Docs Home Pulumi IaC Pulumi ESC Pulumi Insights Pulumi Cloud Packages Tutorials
  1. Packages
  2. DataRobot
  3. API Docs
  4. DatasetFromDatasource
DataRobot v0.9.0 published on Tuesday, Apr 8, 2025 by DataRobot, Inc.
datarobot-community/pulumi-datarobot

datarobot.DatasetFromDatasource

Explore with Pulumi AI

DataRobot v0.9.0 published on Tuesday, Apr 8, 2025 by DataRobot, Inc.
datarobot-community/pulumi-datarobot

Data Set from Data Source.

Example Usage

import * as pulumi from "@pulumi/pulumi";
import * as datarobot from "@datarobot/pulumi-datarobot";

const example = new datarobot.DatasetFromDatasource("example", {
    datasourceId: datarobot_datasource.example.id,
    credentialId: datarobot_credential.example.id,
    doSnapshot: false,
    persistDataAfterIngestion: false,
    useKerberos: true,
    categories: ["TRAINING"],
    useCaseIds: [datarobot_use_case.example.id],
});
export const exampleId = example.id;
Copy
import pulumi
import pulumi_datarobot as datarobot

example = datarobot.DatasetFromDatasource("example",
    datasource_id=datarobot_datasource["example"]["id"],
    credential_id=datarobot_credential["example"]["id"],
    do_snapshot=False,
    persist_data_after_ingestion=False,
    use_kerberos=True,
    categories=["TRAINING"],
    use_case_ids=[datarobot_use_case["example"]["id"]])
pulumi.export("exampleId", example.id)
Copy
package main

import (
	"github.com/datarobot-community/pulumi-datarobot/sdk/go/datarobot"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		example, err := datarobot.NewDatasetFromDatasource(ctx, "example", &datarobot.DatasetFromDatasourceArgs{
			DatasourceId:              pulumi.Any(datarobot_datasource.Example.Id),
			CredentialId:              pulumi.Any(datarobot_credential.Example.Id),
			DoSnapshot:                pulumi.Bool(false),
			PersistDataAfterIngestion: pulumi.Bool(false),
			UseKerberos:               pulumi.Bool(true),
			Categories: pulumi.StringArray{
				pulumi.String("TRAINING"),
			},
			UseCaseIds: pulumi.StringArray{
				datarobot_use_case.Example.Id,
			},
		})
		if err != nil {
			return err
		}
		ctx.Export("exampleId", example.ID())
		return nil
	})
}
Copy
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Datarobot = DataRobotPulumi.Datarobot;

return await Deployment.RunAsync(() => 
{
    var example = new Datarobot.DatasetFromDatasource("example", new()
    {
        DatasourceId = datarobot_datasource.Example.Id,
        CredentialId = datarobot_credential.Example.Id,
        DoSnapshot = false,
        PersistDataAfterIngestion = false,
        UseKerberos = true,
        Categories = new[]
        {
            "TRAINING",
        },
        UseCaseIds = new[]
        {
            datarobot_use_case.Example.Id,
        },
    });

    return new Dictionary<string, object?>
    {
        ["exampleId"] = example.Id,
    };
});
Copy
package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.datarobot.DatasetFromDatasource;
import com.pulumi.datarobot.DatasetFromDatasourceArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;

public class App {
    public static void main(String[] args) {
        Pulumi.run(App::stack);
    }

    public static void stack(Context ctx) {
        var example = new DatasetFromDatasource("example", DatasetFromDatasourceArgs.builder()
            .datasourceId(datarobot_datasource.example().id())
            .credentialId(datarobot_credential.example().id())
            .doSnapshot(false)
            .persistDataAfterIngestion(false)
            .useKerberos(true)
            .categories("TRAINING")
            .useCaseIds(datarobot_use_case.example().id())
            .build());

        ctx.export("exampleId", example.id());
    }
}
Copy
resources:
  example:
    type: datarobot:DatasetFromDatasource
    properties:
      datasourceId: ${datarobot_datasource.example.id}
      credentialId: ${datarobot_credential.example.id}
      # Optional
      doSnapshot: false
      persistDataAfterIngestion: false
      useKerberos: true
      categories:
        - TRAINING
      useCaseIds:
        - ${datarobot_use_case.example.id}
outputs:
  exampleId: ${example.id}
Copy

