Docs Packages
  1. Packages
  2. Databricks
  3. API Docs
  4. LakehouseMonitor
Databricks v1.38.0 published on Monday, Apr 29, 2024 by Pulumi
pulumi/pulumi-databricks

databricks.LakehouseMonitor

Explore with Pulumi AI

databricks logo
Databricks v1.38.0 published on Monday, Apr 29, 2024 by Pulumi
pulumi/pulumi-databricks

    This resource allows you to manage Lakehouse Monitors in Databricks.

    A databricks.LakehouseMonitor is attached to a databricks.SqlTable and can be of type timeseries, snapshot or inference.

    Example Usage

    Coming soon!

    Coming soon!

    Coming soon!

    Coming soon!

    package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.databricks.Catalog;
import com.pulumi.databricks.CatalogArgs;
import com.pulumi.databricks.Schema;
import com.pulumi.databricks.SchemaArgs;
import com.pulumi.databricks.SqlTable;
import com.pulumi.databricks.SqlTableArgs;
import com.pulumi.databricks.inputs.SqlTableColumnArgs;
import com.pulumi.databricks.LakehouseMonitor;
import com.pulumi.databricks.LakehouseMonitorArgs;
import com.pulumi.databricks.inputs.LakehouseMonitorTimeSeriesArgs;
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 sandbox = new Catalog("sandbox", CatalogArgs.builder()        
            .name("sandbox")
            .comment("this catalog is managed by terraform")
            .properties(Map.of("purpose", "testing"))
            .build());

        var things = new Schema("things", SchemaArgs.builder()        
            .catalogName(sandbox.id())
            .name("things")
            .comment("this database is managed by terraform")
            .properties(Map.of("kind", "various"))
            .build());

        var myTestTable = new SqlTable("myTestTable", SqlTableArgs.builder()        
            .catalogName("main")
            .schemaName(things.name())
            .name("bar")
            .tableType("MANAGED")
            .dataSourceFormat("DELTA")
            .columns(SqlTableColumnArgs.builder()
                .name("timestamp")
                .position(1)
                .type("int")
                .build())
            .build());

        var testTimeseriesMonitor = new LakehouseMonitor("testTimeseriesMonitor", LakehouseMonitorArgs.builder()        
            .tableName(Output.tuple(sandbox.name(), things.name(), myTestTable.name()).applyValue(values -> {
                var sandboxName = values.t1;
                var thingsName = values.t2;
                var myTestTableName = values.t3;
                return String.format("%s.%s.%s", sandboxName,thingsName,myTestTableName);
            }))
            .assetsDir(myTestTable.name().applyValue(name -> String.format("/Shared/provider-test/databricks_lakehouse_monitoring/%s", name)))
            .outputSchemaName(Output.tuple(sandbox.name(), things.name()).applyValue(values -> {
                var sandboxName = values.t1;
                var thingsName = values.t2;
                return String.format("%s.%s", sandboxName,thingsName);
            }))
            .timeSeries(LakehouseMonitorTimeSeriesArgs.builder()
                .granularities("1 hour")
                .timestampCol("timestamp")
                .build())
            .build());

    }
}

    resources:
  sandbox:
    type: databricks:Catalog
    properties:
      name: sandbox
      comment: this catalog is managed by terraform
      properties:
        purpose: testing
  things:
    type: databricks:Schema
    properties:
      catalogName: ${sandbox.id}
      name: things
      comment: this database is managed by terraform
      properties:
        kind: various
  myTestTable:
    type: databricks:SqlTable
    properties:
      catalogName: main
      schemaName: ${things.name}
      name: bar
      tableType: MANAGED
      dataSourceFormat: DELTA
      columns:
        - name: timestamp
          position: 1
          type: int
  testTimeseriesMonitor:
    type: databricks:LakehouseMonitor
    properties:
      tableName: ${sandbox.name}.${things.name}.${myTestTable.name}
      assetsDir: /Shared/provider-test/databricks_lakehouse_monitoring/${myTestTable.name}
      outputSchemaName: ${sandbox.name}.${things.name}
      timeSeries:
        granularities:
          - 1 hour
        timestampCol: timestamp

    Inference Monitor

    import * as pulumi from "@pulumi/pulumi";
import * as databricks from "@pulumi/databricks";

const testMonitorInference = new databricks.LakehouseMonitor("testMonitorInference", {
    tableName: `${sandbox.name}.${things.name}.${myTestTable.name}`,
    assetsDir: `/Shared/provider-test/databricks_lakehouse_monitoring/${myTestTable.name}`,
    outputSchemaName: `${sandbox.name}.${things.name}`,
    inferenceLog: {
        granularities: ["1 hour"],
        timestampCol: "timestamp",
        predictionCol: "prediction",
        modelIdCol: "model_id",
        problemType: "PROBLEM_TYPE_REGRESSION",
    },
});

    import pulumi
import pulumi_databricks as databricks

test_monitor_inference = databricks.LakehouseMonitor("testMonitorInference",
    table_name=f"{sandbox['name']}.{things['name']}.{my_test_table['name']}",
    assets_dir=f"/Shared/provider-test/databricks_lakehouse_monitoring/{my_test_table['name']}",
    output_schema_name=f"{sandbox['name']}.{things['name']}",
    inference_log=databricks.LakehouseMonitorInferenceLogArgs(
        granularities=["1 hour"],
        timestamp_col="timestamp",
        prediction_col="prediction",
        model_id_col="model_id",
        problem_type="PROBLEM_TYPE_REGRESSION",
    ))

    package main

import (
	"fmt"

	"github.com/pulumi/pulumi-databricks/sdk/go/databricks"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := databricks.NewLakehouseMonitor(ctx, "testMonitorInference", &databricks.LakehouseMonitorArgs{
			TableName:        pulumi.String(fmt.Sprintf("%v.%v.%v", sandbox.Name, things.Name, myTestTable.Name)),
			AssetsDir:        pulumi.String(fmt.Sprintf("/Shared/provider-test/databricks_lakehouse_monitoring/%v", myTestTable.Name)),
			OutputSchemaName: pulumi.String(fmt.Sprintf("%v.%v", sandbox.Name, things.Name)),
			InferenceLog: &databricks.LakehouseMonitorInferenceLogArgs{
				Granularities: pulumi.StringArray{
					pulumi.String("1 hour"),
				},
				TimestampCol:  pulumi.String("timestamp"),
				PredictionCol: pulumi.String("prediction"),
				ModelIdCol:    pulumi.String("model_id"),
				ProblemType:   pulumi.String("PROBLEM_TYPE_REGRESSION"),
			},
		})
		if err != nil {
			return err
		}
		return nil
	})
}

    using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Databricks = Pulumi.Databricks;

return await Deployment.RunAsync(() => 
{
    var testMonitorInference = new Databricks.LakehouseMonitor("testMonitorInference", new()
    {
        TableName = $"{sandbox.Name}.{things.Name}.{myTestTable.Name}",
        AssetsDir = $"/Shared/provider-test/databricks_lakehouse_monitoring/{myTestTable.Name}",
        OutputSchemaName = $"{sandbox.Name}.{things.Name}",
        InferenceLog = new Databricks.Inputs.LakehouseMonitorInferenceLogArgs
        {
            Granularities = new[]
            {
                "1 hour",
            },
            TimestampCol = "timestamp",
            PredictionCol = "prediction",
            ModelIdCol = "model_id",
            ProblemType = "PROBLEM_TYPE_REGRESSION",
        },
    });

});

    package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.databricks.LakehouseMonitor;
import com.pulumi.databricks.LakehouseMonitorArgs;
import com.pulumi.databricks.inputs.LakehouseMonitorInferenceLogArgs;
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 testMonitorInference = new LakehouseMonitor("testMonitorInference", LakehouseMonitorArgs.builder()        
            .tableName(String.format("%s.%s.%s", sandbox.name(),things.name(),myTestTable.name()))
            .assetsDir(String.format("/Shared/provider-test/databricks_lakehouse_monitoring/%s", myTestTable.name()))
            .outputSchemaName(String.format("%s.%s", sandbox.name(),things.name()))
            .inferenceLog(LakehouseMonitorInferenceLogArgs.builder()
                .granularities("1 hour")
                .timestampCol("timestamp")
                .predictionCol("prediction")
                .modelIdCol("model_id")
                .problemType("PROBLEM_TYPE_REGRESSION")
                .build())
            .build());

