# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/deletedProjects/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
Parameters
Name
In
Type
Required
Description
searchFor
query
string
false
Project or dataset name to filter by
creator
query
string
false
Creator ID to filter projects by
organization
query
string
false
ID of organization that projects should belong to. Given project belongs to the organization the user who created the project is part of that organization.If there are no users in organization, then no projects will match the query.
deletedBefore
query
string(date-time)
false
ISO-8601 formatted date projects were deleted before
deletedAfter
query
string(date-time)
false
ISO-8601 formatted date projects were deleted after
# You can also use wget
curl-XPATCHhttps://app.datarobot.com/api/v2/deletedProjects/{projectId}/\-H"Content-Type: application/json"\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"\-d'{undefined}'
Get current number of deleted projects matching search criteria. Value is limited by DELETED_PROJECTS_BATCH_LIMIT system setting. That means that the actual amount of deleted projects can be greater than the limit, but counting will stop when reaching it.
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/deletedProjectsCount/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
Parameters
Name
In
Type
Required
Description
searchFor
query
string
false
Project or dataset name to filter by
creator
query
string
false
Creator ID to filter projects by
organization
query
string
false
ID of organization that projects should belong to. Given project belongs to the organization the user who created the project is part of that organization.If there are no users in organization, then no projects will match the query.
deletedBefore
query
string(date-time)
false
ISO-8601 formatted date projects were deleted before
deletedAfter
query
string(date-time)
false
ISO-8601 formatted date projects were deleted after
projectId
query
string
false
Project ID to search
limit
query
integer
false
Count deleted projects until specified value reached.
Soft-deleted projects amount, current counting limit value and boolean flag to notify if an actual amount of soft-deleted projects in the system exceeds the limit value.
Create a project from an HDFS file via WebHDFS API. Represent the file using URL, optionally, port, and optionally, user/password credentials. For example, {"url": "hdfs://<ip>/path/to/file.csv", "port": "50070"}.
# You can also use wget
curl-XPOSThttps://app.datarobot.com/api/v2/hdfsProjects/\-H"Content-Type: application/json"\-H"Authorization: Bearer {access-token}"\-d'{HdfsProjectCreate}'
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projectCleanupJobs/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
# You can also use wget
curl-XPOSThttps://app.datarobot.com/api/v2/projectCleanupJobs/\-H"Content-Type: application/json"\-H"Authorization: Bearer {access-token}"\-d'{ProjectNuke}'
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projectCleanupJobs/{statusId}/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projectCleanupJobs/{statusId}/download/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projectCleanupJobs/{statusId}/summary/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
Create a clone of an existing project.
The resultant project will begin the initial exploratory
data analysis and will be ready to set the target of the new project shortly.
# You can also use wget
curl-XPOSThttps://app.datarobot.com/api/v2/projectClones/\-H"Content-Type: application/json"\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"\-d'{ProjectClone}'
Information related to the current model of the deployment.
»» allowedPairwiseInteractionGroups
[array]
false
For GAM models - specify groups of columns for which pairwise interactions will be allowed. E.g. if set to [["A", "B", "C"], ["C", "D"]] then GAM models will allow interactions between columns AxB, BxC, AxC, CxD. All others (AxD, BxD) will not be considered. If not specified - all possible interactions will be considered by model.
»» blendBestModels
boolean
true
blend best models during Autopilot run [DEPRECATED]
»» blueprintThreshold
integer¦null
true
an upper bound on running time (in hours), such that models exceeding the bound will be excluded in subsequent autopilot runs
»» considerBlendersInRecommendation
boolean
false
Include blenders when selecting a model to prepare for deployment in an Autopilot Run.[DEPRECATED]
»» defaultMonotonicDecreasingFeaturelistId
string¦null
true
null or str, the ID of the featurelist specifying a set of features with a monotonically decreasing relationship to the target. All blueprints generated in the project use this as their default monotonic constraint, but it can be overriden at model submission time.
»» defaultMonotonicIncreasingFeaturelistId
string¦null
true
null or str, the ID of the featurelist specifying a set of features with a monotonically increasing relationship to the target. All blueprints generated in the project use this as their default monotonic constraint, but it can be overriden at model submission time.
»» downsampledMajorityRows
integer¦null
true
the total number of the majority rows available for modeling, or null for projects without smart downsampling
»» downsampledMinorityRows
integer¦null
true
the total number of the minority rows available for modeling, or null for projects without smart downsampling
»» eventsCount
string¦null
false
the name of the event count column, if specified, otherwise null.
»» exposure
string¦null
false
the name of the exposure column, if specified.
»» majorityDownsamplingRate
number¦null
true
the percentage between 0 and 100 of the majority rows that are kept, or null for projects without smart downsampling
»» minSecondaryValidationModelCount
boolean
false
Compute "All backtest" scores (datetime models) or cross validation scores for the specified number of highest ranking models on the Leaderboard, if over the Autopilot default.
»» offset
[string]¦null
false
the list of names of the offset columns, if specified, otherwise null.
»» onlyIncludeMonotonicBlueprints
boolean
true
whether the project only includes blueprints support enforcing monotonic constraints
»» prepareModelForDeployment
boolean¦null
true
Prepare model for deployment during Autopilot run. The preparation includes creating reduced feature list models, retraining best model on higher sample size, computing insights and assigning "RECOMMENDED FOR DEPLOYMENT" label.
»» responseCap
any
true
defaults to False, if specified used to cap the maximum response of a model
oneOf
Name
Type
Required
Restrictions
Description
»»» anonymous
boolean
false
none
xor
Name
Type
Required
Restrictions
Description
»»» anonymous
number
false
maximum: 1 minimum: 0.5
none
continued
Name
Type
Required
Restrictions
Description
»» runLeakageRemovedFeatureList
boolean
false
Run Autopilot on Leakage Removed feature list (if exists).
»» scoringCodeOnly
boolean
false
Keep only models that can be converted to scorable java code during Autopilot run.
»» seed
string¦null
true
defaults to null, the random seed to be used if specified
»» shapOnlyMode
boolean¦null
true
Keep only models that support SHAP values during Autopilot run. Use SHAP-based insights wherever possible. For pre SHAP-only mode projects this is always null.
»» smartDownsampled
boolean
true
whether the project uses smart downsampling to throw away excess rows of the majority class. Smart downsampled projects express all sample percents in terms of percent of minority rows (as opposed to percent of all rows).
»» weights
string¦null
true
the name of the weight column, if specified, otherwise null.
» autopilotClusterList
[integer]¦null
false
maxItems: 10
Optional. A list of integers where each value will be used as the number of clusters in Autopilot model(s) for unsupervised clustering projects. Cannot be specified unless unsupervisedMode is true and unsupervisedType is set to 'clustering'.
» autopilotMode
integer
true
The current autopilot mode, 0 for full autopilot, 2 for manual mode, 3 for quick mode, 4 for comprehensive mode
» created
string(date-time)
true
The time of project creation.