Create DatasetFromDatasource Resource

Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

Constructor syntax

new DatasetFromDatasource(name: string, args: DatasetFromDatasourceArgs, opts?: CustomResourceOptions);
@overload
def DatasetFromDatasource(resource_name: str,
                          args: DatasetFromDatasourceArgs,
                          opts: Optional[ResourceOptions] = None)

@overload
def DatasetFromDatasource(resource_name: str,
                          opts: Optional[ResourceOptions] = None,
                          credential_id: Optional[str] = None,
                          data_source_id: Optional[str] = None,
                          categories: Optional[Sequence[str]] = None,
                          do_snapshot: Optional[bool] = None,
                          persist_data_after_ingestion: Optional[bool] = None,
                          sample_size_rows: Optional[int] = None,
                          use_case_ids: Optional[Sequence[str]] = None,
                          use_kerberos: Optional[bool] = None)
func NewDatasetFromDatasource(ctx *Context, name string, args DatasetFromDatasourceArgs, opts ...ResourceOption) (*DatasetFromDatasource, error)
public DatasetFromDatasource(string name, DatasetFromDatasourceArgs args, CustomResourceOptions? opts = null)
public DatasetFromDatasource(String name, DatasetFromDatasourceArgs args)
public DatasetFromDatasource(String name, DatasetFromDatasourceArgs args, CustomResourceOptions options)

type: datarobot:DatasetFromDatasource
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

Parameters

name This property is required. string
The unique name of the resource.
args This property is required. DatasetFromDatasourceArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
resource_name This property is required. str
The unique name of the resource.
args This property is required. DatasetFromDatasourceArgs
The arguments to resource properties.
opts ResourceOptions
Bag of options to control resource's behavior.
ctx Context
Context object for the current deployment.
name This property is required. string
The unique name of the resource.
args This property is required. DatasetFromDatasourceArgs
The arguments to resource properties.
opts ResourceOption
Bag of options to control resource's behavior.
name This property is required. string
The unique name of the resource.
args This property is required. DatasetFromDatasourceArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
name This property is required. String
The unique name of the resource.
args This property is required. DatasetFromDatasourceArgs
The arguments to resource properties.
options CustomResourceOptions
Bag of options to control resource's behavior.

Constructor example

The following reference example uses placeholder values for all input properties.

var datasetFromDatasourceResource = new Datarobot.DatasetFromDatasource("datasetFromDatasourceResource", new()
{
    CredentialId = "string",
    DataSourceId = "string",
    Categories = new[]
    {
        "string",
    },
    DoSnapshot = false,
    PersistDataAfterIngestion = false,
    SampleSizeRows = 0,
    UseCaseIds = new[]
    {
        "string",
    },
    UseKerberos = false,
});
Copy
example, err := datarobot.NewDatasetFromDatasource(ctx, "datasetFromDatasourceResource", &datarobot.DatasetFromDatasourceArgs{
	CredentialId: pulumi.String("string"),
	DataSourceId: pulumi.String("string"),
	Categories: pulumi.StringArray{
		pulumi.String("string"),
	},
	DoSnapshot:                pulumi.Bool(false),
	PersistDataAfterIngestion: pulumi.Bool(false),
	SampleSizeRows:            pulumi.Int(0),
	UseCaseIds: pulumi.StringArray{
		pulumi.String("string"),
	},
	UseKerberos: pulumi.Bool(false),
})
Copy
var datasetFromDatasourceResource = new DatasetFromDatasource("datasetFromDatasourceResource", DatasetFromDatasourceArgs.builder()
    .credentialId("string")
    .dataSourceId("string")
    .categories("string")
    .doSnapshot(false)
    .persistDataAfterIngestion(false)
    .sampleSizeRows(0)
    .useCaseIds("string")
    .useKerberos(false)
    .build());
Copy
dataset_from_datasource_resource = datarobot.DatasetFromDatasource("datasetFromDatasourceResource",
    credential_id="string",
    data_source_id="string",
    categories=["string"],
    do_snapshot=False,
    persist_data_after_ingestion=False,
    sample_size_rows=0,
    use_case_ids=["string"],
    use_kerberos=False)
Copy
const datasetFromDatasourceResource = new datarobot.DatasetFromDatasource("datasetFromDatasourceResource", {
    credentialId: "string",
    dataSourceId: "string",
    categories: ["string"],
    doSnapshot: false,
    persistDataAfterIngestion: false,
    sampleSizeRows: 0,
    useCaseIds: ["string"],
    useKerberos: false,
});
Copy
type: datarobot:DatasetFromDatasource
properties:
    categories:
        - string
    credentialId: string
    dataSourceId: string
    doSnapshot: false
    persistDataAfterIngestion: false
    sampleSizeRows: 0
    useCaseIds:
        - string
    useKerberos: false
Copy

DatasetFromDatasource Resource Properties

To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.

