acryl-datahub-cloud 0.3.8rc8__py3-none-any.whl → 0.3.8rc9__py3-none-any.whl

acryl_datahub_cloud/metadata/schemas/MLModelGroupProperties.avsc

@@ -0,0 +1,123 @@
+{
+  "type": "record",
+  "Aspect": {
+    "name": "mlModelGroupProperties"
+  },
+  "name": "MLModelGroupProperties",
+  "namespace": "com.linkedin.pegasus2avro.ml.metadata",
+  "fields": [
+    {
+      "Searchable": {
+        "/*": {
+          "fieldType": "TEXT",
+          "queryByDefault": true
+        }
+      },
+      "type": {
+        "type": "map",
+        "values": "string"
+      },
+      "name": "customProperties",
+      "default": {},
+      "doc": "Custom property bag."
+    },
+    {
+      "Searchable": {
+        "fieldType": "TEXT",
+        "hasValuesFieldName": "hasDescription"
+      },
+      "type": [
+        "null",
+        "string"
+      ],
+      "name": "description",
+      "default": null,
+      "doc": "Documentation of the MLModelGroup"
+    },
+    {
+      "type": [
+        "null",
+        "long"
+      ],
+      "name": "createdAt",
+      "default": null,
+      "doc": "Date when the MLModelGroup was developed"
+    },
+    {
+      "type": [
+        "null",
+        {
+          "type": "record",
+          "name": "VersionTag",
+          "namespace": "com.linkedin.pegasus2avro.common",
+          "fields": [
+            {
+              "type": [
+                "null",
+                "string"
+              ],
+              "name": "versionTag",
+              "default": null
+            },
+            {
+              "type": [
+                "null",
+                {
+                  "type": "record",
+                  "name": "MetadataAttribution",
+                  "namespace": "com.linkedin.pegasus2avro.common",
+                  "fields": [
+                    {
+                      "type": "long",
+                      "name": "time",
+                      "doc": "When this metadata was updated."
+                    },
+                    {
+                      "java": {
+                        "class": "com.linkedin.pegasus2avro.common.urn.Urn"
+                      },
+                      "type": "string",
+                      "name": "actor",
+                      "doc": "The entity (e.g. a member URN) responsible for applying the assocated metadata. This can\neither be a user (in case of UI edits) or the datahub system for automation.",
+                      "Urn": "Urn"
+                    },
+                    {
+                      "java": {
+                        "class": "com.linkedin.pegasus2avro.common.urn.Urn"
+                      },
+                      "type": [
+                        "null",
+                        "string"
+                      ],
+                      "name": "source",
+                      "default": null,
+                      "doc": "The DataHub source responsible for applying the associated metadata. This will only be filled out\nwhen a DataHub source is responsible. This includes the specific metadata test urn, the automation urn.",
+                      "Urn": "Urn"
+                    },
+                    {
+                      "type": {
+                        "type": "map",
+                        "values": "string"
+                      },
+                      "name": "sourceDetail",
+                      "default": {},
+                      "doc": "The details associated with why this metadata was applied. For example, this could include\nthe actual regex rule, sql statement, ingestion pipeline ID, etc.\nAlso can include flags like 'propagated'=true or 'inferred'=true."
+                    }
+                  ],
+                  "doc": "Information about who, why, and how this metadata was applied"
+                }
+              ],
+              "name": "metadataAttribution",
+              "default": null
+            }
+          ],
+          "doc": "A resource-defined string representing the resource state for the purpose of concurrency control"
+        }
+      ],
+      "name": "version",
+      "default": null,
+      "doc": "Version of the MLModelGroup"
+    }
+  ],
+  "doc": "Properties associated with an ML Model Group"
+}