» featureEngineeringPredictionPoint
string¦null
false
The date column to be used as the prediction point for time-based feature engineering.
» fileName
string
true
The name of the dataset used to create the project.
» holdoutUnlocked
boolean
true
whether the holdout has been unlocked
» id
string
true
The ID of a project.
» maxClusters
integer¦null
false
maximum: 100 minimum: 2
Only valid when unsupervisedMode is True and unsupervisedType is 'clustering'. The maximum number of clusters allowed when training clustering models. If specified cannot be exceed the number of rows in a project's dataset divided by 50 and must be less than or equal to minClusters. If unsupervisedMode is True and unsupervisedType is 'clustering' then defaults to the number of rows in the project's dataset divided by 50 or 100 if that number of greater than 100.
» maxTrainPct
number
true
the maximum percentage of the dataset that can be used to successfully train a model without going into the validation data.
» maxTrainRows
integer
true
the maximum number of rows of the dataset that can be used to successfully train a model without going into the validation data
» metric
string
true
the metric used to select the best-performing models.
» minClusters
integer¦null
false
maximum: 100 minimum: 2
Only valid when unsupervisedMode is True and unsupervisedType is 'clustering'. The minimum number of clusters allowed when training clustering models. If specified cannot be exceed the number of rows in a project's dataset divided by 50 and must be less than or equal to maxClusters. If unsupervisedMode is True and unsupervisedType is 'clustering' then defaults to 2.
The partition object of a project indicates the settings used for partitioning. Depending on the partitioning selected, many of the options will be null. Note that for projects whose cvMethod is "datetime", full specification of the partitioning method can be found at GET /api/v2/projects/{projectId}/datetimePartitioning/.
»» cvHoldoutLevel
any
true
if a user partition column was used with cross validation, the value assigned to the holdout set
anyOf
Name
Type
Required
Restrictions
Description
»»» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
»»» anonymous
number
false
none
or
Name
Type
Required
Restrictions
Description
»»» anonymous
integer
false
none
continued
Name
Type
Required
Restrictions
Description
»» cvMethod
string
true
the partitioning method used. Note that "date" partitioning is an old partitioning method no longer supported for new projects, as of API version v2.0.
»» datetimeCol
string¦null
true
if a date partition column was used, the name of the column. Note that datetimeCol applies to an old partitioning method no longer supported for new projects, as of API version v2.0.
»» datetimePartitionColumn
string
false
if a datetime partition column was used, the name of the column
»» holdoutLevel
any
true
if a user partition column was used with train-validation-holdout split, the value assigned to the holdout set
anyOf
Name
Type
Required
Restrictions
Description
»»» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
»»» anonymous
number
false
none
or
Name
Type
Required
Restrictions
Description
»»» anonymous
integer
false
none
continued
Name
Type
Required
Restrictions
Description
»» holdoutPct
number
true
the percentage of the dataset reserved for the holdout set
»» partitionKeyCols
[string]¦null
true
An array containing a single string - the name of the group partition column
»» reps
number¦null
true
if cross validation was used, the number of folds to use
»» trainingLevel
any
true
if a user partition column was used with train-validation-holdout split, the value assigned to the training set
anyOf
Name
Type
Required
Restrictions
Description
»»» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
»»» anonymous
number
false
none
or
Name
Type
Required
Restrictions
Description
»»» anonymous
integer
false
none
continued
Name
Type
Required
Restrictions
Description
»» useTimeSeries
boolean¦null
true
A boolean value indicating whether a time series project was created as opposed to a regular project using datetime partitioning.
»» userPartitionCol
string¦null
true
if a user partition column was used, the name of the column
»» validationLevel
any
true
if a user partition column was used with train-validation-holdout split, the value assigned to the validation set
anyOf
Name
Type
Required
Restrictions
Description
»»» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
»»» anonymous
number
false
none
or
Name
Type
Required
Restrictions
Description
»»» anonymous
integer
false
none
continued
Name
Type
Required
Restrictions
Description
»» validationPct
number¦null
true
if train-validation-holdout split was used, the percentage of the dataset used for the validation set
»» validationType
string
true
either CV for cross-validation or TVH for train-validation-holdout split
» positiveClass
number¦null
true
if the project uses binary classification, the class designated to be the positive class. Otherwise, null.
» projectName
string
true
The name of a project.
» stage
string
true
the stage of the project - if modeling, then the target is successfully set, and modeling or predictions can proceed.
» target
string
true
the target of the project, null if project is unsupervised.
» targetType
string¦null
true
The target type of the project.
» unsupervisedMode
boolean
true
indicates whether a project is unsupervised.
» unsupervisedType
string¦null
false
Only valid when unsupervisedMode is True. The type of unsupervised project, anomaly or clustering. If unsupervisedMode, defaults to 'anomaly'.
» useFeatureDiscovery
boolean
true
A boolean value indicating whether a feature discovery project was created as opposed to a regular project.
# You can also use wget
curl-XPOSThttps://app.datarobot.com/api/v2/projects/\-H"Content-Type: application/json"\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"\-d'{ProjectCreate}'
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projects/{projectId}/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
Change project name, worker count, or unlock the holdout.
If any of the optional json arguments are not provided,
that aspect of the project will not be altered.
# You can also use wget
curl-XPATCHhttps://app.datarobot.com/api/v2/projects/{projectId}/\-H"Content-Type: application/json"\-H"Authorization: Bearer {access-token}"\-d'{undefined}'
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projects/{projectId}/accessControl/?offset=0&limit=0\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
Parameters
Name
In
Type
Required
Description
offset
query
integer
true
This many results will be skipped
limit
query
integer
true
At most this many results are returned
username
query
string
false
Optional, only return the access control information for a user with this username.
userId
query
string
false
Optional, only return the access control information for a user with this user ID.
# You can also use wget
curl-XPATCHhttps://app.datarobot.com/api/v2/projects/{projectId}/accessControl/\-H"Content-Type: application/json"\-H"Authorization: Bearer {access-token}"\-d'{undefined}'
# You can also use wget
curl-XPATCHhttps://app.datarobot.com/api/v2/projects/{projectId}/aim/\-H"Content-Type: application/json"\-H"Authorization: Bearer {access-token}"\-d'{undefined}'
# You can also use wget
curl-XPOSThttps://app.datarobot.com/api/v2/projects/{projectId}/autopilot/\-H"Content-Type: application/json"\-H"Authorization: Bearer {access-token}"\-d'{undefined}'
# You can also use wget
curl-XPOSThttps://app.datarobot.com/api/v2/projects/{projectId}/autopilots/\-H"Content-Type: application/json"\-H"Authorization: Bearer {access-token}"\-d'{undefined}'
Autopilot on this featurelist has already completed or is already in progress. This status code is also returned if target was not selected for specified project.
None
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/projects/{projectId}/externalTimeSeriesBaselineDataValidationJobs/¶
This route validates if a provided catalog version id can be used as baseline for calculating metrics. This functionality is available only for time series projects.For a baseline dataset to be valid, the number of unique date amd multiseries_id columnrows must match the unique number of date and multiseries_id column rows in the uploadedtraining dataset. This functionality is limited to one forecast distance. Additionally, the catalog must be a snapshot.
