Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Spark example jobs to spark 3.4 #3471

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open

Spark example jobs to spark 3.4 #3471

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
4197e66
Passing Default Storage for avoiding workspace network setting policies
vaibhj Nov 22, 2024
5da8f70
trying quick fix
vaibhj Nov 22, 2024
323f4fd
fix
vaibhj Nov 22, 2024
701483a
fix
vaibhj Nov 22, 2024
84623e1
Merge branch 'main' of https://github.com/Azure/azureml-examples into…
vaibhj Dec 13, 2024
48a013a
Spark examples to spark 3.4
vaibhj Dec 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion cli/jobs/spark/serverless-spark-pipeline-default-identity.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,4 +22,4 @@ jobs:

resources:
instance_type: standard_e8s_v3
runtime_version: "3.3"
runtime_version: "3.4"
2 changes: 1 addition & 1 deletion cli/jobs/spark/serverless-spark-pipeline-managed-identity.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,4 +25,4 @@ jobs:

resources:
instance_type: standard_e8s_v3
runtime_version: "3.3"
runtime_version: "3.4"
2 changes: 1 addition & 1 deletion cli/jobs/spark/serverless-spark-pipeline-user-identity.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,4 +25,4 @@ jobs:

resources:
instance_type: standard_e8s_v3
runtime_version: "3.3"
runtime_version: "3.4"
2 changes: 1 addition & 1 deletion cli/jobs/spark/serverless-spark-standalone-default-identity.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,5 +31,5 @@ args: >-

resources:
instance_type: standard_e4s_v3
runtime_version: "3.3"
runtime_version: "3.4"

2 changes: 1 addition & 1 deletion cli/jobs/spark/serverless-spark-standalone-managed-identity.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,5 +34,5 @@ identity:

resources:
instance_type: standard_e4s_v3
runtime_version: "3.3"
runtime_version: "3.4"

2 changes: 1 addition & 1 deletion cli/jobs/spark/serverless-spark-standalone-user-identity.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,5 +34,5 @@ identity:

resources:
instance_type: standard_e4s_v3
runtime_version: "3.3"
runtime_version: "3.4"

2 changes: 1 addition & 1 deletion cli/monitoring/advanced-model-monitoring.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ create_monitor:

compute:
instance_type: standard_e4s_v3
runtime_version: "3.3"
runtime_version: "3.4"

monitoring_target:
ml_task: classification
Expand Down
2 changes: 1 addition & 1 deletion cli/monitoring/custom-monitoring.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ trigger:
create_monitor:
compute:
instance_type: "standard_e8s_v3"
runtime_version: "3.3"
runtime_version: "3.4"

monitoring_signals:
customSignal:
Expand Down
2 changes: 1 addition & 1 deletion cli/monitoring/generation-safety-quality-monitoring.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ trigger:
create_monitor:
compute:
instance_type: "standard_e8s_v3"
runtime_version: "3.3"
runtime_version: "3.4"
monitoring_target:
ml_task: classification
endpoint_deployment_id: fake_endpoint_id
Expand Down
2 changes: 1 addition & 1 deletion cli/monitoring/model-monitoring-with-collected-data.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ trigger:
create_monitor:
compute:
instance_type: standard_e4s_v3
runtime_version: "3.3"
runtime_version: "3.4"
monitoring_target:
ml_task: classification
endpoint_deployment_id: azureml:fraud-detection-endpoint:fraud-detection-deployment
Expand Down
2 changes: 1 addition & 1 deletion cli/monitoring/out-of-box-monitoring.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ create_monitor:

compute: # specify a spark compute for monitoring job
instance_type: standard_e4s_v3
runtime_version: "3.3"
runtime_version: "3.4"