acryl_datahub_cloud/metadata/schemas/MLModelKey.avsc

@@ -0,0 +1,117 @@
+{
+  "type": "record",
+  "Aspect": {
+    "name": "mlModelKey",
+    "keyForEntity": "mlModel",
+    "entityCategory": "core",
+    "entityAspects": [
+      "glossaryTerms",
+      "editableMlModelProperties",
+      "domains",
+      "proposals",
+      "ownership",
+      "mlModelProperties",
+      "intendedUse",
+      "mlModelFactorPrompts",
+      "mlModelMetrics",
+      "mlModelEvaluationData",
+      "mlModelTrainingData",
+      "mlModelQuantitativeAnalyses",
+      "mlModelEthicalConsiderations",
+      "mlModelCaveatsAndRecommendations",
+      "institutionalMemory",
+      "sourceCode",
+      "status",
+      "cost",
+      "deprecation",
+      "browsePaths",
+      "globalTags",
+      "dataPlatformInstance",
+      "browsePathsV2",
+      "structuredProperties",
+      "forms",
+      "testResults",
+      "share",
+      "origin",
+      "lineageFeatures",
+      "documentation",
+      "incidentsSummary",
+      "versionProperties"
+    ]
+  },
+  "name": "MLModelKey",
+  "namespace": "com.linkedin.pegasus2avro.metadata.key",
+  "fields": [
+    {
+      "java": {
+        "class": "com.linkedin.pegasus2avro.common.urn.Urn"
+      },
+      "type": "string",
+      "name": "platform",
+      "doc": "Standardized platform urn for the model",
+      "Urn": "Urn"
+    },
+    {
+      "Searchable": {
+        "boostScore": 10.0,
+        "enableAutocomplete": true,
+        "fieldNameAliases": [
+          "_entityName"
+        ],
+        "fieldType": "WORD_GRAM"
+      },
+      "type": "string",
+      "name": "name",
+      "doc": "Name of the MLModel"
+    },
+    {
+      "Searchable": {
+        "addToFilters": true,
+        "fieldType": "TEXT_PARTIAL",
+        "filterNameOverride": "Environment",
+        "queryByDefault": false
+      },
+      "type": {
+        "type": "enum",
+        "symbolDocs": {
+          "CORP": "Designates corporation fabrics",
+          "DEV": "Designates development fabrics",
+          "EI": "Designates early-integration fabrics",
+          "NON_PROD": "Designates non-production fabrics",
+          "PRD": "Alternative Prod spelling",
+          "PRE": "Designates pre-production fabrics",
+          "PROD": "Designates production fabrics",
+          "QA": "Designates quality assurance fabrics",
+          "RVW": "Designates review fabrics",
+          "SANDBOX": "Designates sandbox fabrics",
+          "STG": "Designates staging fabrics",
+          "TEST": "Designates testing fabrics",
+          "TST": "Alternative Test spelling",
+          "UAT": "Designates user acceptance testing fabrics"
+        },
+        "name": "FabricType",
+        "namespace": "com.linkedin.pegasus2avro.common",
+        "symbols": [
+          "DEV",
+          "TEST",
+          "QA",
+          "UAT",
+          "EI",
+          "PRE",
+          "STG",
+          "NON_PROD",
+          "PROD",
+          "CORP",
+          "RVW",
+          "PRD",
+          "TST",
+          "SANDBOX"
+        ],
+        "doc": "Fabric group type"
+      },
+      "name": "origin",
+      "doc": "Fabric type where model belongs to or where it was generated"
+    }
+  ],
+  "doc": "Key for an ML model"
+}