# You can also use wget
curl-XPOSThttps://app.datarobot.com/api/v2/projects/{projectId}/externalTimeSeriesBaselineDataValidationJobs/\-H"Content-Type: application/json"\-H"Authorization: Bearer {access-token}"\-d'{undefined}'
Validate baseline data that is provided in the form of a catalog version id. We willconfirm that the dataset contains the proper date, target column, and multiseries ID column. If the provided dataset meets the criteria, the job will be successful.
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/projects/{projectId}/externalTimeSeriesBaselineDataValidationJobs/{baselineValidationJobId}/¶
Retrieve information to confirm if the validation job triggered via /api/v2/projects/(projectId)/externalTimeSeriesBaselineDataValidationJobs/ is valid.
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projects/{projectId}/externalTimeSeriesBaselineDataValidationJobs/{baselineValidationJobId}/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
Parameters
Name
In
Type
Required
Description
projectId
path
string
true
The project to retrieve the validation job information from.
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projects/{projectId}/jobs/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
Parameters
Name
In
Type
Required
Description
status
query
string
false
If provided, only jobs with the same status will be included in the results; otherwise, queued and inprogress jobs (but not errored jobs) will be returned.
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projects/{projectId}/jobs/{jobId}/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
The requested job has already finished. See the Location header for the job details.
None
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
GET /api/v2/projects/{projectId}/multiseriesIds/{multiseriesId}/crossSeriesProperties/¶
Retrieve eligible cross-series group-by columns.
Note that validation will have to have been triggered via [POST /api/v2/projects/{projectId}/crossSeriesProperties/][post-apiv2projectsprojectidcrossseriesproperties] in order for results to appear here.
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projects/{projectId}/multiseriesIds/{multiseriesId}/crossSeriesProperties/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
Parameters
Name
In
Type
Required
Description
crossSeriesGroupByColumns
query
any
false
The names of the columns to retrieve the validation status for. If not specified, all eligible columns will be returned.
projectId
path
string
true
The project to retrieve cross-series group-by columns for.
multiseriesId
path
string
true
The name of the column to be used as the multiseries ID column.
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projects/{projectId}/multiseriesNames/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
Parameters
Name
In
Type
Required
Description
offset
query
integer
false
Number of results to skip.
limit
query
integer
false
At most this many results are returned. The default may change without notice.
To perform this operation, you must be authenticated by means of one of the following methods:
BearerAuth
POST /api/v2/projects/{projectId}/multiseriesProperties/¶
Analyze relationships between potential partition and multiseries ID columns. Time series projects require that each timestamp have at most one row corresponding to it. However, multiple series of data can be handled within a single project by designating a multiseries ID column that assigns each row to a particular series. See the :ref:multiseries <multiseries> docs on time series projects for more information. A detection job analyzing the relationship between the multiseries ID column and the datetime partition column must be ran before it can be used. If the desired multiseries ID column(s) are known, it can be specified to limit the analysis to only those columns.
# You can also use wget
curl-XPOSThttps://app.datarobot.com/api/v2/projects/{projectId}/multiseriesProperties/\-H"Content-Type: application/json"\-H"Authorization: Bearer {access-token}"\-d'{undefined}'
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projects/{projectId}/segmentationTaskJobResults/{segmentationTaskId}/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
Parameters
Name
In
Type
Required
Description
projectId
path
string
true
The project ID
segmentationTaskId
path
string
true
The ID of the segmentation task to check the status of.
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projects/{projectId}/segmentationTasks/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
# You can also use wget
curl-XPOSThttps://app.datarobot.com/api/v2/projects/{projectId}/segmentationTasks/\-H"Content-Type: application/json"\-H"Authorization: Bearer {access-token}"\-d'{undefined}'
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projects/{projectId}/segmentationTasks/{segmentationTaskId}/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projects/{projectId}/segmentationTasks/{segmentationTaskId}/mappings/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
The only supported operation right now is segment restart, which removes existing child segment project and starts another child project instead for the given segment. Should be only used for child segments which are stuck during project startup or upload.
# You can also use wget
curl-XPATCHhttps://app.datarobot.com/api/v2/projects/{projectId}/segments/{segmentId}/\-H"Content-Type: application/json"\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"\-d'{undefined}'
# You can also use wget
curl-XGEThttps://app.datarobot.com/api/v2/projects/{projectId}/status/\-H"Accept: application/json"\-H"Authorization: Bearer {access-token}"
Include additional, longer-running models that will be run by the autopilot and available to run manually.
aggregationType
string
false
For multiseries projects only. The aggregation type to apply when creating cross-series features.
allowPartialHistoryTimeSeriesPredictions
boolean
false
Specifies whether the time series predictions can use partial historical data.
allowedPairwiseInteractionGroups
[array]¦null
false
maxItems: 100
For GAM models - specify groups of columns for which pairwise interactions will be allowed. E.g. if set to [['A', 'B', 'C'], ['C', 'D']] then GAM models will allow interactions between columns AxB, BxC, AxC, CxD. All others (AxD, BxD) will not be considered. If not specified - all possible interactions will be considered by model.
allowedPairwiseInteractionGroupsFilename
string¦null
false
Filename that was used to upload allowed_pairwise_interaction_groups. Necessary for persistence of UI/UX when you specify that parameter via file.
autopilotClusterList
[integer]¦null
false
maxItems: 10
A list of integers where each value will be used as the number of clusters in Autopilot model(s) for unsupervised clustering projects. Cannot be specified unless unsupervisedMode is true and unsupervisedType is set to clustering.
autopilotDataSamplingMethod
string
false
Defines how autopilot will select subsample from training dataset in OTV/TS projects. Defaults to 'latest' for 'rowCount' dataSelectionMethod and to 'random' for 'duration'.
autopilotDataSelectionMethod
string
true
The Data Selection method to be used by autopilot when creating models for datetime-partitioned datasets.
autopilotWithFeatureDiscovery
boolean
false
If true, autopilot will run on a feature list that includes features found via search for interactions.
Include blenders when selecting a model to prepare for deployment in an Autopilot Run. This option is not supported in SHAP-only mode or for multilabel projects.
credentials
[oneOf]
false
maxItems: 30
List of credentials for the secondary datasets used in feature discovery project.