Inputs

In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.

The DatasetFromDatasource resource accepts the following input properties:

CredentialId This property is required. string
The ID of the set of credentials to use.
DataSourceId This property is required. string
The ID for the DataSource to use as the source of data.
Categories List<string>
An array of strings describing the intended use of the dataset.
DoSnapshot bool
If unset, uses the server default: True. If true, creates a snapshot dataset; if false, creates a remote dataset.
PersistDataAfterIngestion bool
If unset, uses the server default: True. If true, will enforce saving all data (for download and sampling) and will allow a user to view extended data profile (which includes data statistics like min/max/median/mean, histogram, etc.). If false, will not enforce saving data. The data schema (feature names and types) still will be available.
SampleSizeRows int
The number of rows fetched during dataset registration.
UseCaseIds List<string>
The list of Use Case IDs to add the Dataset to.
UseKerberos bool
If unset, uses the server default: False. If true, use kerberos authentication for database authentication.
CredentialId This property is required. string
The ID of the set of credentials to use.
DataSourceId This property is required. string
The ID for the DataSource to use as the source of data.
Categories []string
An array of strings describing the intended use of the dataset.
DoSnapshot bool
If unset, uses the server default: True. If true, creates a snapshot dataset; if false, creates a remote dataset.
PersistDataAfterIngestion bool
If unset, uses the server default: True. If true, will enforce saving all data (for download and sampling) and will allow a user to view extended data profile (which includes data statistics like min/max/median/mean, histogram, etc.). If false, will not enforce saving data. The data schema (feature names and types) still will be available.
SampleSizeRows int
The number of rows fetched during dataset registration.
UseCaseIds []string
The list of Use Case IDs to add the Dataset to.
UseKerberos bool
If unset, uses the server default: False. If true, use kerberos authentication for database authentication.
credentialId This property is required. String
The ID of the set of credentials to use.
dataSourceId This property is required. String
The ID for the DataSource to use as the source of data.
categories List<String>
An array of strings describing the intended use of the dataset.
doSnapshot Boolean
If unset, uses the server default: True. If true, creates a snapshot dataset; if false, creates a remote dataset.
persistDataAfterIngestion Boolean
If unset, uses the server default: True. If true, will enforce saving all data (for download and sampling) and will allow a user to view extended data profile (which includes data statistics like min/max/median/mean, histogram, etc.). If false, will not enforce saving data. The data schema (feature names and types) still will be available.
sampleSizeRows Integer
The number of rows fetched during dataset registration.
useCaseIds List<String>
The list of Use Case IDs to add the Dataset to.
useKerberos Boolean
If unset, uses the server default: False. If true, use kerberos authentication for database authentication.
credentialId This property is required. string
The ID of the set of credentials to use.
dataSourceId This property is required. string
The ID for the DataSource to use as the source of data.
categories string[]
An array of strings describing the intended use of the dataset.
doSnapshot boolean
If unset, uses the server default: True. If true, creates a snapshot dataset; if false, creates a remote dataset.
persistDataAfterIngestion boolean
If unset, uses the server default: True. If true, will enforce saving all data (for download and sampling) and will allow a user to view extended data profile (which includes data statistics like min/max/median/mean, histogram, etc.). If false, will not enforce saving data. The data schema (feature names and types) still will be available.
sampleSizeRows number
The number of rows fetched during dataset registration.
useCaseIds string[]
The list of Use Case IDs to add the Dataset to.
useKerberos boolean
If unset, uses the server default: False. If true, use kerberos authentication for database authentication.
credential_id This property is required. str
The ID of the set of credentials to use.
data_source_id This property is required. str
The ID for the DataSource to use as the source of data.
categories Sequence[str]
An array of strings describing the intended use of the dataset.
do_snapshot bool
If unset, uses the server default: True. If true, creates a snapshot dataset; if false, creates a remote dataset.
persist_data_after_ingestion bool
If unset, uses the server default: True. If true, will enforce saving all data (for download and sampling) and will allow a user to view extended data profile (which includes data statistics like min/max/median/mean, histogram, etc.). If false, will not enforce saving data. The data schema (feature names and types) still will be available.
sample_size_rows int
The number of rows fetched during dataset registration.
use_case_ids Sequence[str]
The list of Use Case IDs to add the Dataset to.
use_kerberos bool
If unset, uses the server default: False. If true, use kerberos authentication for database authentication.
credentialId This property is required. String
The ID of the set of credentials to use.
dataSourceId This property is required. String
The ID for the DataSource to use as the source of data.
categories List<String>
An array of strings describing the intended use of the dataset.
doSnapshot Boolean
If unset, uses the server default: True. If true, creates a snapshot dataset; if false, creates a remote dataset.
persistDataAfterIngestion Boolean
If unset, uses the server default: True. If true, will enforce saving all data (for download and sampling) and will allow a user to view extended data profile (which includes data statistics like min/max/median/mean, histogram, etc.). If false, will not enforce saving data. The data schema (feature names and types) still will be available.
sampleSizeRows Number
The number of rows fetched during dataset registration.
useCaseIds List<String>
The list of Use Case IDs to add the Dataset to.
useKerberos Boolean
If unset, uses the server default: False. If true, use kerberos authentication for database authentication.

