In |
eta
double | (same as learn_rate) Learning rate (from 0.0 to 1.0) | In |
sample_rate
double | (same as subsample) Row sample rate per tree (from 0.0 to 1.0) | In |
subsample
double | (same as sample_rate) Row sample rate per tree (from 0.0 to 1.0) | In |
col_sample_rate
double | (same as colsample_bylevel) Column sample rate (from 0.0 to 1.0) | In |
colsample_bylevel
double | (same as col_sample_rate) Column sample rate (from 0.0 to 1.0) | In |
col_sample_rate_per_tree
double | (same as colsample_bytree) Column sample rate per tree (from 0.0 to 1.0) | In |
colsample_bytree
double | (same as col_sample_rate_per_tree) Column sample rate per tree (from 0.0 to 1.0) | In |
max_abs_leafnode_pred
float | (same as max_delta_step) Maximum absolute value of a leaf node prediction | In |
max_delta_step
float | (same as max_abs_leafnode_pred) Maximum absolute value of a leaf node prediction | In |
score_tree_interval
int | Score the model after every so many trees. Disabled if set to 0. | In |
seed
long | Seed for pseudo random number generator (if applicable) | In |
min_split_improvement
float | (same as gamma) Minimum relative improvement in squared error reduction for a split to happen | In |
gamma
float | (same as min_split_improvement) Minimum relative improvement in squared error reduction for a split to happen | In |
max_bins
int | For tree_method=hist only: maximum number of bins | In |
max_leaves
int | For tree_method=hist only: maximum number of leaves | In |
min_sum_hessian_in_leaf
float | For tree_method=hist only: the mininum sum of hessian in a leaf to keep splitting | In |
min_data_in_leaf
float | For tree_method=hist only: the mininum data in a leaf to keep splitting | In |
tree_method
enum | Tree method | In |
grow_policy
enum | Grow policy - depthwise is standard GBM, lossguide is LightGBM | In |
booster
enum | Booster type | In |
reg_lambda
float | L2 regularization | In |
reg_alpha
float | L1 regularization | In |
quiet_mode
boolean | Enable quiet mode | In |
sample_type
enum | For booster=dart only: sample_type | In |
normalize_type
enum | For booster=dart only: normalize_type | In |
rate_drop
float | For booster=dart only: rate_drop (0..1) | In |
one_drop
boolean | For booster=dart only: one_drop | In |
skip_drop
float | For booster=dart only: skip_drop (0..1) | In |
dmatrix_type
enum | Type of DMatrix. For sparse, NAs and 0 are treated equally. | In |
backend
enum | Backend. By default (auto), a GPU is used if available. | In |
gpu_id
int | Which GPU to use. | In |
distribution
enum | Distribution function | In |
tweedie_power
double | Tweedie power for Tweedie regression, must be between 1 and 2. | In |
quantile_alpha
double | Desired quantile for Quantile regression, must be between 0 and 1. | In |
huber_alpha
double | Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). | In |
max_categorical_levels
int | For every categorical feature, only use this many most frequent categorical levels for model training. Only used for categorical_encoding == EnumLimited. | In |
model_id
Key | Destination id for this model; auto-generated if not specified. | In/Out |
training_frame
Key | Id of the training data frame (Not required, to allow initial validation of model parameters). | In/Out |
validation_frame
Key | Id of the validation data frame. | In/Out |
nfolds
int | Number of folds for N-fold cross-validation (0 to disable or >= 2). | In/Out |
keep_cross_validation_predictions
boolean | Whether to keep the predictions of the cross-validation models. | In/Out |
keep_cross_validation_fold_assignment
boolean | Whether to keep the cross-validation fold assignment. | In/Out |
parallelize_cross_validation
boolean | Allow parallel training of cross-validation models | In/Out |
response_column
VecSpecifier | Response variable column. | In/Out |
weights_column
VecSpecifier | 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. | In/Out |
offset_column
VecSpecifier | Offset column. This will be added to the combination of columns before applying the link function. | In/Out |
fold_column
VecSpecifier | Column with cross-validation fold index assignment per observation. | In/Out |
fold_assignment
enum | 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. | In/Out |
categorical_encoding
enum | Encoding scheme for categorical features | In/Out |
ignored_columns
string[] | Names of columns to ignore for training. | In/Out |
ignore_const_cols
boolean | Ignore constant columns. | In/Out |
score_each_iteration
boolean | Whether to score during each iteration of model training. | In/Out |
checkpoint
Key | Model checkpoint to resume training with. | In/Out |
stopping_rounds
int | 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) | In/Out |
max_runtime_secs
double | Maximum allowed runtime in seconds for model training. Use 0 to disable. | In/Out |
stopping_metric
enum | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) | In/Out |
stopping_tolerance
double | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) | In/Out |
XGBoostV3
parameters
XGBoostParameters | Model builder parameters. | In |
_exclude_fields
string | Comma-separated list of JSON field paths to exclude from the result, used like: “/3/Frames?_exclude_fields=frames/frame_id/URL,__meta” | In |
algo
string | The algo name for this ModelBuilder. | Out |
algo_full_name
string | The pretty algo name for this ModelBuilder (e.g., Generalized Linear Model, rather than GLM). | Out |
can_build
enum[] | Model categories this ModelBuilder can build. | Out |
supervised
boolean | Indicator whether the model is supervised or not. | Out |
visibility
enum | Should the builder always be visible, be marked as beta, or only visible if the user starts up with the experimental flag? | Out |
job
Job | Job Key | Out |
messages
ValidationMessage[] | Parameter validation messages | Out |
error_count
int | Count of parameter validation errors | Out |
__http_status
int | HTTP status to return for this build. | Out |