For multiseries projects with cross-series features enabled only. List of columns (currently of length 1). Setting that indicates how to further split series into related groups. For example, if every series is sales of an individual product, the series group-by could be the product category with values like "men's clothing", "sports equipment", etc.
cvHoldoutLevel
any
false
The value of the partition column indicating a row is part of the holdout set. This level is optional - if not specified or if provided as null, then no holdout will be used in the project. The rest of the levels indicate which cross validation fold each row should fall into.
anyOf
Name
Type
Required
Restrictions
Description
» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
integer
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
number
false
none
continued
Name
Type
Required
Restrictions
Description
cvMethod
string
false
The partitioning method to be applied to the training data.
dateRemoval
boolean
false
If true, enable creating additional feature lists without dates (does not apply to time-aware projects).
datetimePartitionColumn
string
false
The date column that will be used as a datetime partition column.
datetimePartitioningId
string
false
The ID of a datetime partitioning to use for the project.When datetime_partitioning_id is specified, no other datetime partitioning related field is allowed to be specified, as these fields get loaded from the already created partitioning.
defaultToAPriori
boolean
false
Renamed to defaultToKnownInAdvance.
defaultToDoNotDerive
boolean
false
For time series projects only. Sets whether all features default to being treated as do-not-derive features, excluding them from feature derivation. Individual features can be set to a value different than the default by using the featureSettings parameter.
defaultToKnownInAdvance
boolean
false
For time series projects only. Sets whether all features default to being treated as known in advance features, which are features that are known into the future. Features marked as known in advance must be specified into the future when making predictions. The default is false, all features are not known in advance. Individual features can be set to a value different than the default using the featureSettings parameter. See the :ref:Time Series Overview <time_series_overview> for more context.
differencingMethod
string
false
For time series projects only. Used to specify which differencing method to apply if the data is stationary. For classification problems simple and seasonal are not allowed. Parameter periodicities must be specified if seasonal is chosen. Defaults to auto.
disableHoldout
boolean
false
Whether to suppress allocating a holdout fold. If disableHoldout is set to true, holdoutStartDate and holdoutDuration must not be set.
eventsCount
string
false
The name of a column specifying events count. The data in this column must be pure numeric and non negative without missing values
exponentiallyWeightedMovingAlpha
number
false
maximum: 1 minimum: 0
Discount factor (alpha) used for exponentially weighted moving features
exposure
string
false
The name of a column specifying row exposure.The data in this column must be pure numeric (e.g. not currency, date, length, etc.) and without missing values
externalPredictions
[string]
false
maxItems: 100 minItems: 1
List of external prediction columns from the dataset.
externalTimeSeriesBaselineDatasetId
string
false
Catalog version id for external prediction data that can be used as a baseline to calculate new metrics.
externalTimeSeriesBaselineDatasetName
string¦null
false
The name of the time series baseline dataset for the project.
fairnessMetricsSet
string
false
Metric to use for calculating fairness. Can be one of proportionalParity, equalParity, predictionBalance, trueFavorableAndUnfavorableRateParity or FavorableAndUnfavorablePredictiveValueParity. Used and required only if Bias & Fairness in AutoML feature is enabled.
fairnessThreshold
number
false
maximum: 1 minimum: 0
The threshold value of the fairness metric. The valid range is [0:1]; the default fairness metric value is 0.8. This metric is only applicable if the Bias & Fairness in AutoML feature is enabled.
featureDerivationWindowEnd
integer
false
maximum: 0
For time series projects only. How many timeUnits of the datetimePartitionColumn into the past relative to the forecast point the feature derivation window should end.
featureDerivationWindowStart
integer
false
maximum: 0
For time series projects only. How many timeUnits of the datetimePartitionColumn into the past relative to the forecast point the feature derivation window should begin.
featureDiscoverySupervisedFeatureReduction
boolean
false
Run supervised feature reduction for feature discovery projects.
featureEngineeringPredictionPoint
string¦null
false
The date column to be used as the prediction point for time-based feature engineering.
An array specifying per feature settings. Features can be left unspecified.
featurelistId
string
false
The ID of a featurelist to use for autopilot.
forecastDistance
string
false
The name of a column specifying the forecast distance to which each row of the dataset belongs. Column unique values are used to subset the modeling data and build a separate model for each unique column value. Similar to time series this column is well suited to be used as forecast distance.
forecastOffsets
[string]
false
maxItems: 100 minItems: 1
An array of strings with names of a columns specifying row offsets. Columns values are used as offset or predictions to boost for models. The data in this column must be pure numeric (e.g. not currency, date, length, etc.).
forecastWindowEnd
integer
false
minimum: 0
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should end.
forecastWindowStart
integer
false
minimum: 0
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should start.
gapDuration
string(duration)
false
The duration of the gap between holdout training and holdout scoring data. For time series projects, defaults to the duration of the gap between the end of the feature derivation window and the beginning of the forecast window. For OTV projects, defaults to a zero duration (P0Y0M0D).
holdoutDuration
string(duration)
false
The duration of holdout scoring data. When specifying holdoutDuration, holdoutStartDate must also be specified. This attribute cannot be specified when disableHoldout is true.
holdoutEndDate
string(date-time)
false
The end date of holdout scoring data. When specifying holdoutEndDate, holdoutStartDate must also be specified. This attribute cannot be specified when disableHoldout is true.
holdoutLevel
any
false
The value of the partition column indicating a row is part of the holdout set. This level is optional - if not specified or if provided as null, then no holdout will be used in the project. However, the column must have exactly 2 values in order for this option to be valid
anyOf
Name
Type
Required
Restrictions
Description
» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
integer
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
number
false
none
continued
Name
Type
Required
Restrictions
Description
holdoutPct
number
false
maximum: 98 minimum: 0
The percentage of the dataset to assign to the holdout set
holdoutStartDate
string(date-time)
false
The start date of holdout scoring data. When specifying holdoutStartDate, one of holdoutEndDate or holdoutDuration must also be specified. This attribute cannot be specified when disableHoldout is true.
includeBiasMitigationFeatureAsPredictorVariable
boolean
false
Specifies whether the mitigation feature will be used as a predictor variable (i.e., treated like other categorical features in the input to train the modeler), in addition to being used for bias mitigation. If false, the mitigation feature will be used only for bias mitigation, and not for training the modeler task.
incrementalLearningEarlyStoppingRounds
integer
false
minimum: 0
Early stopping rounds for the auto incremental learning service
incrementalLearningOnBestModel
boolean
false
Automatically run incremental learning on the best model during Autopilot run.
incrementalLearningOnlyMode
boolean
false
Keep only models that support incremental learning during Autopilot run.
isHoldoutModified
boolean
false
A boolean value indicating whether holdout settings (start/end dates) have been modified by user.
majorityDownsamplingRate
number
false
The percentage between 0 and 100 of the majority rows that should be kept. Must be specified only if using smart downsampling. If not specified, a default will be selected based on the dataset distribution. The chosen rate may not cause the majority class to become smaller than the minority class.
metric
string
false
The metric to use to select the best models. See /api/v2/projects/(projectId)/features/metrics/ for the metrics that may be valid for a potential target. Note that weighted metrics must be used with a weights column.
minSecondaryValidationModelCount
integer
false
maximum: 10 minimum: 0
Compute 'All backtest' scores (datetime models) or cross validation scores for the specified number of highest ranking models on the Leaderboard, if over the Autopilot default.
mode
string
false
The autopilot mode to use. Either 'quick', 'auto', 'manual' or 'comprehensive'
modelSplits
integer
false
maximum: 10 minimum: 1
Sets the cap on the number of jobs per model used when building models to control number of jobs in the queue. Higher number of modelSplits will allow for less downsampling leading to the use of more post-processed data.
monotonicDecreasingFeaturelistId
string¦null
false
The ID of the featurelist that defines the set of features with a monotonically decreasing relationship to the target. If null, no such constraints are enforced. When specified, this will set a default for the project that can be overriden at model submission time if desired.
monotonicIncreasingFeaturelistId
string¦null
false
The ID of the featurelist that defines the set of features with a monotonically increasing relationship to the target. If null, no such constraints are enforced. When specified, this will set a default for the project that can be overriden at model submission time if desired.
multiseriesIdColumns
[string]
false
minItems: 1
May be used only with time series projects. An array of the column names identifying the series to which each row of the dataset belongs. Currently only one multiseries ID column is supported. See the :ref:multiseries <multiseries> section of the time series documentation for more context.
numberOfBacktests
integer
false
The number of backtests to use. If omitted, defaults to a positive value selected by the server based on the validation and gap durations.