    }
}

    resources:
  testMonitorInference:
    type: databricks:LakehouseMonitor
    properties:
      tableName: ${sandbox.name}.${things.name}.${myTestTable.name}
      assetsDir: /Shared/provider-test/databricks_lakehouse_monitoring/${myTestTable.name}
      outputSchemaName: ${sandbox.name}.${things.name}
      inferenceLog:
        granularities:
          - 1 hour
        timestampCol: timestamp
        predictionCol: prediction
        modelIdCol: model_id
        problemType: PROBLEM_TYPE_REGRESSION

    Snapshot Monitor

    import * as pulumi from "@pulumi/pulumi";
import * as databricks from "@pulumi/databricks";

const testMonitorInference = new databricks.LakehouseMonitor("testMonitorInference", {
    tableName: `${sandbox.name}.${things.name}.${myTestTable.name}`,
    assetsDir: `/Shared/provider-test/databricks_lakehouse_monitoring/${myTestTable.name}`,
    outputSchemaName: `${sandbox.name}.${things.name}`,
    snapshot: {},
});

    import pulumi
import pulumi_databricks as databricks

test_monitor_inference = databricks.LakehouseMonitor("testMonitorInference",
    table_name=f"{sandbox['name']}.{things['name']}.{my_test_table['name']}",
    assets_dir=f"/Shared/provider-test/databricks_lakehouse_monitoring/{my_test_table['name']}",
    output_schema_name=f"{sandbox['name']}.{things['name']}",
    snapshot=databricks.LakehouseMonitorSnapshotArgs())

    package main

import (
	"fmt"

	"github.com/pulumi/pulumi-databricks/sdk/go/databricks"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := databricks.NewLakehouseMonitor(ctx, "testMonitorInference", &databricks.LakehouseMonitorArgs{
			TableName:        pulumi.String(fmt.Sprintf("%v.%v.%v", sandbox.Name, things.Name, myTestTable.Name)),
			AssetsDir:        pulumi.String(fmt.Sprintf("/Shared/provider-test/databricks_lakehouse_monitoring/%v", myTestTable.Name)),
			OutputSchemaName: pulumi.String(fmt.Sprintf("%v.%v", sandbox.Name, things.Name)),
			Snapshot:         nil,
		})
		if err != nil {
			return err
		}
		return nil
	})
}

    using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Databricks = Pulumi.Databricks;

return await Deployment.RunAsync(() => 
{
    var testMonitorInference = new Databricks.LakehouseMonitor("testMonitorInference", new()
    {
        TableName = $"{sandbox.Name}.{things.Name}.{myTestTable.Name}",
        AssetsDir = $"/Shared/provider-test/databricks_lakehouse_monitoring/{myTestTable.Name}",
        OutputSchemaName = $"{sandbox.Name}.{things.Name}",
        Snapshot = null,
    });

});

    package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.databricks.LakehouseMonitor;
import com.pulumi.databricks.LakehouseMonitorArgs;
import com.pulumi.databricks.inputs.LakehouseMonitorSnapshotArgs;
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 testMonitorInference = new LakehouseMonitor("testMonitorInference", LakehouseMonitorArgs.builder()        
            .tableName(String.format("%s.%s.%s", sandbox.name(),things.name(),myTestTable.name()))
            .assetsDir(String.format("/Shared/provider-test/databricks_lakehouse_monitoring/%s", myTestTable.name()))
            .outputSchemaName(String.format("%s.%s", sandbox.name(),things.name()))
            .snapshot()
            .build());

    }
}

    resources:
  testMonitorInference:
    type: databricks:LakehouseMonitor
    properties:
      tableName: ${sandbox.name}.${things.name}.${myTestTable.name}
      assetsDir: /Shared/provider-test/databricks_lakehouse_monitoring/${myTestTable.name}
      outputSchemaName: ${sandbox.name}.${things.name}
      snapshot: {}

    The following resources are often used in the same context:

    • databricks.Catalog
    • databricks.Schema
    • databricks.SqlTable

    Create LakehouseMonitor Resource

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

    Constructor syntax

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

@overload
def LakehouseMonitor(resource_name: str,
                     opts: Optional[ResourceOptions] = None,
                     assets_dir: Optional[str] = None,
                     table_name: Optional[str] = None,
                     output_schema_name: Optional[str] = None,
                     notifications: Optional[LakehouseMonitorNotificationsArgs] = None,
                     inference_log: Optional[LakehouseMonitorInferenceLogArgs] = None,
                     latest_monitor_failure_msg: Optional[str] = None,
                     data_classification_config: Optional[LakehouseMonitorDataClassificationConfigArgs] = None,
                     custom_metrics: Optional[Sequence[LakehouseMonitorCustomMetricArgs]] = None,
                     schedule: Optional[LakehouseMonitorScheduleArgs] = None,
                     skip_builtin_dashboard: Optional[bool] = None,
                     slicing_exprs: Optional[Sequence[str]] = None,
                     snapshot: Optional[LakehouseMonitorSnapshotArgs] = None,
                     baseline_table_name: Optional[str] = None,
                     time_series: Optional[LakehouseMonitorTimeSeriesArgs] = None,
                     warehouse_id: Optional[str] = None)
    func NewLakehouseMonitor(ctx *Context, name string, args LakehouseMonitorArgs, opts ...ResourceOption) (*LakehouseMonitor, error)
    public LakehouseMonitor(string name, LakehouseMonitorArgs args, CustomResourceOptions? opts = null)
    public LakehouseMonitor(String name, LakehouseMonitorArgs args)
public LakehouseMonitor(String name, LakehouseMonitorArgs args, CustomResourceOptions options)

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

    Parameters

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

    Example

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

    var lakehouseMonitorResource = new Databricks.LakehouseMonitor("lakehouseMonitorResource", new()
{
    AssetsDir = "string",
    TableName = "string",
    OutputSchemaName = "string",
    Notifications = new Databricks.Inputs.LakehouseMonitorNotificationsArgs
    {
        OnFailure = new Databricks.Inputs.LakehouseMonitorNotificationsOnFailureArgs
        {
            EmailAddresses = new[]
            {
                "string",
            },
        },
        OnNewClassificationTagDetected = new Databricks.Inputs.LakehouseMonitorNotificationsOnNewClassificationTagDetectedArgs
        {
            EmailAddresses = new[]
            {
                "string",
            },
        },
    },
    InferenceLog = new Databricks.Inputs.LakehouseMonitorInferenceLogArgs
    {
        Granularities = new[]
        {
            "string",
        },
        ModelIdCol = "string",
        PredictionCol = "string",
        ProblemType = "string",
        TimestampCol = "string",
        LabelCol = "string",
        PredictionProbaCol = "string",
    },
    LatestMonitorFailureMsg = "string",
    DataClassificationConfig = new Databricks.Inputs.LakehouseMonitorDataClassificationConfigArgs
    {
        Enabled = false,
    },
    CustomMetrics = new[]
    {
        new Databricks.Inputs.LakehouseMonitorCustomMetricArgs
        {
            Definition = "string",
            InputColumns = new[]
            {
                "string",
            },
            Name = "string",
            OutputDataType = "string",
            Type = "string",
        },
    },
    Schedule = new Databricks.Inputs.LakehouseMonitorScheduleArgs
    {
        QuartzCronExpression = "string",
        TimezoneId = "string",
        PauseStatus = "string",
    },
    SkipBuiltinDashboard = false,
    SlicingExprs = new[]
    {
        "string",
    },
    Snapshot = null,
    BaselineTableName = "string",
    TimeSeries = new Databricks.Inputs.LakehouseMonitorTimeSeriesArgs
    {
        Granularities = new[]
        {
            "string",
        },
        TimestampCol = "string",
    },
    WarehouseId = "string",
});

