monitor_schema.models.ComparisonConfig#
- class monitor_schema.models.ComparisonConfig[source]#
Compare whether the target against either an expect value or against the baseline.
This is useful to detect data type change, for instance.
Show JSON schema
{ "title": "ComparisonConfig", "description": "Compare whether the target against either an expect value or against the baseline.\n\nThis is useful to detect data type change, for instance.", "type": "object", "properties": { "schemaVersion": { "title": "SchemaVersion", "description": "The schema version of an algorithm. Typically this value is not required.", "type": "integer" }, "params": { "title": "Params", "description": "Extra parameters for the algorithm", "type": "object", "additionalProperties": { "type": "string", "maxLength": 1000 } }, "metric": { "title": "Metric", "description": "The target metric. This field cannot be change once the analyzer is created.", "anyOf": [ { "$ref": "#/definitions/DatasetMetric" }, { "$ref": "#/definitions/SimpleColumnMetric" }, { "type": "string", "maxLength": 100 } ] }, "type": { "title": "Type", "enum": [ "comparison" ], "type": "string" }, "operator": { "description": "The operator for the comparison. The right hand side is the target batch's metric. The left handside is the expected value or a baseline's metric.", "allOf": [ { "$ref": "#/definitions/ComparisonOperator" } ] }, "expected": { "title": "Expected", "description": "The expected value of the equality. If the value is not set we will extract the corresponding metric from the baseline and perform the comparison", "allOf": [ { "$ref": "#/definitions/ExpectedValue" } ] }, "baseline": { "title": "Baseline", "description": "A baseline for running the analyzer.", "discriminator": { "propertyName": "type", "mapping": { "TrailingWindow": "#/definitions/TrailingWindowBaseline", "Reference": "#/definitions/ReferenceProfileId", "TimeRange": "#/definitions/TimeRangeBaseline", "CurrentBatch": "#/definitions/SingleBatchBaseline" } }, "oneOf": [ { "$ref": "#/definitions/TrailingWindowBaseline" }, { "$ref": "#/definitions/ReferenceProfileId" }, { "$ref": "#/definitions/TimeRangeBaseline" }, { "$ref": "#/definitions/SingleBatchBaseline" } ] } }, "required": [ "metric", "type", "operator" ], "additionalProperties": false, "definitions": { "DatasetMetric": { "title": "DatasetMetric", "description": "Metrics that are applicable at the dataset level.", "enum": [ "profile.count", "profile.last_ingestion_time", "profile.first_ingestion_time", "column_row_count_sum", "shape_column_count", "shape_row_count", "input.count", "output.count", "classification.f1", "classification.precision", "classification.recall", "classification.accuracy", "classification.fpr", "classification.auroc", "regression.mse", "regression.mae", "regression.rmse" ], "type": "string" }, "SimpleColumnMetric": { "title": "SimpleColumnMetric", "description": "Simple column metrics that are basically just a single number.", "enum": [ "count", "median", "max", "min", "mean", "stddev", "variance", "unique_upper", "unique_upper_ratio", "unique_est", "unique_est_ratio", "unique_lower", "unique_lower_ratio", "count_bool", "count_bool_ratio", "count_integral", "count_integral_ratio", "count_fractional", "count_fractional_ratio", "count_string", "count_string_ratio", "count_null", "count_null_ratio", "inferred_data_type", "quantile_5", "quantile_75", "quantile_25", "quantile_90", "quantile_95", "quantile_99" ], "type": "string" }, "ComparisonOperator": { "title": "ComparisonOperator", "description": "Operators for performing a comparison.", "enum": [ "eq", "gt", "lt", "ge", "le" ], "type": "string" }, "ExpectedValue": { "title": "ExpectedValue", "description": "Expected value: one of these fields must be set.", "type": "object", "properties": { "str": { "title": "Str", "maxLength": 100, "type": "string" }, "int": { "title": "Int", "type": "integer" }, "float": { "title": "Float", "type": "number" } }, "additionalProperties": false }, "TimeRange": { "title": "TimeRange", "description": "Support for a specific time range.", "type": "object", "properties": { "start": { "title": "Start", "description": "Inclusive. Start time of a time range.", "type": "string", "format": "date-time" }, "end": { "title": "End", "description": "Exclusive. End time of a time range.", "type": "string", "format": "date-time" } }, "required": [ "start", "end" ], "additionalProperties": false }, "TrailingWindowBaseline": { "title": "TrailingWindowBaseline", "description": "A dynamic trailing window.\n\nThis is useful if you don't have a static baseline to monitor against. This is the default mode for most\nmonitors.", "type": "object", "properties": { "datasetId": { "title": "DatasetId", "description": "The unique ID of an dataset. This is specific to WhyLabs. If the dataset ID does not exist, user will get a validation exception when saving the config with WhyLabs API", "maxLength": 100, "pattern": "[a-zA-Z0-9\\-_\\.]