Number of incremental_learning iterations before best model selection.
offset
[string]
false
An array of strings with names of a columns specifying row offsets.The data in this column must be pure numeric (e.g. not currency, date, length, etc.) and without missing values
onlyIncludeMonotonicBlueprints
boolean
true
When true, only blueprints that support enforcing montonic constraints will be available in the project or selected for autopilot.
partitionKeyCols
[string]
false
An array containing a single string - the name of the group partition column
A list of periodicities for time series projects only. For classification problems periodicities are not allowed. If this is provided, parameter 'differencing_method' will default to 'seasonal' if not provided or 'auto'.
positiveClass
any
false
A value from the target column to use for the positive class. May only be specified for projects doing binary classification.If not specified, a positive class is selected automatically.
anyOf
Name
Type
Required
Restrictions
Description
» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
integer
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
number
false
none
continued
Name
Type
Required
Restrictions
Description
preferableTargetValue
any
false
A target value that should be treated as a positive outcome for the prediction. For example if we want to check gender discrimination for giving a loan and our target named is_bad, then the positive outcome for the prediction would be No, which means that the loan is good and that's what we treat as a preferable result for the loaner. Used and required only if Bias & Fairness in AutoML feature is enabled.
anyOf
Name
Type
Required
Restrictions
Description
» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
integer
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
number
false
none
continued
Name
Type
Required
Restrictions
Description
prepareModelForDeployment
boolean
false
Prepare model for deployment during Autopilot run. The preparation includes creating reduced feature list models, retraining best model on higher sample size, computing insights and assigning 'RECOMMENDED FOR DEPLOYMENT' label.
primaryLocationColumn
string¦null
false
Primary geospatial location column.
protectedFeatures
[string]
false
maxItems: 10 minItems: 1
A list of project feature to mark as protected for Bias metric calculation and Fairness correction. Used and required only if Bias & Fairness in AutoML feature is enabled.
quantileLevel
number
false
maximum: 1 (exclusive) minimum: 0 (exclusive)
The quantile level between 0.01 and 0.99 for specifying the Quantile metric.
quickrun
boolean
false
(Deprecated): 'quick' should be used in the mode parameter instead of using this parameter. If set to true, autopilot mode will be set to 'quick'.Cannot be set to true when mode is set to 'comprehensive' or 'manual'.
rateTopPctThreshold
number
false
maximum: 100 minimum: 0
The percentage threshold between 0.1 and 50 for specifying the Rate@Top% metric.
relationshipsConfigurationId
string¦null
false
Relationships configuration id to be used for Feature Discovery projects.
reps
integer
false
maximum: 999999 minimum: 2
The number of cross validation folds to use.
responseCap
number
false
maximum: 1 minimum: 0.5
Used to cap the maximum response of a model
runLeakageRemovedFeatureList
boolean
false
Run Autopilot on Leakage Removed feature list (if exists).
sampleStepPct
number
false
maximum: 100 minimum: 0 (exclusive)
A float between 0 and 100 indicating the desired percentage of data to sample when training models in comprehensive Autopilot. Note: this only supported for comprehensive Autopilot and the specified value may be lowered in order to be compatible with the project's dataset and partition settings.
scoringCodeOnly
boolean
false
Keep only models that can be converted to scorable java code during Autopilot run.
seed
integer
false
maximum: 999999999 minimum: 0
A seed to use for randomization.
segmentationTaskId
string¦null
false
Specifies the SegmentationTask that will be used for dividing the project up into multiple segmented projects.
seriesId
string
false
The name of a column specifying the series ID to which each row of the dataset belongs. Typically the series was used to derive the additional features, that are independent from each other. Column unique values are used to subset the modeling data and build a separate model for each unique column value. Similar to time series this column is well suited to be used as multi-series ID column.
shapOnlyMode
boolean
false
Keep only models that support SHAP values during Autopilot run. Use SHAP-based insights wherever possible.
smartDownsampled
boolean
false
Whether to use smart downsampling to throw away excess rows of the majority class. Only applicable to classification and zero-boosted regression projects.
stopWords
[string]
false
maxItems: 1000
A list of stop words to be used for text blueprints. Note: stop_words=True must be set in the blueprint preprocessing parameters for this list of stop words to actually be used during preprocessing.
target
string
false
The name of the target feature.
targetType
string
false
Used to specify the targetType to use for a project when it is ambiguous, i.e. a numeric target with a few unique values that could be used for either regression or multiclass.
trainingLevel
any
false
The value of the partition column indicating a row is part of the training set.
anyOf
Name
Type
Required
Restrictions
Description
» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
integer
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
number
false
none
continued
Name
Type
Required
Restrictions
Description
treatAsExponential
string
false
For time series projects only. Used to specify whether to treat data as exponential trend and apply transformations like log-transform. For classification problems always is not allowed.
unsupervisedMode
boolean
false
If True, unsupervised project (without target) will be created. target cannot be specified if unsupervisedMode is True.
unsupervisedType
string¦null
false
The type of unsupervised project. Only valid when unsupervisedMode is true. If unsupervisedMode, defaults to anomaly.
useCrossSeriesFeatures
boolean
false
Indicating if user wants to use cross-series features.
useGpu
boolean
false
Indicates whether project should use GPU workers
useProjectSettings
boolean
false
Specifies whether datetime-partitioned project should use project settings (i.e. backtests configuration has been modified by the user).
useSupervisedFeatureReduction
boolean
false
When true, during feature generation DataRobot runs a supervised algorithm that identifies those features with predictive impact on the target and builds feature lists using only qualifying features. Setting false can severely impact autopilot duration, especially for datasets with many features.
useTimeSeries
boolean
false
A boolean value indicating whether a time series project should be created instead of a regular project which uses datetime partitioning.
userPartitionCol
string
false
The name of the column containing the partition assignments.
validationDuration
string(duration)
false
The default validation duration for all backtests. If the primary date/time feature in a time series project is irregular, you cannot set a default validation length. Instead, set each duration individually. For an OTV project setting the validation duration will always use regular partitioning. Omitting it will use irregular partitioning if the date/time feature is irregular.
validationLevel
any
false
The value of the partition column indicating a row is part of the validation set.
anyOf
Name
Type
Required
Restrictions
Description
» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
integer
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
number
false
none
continued
Name
Type
Required
Restrictions
Description
validationPct
number
false
maximum: 99 minimum: 0
The percentage of the dataset to assign to the validation set
validationType
string
false
The validation method to be used. CV for cross validation or TVH for train-validation-holdout split.
weights
string
false
The name of a column specifying row weights. The data in this column must be pure numeric (e.g. not currency, date, length, etc.) and without missing values
windowsBasisUnit
string
false
For time series projects only. Indicates which unit is basis for feature derivation window and forecast window. Valid options are detected time unit or ROW. If omitted, the default value is detected time unit.