Outputs

All input properties are implicitly available as output properties. Additionally, the DatasetFromDatasource resource produces the following output properties:

Id string
The provider-assigned unique ID for this managed resource.
Id string
The provider-assigned unique ID for this managed resource.
id String
The provider-assigned unique ID for this managed resource.
id string
The provider-assigned unique ID for this managed resource.
id str
The provider-assigned unique ID for this managed resource.
id String
The provider-assigned unique ID for this managed resource.

Look up Existing DatasetFromDatasource Resource

Get an existing DatasetFromDatasource resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.

public static get(name: string, id: Input<ID>, state?: DatasetFromDatasourceState, opts?: CustomResourceOptions): DatasetFromDatasource
@staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        categories: Optional[Sequence[str]] = None,
        credential_id: Optional[str] = None,
        data_source_id: Optional[str] = None,
        do_snapshot: Optional[bool] = None,
        persist_data_after_ingestion: Optional[bool] = None,
        sample_size_rows: Optional[int] = None,
        use_case_ids: Optional[Sequence[str]] = None,
        use_kerberos: Optional[bool] = None) -> DatasetFromDatasource
func GetDatasetFromDatasource(ctx *Context, name string, id IDInput, state *DatasetFromDatasourceState, opts ...ResourceOption) (*DatasetFromDatasource, error)
public static DatasetFromDatasource Get(string name, Input<string> id, DatasetFromDatasourceState? state, CustomResourceOptions? opts = null)
public static DatasetFromDatasource get(String name, Output<String> id, DatasetFromDatasourceState state, CustomResourceOptions options)
resources:  _:    type: datarobot:DatasetFromDatasource    get:      id: ${id}
name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
resource_name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
The following state arguments are supported:
Categories List<string>
An array of strings describing the intended use of the dataset.
CredentialId string
The ID of the set of credentials to use.
DataSourceId string
The ID for the DataSource to use as the source of data.
DoSnapshot bool
If unset, uses the server default: True. If true, creates a snapshot dataset; if false, creates a remote dataset.
PersistDataAfterIngestion bool
If unset, uses the server default: True. If true, will enforce saving all data (for download and sampling) and will allow a user to view extended data profile (which includes data statistics like min/max/median/mean, histogram, etc.). If false, will not enforce saving data. The data schema (feature names and types) still will be available.
SampleSizeRows int
The number of rows fetched during dataset registration.
UseCaseIds List<string>
The list of Use Case IDs to add the Dataset to.
UseKerberos bool
If unset, uses the server default: False. If true, use kerberos authentication for database authentication.
Categories []string
An array of strings describing the intended use of the dataset.
CredentialId string
The ID of the set of credentials to use.
DataSourceId string
The ID for the DataSource to use as the source of data.
DoSnapshot bool
If unset, uses the server default: True. If true, creates a snapshot dataset; if false, creates a remote dataset.
PersistDataAfterIngestion bool
If unset, uses the server default: True. If true, will enforce saving all data (for download and sampling) and will allow a user to view extended data profile (which includes data statistics like min/max/median/mean, histogram, etc.). If false, will not enforce saving data. The data schema (feature names and types) still will be available.
SampleSizeRows int
The number of rows fetched during dataset registration.
UseCaseIds []string
The list of Use Case IDs to add the Dataset to.
UseKerberos bool
If unset, uses the server default: False. If true, use kerberos authentication for database authentication.
categories List<String>
An array of strings describing the intended use of the dataset.
credentialId String
The ID of the set of credentials to use.