+", "type": "string" }, "inheritSegment": { "title": "InheritSegment", "description": "Default to false. Whether to use the segment from the target to filter down the baseline", "type": "boolean" }, "type": { "title": "Type", "enum": [ "TrailingWindow" ], "type": "string" }, "size": { "title": "Size", "description": "Window size", "exclusiveMinimum": 3, "maximum": 90, "type": "integer" }, "offset": { "title": "Offset", "description": "Offset from the current batch for the range of the trailing window. Default to 1 (the previous batch). This means that if set this to 0, the baseline will include the current batch's value, orif we set it o 7, then the window is off by 7.", "type": "integer" }, "exclusionRanges": { "title": "ExclusionRanges", "description": "The list of exclusion ranges", "maxItems": 100, "type": "array", "items": { "$ref": "#/definitions/TimeRange" } } }, "required": [ "type", "size" ], "additionalProperties": false }, "ReferenceProfileId": { "title": "ReferenceProfileId", "description": "A baseline based on a static reference profile.\n\nA typical use case is to use a \"gold\" dataset and upload its profile to WhyLabs. This can be a training dataset\nas well for an ML model.", "type": "object", "properties": { "datasetId": { "title": "DatasetId", "description": "The unique ID of an dataset. This is specific to WhyLabs. If the dataset ID does not exist, user will get a validation exception when saving the config with WhyLabs API", "maxLength": 100, "pattern": "[a-zA-Z0-9\\-_\\.]+", "type": "string" }, "type": { "title": "Type", "enum": [ "Reference" ], "type": "string" }, "profileId": { "title": "ProfileId", "description": "The unique profile ID for the reference profile", "maxLength": 100, "type": "string" } }, "required": [ "type", "profileId" ], "additionalProperties": false }, "TimeRangeBaseline": { "title": "TimeRangeBaseline", "description": "A static time range.\n\nInstead of using a single profile or a trailing window, user can lock in a \"good\" period.", "type": "object", "properties": { "datasetId": { "title": "DatasetId", "description": "The unique ID of an dataset. This is specific to WhyLabs. If the dataset ID does not exist, user will get a validation exception when saving the config with WhyLabs API", "maxLength": 100, "pattern": "[a-zA-Z0-9\\-_\\.]+", "type": "string" }, "inheritSegment": { "title": "InheritSegment", "description": "Default to false. Whether to use the segment from the target to filter down the baseline", "type": "boolean" }, "type": { "title": "Type", "enum": [ "TimeRange" ], "type": "string" }, "range": { "title": "Range", "description": "The range to set the time range with", "allOf": [ { "$ref": "#/definitions/TimeRange" } ] } }, "required": [ "type", "range" ], "additionalProperties": false }, "SingleBatchBaseline": { "title": "SingleBatchBaseline", "description": "Using current batch.\n\nThis is used when you want to use one batch to monitor another batch in a different metric entity.", "type": "object", "properties": { "datasetId": { "title": "DatasetId", "description": "The unique ID of an dataset. This is specific to WhyLabs. If the dataset ID does not exist, user will get a validation exception when saving the config with WhyLabs API", "maxLength": 100, "pattern": "[a-zA-Z0-9\\-_\\.]+", "type": "string" }, "inheritSegment": { "title": "InheritSegment", "description": "Default to false. Whether to use the segment from the target to filter down the baseline", "type": "boolean" }, "type": { "title": "Type", "enum": [ "CurrentBatch" ], "type": "string" }, "offset": { "title": "Offset", "description": "Offset from the current batch for the baseline. Default to 0 - (the current batch). This means that if this field set this to 0, the baseline be the current batch's value. The dataset fieldis required to be set for this baseline config.Typical use case is to use another entity to monitor against the current entity", "type": "integer" } }, "required": [ "datasetId", "type" ], "additionalProperties": false } } }
- Config:
schema_extra: function = <function AlgorithmConfig.Config.schema_extra at 0x1090d61f0>
- Fields:
- field baseline: TrailingWindowBaseline | ReferenceProfileId | TimeRangeBaseline | SingleBatchBaseline | None = None#
A baseline for running the analyzer.
- field expected: ExpectedValue | None = None#
The expected value of the equality. If the value is not set we will extract the corresponding metric from the baseline and perform the comparison
- field operator: ComparisonOperator [Required]#
The operator for the comparison. The right hand side is the target batch’s metric. The left handside is the expected value or a baseline’s metric.
- field type: comparison: 'comparison'>] [Required]#