Optional. A list of integers where each value will be used as the number of clusters in Autopilot model(s) for unsupervised clustering projects. Cannot be specified unless unsupervisedMode is true and unsupervisedType is set to 'clustering'.
blendBestModels
boolean
false
Blend best models during Autopilot run. This option is not supported in SHAP-only mode or for multilabel projects.
considerBlendersInRecommendation
boolean
false
Include blenders when selecting a model to prepare for deployment in an Autopilot Run. This option is not supported in SHAP-only mode or for multilabel projects.
featurelistId
string
true
The ID of a featurelist that should be used for autopilot.
mode
string
false
The autopilot mode.
prepareModelForDeployment
boolean
false
Prepare model for deployment during Autopilot run. The preparation includes creating reduced feature list models, retraining best model on higher sample size, computing insights and assigning "RECOMMENDED FOR DEPLOYMENT" label.
runLeakageRemovedFeatureList
boolean
false
Run Autopilot on Leakage Removed feature list (if exists).
scoringCodeOnly
boolean
false
Keep only models that can be converted to scorable java code during Autopilot run.
The name of the class that will be assigned to all rows with aggregated classes. Should not match any excluded_from_aggregation or we will have 2 classes with the same name and no way to distinguish between them. This option is only available formulticlass projects. By default 'DR_RARE_TARGET_VALUES' is used.
excludedFromAggregation
[string]
false
List of target values that should be guaranteed to kept as is, regardless of other settings.
maxUnaggregatedClassValues
integer
false
maximum: 1000 minimum: 3
The maximum number of unique labels before aggregation kicks in. Should be at least len(excludedFromAggregation) + 1 for multiclass and at least len(excludedFromAggregation) for multilabel.
minClassSupport
integer
false
Minimum number of instances necessary for each target value in the dataset. All values with fewer instances than this value will be aggregated
The version id of the external baseline data item in the AI catalog.
datetimePartitionColumn
string
true
The date column that will be used as the datetime partition column for the specified project.
forecastWindowEnd
integer
true
minimum: 0
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should end.
forecastWindowStart
integer
true
minimum: 0
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should start.
holdoutEndDate
string(date-time)
false
The end date of holdout scoring data.
holdoutStartDate
string(date-time)
false
The start date of holdout scoring data.
multiseriesIdColumns
[string]
false
maxItems: 1 minItems: 1
An array of column names identifying the multiseries ID column(s)to use to identify series within the data. Must match the multiseries ID column(s) for the specified project. Currently, only one multiseries ID column may be specified.
The version id of the external baseline data item in the AI catalog.
datetimePartitionColumn
string
true
The date column that will be used as the datetime partition column for the specified project.
forecastWindowEnd
integer
false
minimum: 0
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should end.
forecastWindowStart
integer
false
minimum: 0
For time series projects only. How many timeUnits of the datetimePartitionColumn into the future relative to the forecast point the forecast window should start.
holdoutEndDate
string(date-time)
false
The end date of holdout scoring data.
holdoutStartDate
string(date-time)
false
The start date of holdout scoring data.
isExternalBaselineDatasetValid
boolean
true
Indicates whether the external dataset has pass the validation check or not.
message
string¦null
true
A message providing mode detail on the validation result.
multiseriesIdColumns
[string]
false
maxItems: 1 minItems: 1
An array of column names identifying the multiseries ID column(s)to use to identify series within the data. Must match the multiseries ID column(s) for the specified project. Currently, only one multiseries ID column may be specified.
projectId
string
true
The project id of the external baseline data item.
For time series projects only. Sets whether the feature is do-not-derive, i.e., is excluded from feature derivation. If not specified, the feature uses the value from the defaultToDoNotDerive flag.
featureName
string
true
The name of the feature being specified.
knownInAdvance
boolean
false
For time series projects only. Sets whether the feature is known in advance, i.e., values for future dates are known at prediction time. If not specified, the feature uses the value from the defaultToKnownInAdvance flag.
The Google Cloud Platform (GCP) key. Output is the downloaded JSON resulting from creating a service account User Managed Key (in the IAM & admin > Service accounts section of GCP).Required if googleConfigId/configId is not specified.Cannot include this parameter if googleConfigId/configId is specified.
The Google Cloud Platform (GCP) key. Output is the downloaded JSON resulting from creating a service account User Managed Key (in the IAM & admin > Service accounts section of GCP).Required if googleConfigId/configId is not specified.Cannot include this parameter if googleConfigId/configId is specified.
googleConfigId
string
false
ID of Secure configurations shared by admin. This is deprecated.Please use configId instead. If specified, cannot include gcpKey.
Password for authenticating to HDFS using Kerberos. The password will be encrypted on the server side in scope of HTTP request and never saved or stored.
port
integer
false
Port of the WebHDFS Namenode server. If not specified, defaults to HDFS default port 50070.
projectName
string
false
Name of the project to be created. If not specified, project name will be based on the file name.
url
string(uri)
true
URL of the WebHDFS resource. Represent the file using the hdfs:// protocol marker (for example, hdfs:///tmp/somedataset.csv).
user
string
false
Username for authenticating to HDFS using Kerberos
The partition object of a project indicates the settings used for partitioning. Depending on the partitioning selected, many of the options will be null.
If a user partition column was used with cross validation, the value assigned to the holdout set
cvMethod
string
true
The partitioning method used. Note that "date" partitioning is an old partitioning method no longer supported for new projects, as of API version v2.0.
datetimeCol
string¦null
true
If a date partition column was used, the name of the column. Note that datetimeCol applies to an old partitioning method no longer supported for new projects, as of API version v2.0.
datetimePartitionColumn
string¦null
false
If a datetime partition column was used, the name of the column.
holdoutLevel
string¦null
true
If a user partition column was used with train-validation-holdout split, the value assigned to the holdout set.
holdoutPct
number¦null
true
The percentage of the dataset reserved for the holdout set.
partitionKeyCols
[string]¦null
true
An array containing a single string - the name of the group partition column
reps
integer¦null
true
If cross validation was used, the number of folds to use.
trainingLevel
string¦null
true
If a user partition column was used with train-validation-holdout split, the value assigned to the training set.
useTimeSeries
boolean¦null
false
Indicates whether a time series project was created as opposed to a regular project using datetime partitioning.
userPartitionCol
string¦null
true
If a user partition column was used, the name of the column.
validationLevel
string¦null
true
If a user partition column was used with train-validation-holdout split, the value assigned to the validation set.
validationPct
number¦null
true
If train-validation-holdout split was used, the percentage of the dataset used for the validation set.
validationType
string
true
The type of validation used. Either CV (cross validation) or TVH (train-validation-holdout split).