monitoring_target:
ml_task: classification # model task type: [classification, regression, question_answering]
Expand Down
2 changes: 1 addition & 1 deletion sdk/python/jobs/spark/setup_spark.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,7 @@ else
az storage fs create -n $GEN2_FILE_SYSTEM --account-name $GEN2_STORAGE_NAME
az synapse workspace create --name $SYNAPSE_WORKSPACE_NAME --resource-group $RESOURCE_GROUP --storage-account $GEN2_STORAGE_NAME --file-system $GEN2_FILE_SYSTEM --sql-admin-login-user $SQL_ADMIN_LOGIN_USER --sql-admin-login-password $RANDOM_STRING --location $LOCATION
az role assignment create --role "Storage Blob Data Owner" --assignee $AML_USER_MANAGED_ID_OID --scope /subscriptions/$SUBSCRIPTION_ID/resourceGroups/$RESOURCE_GROUP/providers/Microsoft.Storage/storageAccounts/$GEN2_STORAGE_NAME/blobServices/default/containers/$GEN2_FILE_SYSTEM
az synapse spark pool create --name $SPARK_POOL_NAME --workspace-name $SYNAPSE_WORKSPACE_NAME --resource-group $RESOURCE_GROUP --spark-version 3.3 --node-count 3 --node-size Medium --min-node-count 3 --max-node-count 10 --enable-auto-scale true
az synapse spark pool create --name $SPARK_POOL_NAME --workspace-name $SYNAPSE_WORKSPACE_NAME --resource-group $RESOURCE_GROUP --spark-version 3.4 --node-count 3 --node-size Medium --min-node-count 3 --max-node-count 10 --enable-auto-scale true
az synapse workspace firewall-rule create --name allowAll --workspace-name $SYNAPSE_WORKSPACE_NAME --resource-group $RESOURCE_GROUP --start-ip-address 0.0.0.0 --end-ip-address 255.255.255.255
#</create_attached_resources>

Expand Down
6 changes: 3 additions & 3 deletions sdk/python/jobs/spark/submit_spark_pipeline_jobs.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,7 +342,7 @@
" spark_step.identity = ManagedIdentityConfiguration()\n",
" spark_step.resources = {\n",
" \"instance_type\": \"Standard_E8S_V3\",\n",
" \"runtime_version\": \"3.3.0\",\n",
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you actually set this as 2-digit not 3, aka 3.4

" \"runtime_version\": \"3.4.0\",\n",
" }\n",
"\n",
"\n",
Expand Down Expand Up @@ -422,7 +422,7 @@
" spark_step.identity = UserIdentityConfiguration()\n",
" spark_step.resources = {\n",
" \"instance_type\": \"Standard_E8S_V3\",\n",
" \"runtime_version\": \"3.3.0\",\n",
" \"runtime_version\": \"3.4.0\",\n",
" }\n",
"\n",
"\n",
Expand Down Expand Up @@ -501,7 +501,7 @@
" spark_step.outputs.wrangled_data.mode = InputOutputModes.DIRECT\n",
" spark_step.resources = {\n",
" \"instance_type\": \"Standard_E8S_V3\",\n",
" \"runtime_version\": \"3.3.0\",\n",
" \"runtime_version\": \"3.4.0\",\n",
" }\n",
"\n",
"\n",
Expand Down
6 changes: 3 additions & 3 deletions sdk/python/jobs/spark/submit_spark_standalone_jobs.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,7 +267,7 @@
" executor_instances=2,\n",
" resources={\n",
" \"instance_type\": \"Standard_E8S_V3\",\n",
" \"runtime_version\": \"3.3.0\",\n",
" \"runtime_version\": \"3.4.0\",\n",
" },\n",
" inputs={\n",
" \"titanic_data\": Input(\n",
Expand Down Expand Up @@ -329,7 +329,7 @@
" executor_instances=2,\n",
" resources={\n",
" \"instance_type\": \"Standard_E8S_V3\",\n",
" \"runtime_version\": \"3.3.0\",\n",
" \"runtime_version\": \"3.4.0\",\n",
" },\n",
" inputs={\n",
" \"titanic_data\": Input(\n",
Expand Down Expand Up @@ -391,7 +391,7 @@
" executor_instances=2,\n",
" resources={\n",
" \"instance_type\": \"Standard_E8S_V3\",\n",
" \"runtime_version\": \"3.3.0\",\n",
" \"runtime_version\": \"3.4.0\",\n",
" },\n",
" inputs={\n",
" \"titanic_data\": Input(\n",
Expand Down
4 changes: 2 additions & 2 deletions sdk/python/jobs/spark/submit_spark_standalone_jobs_managed_vnet.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -535,7 +535,7 @@
" executor_instances=2,\n",
" resources={\n",
" \"instance_type\": \"Standard_E8S_V3\",\n",
" \"runtime_version\": \"3.3.0\",\n",
" \"runtime_version\": \"3.4.0\",\n",
" },\n",
" inputs={\n",
" \"titanic_data\": Input(\n",
Expand Down Expand Up @@ -769,7 +769,7 @@
" executor_instances=2,\n",
" resources={\n",
" \"instance_type\": \"Standard_E8S_V3\",\n",
" \"runtime_version\": \"3.3.0\",\n",
" \"runtime_version\": \"3.4.0\",\n",
" },\n",
" inputs={\n",
" \"titanic_data\": Input(\n",
Expand Down
Loading