dataSourceId String
The ID for the DataSource to use as the source of data.
doSnapshot Boolean
If unset, uses the server default: True. If true, creates a snapshot dataset; if false, creates a remote dataset.
persistDataAfterIngestion Boolean
If unset, uses the server default: True. If true, will enforce saving all data (for download and sampling) and will allow a user to view extended data profile (which includes data statistics like min/max/median/mean, histogram, etc.). If false, will not enforce saving data. The data schema (feature names and types) still will be available.
sampleSizeRows Integer
The number of rows fetched during dataset registration.
useCaseIds List<String>
The list of Use Case IDs to add the Dataset to.
useKerberos Boolean
If unset, uses the server default: False. If true, use kerberos authentication for database authentication.
categories string[]
An array of strings describing the intended use of the dataset.
credentialId string
The ID of the set of credentials to use.
dataSourceId string
The ID for the DataSource to use as the source of data.
doSnapshot boolean
If unset, uses the server default: True. If true, creates a snapshot dataset; if false, creates a remote dataset.
persistDataAfterIngestion boolean
If unset, uses the server default: True. If true, will enforce saving all data (for download and sampling) and will allow a user to view extended data profile (which includes data statistics like min/max/median/mean, histogram, etc.). If false, will not enforce saving data. The data schema (feature names and types) still will be available.
sampleSizeRows number
The number of rows fetched during dataset registration.
useCaseIds string[]
The list of Use Case IDs to add the Dataset to.
useKerberos boolean
If unset, uses the server default: False. If true, use kerberos authentication for database authentication.
categories Sequence[str]
An array of strings describing the intended use of the dataset.
credential_id str
The ID of the set of credentials to use.
data_source_id str
The ID for the DataSource to use as the source of data.
do_snapshot bool
If unset, uses the server default: True. If true, creates a snapshot dataset; if false, creates a remote dataset.
persist_data_after_ingestion bool
If unset, uses the server default: True. If true, will enforce saving all data (for download and sampling) and will allow a user to view extended data profile (which includes data statistics like min/max/median/mean, histogram, etc.). If false, will not enforce saving data. The data schema (feature names and types) still will be available.
sample_size_rows int
The number of rows fetched during dataset registration.
use_case_ids Sequence[str]
The list of Use Case IDs to add the Dataset to.
use_kerberos bool
If unset, uses the server default: False. If true, use kerberos authentication for database authentication.
categories List<String>
An array of strings describing the intended use of the dataset.
credentialId String
The ID of the set of credentials to use.
dataSourceId String
The ID for the DataSource to use as the source of data.
doSnapshot Boolean
If unset, uses the server default: True. If true, creates a snapshot dataset; if false, creates a remote dataset.
persistDataAfterIngestion Boolean
If unset, uses the server default: True. If true, will enforce saving all data (for download and sampling) and will allow a user to view extended data profile (which includes data statistics like min/max/median/mean, histogram, etc.). If false, will not enforce saving data. The data schema (feature names and types) still will be available.
sampleSizeRows Number
The number of rows fetched during dataset registration.
useCaseIds List<String>
The list of Use Case IDs to add the Dataset to.
useKerberos Boolean
If unset, uses the server default: False. If true, use kerberos authentication for database authentication.

Package Details

Repository
datarobot datarobot-community/pulumi-datarobot
License
Apache-2.0
Notes
This Pulumi package is based on the datarobot Terraform Provider.
DataRobot v0.9.0 published on Tuesday, Apr 8, 2025 by DataRobot, Inc.
datarobot-community/pulumi-datarobot