    example, err := databricks.NewLakehouseMonitor(ctx, "lakehouseMonitorResource", &databricks.LakehouseMonitorArgs{
	AssetsDir:        pulumi.String("string"),
	TableName:        pulumi.String("string"),
	OutputSchemaName: pulumi.String("string"),
	Notifications: &databricks.LakehouseMonitorNotificationsArgs{
		OnFailure: &databricks.LakehouseMonitorNotificationsOnFailureArgs{
			EmailAddresses: pulumi.StringArray{
				pulumi.String("string"),
			},
		},
		OnNewClassificationTagDetected: &databricks.LakehouseMonitorNotificationsOnNewClassificationTagDetectedArgs{
			EmailAddresses: pulumi.StringArray{
				pulumi.String("string"),
			},
		},
	},
	InferenceLog: &databricks.LakehouseMonitorInferenceLogArgs{
		Granularities: pulumi.StringArray{
			pulumi.String("string"),
		},
		ModelIdCol:         pulumi.String("string"),
		PredictionCol:      pulumi.String("string"),
		ProblemType:        pulumi.String("string"),
		TimestampCol:       pulumi.String("string"),
		LabelCol:           pulumi.String("string"),
		PredictionProbaCol: pulumi.String("string"),
	},
	LatestMonitorFailureMsg: pulumi.String("string"),
	DataClassificationConfig: &databricks.LakehouseMonitorDataClassificationConfigArgs{
		Enabled: pulumi.Bool(false),
	},
	CustomMetrics: databricks.LakehouseMonitorCustomMetricArray{
		&databricks.LakehouseMonitorCustomMetricArgs{
			Definition: pulumi.String("string"),
			InputColumns: pulumi.StringArray{
				pulumi.String("string"),
			},
			Name:           pulumi.String("string"),
			OutputDataType: pulumi.String("string"),
			Type:           pulumi.String("string"),
		},
	},
	Schedule: &databricks.LakehouseMonitorScheduleArgs{
		QuartzCronExpression: pulumi.String("string"),
		TimezoneId:           pulumi.String("string"),
		PauseStatus:          pulumi.String("string"),
	},
	SkipBuiltinDashboard: pulumi.Bool(false),
	SlicingExprs: pulumi.StringArray{
		pulumi.String("string"),
	},
	Snapshot:          nil,
	BaselineTableName: pulumi.String("string"),
	TimeSeries: &databricks.LakehouseMonitorTimeSeriesArgs{
		Granularities: pulumi.StringArray{
			pulumi.String("string"),
		},
		TimestampCol: pulumi.String("string"),
	},
	WarehouseId: pulumi.String("string"),
})

    var lakehouseMonitorResource = new LakehouseMonitor("lakehouseMonitorResource", LakehouseMonitorArgs.builder()        
    .assetsDir("string")
    .tableName("string")
    .outputSchemaName("string")
    .notifications(LakehouseMonitorNotificationsArgs.builder()
        .onFailure(LakehouseMonitorNotificationsOnFailureArgs.builder()
            .emailAddresses("string")
            .build())
        .onNewClassificationTagDetected(LakehouseMonitorNotificationsOnNewClassificationTagDetectedArgs.builder()
            .emailAddresses("string")
            .build())
        .build())
    .inferenceLog(LakehouseMonitorInferenceLogArgs.builder()
        .granularities("string")
        .modelIdCol("string")
        .predictionCol("string")
        .problemType("string")
        .timestampCol("string")
        .labelCol("string")
        .predictionProbaCol("string")
        .build())
    .latestMonitorFailureMsg("string")
    .dataClassificationConfig(LakehouseMonitorDataClassificationConfigArgs.builder()
        .enabled(false)
        .build())
    .customMetrics(LakehouseMonitorCustomMetricArgs.builder()
        .definition("string")
        .inputColumns("string")
        .name("string")
        .outputDataType("string")
        .type("string")
        .build())
    .schedule(LakehouseMonitorScheduleArgs.builder()
        .quartzCronExpression("string")
        .timezoneId("string")
        .pauseStatus("string")
        .build())
    .skipBuiltinDashboard(false)
    .slicingExprs("string")
    .snapshot()
    .baselineTableName("string")
    .timeSeries(LakehouseMonitorTimeSeriesArgs.builder()
        .granularities("string")
        .timestampCol("string")
        .build())
    .warehouseId("string")
    .build());

    lakehouse_monitor_resource = databricks.LakehouseMonitor("lakehouseMonitorResource",
    assets_dir="string",
    table_name="string",
    output_schema_name="string",
    notifications=databricks.LakehouseMonitorNotificationsArgs(
        on_failure=databricks.LakehouseMonitorNotificationsOnFailureArgs(
            email_addresses=["string"],
        ),
        on_new_classification_tag_detected=databricks.LakehouseMonitorNotificationsOnNewClassificationTagDetectedArgs(
            email_addresses=["string"],
        ),
    ),
    inference_log=databricks.LakehouseMonitorInferenceLogArgs(
        granularities=["string"],
        model_id_col="string",
        prediction_col="string",
        problem_type="string",
        timestamp_col="string",
        label_col="string",
        prediction_proba_col="string",
    ),
    latest_monitor_failure_msg="string",
    data_classification_config=databricks.LakehouseMonitorDataClassificationConfigArgs(
        enabled=False,
    ),
    custom_metrics=[databricks.LakehouseMonitorCustomMetricArgs(
        definition="string",
        input_columns=["string"],
        name="string",
        output_data_type="string",
        type="string",
    )],
    schedule=databricks.LakehouseMonitorScheduleArgs(
        quartz_cron_expression="string",
        timezone_id="string",
        pause_status="string",
    ),
    skip_builtin_dashboard=False,
    slicing_exprs=["string"],
    snapshot=databricks.LakehouseMonitorSnapshotArgs(),
    baseline_table_name="string",
    time_series=databricks.LakehouseMonitorTimeSeriesArgs(
        granularities=["string"],
        timestamp_col="string",
    ),
    warehouse_id="string")

    const lakehouseMonitorResource = new databricks.LakehouseMonitor("lakehouseMonitorResource", {
    assetsDir: "string",
    tableName: "string",
    outputSchemaName: "string",
    notifications: {
        onFailure: {
            emailAddresses: ["string"],
        },
        onNewClassificationTagDetected: {
            emailAddresses: ["string"],
        },
    },
    inferenceLog: {
        granularities: ["string"],
        modelIdCol: "string",
        predictionCol: "string",
        problemType: "string",
        timestampCol: "string",
        labelCol: "string",
        predictionProbaCol: "string",
    },
    latestMonitorFailureMsg: "string",
    dataClassificationConfig: {
        enabled: false,
    },
    customMetrics: [{
        definition: "string",
        inputColumns: ["string"],
        name: "string",
        outputDataType: "string",
        type: "string",
    }],
    schedule: {
        quartzCronExpression: "string",
        timezoneId: "string",
        pauseStatus: "string",
    },
    skipBuiltinDashboard: false,
    slicingExprs: ["string"],
    snapshot: {},
    baselineTableName: "string",
    timeSeries: {
        granularities: ["string"],
        timestampCol: "string",
    },
    warehouseId: "string",
});

    type: databricks:LakehouseMonitor
properties:
    assetsDir: string
    baselineTableName: string
    customMetrics:
        - definition: string
          inputColumns:
            - string
          name: string
          outputDataType: string
          type: string
    dataClassificationConfig:
        enabled: false
    inferenceLog:
        granularities:
            - string
        labelCol: string
        modelIdCol: string
        predictionCol: string
        predictionProbaCol: string
        problemType: string
        timestampCol: string
    latestMonitorFailureMsg: string
    notifications:
        onFailure:
            emailAddresses:
                - string
        onNewClassificationTagDetected:
            emailAddresses:
                - string
    outputSchemaName: string
    schedule:
        pauseStatus: string
        quartzCronExpression: string
        timezoneId: string
    skipBuiltinDashboard: false
    slicingExprs:
        - string
    snapshot: {}
    tableName: string
    timeSeries:
        granularities:
            - string
        timestampCol: string
    warehouseId: string

