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

acryl_datahub_cloud/metadata/schemas/MLPrimaryKeyProperties.avsc

@@ -0,0 +1,185 @@
+{
+  "type": "record",
+  "Aspect": {
+    "name": "mlPrimaryKeyProperties"
+  },
+  "name": "MLPrimaryKeyProperties",
+  "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 MLPrimaryKey"
+    },
+    {
+      "type": [
+        "null",
+        {
+          "type": "enum",
+          "symbolDocs": {
+            "AUDIO": "Audio Data",
+            "BINARY": "Binary data is discrete data that can be in only one of two categories - either yes or no, 1 or 0, off or on, etc",
+            "BYTE": "Bytes data are binary-encoded values that can represent complex objects.",
+            "CONTINUOUS": "Continuous data are made of uncountable values, often the result of a measurement such as height, weight, age etc.",
+            "COUNT": "Count data is discrete whole number data - no negative numbers here.\nCount data often has many small values, such as zero and one.",
+            "IMAGE": "Image Data",
+            "INTERVAL": "Interval data has equal spaces between the numbers and does not represent a temporal pattern.\nExamples include percentages, temperatures, and income.",
+            "MAP": "Mapping Data Type ex: dict, map",
+            "NOMINAL": "Nominal data is made of discrete values with no numerical relationship between the different categories - mean and median are meaningless.\nAnimal species is one example. For example, pig is not higher than bird and lower than fish.",
+            "ORDINAL": "Ordinal data are discrete integers that can be ranked or sorted.\nFor example, the distance between first and second may not be the same as the distance between second and third.",
+            "SEQUENCE": "Sequence Data Type ex: list, tuple, range",
+            "SET": "Set Data Type ex: set, frozenset",
+            "TEXT": "Text Data",
+            "TIME": "Time data is a cyclical, repeating continuous form of data.\nThe relevant time features can be any period- daily, weekly, monthly, annual, etc.",
+            "UNKNOWN": "Unknown data are data that we don't know the type for.",
+            "USELESS": "Useless data is unique, discrete data with no potential relationship with the outcome variable.\nA useless feature has high cardinality. An example would be bank account numbers that were generated randomly.",
+            "VIDEO": "Video Data"
+          },
+          "name": "MLFeatureDataType",
+          "namespace": "com.linkedin.pegasus2avro.common",
+          "symbols": [
+            "USELESS",
+            "NOMINAL",
+            "ORDINAL",
+            "BINARY",
+            "COUNT",
+            "TIME",
+            "INTERVAL",
+            "IMAGE",
+            "VIDEO",
+            "AUDIO",
+            "TEXT",
+            "MAP",
+            "SEQUENCE",
+            "SET",
+            "CONTINUOUS",
+            "BYTE",
+            "UNKNOWN"
+          ],
+          "doc": "MLFeature Data Type"
+        }
+      ],
+      "name": "dataType",
+      "default": null,
+      "doc": "Data Type of the MLPrimaryKey"
+    },
+    {
+      "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 MLPrimaryKey"
+    },
+    {
+      "Relationship": {
+        "/*": {
+          "entityTypes": [
+            "dataset"
+          ],
+          "isLineage": true,
+          "name": "DerivedFrom"
+        }
+      },
+      "type": {
+        "type": "array",
+        "items": "string"
+      },
+      "name": "sources",
+      "doc": "Source of the MLPrimaryKey",
+      "Urn": "Urn",
+      "urn_is_array": true
+    }
+  ],
+  "doc": "Properties associated with a MLPrimaryKey"
+}