acryl_datahub_cloud/metadata/schemas/MLModelProperties.avsc

@@ -0,0 +1,414 @@
+{
+  "type": "record",
+  "Aspect": {
+    "name": "mlModelProperties"
+  },
+  "name": "MLModelProperties",
+  "namespace": "com.linkedin.pegasus2avro.ml.metadata",
+  "fields": [
+    {
+      "Searchable": {
+        "/*": {
+          "fieldType": "TEXT",
+          "queryByDefault": true
+        }
+      },
+      "type": {
+        "type": "map",
+        "values": "string"
+      },
+      "name": "customProperties",
+      "default": {},
+      "doc": "Custom property bag."
+    },
+    {
+      "Searchable": {
+        "fieldType": "KEYWORD"
+      },
+      "java": {
+        "class": "com.linkedin.pegasus2avro.common.url.Url",
+        "coercerClass": "com.linkedin.pegasus2avro.common.url.UrlCoercer"
+      },
+      "type": [
+        "null",
+        "string"
+      ],
+      "name": "externalUrl",
+      "default": null,
+      "doc": "URL where the reference exist"
+    },
+    {
+      "Searchable": {
+        "fieldType": "TEXT",
+        "hasValuesFieldName": "hasDescription"
+      },
+      "type": [
+        "null",
+        "string"
+      ],
+      "name": "description",
+      "default": null,
+      "doc": "Documentation of the MLModel"
+    },
+    {
+      "type": [
+        "null",
+        "long"
+      ],
+      "name": "date",
+      "default": null,
+      "doc": "Date when the MLModel was developed"
+    },
+    {
+      "type": [
+        "null",
+        {
+          "type": "record",
+          "name": "VersionTag",
+          "namespace": "com.linkedin.pegasus2avro.common",
+          "fields": [
+            {
+              "type": [
+                "null",
+                "string"
+              ],
+              "name": "versionTag",
+              "default": null
+            },
+            {
+              "type": [
+                "null",
+                {
+                  "type": "record",
+                  "name": "MetadataAttribution",
+                  "namespace": "com.linkedin.pegasus2avro.common",
+                  "fields": [
+                    {
+                      "type": "long",
+                      "name": "time",
+                      "doc": "When this metadata was updated."
+                    },
+                    {
+                      "java": {
+                        "class": "com.linkedin.pegasus2avro.common.urn.Urn"
+                      },
+                      "type": "string",
+                      "name": "actor",
+                      "doc": "The entity (e.g. a member URN) responsible for applying the assocated metadata. This can\neither be a user (in case of UI edits) or the datahub system for automation.",
+                      "Urn": "Urn"
+                    },
+                    {
+                      "java": {
+                        "class": "com.linkedin.pegasus2avro.common.urn.Urn"
+                      },
+                      "type": [
+                        "null",
+                        "string"
+                      ],
+                      "name": "source",
+                      "default": null,
+                      "doc": "The DataHub source responsible for applying the associated metadata. This will only be filled out\nwhen a DataHub source is responsible. This includes the specific metadata test urn, the automation urn.",
+                      "Urn": "Urn"
+                    },
+                    {
+                      "type": {
+                        "type": "map",
+                        "values": "string"
+                      },
+                      "name": "sourceDetail",
+                      "default": {},
+                      "doc": "The details associated with why this metadata was applied. For example, this could include\nthe actual regex rule, sql statement, ingestion pipeline ID, etc.\nAlso can include flags like 'propagated'=true or 'inferred'=true."
+                    }
+                  ],
+                  "doc": "Information about who, why, and how this metadata was applied"
+                }
+              ],
+              "name": "metadataAttribution",
+              "default": null
+            }
+          ],
+          "doc": "A resource-defined string representing the resource state for the purpose of concurrency control"
+        }
+      ],
+      "name": "version",
+      "default": null,
+      "doc": "Version of the MLModel"
+    },
+    {
+      "Searchable": {
+        "fieldType": "TEXT_PARTIAL"
+      },
+      "type": [
+        "null",
+        "string"
+      ],
+      "name": "type",
+      "default": null,
+      "doc": "Type of Algorithm or MLModel such as whether it is a Naive Bayes classifier, Convolutional Neural Network, etc"
+    },
+    {
+      "type": [
+        "null",
+        {
+          "type": "map",
+          "values": [
+            "string",
+            "int",
+            "float",
+            "double",
+            "boolean"
+          ]
+        }
+      ],
+      "name": "hyperParameters",
+      "default": null,
+      "doc": "Hyper Parameters of the MLModel\n\nNOTE: these are deprecated in favor of hyperParams"
+    },
+    {
+      "type": [
+        "null",
+        {
+          "type": "array",
+          "items": {
+            "type": "record",
+            "Aspect": {
+              "name": "mlHyperParam"
+            },
+            "name": "MLHyperParam",
+            "namespace": "com.linkedin.pegasus2avro.ml.metadata",
+            "fields": [
+              {
+                "type": "string",
+                "name": "name",
+                "doc": "Name of the MLHyperParam"
+              },
+              {
+                "type": [
+                  "null",
+                  "string"
+                ],
+                "name": "description",
+                "default": null,
+                "doc": "Documentation of the MLHyperParam"
+              },
+              {
+                "type": [
+                  "null",
+                  "string"
+                ],
+                "name": "value",
+                "default": null,
+                "doc": "The value of the MLHyperParam"
+              },
+              {
+                "type": [
+                  "null",
+                  "long"
+                ],
+                "name": "createdAt",
+                "default": null,
+                "doc": "Date when the MLHyperParam was developed"
+              }
+            ],
+            "doc": "Properties associated with an ML Hyper Param"
+          }
+        }
+      ],
+      "name": "hyperParams",
+      "default": null,
+      "doc": "Hyperparameters of the MLModel"
+    },
+    {
+      "type": [
+        "null",
+        {
+          "type": "array",
+          "items": {
+            "type": "record",
+            "Aspect": {
+              "name": "mlMetric"
+            },
+            "name": "MLMetric",
+            "namespace": "com.linkedin.pegasus2avro.ml.metadata",
+            "fields": [
+              {
+                "type": "string",
+                "name": "name",
+                "doc": "Name of the mlMetric"
+              },
+              {
+                "type": [
+                  "null",
+                  "string"
+                ],
+                "name": "description",
+                "default": null,
+                "doc": "Documentation of the mlMetric"
+              },
+              {
+                "type": [
+                  "null",
+                  "string"
+                ],
+                "name": "value",
+                "default": null,
+                "doc": "The value of the mlMetric"
+              },
+              {
+                "type": [
+                  "null",
+                  "long"
+                ],
+                "name": "createdAt",
+                "default": null,
+                "doc": "Date when the mlMetric was developed"
+              }
+            ],
+            "doc": "Properties associated with an ML Metric"
+          }
+        }
+      ],
+      "name": "trainingMetrics",
+      "default": null,
+      "doc": "Metrics of the MLModel used in training"
+    },
+    {
+      "type": [
+        "null",
+        {
+          "type": "array",
+          "items": "com.linkedin.pegasus2avro.ml.metadata.MLMetric"
+        }
+      ],
+      "name": "onlineMetrics",
+      "default": null,
+      "doc": "Metrics of the MLModel used in production"
+    },
+    {
+      "Relationship": {
+        "/*": {
+          "entityTypes": [
+            "mlFeature"
+          ],
+          "isLineage": true,
+          "name": "Consumes"
+        }
+      },
+      "type": [
+        "null",
+        {
+          "type": "array",
+          "items": "string"
+        }
+      ],
+      "name": "mlFeatures",
+      "default": null,
+      "doc": "List of features used for MLModel training",
+      "Urn": "MLFeatureUrn",
+      "urn_is_array": true
+    },
+    {
+      "type": {
+        "type": "array",
+        "items": "string"
+      },
+      "name": "tags",
+      "default": [],
+      "doc": "Tags for the MLModel"
+    },
+    {
+      "Relationship": {
+        "/*": {
+          "entityTypes": [
+            "mlModelDeployment"
+          ],
+          "name": "DeployedTo"
+        }
+      },
+      "type": [
+        "null",
+        {
+          "type": "array",
+          "items": "string"
+        }
+      ],
+      "name": "deployments",
+      "default": null,
+      "doc": "Deployments for the MLModel",
+      "Urn": "Urn",
+      "urn_is_array": true
+    },
+    {
+      "Relationship": {
+        "/*": {
+          "entityTypes": [
+            "dataJob"
+          ],
+          "isLineage": true,
+          "name": "TrainedBy"
+        }
+      },
+      "type": [
+        "null",
+        {
+          "type": "array",
+          "items": "string"
+        }
+      ],
+      "name": "trainingJobs",
+      "default": null,
+      "doc": "List of jobs (if any) used to train the model",
+      "Urn": "Urn",
+      "urn_is_array": true
+    },
+    {
+      "Relationship": {
+        "/*": {
+          "entityTypes": [
+            "dataJob"
+          ],
+          "isLineage": true,
+          "isUpstream": false,
+          "name": "UsedBy"
+        }
+      },
+      "type": [
+        "null",
+        {
+          "type": "array",
+          "items": "string"
+        }
+      ],
+      "name": "downstreamJobs",
+      "default": null,
+      "doc": "List of jobs (if any) that use the model",
+      "Urn": "Urn",
+      "urn_is_array": true
+    },
+    {
+      "Relationship": {
+        "/*": {
+          "entityTypes": [
+            "mlModelGroup"
+          ],
+          "isLineage": true,
+          "isUpstream": false,
+          "name": "MemberOf"
+        }
+      },
+      "type": [
+        "null",
+        {
+          "type": "array",
+          "items": "string"
+        }
+      ],
+      "name": "groups",
+      "default": null,
+      "doc": "Groups the model belongs to",
+      "Urn": "Urn",
+      "urn_is_array": true
+    }
+  ],
+  "doc": "Properties associated with a ML Model"
+}