    LakehouseMonitor Resource Properties

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

    Inputs

    The LakehouseMonitor resource accepts the following input properties:

    AssetsDir string
    The directory to store the monitoring assets (Eg. Dashboard and Metric Tables)
    OutputSchemaName string
    Schema where output metric tables are created
    TableName string
    The full name of the table to attach the monitor too. Its of the format {catalog}.{schema}.{tableName}
    BaselineTableName string
    Name of the baseline table from which drift metrics are computed from.Columns in the monitored table should also be present in the baseline table.
    CustomMetrics List<LakehouseMonitorCustomMetric>
    Custom metrics to compute on the monitored table. These can be aggregate metrics, derived metrics (from already computed aggregate metrics), or drift metrics (comparing metrics across time windows).
    DataClassificationConfig LakehouseMonitorDataClassificationConfig
    The data classification config for the monitor
    InferenceLog LakehouseMonitorInferenceLog
    Configuration for the inference log monitor
    LatestMonitorFailureMsg string
    Notifications LakehouseMonitorNotifications
    The notification settings for the monitor. The following optional blocks are supported, each consisting of the single string array field with name email_addresses containing a list of emails to notify:
    Schedule LakehouseMonitorSchedule
    The schedule for automatically updating and refreshing metric tables. This block consists of following fields:
    SkipBuiltinDashboard bool
    Whether to skip creating a default dashboard summarizing data quality metrics.
    SlicingExprs List<string>
    List of column expressions to slice data with for targeted analysis. The data is grouped by each expression independently, resulting in a separate slice for each predicate and its complements. For high-cardinality columns, only the top 100 unique values by frequency will generate slices.
    Snapshot LakehouseMonitorSnapshot
    Configuration for monitoring snapshot tables.
    TimeSeries LakehouseMonitorTimeSeries
    Configuration for monitoring timeseries tables.
    WarehouseId string
    Optional argument to specify the warehouse for dashboard creation. If not specified, the first running warehouse will be used.
    AssetsDir string
    The directory to store the monitoring assets (Eg. Dashboard and Metric Tables)
    OutputSchemaName string
    Schema where output metric tables are created
    TableName string
    The full name of the table to attach the monitor too. Its of the format {catalog}.{schema}.{tableName}
    BaselineTableName string
    Name of the baseline table from which drift metrics are computed from.Columns in the monitored table should also be present in the baseline table.
    CustomMetrics []LakehouseMonitorCustomMetricArgs
    Custom metrics to compute on the monitored table. These can be aggregate metrics, derived metrics (from already computed aggregate metrics), or drift metrics (comparing metrics across time windows).
    DataClassificationConfig LakehouseMonitorDataClassificationConfigArgs
    The data classification config for the monitor
    InferenceLog LakehouseMonitorInferenceLogArgs
    Configuration for the inference log monitor
    LatestMonitorFailureMsg string
    Notifications LakehouseMonitorNotificationsArgs
    The notification settings for the monitor. The following optional blocks are supported, each consisting of the single string array field with name email_addresses containing a list of emails to notify:
    Schedule LakehouseMonitorScheduleArgs
    The schedule for automatically updating and refreshing metric tables. This block consists of following fields:
    SkipBuiltinDashboard bool
    Whether to skip creating a default dashboard summarizing data quality metrics.
    SlicingExprs []string
    List of column expressions to slice data with for targeted analysis. The data is grouped by each expression independently, resulting in a separate slice for each predicate and its complements. For high-cardinality columns, only the top 100 unique values by frequency will generate slices.
    Snapshot LakehouseMonitorSnapshotArgs
    Configuration for monitoring snapshot tables.
    TimeSeries LakehouseMonitorTimeSeriesArgs
    Configuration for monitoring timeseries tables.
    WarehouseId string
    Optional argument to specify the warehouse for dashboard creation. If not specified, the first running warehouse will be used.
    assetsDir String
    The directory to store the monitoring assets (Eg. Dashboard and Metric Tables)
    outputSchemaName String
    Schema where output metric tables are created
    tableName String
    The full name of the table to attach the monitor too. Its of the format {catalog}.{schema}.{tableName}
    baselineTableName String
    Name of the baseline table from which drift metrics are computed from.Columns in the monitored table should also be present in the baseline table.
    customMetrics List<LakehouseMonitorCustomMetric>
    Custom metrics to compute on the monitored table. These can be aggregate metrics, derived metrics (from already computed aggregate metrics), or drift metrics (comparing metrics across time windows).
    dataClassificationConfig LakehouseMonitorDataClassificationConfig
    The data classification config for the monitor
    inferenceLog LakehouseMonitorInferenceLog
    Configuration for the inference log monitor
    latestMonitorFailureMsg String
    notifications LakehouseMonitorNotifications
    The notification settings for the monitor. The following optional blocks are supported, each consisting of the single string array field with name email_addresses containing a list of emails to notify:
    schedule LakehouseMonitorSchedule
    The schedule for automatically updating and refreshing metric tables. This block consists of following fields:
    skipBuiltinDashboard Boolean
    Whether to skip creating a default dashboard summarizing data quality metrics.
    slicingExprs List<String>
    List of column expressions to slice data with for targeted analysis. The data is grouped by each expression independently, resulting in a separate slice for each predicate and its complements. For high-cardinality columns, only the top 100 unique values by frequency will generate slices.
    snapshot LakehouseMonitorSnapshot
    Configuration for monitoring snapshot tables.
    timeSeries LakehouseMonitorTimeSeries
    Configuration for monitoring timeseries tables.
    warehouseId String
    Optional argument to specify the warehouse for dashboard creation. If not specified, the first running warehouse will be used.
    assetsDir string
    The directory to store the monitoring assets (Eg. Dashboard and Metric Tables)
    outputSchemaName string
    Schema where output metric tables are created
    tableName string
    The full name of the table to attach the monitor too. Its of the format {catalog}.{schema}.{tableName}
    baselineTableName string
    Name of the baseline table from which drift metrics are computed from.Columns in the monitored table should also be present in the baseline table.
    customMetrics LakehouseMonitorCustomMetric[]
    Custom metrics to compute on the monitored table. These can be aggregate metrics, derived metrics (from already computed aggregate metrics), or drift metrics (comparing metrics across time windows).
    dataClassificationConfig LakehouseMonitorDataClassificationConfig
    The data classification config for the monitor
    inferenceLog LakehouseMonitorInferenceLog
    Configuration for the inference log monitor
    latestMonitorFailureMsg string
    notifications LakehouseMonitorNotifications
    The notification settings for the monitor. The following optional blocks are supported, each consisting of the single string array field with name email_addresses containing a list of emails to notify:
    schedule LakehouseMonitorSchedule
    The schedule for automatically updating and refreshing metric tables. This block consists of following fields:
    skipBuiltinDashboard boolean
    Whether to skip creating a default dashboard summarizing data quality metrics.
    slicingExprs string[]
    List of column expressions to slice data with for targeted analysis. The data is grouped by each expression independently, resulting in a separate slice for each predicate and its complements. For high-cardinality columns, only the top 100 unique values by frequency will generate slices.
    snapshot LakehouseMonitorSnapshot
    Configuration for monitoring snapshot tables.
    timeSeries LakehouseMonitorTimeSeries
    Configuration for monitoring timeseries tables.
    warehouseId string
    Optional argument to specify the warehouse for dashboard creation. If not specified, the first running warehouse will be used.
    assets_dir str
    The directory to store the monitoring assets (Eg. Dashboard and Metric Tables)
    output_schema_name str
    Schema where output metric tables are created
    table_name str
    The full name of the table to attach the monitor too. Its of the format {catalog}.{schema}.{tableName}
    baseline_table_name str
    Name of the baseline table from which drift metrics are computed from.Columns in the monitored table should also be present in the baseline table.
    custom_metrics Sequence[LakehouseMonitorCustomMetricArgs]
    Custom metrics to compute on the monitored table. These can be aggregate metrics, derived metrics (from already computed aggregate metrics), or drift metrics (comparing metrics across time windows).
    data_classification_config LakehouseMonitorDataClassificationConfigArgs
    The data classification config for the monitor
    inference_log LakehouseMonitorInferenceLogArgs
    Configuration for the inference log monitor
    latest_monitor_failure_msg str
    notifications LakehouseMonitorNotificationsArgs
    The notification settings for the monitor. The following optional blocks are supported, each consisting of the single string array field with name email_addresses containing a list of emails to notify:
    schedule LakehouseMonitorScheduleArgs
    The schedule for automatically updating and refreshing metric tables. This block consists of following fields:
    skip_builtin_dashboard bool
    Whether to skip creating a default dashboard summarizing data quality metrics.
    slicing_exprs Sequence[str]
    List of column expressions to slice data with for targeted analysis. The data is grouped by each expression independently, resulting in a separate slice for each predicate and its complements. For high-cardinality columns, only the top 100 unique values by frequency will generate slices.
    snapshot LakehouseMonitorSnapshotArgs
    Configuration for monitoring snapshot tables.
    time_series LakehouseMonitorTimeSeriesArgs
    Configuration for monitoring timeseries tables.
    warehouse_id str
    Optional argument to specify the warehouse for dashboard creation. If not specified, the first running warehouse will be used.
    assetsDir String
    The directory to store the monitoring assets (Eg. Dashboard and Metric Tables)
    outputSchemaName String
    Schema where output metric tables are created
    tableName String
    The full name of the table to attach the monitor too. Its of the format {catalog}.{schema}.{tableName}
    baselineTableName String
    Name of the baseline table from which drift metrics are computed from.Columns in the monitored table should also be present in the baseline table.
    customMetrics List<Property Map>
    Custom metrics to compute on the monitored table. These can be aggregate metrics, derived metrics (from already computed aggregate metrics), or drift metrics (comparing metrics across time windows).
    dataClassificationConfig Property Map
    The data classification config for the monitor
    inferenceLog Property Map
    Configuration for the inference log monitor
    latestMonitorFailureMsg String
    notifications Property Map
    The notification settings for the monitor. The following optional blocks are supported, each consisting of the single string array field with name email_addresses containing a list of emails to notify:
    schedule Property Map
    The schedule for automatically updating and refreshing metric tables. This block consists of following fields:
    skipBuiltinDashboard Boolean
    Whether to skip creating a default dashboard summarizing data quality metrics.
    slicingExprs List<String>
    List of column expressions to slice data with for targeted analysis. The data is grouped by each expression independently, resulting in a separate slice for each predicate and its complements. For high-cardinality columns, only the top 100 unique values by frequency will generate slices.
    snapshot Property Map
    Configuration for monitoring snapshot tables.
    timeSeries Property Map
    Configuration for monitoring timeseries tables.
    warehouseId String
    Optional argument to specify the warehouse for dashboard creation. If not specified, the first running warehouse will be used.