The ID of the latest version of the catalog entry.
password
string
true
The password (in cleartext) for database authentication. The password will be encrypted on the server side in scope of HTTP request and never saved or stored.
url
string
false
The link to retrieve more detailed information about the entity that uses this catalog dataset.
For GAM models - specify groups of columns for which pairwise interactions will be allowed. E.g. if set to [["A", "B", "C"], ["C", "D"]] then GAM models will allow interactions between columns AxB, BxC, AxC, CxD. All others (AxD, BxD) will not be considered. If not specified - all possible interactions will be considered by model.
blendBestModels
boolean
true
blend best models during Autopilot run [DEPRECATED]
blueprintThreshold
integer¦null
true
an upper bound on running time (in hours), such that models exceeding the bound will be excluded in subsequent autopilot runs
considerBlendersInRecommendation
boolean
false
Include blenders when selecting a model to prepare for deployment in an Autopilot Run.[DEPRECATED]
defaultMonotonicDecreasingFeaturelistId
string¦null
true
null or str, the ID of the featurelist specifying a set of features with a monotonically decreasing relationship to the target. All blueprints generated in the project use this as their default monotonic constraint, but it can be overriden at model submission time.
defaultMonotonicIncreasingFeaturelistId
string¦null
true
null or str, the ID of the featurelist specifying a set of features with a monotonically increasing relationship to the target. All blueprints generated in the project use this as their default monotonic constraint, but it can be overriden at model submission time.
downsampledMajorityRows
integer¦null
true
the total number of the majority rows available for modeling, or null for projects without smart downsampling
downsampledMinorityRows
integer¦null
true
the total number of the minority rows available for modeling, or null for projects without smart downsampling
eventsCount
string¦null
false
the name of the event count column, if specified, otherwise null.
exposure
string¦null
false
the name of the exposure column, if specified.
majorityDownsamplingRate
number¦null
true
the percentage between 0 and 100 of the majority rows that are kept, or null for projects without smart downsampling
minSecondaryValidationModelCount
boolean
false
Compute "All backtest" scores (datetime models) or cross validation scores for the specified number of highest ranking models on the Leaderboard, if over the Autopilot default.
offset
[string]¦null
false
the list of names of the offset columns, if specified, otherwise null.
onlyIncludeMonotonicBlueprints
boolean
true
whether the project only includes blueprints support enforcing monotonic constraints
prepareModelForDeployment
boolean¦null
true
Prepare model for deployment during Autopilot run. The preparation includes creating reduced feature list models, retraining best model on higher sample size, computing insights and assigning "RECOMMENDED FOR DEPLOYMENT" label.
responseCap
any
true
defaults to False, if specified used to cap the maximum response of a model
oneOf
Name
Type
Required
Restrictions
Description
» anonymous
boolean
false
none
xor
Name
Type
Required
Restrictions
Description
» anonymous
number
false
maximum: 1 minimum: 0.5
none
continued
Name
Type
Required
Restrictions
Description
runLeakageRemovedFeatureList
boolean
false
Run Autopilot on Leakage Removed feature list (if exists).
scoringCodeOnly
boolean
false
Keep only models that can be converted to scorable java code during Autopilot run.
seed
string¦null
true
defaults to null, the random seed to be used if specified
shapOnlyMode
boolean¦null
true
Keep only models that support SHAP values during Autopilot run. Use SHAP-based insights wherever possible. For pre SHAP-only mode projects this is always null.
smartDownsampled
boolean
true
whether the project uses smart downsampling to throw away excess rows of the majority class. Smart downsampled projects express all sample percents in terms of percent of minority rows (as opposed to percent of all rows).
weights
string¦null
true
the name of the weight column, if specified, otherwise null.
The ID of the set of credentials to authenticate with the database. Can only be used along with datasetId or dataSourceId.
dataSourceId
string
false
Identifier for the data source to retrieve.
datasetId
string
false
The ID of the dataset entry to use for the project dataset.
datasetVersionId
string
false
Only used when also providing a datasetId, and specifies the the ID of the dataset version to use for the project dataset. If not specified, the latest version associated with the dataset ID is used.
password
string
false
The password (in cleartext) for database authentication. The password will be encrypted on the server side as part of the HTTP request and never saved or stored. Can only be used along with datasetId or dataSourceId. DEPRECATED: please use credentialId or credentialData instead.
projectName
string
false
The name of the project to be created. If not specified, 'Untitled Project' will be used for database connections and file name will be used as the project name.
recipeId
string
false
The ID of the wrangling recipe that will be used for project creation.
url
string(url)
false
The URL to download the dataset used to create the project.
useKerberos
boolean
false
If true, use Kerberos authentication for database authentication. Default is false. Can only be used along with datasetId or dataSourceId.
user
string
false
The username for database authentication. Can only be used along with datasetId or dataSourceId. DEPRECATED: please use credentialId or credentialData instead.
Information related to the current model of the deployment.
autopilotClusterList
[integer]¦null
false
maxItems: 10
Optional. A list of integers where each value will be used as the number of clusters in Autopilot model(s) for unsupervised clustering projects. Cannot be specified unless unsupervisedMode is true and unsupervisedType is set to 'clustering'.
autopilotMode
integer
true
The current autopilot mode, 0 for full autopilot, 2 for manual mode, 3 for quick mode, 4 for comprehensive mode
created
string(date-time)
true
The time of project creation.
featureEngineeringPredictionPoint
string¦null
false
The date column to be used as the prediction point for time-based feature engineering.
fileName
string
true
The name of the dataset used to create the project.
holdoutUnlocked
boolean
true
whether the holdout has been unlocked
id
string
true
The ID of a project.
maxClusters
integer¦null
false
maximum: 100 minimum: 2
Only valid when unsupervisedMode is True and unsupervisedType is 'clustering'. The maximum number of clusters allowed when training clustering models. If specified cannot be exceed the number of rows in a project's dataset divided by 50 and must be less than or equal to minClusters. If unsupervisedMode is True and unsupervisedType is 'clustering' then defaults to the number of rows in the project's dataset divided by 50 or 100 if that number of greater than 100.
maxTrainPct
number
true
the maximum percentage of the dataset that can be used to successfully train a model without going into the validation data.
maxTrainRows
integer
true
the maximum number of rows of the dataset that can be used to successfully train a model without going into the validation data
metric
string
true
the metric used to select the best-performing models.
minClusters
integer¦null
false
maximum: 100 minimum: 2
Only valid when unsupervisedMode is True and unsupervisedType is 'clustering'. The minimum number of clusters allowed when training clustering models. If specified cannot be exceed the number of rows in a project's dataset divided by 50 and must be less than or equal to maxClusters. If unsupervisedMode is True and unsupervisedType is 'clustering' then defaults to 2.