acryl_datahub_cloud/metadata/schemas/MLPrimaryKeyKey.avsc

@@ -0,0 +1,53 @@
+{
+  "type": "record",
+  "Aspect": {
+    "name": "mlPrimaryKeyKey",
+    "keyForEntity": "mlPrimaryKey",
+    "entityCategory": "core",
+    "entityAspects": [
+      "glossaryTerms",
+      "editableMlPrimaryKeyProperties",
+      "domains",
+      "proposals",
+      "mlPrimaryKeyProperties",
+      "ownership",
+      "institutionalMemory",
+      "status",
+      "deprecation",
+      "globalTags",
+      "dataPlatformInstance",
+      "structuredProperties",
+      "forms",
+      "testResults",
+      "share",
+      "origin",
+      "lineageFeatures"
+    ]
+  },
+  "name": "MLPrimaryKeyKey",
+  "namespace": "com.linkedin.pegasus2avro.metadata.key",
+  "fields": [
+    {
+      "Searchable": {
+        "fieldType": "TEXT_PARTIAL"
+      },
+      "type": "string",
+      "name": "featureNamespace",
+      "doc": "Namespace for the primary key"
+    },
+    {
+      "Searchable": {
+        "boostScore": 8.0,
+        "enableAutocomplete": true,
+        "fieldNameAliases": [
+          "_entityName"
+        ],
+        "fieldType": "WORD_GRAM"
+      },
+      "type": "string",
+      "name": "name",
+      "doc": "Name of the primary key"
+    }
+  ],
+  "doc": "Key for an MLPrimaryKey"
+}