    Outputs

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

    DashboardId string
    The ID of the generated dashboard.
    DriftMetricsTableName string
    The full name of the drift metrics table. Format: catalog_name.schema_name.table_name.
    Id string
    The provider-assigned unique ID for this managed resource.
    MonitorVersion string
    The version of the monitor config (e.g. 1,2,3). If negative, the monitor may be corrupted
    ProfileMetricsTableName string
    The full name of the profile metrics table. Format: catalog_name.schema_name.table_name.
    Status string
    Status of the Monitor
    DashboardId string
    The ID of the generated dashboard.
    DriftMetricsTableName string
    The full name of the drift metrics table. Format: catalog_name.schema_name.table_name.
    Id string
    The provider-assigned unique ID for this managed resource.
    MonitorVersion string
    The version of the monitor config (e.g. 1,2,3). If negative, the monitor may be corrupted
    ProfileMetricsTableName string
    The full name of the profile metrics table. Format: catalog_name.schema_name.table_name.
    Status string
    Status of the Monitor
    dashboardId String
    The ID of the generated dashboard.
    driftMetricsTableName String
    The full name of the drift metrics table. Format: catalog_name.schema_name.table_name.
    id String
    The provider-assigned unique ID for this managed resource.
    monitorVersion String
    The version of the monitor config (e.g. 1,2,3). If negative, the monitor may be corrupted
    profileMetricsTableName String
    The full name of the profile metrics table. Format: catalog_name.schema_name.table_name.
    status String
    Status of the Monitor
    dashboardId string
    The ID of the generated dashboard.
    driftMetricsTableName string
    The full name of the drift metrics table. Format: catalog_name.schema_name.table_name.
    id string
    The provider-assigned unique ID for this managed resource.
    monitorVersion string
    The version of the monitor config (e.g. 1,2,3). If negative, the monitor may be corrupted
    profileMetricsTableName string
    The full name of the profile metrics table. Format: catalog_name.schema_name.table_name.
    status string
    Status of the Monitor
    dashboard_id str
    The ID of the generated dashboard.
    drift_metrics_table_name str
    The full name of the drift metrics table. Format: catalog_name.schema_name.table_name.
    id str
    The provider-assigned unique ID for this managed resource.
    monitor_version str
    The version of the monitor config (e.g. 1,2,3). If negative, the monitor may be corrupted
    profile_metrics_table_name str
    The full name of the profile metrics table. Format: catalog_name.schema_name.table_name.
    status str
    Status of the Monitor
    dashboardId String
    The ID of the generated dashboard.
    driftMetricsTableName String
    The full name of the drift metrics table. Format: catalog_name.schema_name.table_name.
    id String
    The provider-assigned unique ID for this managed resource.
    monitorVersion String
    The version of the monitor config (e.g. 1,2,3). If negative, the monitor may be corrupted
    profileMetricsTableName String
    The full name of the profile metrics table. Format: catalog_name.schema_name.table_name.
    status String
    Status of the Monitor