The partition object of a project indicates the settings used for partitioning. Depending on the partitioning selected, many of the options will be null. Note that for projects whose cvMethod is "datetime", full specification of the partitioning method can be found at GET /api/v2/projects/{projectId}/datetimePartitioning/.
positiveClass
number¦null
true
if the project uses binary classification, the class designated to be the positive class. Otherwise, null.
projectName
string
true
The name of a project.
stage
string
true
the stage of the project - if modeling, then the target is successfully set, and modeling or predictions can proceed.
target
string
true
the target of the project, null if project is unsupervised.
targetType
string¦null
true
The target type of the project.
unsupervisedMode
boolean
true
indicates whether a project is unsupervised.
unsupervisedType
string¦null
false
Only valid when unsupervisedMode is True. The type of unsupervised project, anomaly or clustering. If unsupervisedMode, defaults to 'anomaly'.
useFeatureDiscovery
boolean
true
A boolean value indicating whether a feature discovery project was created as opposed to a regular project.
The partition object of a project indicates the settings used for partitioning. Depending on the partitioning selected, many of the options will be null. Note that for projects whose cvMethod is "datetime", full specification of the partitioning method can be found at GET /api/v2/projects/{projectId}/datetimePartitioning/.
if a user partition column was used with cross validation, the value assigned to the holdout set
anyOf
Name
Type
Required
Restrictions
Description
» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
number
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
integer
false
none
continued
Name
Type
Required
Restrictions
Description
cvMethod
string
true
the partitioning method used. Note that "date" partitioning is an old partitioning method no longer supported for new projects, as of API version v2.0.
datetimeCol
string¦null
true
if a date partition column was used, the name of the column. Note that datetimeCol applies to an old partitioning method no longer supported for new projects, as of API version v2.0.
datetimePartitionColumn
string
false
if a datetime partition column was used, the name of the column
holdoutLevel
any
true
if a user partition column was used with train-validation-holdout split, the value assigned to the holdout set
anyOf
Name
Type
Required
Restrictions
Description
» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
number
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
integer
false
none
continued
Name
Type
Required
Restrictions
Description
holdoutPct
number
true
the percentage of the dataset reserved for the holdout set
partitionKeyCols
[string]¦null
true
An array containing a single string - the name of the group partition column
reps
number¦null
true
if cross validation was used, the number of folds to use
trainingLevel
any
true
if a user partition column was used with train-validation-holdout split, the value assigned to the training set
anyOf
Name
Type
Required
Restrictions
Description
» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
number
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
integer
false
none
continued
Name
Type
Required
Restrictions
Description
useTimeSeries
boolean¦null
true
A boolean value indicating whether a time series project was created as opposed to a regular project using datetime partitioning.
userPartitionCol
string¦null
true
if a user partition column was used, the name of the column
validationLevel
any
true
if a user partition column was used with train-validation-holdout split, the value assigned to the validation set
anyOf
Name
Type
Required
Restrictions
Description
» anonymous
string
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
number
false
none
or
Name
Type
Required
Restrictions
Description
» anonymous
integer
false
none
continued
Name
Type
Required
Restrictions
Description
validationPct
number¦null
true
if train-validation-holdout split was used, the percentage of the dataset used for the validation set
validationType
string
true
either CV for cross-validation or TVH for train-validation-holdout split
Information related to the current model of the deployment.
autopilotClusterList
[integer]¦null
false
maxItems: 10
Optional. A list of integers where each value will be used as the number of clusters in Autopilot model(s) for unsupervised clustering projects. Cannot be specified unless unsupervisedMode is true and unsupervisedType is set to 'clustering'.
autopilotMode
string¦null
true
The current autopilot mode. 0: Full Autopilot. 2: Manual Mode. 3: Quick Mode. 4: Comprehensive Autopilot. null: Mode not set.
catalogId
string¦null
true
The ID of the AI catalog entry used to create the project, or null if not created from the AI catalog.
catalogVersionId
string¦null
true
The ID of the AI catalog version used to create the project, or null if not created from the AI catalog.
Indicates whether validation scores are available. A result of 'N/A' in the UI indicates that a model was trained into validation or holdout and also either does not have stacked predictions or uses extended multiclass.
maxClusters
integer¦null
false
maximum: 100 minimum: 2
Only valid when unsupervisedMode is True and unsupervisedType is 'clustering'. The maximum number of clusters allowed when training clustering models. If specified cannot be exceed the number of rows in a project's dataset divided by 50 and must be less than or equal to minClusters. If unsupervisedMode is True and unsupervisedType is 'clustering' then defaults to the number of rows in the project's dataset divided by 50 or 100 if that number of greater than 100.
maxTrainPct
number
true
The maximum percentage of the dataset that can be used to successfully train a model without going into the validation data.
maxTrainRows
integer
true
The maximum number of rows of the dataset that can be used to successfully train a model without going into the validation data.
metric
string
true
The metric used to select the best-performing models.
minClusters
integer¦null
false
maximum: 100 minimum: 2
Only valid when unsupervisedMode is True and unsupervisedType is 'clustering'. The minimum number of clusters allowed when training clustering models. If specified cannot be exceed the number of rows in a project's dataset divided by 50 and must be less than or equal to maxClusters. If unsupervisedMode is True and unsupervisedType is 'clustering' then defaults to 2.
The partition object of a project indicates the settings used for partitioning. Depending on the partitioning selected, many of the options will be null.
positiveClass
any
true
If the project uses binary classification, the class designated to be the positive class.
oneOf
Name
Type
Required
Restrictions
Description
» anonymous
string
false
none
xor
Name
Type
Required
Restrictions
Description
» anonymous
integer
false
none
continued
Name
Type
Required
Restrictions
Description
primaryLocationColumn
string
false
Primary location column name
projectName
string
true
The name of the project.
queryGeneratorId
string¦null
true
The ID of the time series data prep query generator associated with the project, or null if there is no associated query generator.
quickrun
boolean
true
If the Autopilot mode is set to quick. DEPRECATED: look at autopilot_mode instead.
relationshipsConfigurationId
string¦null
false
Relationships configuration id to be used for Feature Discovery projects.
The desired new number of gpu workers if the number of gpu workers should be changed. Must not exceed the number of gpu workers available to the user. 0 is allowed. -1 requests the maximum number available to the user.
holdoutUnlocked
string
false
If specified, the holdout will be unlocked; note that the holdout cannot be relocked after unlocking
projectDescription
string
false
maxLength: 500
The new description of the project, if the description should be updated.
projectName
string
false
maxLength: 100
The new name of the project, if it should be renamed.
workerCount
integer
false
The desired new number of workers if the number of workers should be changed. Must not exceed the number of workers available to the user. 0 is allowed. (New in version v2.14) -1 requests the maximum number available to the user.