add latest dataset profile (#23)

acryldata · Feb 12, 2025 · ea7d2ce · ea7d2ce
1 parent 079500a
commit ea7d2ce
Show file tree

Hide file tree

Showing 2 changed files with 49 additions and 0 deletions.
diff --git a/graphql/latest_profile/README.MD b/graphql/latest_profile/README.MD
@@ -0,0 +1 @@
+Replace `urn` in the query with the URN that you wish to use
diff --git a/graphql/latest_profile/query.graphql b/graphql/latest_profile/query.graphql
@@ -0,0 +1,48 @@
+{
+  dataset(urn: "urn:li:dataset:(urn:li:dataPlatform:snowflake,datahub_community.datahub_slack.message_block_field,PROD)") {
+    latestFullTableProfile: datasetProfiles(
+      limit: 1,
+      filter: {and: [{field: "partitionSpec.partition", values: ["FULL_TABLE_SNAPSHOT", "SAMPLE"]}]}
+    ){
+      ...datasetProfileFields
+    }
+    latestPartitionProfile: datasetProfiles(
+      limit: 1
+      filter: {and: [{field: "partitionSpec.partition", values: ["SAMPLE", "FULL_TABLE_SNAPSHOT"], negated: true}]}
+    ) {
+    	...datasetProfileFields
+    __typename
+  }
+  }
+}
+fragment datasetProfileFields on DatasetProfile {
+  rowCount
+  columnCount
+  sizeInBytes
+  timestampMillis
+  partitionSpec {
+    type
+    partition
+    timePartition {
+      startTimeMillis
+      durationMillis
+      __typename
+    }
+    __typename
+  }
+  fieldProfiles {
+    fieldPath
+    uniqueCount
+    uniqueProportion
+    nullCount
+    nullProportion
+    min
+    max
+    mean
+    median
+    stdev
+    sampleValues
+    __typename
+  }
+  __typename
+}
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		Replace `urn` in the query with the URN that you wish to use