    Look up Existing LakehouseMonitor Resource

    Get an existing LakehouseMonitor 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?: LakehouseMonitorState, opts?: CustomResourceOptions): LakehouseMonitor
    @staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        assets_dir: Optional[str] = None,
        baseline_table_name: Optional[str] = None,
        custom_metrics: Optional[Sequence[LakehouseMonitorCustomMetricArgs]] = None,
        dashboard_id: Optional[str] = None,
        data_classification_config: Optional[LakehouseMonitorDataClassificationConfigArgs] = None,
        drift_metrics_table_name: Optional[str] = None,
        inference_log: Optional[LakehouseMonitorInferenceLogArgs] = None,
        latest_monitor_failure_msg: Optional[str] = None,
        monitor_version: Optional[str] = None,
        notifications: Optional[LakehouseMonitorNotificationsArgs] = None,
        output_schema_name: Optional[str] = None,
        profile_metrics_table_name: Optional[str] = None,
        schedule: Optional[LakehouseMonitorScheduleArgs] = None,
        skip_builtin_dashboard: Optional[bool] = None,
        slicing_exprs: Optional[Sequence[str]] = None,
        snapshot: Optional[LakehouseMonitorSnapshotArgs] = None,
        status: Optional[str] = None,
        table_name: Optional[str] = None,
        time_series: Optional[LakehouseMonitorTimeSeriesArgs] = None,
        warehouse_id: Optional[str] = None) -> LakehouseMonitor
    func GetLakehouseMonitor(ctx *Context, name string, id IDInput, state *LakehouseMonitorState, opts ...ResourceOption) (*LakehouseMonitor, error)
    public static LakehouseMonitor Get(string name, Input<string> id, LakehouseMonitorState? state, CustomResourceOptions? opts = null)
    public static LakehouseMonitor get(String name, Output<String> id, LakehouseMonitorState state, CustomResourceOptions options)
    Resource lookup is not supported in YAML
    name
    The unique name of the resulting resource.
    id
    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
    The unique name of the resulting resource.
    id
    The unique provider ID of the resource to lookup.
    name
    The unique name of the resulting resource.
    id
    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
    The unique name of the resulting resource.
    id
    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
    The unique name of the resulting resource.
    id
    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:
    AssetsDir string
    The directory to store the monitoring assets (Eg. Dashboard and Metric Tables)
    BaselineTableName string
    Name of the baseline table from which drift metrics are computed from.Columns in the monitored table should also be present in the baseline table.
    CustomMetrics List<LakehouseMonitorCustomMetric>
    Custom metrics to compute on the monitored table. These can be aggregate metrics, derived metrics (from already computed aggregate metrics), or drift metrics (comparing metrics across time windows).
    DashboardId string
    The ID of the generated dashboard.
    DataClassificationConfig LakehouseMonitorDataClassificationConfig
    The data classification config for the monitor
    DriftMetricsTableName string
    The full name of the drift metrics table. Format: catalog_name.schema_name.table_name.
    InferenceLog LakehouseMonitorInferenceLog
    Configuration for the inference log monitor
    LatestMonitorFailureMsg string
    MonitorVersion string
    The version of the monitor config (e.g. 1,2,3). If negative, the monitor may be corrupted
    Notifications LakehouseMonitorNotifications
    The notification settings for the monitor. The following optional blocks are supported, each consisting of the single string array field with name email_addresses containing a list of emails to notify:
    OutputSchemaName string
    Schema where output metric tables are created
    ProfileMetricsTableName string
    The full name of the profile metrics table. Format: catalog_name.schema_name.table_name.
    Schedule LakehouseMonitorSchedule
    The schedule for automatically updating and refreshing metric tables. This block consists of following fields:
    SkipBuiltinDashboard bool
    Whether to skip creating a default dashboard summarizing data quality metrics.
    SlicingExprs List<string>
    List of column expressions to slice data with for targeted analysis. The data is grouped by each expression independently, resulting in a separate slice for each predicate and its complements. For high-cardinality columns, only the top 100 unique values by frequency will generate slices.
    Snapshot LakehouseMonitorSnapshot
    Configuration for monitoring snapshot tables.
    Status string
    Status of the Monitor
    TableName string
    The full name of the table to attach the monitor too. Its of the format {catalog}.{schema}.{tableName}
    TimeSeries LakehouseMonitorTimeSeries
    Configuration for monitoring timeseries tables.
    WarehouseId string
    Optional argument to specify the warehouse for dashboard creation. If not specified, the first running warehouse will be used.
    AssetsDir string
    The directory to store the monitoring assets (Eg. Dashboard and Metric Tables)
    BaselineTableName string
    Name of the baseline table from which drift metrics are computed from.Columns in the monitored table should also be present in the baseline table.
    CustomMetrics []LakehouseMonitorCustomMetricArgs
    Custom metrics to compute on the monitored table. These can be aggregate metrics, derived metrics (from already computed aggregate metrics), or drift metrics (comparing metrics across time windows).
    DashboardId string
    The ID of the generated dashboard.
    DataClassificationConfig LakehouseMonitorDataClassificationConfigArgs
    The data classification config for the monitor
    DriftMetricsTableName string
    The full name of the drift metrics table. Format: catalog_name.schema_name.table_name.
    InferenceLog LakehouseMonitorInferenceLogArgs
    Configuration for the inference log monitor
    LatestMonitorFailureMsg string
    MonitorVersion string
    The version of the monitor config (e.g. 1,2,3). If negative, the monitor may be corrupted
    Notifications LakehouseMonitorNotificationsArgs
    The notification settings for the monitor. The following optional blocks are supported, each consisting of the single string array field with name email_addresses containing a list of emails to notify:
    OutputSchemaName string
    Schema where output metric tables are created
    ProfileMetricsTableName string
    The full name of the profile metrics table. Format: catalog_name.schema_name.table_name.
    Schedule LakehouseMonitorScheduleArgs
    The schedule for automatically updating and refreshing metric tables. This block consists of following fields:
    SkipBuiltinDashboard bool
    Whether to skip creating a default dashboard summarizing data quality metrics.
    SlicingExprs []string
    List of column expressions to slice data with for targeted analysis. The data is grouped by each expression independently, resulting in a separate slice for each predicate and its complements. For high-cardinality columns, only the top 100 unique values by frequency will generate slices.
    Snapshot LakehouseMonitorSnapshotArgs
    Configuration for monitoring snapshot tables.
    Status string
    Status of the Monitor
    TableName string
    The full name of the table to attach the monitor too. Its of the format {catalog}.{schema}.{tableName}
    TimeSeries LakehouseMonitorTimeSeriesArgs
    Configuration for monitoring timeseries tables.
    WarehouseId string
    Optional argument to specify the warehouse for dashboard creation. If not specified, the first running warehouse will be used.
    assetsDir String
    The directory to store the monitoring assets (Eg. Dashboard and Metric Tables)
    baselineTableName String
    Name of the baseline table from which drift metrics are computed from.Columns in the monitored table should also be present in the baseline table.
    customMetrics List<LakehouseMonitorCustomMetric>
    Custom metrics to compute on the monitored table. These can be aggregate metrics, derived metrics (from already computed aggregate metrics), or drift metrics (comparing metrics across time windows).
    dashboardId String
    The ID of the generated dashboard.
    dataClassificationConfig LakehouseMonitorDataClassificationConfig
    The data classification config for the monitor
    driftMetricsTableName String
    The full name of the drift metrics table. Format: catalog_name.schema_name.table_name.
    inferenceLog LakehouseMonitorInferenceLog
    Configuration for the inference log monitor
    latestMonitorFailureMsg String
    monitorVersion String
    The version of the monitor config (e.g. 1,2,3). If negative, the monitor may be corrupted
    notifications LakehouseMonitorNotifications
    The notification settings for the monitor. The following optional blocks are supported, each consisting of the single string array field with name email_addresses containing a list of emails to notify:
    outputSchemaName String
    Schema where output metric tables are created
    profileMetricsTableName String
    The full name of the profile metrics table. Format: catalog_name.schema_name.table_name.
    schedule LakehouseMonitorSchedule
    The schedule for automatically updating and refreshing metric tables. This block consists of following fields:
    skipBuiltinDashboard Boolean
    Whether to skip creating a default dashboard summarizing data quality metrics.
    slicingExprs List<String>
    List of column expressions to slice data with for targeted analysis. The data is grouped by each expression independently, resulting in a separate slice for each predicate and its complements. For high-cardinality columns, only the top 100 unique values by frequency will generate slices.
    snapshot LakehouseMonitorSnapshot
    Configuration for monitoring snapshot tables.
    status String
    Status of the Monitor
    tableName String
    The full name of the table to attach the monitor too. Its of the format {catalog}.{schema}.{tableName}
    timeSeries LakehouseMonitorTimeSeries
    Configuration for monitoring timeseries tables.
    warehouseId String
    Optional argument to specify the warehouse for dashboard creation. If not specified, the first running warehouse will be used.
    assetsDir string
    The directory to store the monitoring assets (Eg. Dashboard and Metric Tables)
    baselineTableName string
    Name of the baseline table from which drift metrics are computed from.Columns in the monitored table should also be present in the baseline table.
    customMetrics LakehouseMonitorCustomMetric[]
    Custom metrics to compute on the monitored table. These can be aggregate metrics, derived metrics (from already computed aggregate metrics), or drift metrics (comparing metrics across time windows).
    dashboardId string
    The ID of the generated dashboard.
    dataClassificationConfig LakehouseMonitorDataClassificationConfig
    The data classification config for the monitor
    driftMetricsTableName string
    The full name of the drift metrics table. Format: catalog_name.schema_name.table_name.
    inferenceLog LakehouseMonitorInferenceLog
    Configuration for the inference log monitor
    latestMonitorFailureMsg string
    monitorVersion string
    The version of the monitor config (e.g. 1,2,3). If negative, the monitor may be corrupted
    notifications LakehouseMonitorNotifications
    The notification settings for the monitor. The following optional blocks are supported, each consisting of the single string array field with name email_addresses containing a list of emails to notify:
    outputSchemaName string
    Schema where output metric tables are created
    profileMetricsTableName string
    The full name of the profile metrics table. Format: catalog_name.schema_name.table_name.
    schedule LakehouseMonitorSchedule
    The schedule for automatically updating and refreshing metric tables. This block consists of following fields:
    skipBuiltinDashboard boolean
    Whether to skip creating a default dashboard summarizing data quality metrics.
    slicingExprs string[]
    List of column expressions to slice data with for targeted analysis. The data is grouped by each expression independently, resulting in a separate slice for each predicate and its complements. For high-cardinality columns, only the top 100 unique values by frequency will generate slices.
    snapshot LakehouseMonitorSnapshot
    Configuration for monitoring snapshot tables.
    status string
    Status of the Monitor
    tableName string
    The full name of the table to attach the monitor too. Its of the format {catalog}.{schema}.{tableName}
    timeSeries LakehouseMonitorTimeSeries
    Configuration for monitoring timeseries tables.
    warehouseId string
    Optional argument to specify the warehouse for dashboard creation. If not specified, the first running warehouse will be used.
    assets_dir str
    The directory to store the monitoring assets (Eg. Dashboard and Metric Tables)
    baseline_table_name str
    Name of the baseline table from which drift metrics are computed from.Columns in the monitored table should also be present in the baseline table.
    custom_metrics Sequence[LakehouseMonitorCustomMetricArgs]
    Custom metrics to compute on the monitored table. These can be aggregate metrics, derived metrics (from already computed aggregate metrics), or drift metrics (comparing metrics across time windows).
    dashboard_id str
    The ID of the generated dashboard.
    data_classification_config LakehouseMonitorDataClassificationConfigArgs
    The data classification config for the monitor
    drift_metrics_table_name str
    The full name of the drift metrics table. Format: catalog_name.schema_name.table_name.
    inference_log LakehouseMonitorInferenceLogArgs
    Configuration for the inference log monitor
    latest_monitor_failure_msg str
    monitor_version str
    The version of the monitor config (e.g. 1,2,3). If negative, the monitor may be corrupted
    notifications LakehouseMonitorNotificationsArgs
    The notification settings for the monitor. The following optional blocks are supported, each consisting of the single string array field with name email_addresses containing a list of emails to notify:
    output_schema_name str
    Schema where output metric tables are created
    profile_metrics_table_name str
    The full name of the profile metrics table. Format: catalog_name.schema_name.table_name.
    schedule LakehouseMonitorScheduleArgs
    The schedule for automatically updating and refreshing metric tables. This block consists of following fields:
    skip_builtin_dashboard bool
    Whether to skip creating a default dashboard summarizing data quality metrics.
    slicing_exprs Sequence[str]
    List of column expressions to slice data with for targeted analysis. The data is grouped by each expression independently, resulting in a separate slice for each predicate and its complements. For high-cardinality columns, only the top 100 unique values by frequency will generate slices.
    snapshot LakehouseMonitorSnapshotArgs
    Configuration for monitoring snapshot tables.
    status str
    Status of the Monitor
    table_name str
    The full name of the table to attach the monitor too. Its of the format {catalog}.{schema}.{tableName}
    time_series LakehouseMonitorTimeSeriesArgs
    Configuration for monitoring timeseries tables.
    warehouse_id str
    Optional argument to specify the warehouse for dashboard creation. If not specified, the first running warehouse will be used.
    assetsDir String
    The directory to store the monitoring assets (Eg. Dashboard and Metric Tables)
    baselineTableName String
    Name of the baseline table from which drift metrics are computed from.Columns in the monitored table should also be present in the baseline table.
    customMetrics List<Property Map>
    Custom metrics to compute on the monitored table. These can be aggregate metrics, derived metrics (from already computed aggregate metrics), or drift metrics (comparing metrics across time windows).
    dashboardId String
    The ID of the generated dashboard.
    dataClassificationConfig Property Map
    The data classification config for the monitor
    driftMetricsTableName String
    The full name of the drift metrics table. Format: catalog_name.schema_name.table_name.
    inferenceLog Property Map
    Configuration for the inference log monitor
    latestMonitorFailureMsg String
    monitorVersion String
    The version of the monitor config (e.g. 1,2,3). If negative, the monitor may be corrupted
    notifications Property Map
    The notification settings for the monitor. The following optional blocks are supported, each consisting of the single string array field with name email_addresses containing a list of emails to notify:
    outputSchemaName String
    Schema where output metric tables are created
    profileMetricsTableName String
    The full name of the profile metrics table. Format: catalog_name.schema_name.table_name.
    schedule Property Map
    The schedule for automatically updating and refreshing metric tables. This block consists of following fields:
    skipBuiltinDashboard Boolean
    Whether to skip creating a default dashboard summarizing data quality metrics.
    slicingExprs List<String>
    List of column expressions to slice data with for targeted analysis. The data is grouped by each expression independently, resulting in a separate slice for each predicate and its complements. For high-cardinality columns, only the top 100 unique values by frequency will generate slices.
    snapshot Property Map
    Configuration for monitoring snapshot tables.
    status String
    Status of the Monitor
    tableName String
    The full name of the table to attach the monitor too. Its of the format {catalog}.{schema}.{tableName}
    timeSeries Property Map
    Configuration for monitoring timeseries tables.
    warehouseId String
    Optional argument to specify the warehouse for dashboard creation. If not specified, the first running warehouse will be used.

    Supporting Types

    LakehouseMonitorCustomMetric, LakehouseMonitorCustomMetricArgs

    Definition string
    create metric definition
    InputColumns List<string>
    Columns on the monitored table to apply the custom metrics to.
    Name string
    Name of the custom metric.
    OutputDataType string
    The output type of the custom metric.
    Type string
    The type of the custom metric.
    Definition string
    create metric definition
    InputColumns []string
    Columns on the monitored table to apply the custom metrics to.
    Name string
    Name of the custom metric.
    OutputDataType string
    The output type of the custom metric.
    Type string
    The type of the custom metric.
    definition String
    create metric definition
    inputColumns List<String>
    Columns on the monitored table to apply the custom metrics to.
    name String
    Name of the custom metric.
    outputDataType String
    The output type of the custom metric.
    type String
    The type of the custom metric.
    definition string
    create metric definition
    inputColumns string[]
    Columns on the monitored table to apply the custom metrics to.
    name string
    Name of the custom metric.
    outputDataType string
    The output type of the custom metric.
    type string
    The type of the custom metric.
    definition str
    create metric definition
    input_columns Sequence[str]
    Columns on the monitored table to apply the custom metrics to.
    name str
    Name of the custom metric.
    output_data_type str
    The output type of the custom metric.
    type str
    The type of the custom metric.
    definition String
    create metric definition
    inputColumns List<String>
    Columns on the monitored table to apply the custom metrics to.
    name String
    Name of the custom metric.
    outputDataType String
    The output type of the custom metric.
    type String
    The type of the custom metric.

    LakehouseMonitorDataClassificationConfig, LakehouseMonitorDataClassificationConfigArgs

    Enabled bool
    Enabled bool
    enabled Boolean
    enabled boolean
    enabled bool
    enabled Boolean

    LakehouseMonitorInferenceLog, LakehouseMonitorInferenceLogArgs

    Granularities List<string>
    List of granularities to use when aggregating data into time windows based on their timestamp.
    ModelIdCol string
    Column of the model id or version
    PredictionCol string
    Column of the model prediction
    ProblemType string
    Problem type the model aims to solve. Either PROBLEM_TYPE_CLASSIFICATION or PROBLEM_TYPE_REGRESSION
    TimestampCol string
    Column of the timestamp of predictions
    LabelCol string
    Column of the model label
    PredictionProbaCol string
    Column of the model prediction probabilities
    Granularities []string
    List of granularities to use when aggregating data into time windows based on their timestamp.
    ModelIdCol string
    Column of the model id or version
    PredictionCol string
    Column of the model prediction
    ProblemType string
    Problem type the model aims to solve. Either PROBLEM_TYPE_CLASSIFICATION or PROBLEM_TYPE_REGRESSION
    TimestampCol string
    Column of the timestamp of predictions
    LabelCol string
    Column of the model label
    PredictionProbaCol string
    Column of the model prediction probabilities
    granularities List<String>
    List of granularities to use when aggregating data into time windows based on their timestamp.
    modelIdCol String
    Column of the model id or version
    predictionCol String
    Column of the model prediction
    problemType String
    Problem type the model aims to solve. Either PROBLEM_TYPE_CLASSIFICATION or PROBLEM_TYPE_REGRESSION
    timestampCol String
    Column of the timestamp of predictions
    labelCol String
    Column of the model label
    predictionProbaCol String
    Column of the model prediction probabilities
    granularities string[]
    List of granularities to use when aggregating data into time windows based on their timestamp.
    modelIdCol string
    Column of the model id or version
    predictionCol string
    Column of the model prediction
    problemType string
    Problem type the model aims to solve. Either PROBLEM_TYPE_CLASSIFICATION or PROBLEM_TYPE_REGRESSION
    timestampCol string
    Column of the timestamp of predictions
    labelCol string
    Column of the model label
    predictionProbaCol string
    Column of the model prediction probabilities
    granularities Sequence[str]
    List of granularities to use when aggregating data into time windows based on their timestamp.
    model_id_col str
    Column of the model id or version
    prediction_col str
    Column of the model prediction
    problem_type str
    Problem type the model aims to solve. Either PROBLEM_TYPE_CLASSIFICATION or PROBLEM_TYPE_REGRESSION
    timestamp_col str
    Column of the timestamp of predictions
    label_col str
    Column of the model label
    prediction_proba_col str
    Column of the model prediction probabilities
    granularities List<String>
    List of granularities to use when aggregating data into time windows based on their timestamp.
    modelIdCol String
    Column of the model id or version
    predictionCol String
    Column of the model prediction
    problemType String
    Problem type the model aims to solve. Either PROBLEM_TYPE_CLASSIFICATION or PROBLEM_TYPE_REGRESSION
    timestampCol String
    Column of the timestamp of predictions
    labelCol String
    Column of the model label
    predictionProbaCol String
    Column of the model prediction probabilities

    LakehouseMonitorNotifications, LakehouseMonitorNotificationsArgs

    OnFailure LakehouseMonitorNotificationsOnFailure
    who to send notifications to on monitor failure.
    OnNewClassificationTagDetected LakehouseMonitorNotificationsOnNewClassificationTagDetected
    Who to send notifications to when new data classification tags are detected.
    OnFailure LakehouseMonitorNotificationsOnFailure
    who to send notifications to on monitor failure.
    OnNewClassificationTagDetected LakehouseMonitorNotificationsOnNewClassificationTagDetected
    Who to send notifications to when new data classification tags are detected.
    onFailure LakehouseMonitorNotificationsOnFailure
    who to send notifications to on monitor failure.
    onNewClassificationTagDetected LakehouseMonitorNotificationsOnNewClassificationTagDetected
    Who to send notifications to when new data classification tags are detected.
    onFailure LakehouseMonitorNotificationsOnFailure
    who to send notifications to on monitor failure.
    onNewClassificationTagDetected LakehouseMonitorNotificationsOnNewClassificationTagDetected
    Who to send notifications to when new data classification tags are detected.
    on_failure LakehouseMonitorNotificationsOnFailure
    who to send notifications to on monitor failure.
    on_new_classification_tag_detected LakehouseMonitorNotificationsOnNewClassificationTagDetected
    Who to send notifications to when new data classification tags are detected.
    onFailure Property Map
    who to send notifications to on monitor failure.
    onNewClassificationTagDetected Property Map
    Who to send notifications to when new data classification tags are detected.

    LakehouseMonitorNotificationsOnFailure, LakehouseMonitorNotificationsOnFailureArgs

    EmailAddresses List<string>
    emailAddresses List<String>
    email_addresses Sequence[str]
    emailAddresses List<String>

    LakehouseMonitorNotificationsOnNewClassificationTagDetected, LakehouseMonitorNotificationsOnNewClassificationTagDetectedArgs

    EmailAddresses List<string>
    emailAddresses List<String>
    email_addresses Sequence[str]
    emailAddresses List<String>

    LakehouseMonitorSchedule, LakehouseMonitorScheduleArgs

    QuartzCronExpression string
    string expression that determines when to run the monitor. See Quartz documentation for examples.
    TimezoneId string
    string with timezone id (e.g., PST) in which to evaluate the Quartz expression.
    PauseStatus string
    optional string field that indicates whether a schedule is paused (PAUSED) or not (UNPAUSED).
    QuartzCronExpression string
    string expression that determines when to run the monitor. See Quartz documentation for examples.
    TimezoneId string
    string with timezone id (e.g., PST) in which to evaluate the Quartz expression.
    PauseStatus string
    optional string field that indicates whether a schedule is paused (PAUSED) or not (UNPAUSED).
    quartzCronExpression String
    string expression that determines when to run the monitor. See Quartz documentation for examples.
    timezoneId String
    string with timezone id (e.g., PST) in which to evaluate the Quartz expression.
    pauseStatus String
    optional string field that indicates whether a schedule is paused (PAUSED) or not (UNPAUSED).
    quartzCronExpression string
    string expression that determines when to run the monitor. See Quartz documentation for examples.
    timezoneId string
    string with timezone id (e.g., PST) in which to evaluate the Quartz expression.
    pauseStatus string
    optional string field that indicates whether a schedule is paused (PAUSED) or not (UNPAUSED).
    quartz_cron_expression str
    string expression that determines when to run the monitor. See Quartz documentation for examples.
    timezone_id str
    string with timezone id (e.g., PST) in which to evaluate the Quartz expression.
    pause_status str
    optional string field that indicates whether a schedule is paused (PAUSED) or not (UNPAUSED).
    quartzCronExpression String
    string expression that determines when to run the monitor. See Quartz documentation for examples.
    timezoneId String
    string with timezone id (e.g., PST) in which to evaluate the Quartz expression.
    pauseStatus String
    optional string field that indicates whether a schedule is paused (PAUSED) or not (UNPAUSED).

    LakehouseMonitorTimeSeries, LakehouseMonitorTimeSeriesArgs

    Granularities List<string>
    List of granularities to use when aggregating data into time windows based on their timestamp.
    TimestampCol string
    Column of the timestamp of predictions
    Granularities []string
    List of granularities to use when aggregating data into time windows based on their timestamp.
    TimestampCol string
    Column of the timestamp of predictions
    granularities List<String>
    List of granularities to use when aggregating data into time windows based on their timestamp.
    timestampCol String
    Column of the timestamp of predictions
    granularities string[]
    List of granularities to use when aggregating data into time windows based on their timestamp.
    timestampCol string
    Column of the timestamp of predictions
    granularities Sequence[str]
    List of granularities to use when aggregating data into time windows based on their timestamp.
    timestamp_col str
    Column of the timestamp of predictions
    granularities List<String>
    List of granularities to use when aggregating data into time windows based on their timestamp.
    timestampCol String
    Column of the timestamp of predictions

    Package Details

    Repository
    databricks pulumi/pulumi-databricks
    License
    Apache-2.0
    Notes
    This Pulumi package is based on the databricks Terraform Provider.
    databricks logo
    Databricks v1.38.0 published on Monday, Apr 29, 2024 by Pulumi
    pulumi/pulumi-databricks