-
Notifications
You must be signed in to change notification settings - Fork 1.4k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
17 changed files
with
1,088 additions
and
17 deletions.
There are no files selected for viewing
80 changes: 80 additions & 0 deletions
80
.github/workflows/sdk-featurestore_sample-test_featurestore_sdk_samples.yml
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,80 @@ | ||
| # This code is autogenerated. | ||
| # Code is generated by running custom script: python3 readme.py | ||
| # Any manual changes to this file may cause incorrect behavior. | ||
| # Any manual changes will be overwritten if the code is regenerated. | ||
|
|
||
| name: sdk-featurestore_sample-test_featurestore_sdk_samples | ||
| # This file is created by sdk/python/readme.py. | ||
| # Please do not edit directly. | ||
| on: | ||
| workflow_dispatch: | ||
| schedule: | ||
| - cron: "22 2/12 * * *" | ||
| pull_request: | ||
| branches: | ||
| - main | ||
| paths: | ||
| - sdk/python/featurestore_sample/** | ||
| - .github/workflows/sdk-featurestore_sample-test_featurestore_sdk_samples.yml | ||
| - sdk/python/dev-requirements.txt | ||
| - infra/bootstrapping/** | ||
| - sdk/python/setup.sh | ||
| concurrency: | ||
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} | ||
| cancel-in-progress: true | ||
| jobs: | ||
| build: | ||
| runs-on: ubuntu-latest | ||
| steps: | ||
| - name: check out repo | ||
| uses: actions/checkout@v2 | ||
| - name: setup python | ||
| uses: actions/setup-python@v2 | ||
| with: | ||
| python-version: "3.8" | ||
| - name: pip install notebook reqs | ||
| run: pip install -r sdk/python/dev-requirements.txt | ||
| - name: azure login | ||
| uses: azure/login@v1 | ||
| with: | ||
| creds: ${{secrets.AZUREML_CREDENTIALS}} | ||
| - name: bootstrap resources | ||
| run: | | ||
| echo '${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}'; | ||
| bash bootstrap.sh | ||
| working-directory: infra/bootstrapping | ||
| continue-on-error: false | ||
| - name: setup SDK | ||
| run: | | ||
| source "${{ github.workspace }}/infra/bootstrapping/sdk_helpers.sh"; | ||
| source "${{ github.workspace }}/infra/bootstrapping/init_environment.sh"; | ||
| bash setup.sh | ||
| working-directory: sdk/python | ||
| continue-on-error: true | ||
| - name: setup-cli | ||
| run: | | ||
| source "${{ github.workspace }}/infra/bootstrapping/sdk_helpers.sh"; | ||
| source "${{ github.workspace }}/infra/bootstrapping/init_environment.sh"; | ||
| bash setup.sh | ||
| working-directory: cli | ||
| continue-on-error: true | ||
| - name: setup feature-store resources | ||
| run: | | ||
| bash -x setup-resources.sh test_featurestore_sdk_samples.ipynb | ||
| working-directory: sdk/python/featurestore_sample | ||
| continue-on-error: true | ||
| - name: run featurestore_sample/test_featurestore_sdk_samples.ipynb | ||
| run: | | ||
| source "${{ github.workspace }}/infra/bootstrapping/sdk_helpers.sh"; | ||
| source "${{ github.workspace }}/infra/bootstrapping/init_environment.sh"; | ||
| bash "${{ github.workspace }}/infra/bootstrapping/sdk_helpers.sh" generate_workspace_config "../../.azureml/config.json"; | ||
| bash "${{ github.workspace }}/infra/bootstrapping/sdk_helpers.sh" replace_template_values "test_featurestore_sdk_samples.ipynb"; | ||
| [ -f "../../.azureml/config" ] && cat "../../.azureml/config"; | ||
| papermill -k python test_featurestore_sdk_samples.ipynb test_featurestore_sdk_samples.output.ipynb | ||
| working-directory: sdk/python/featurestore_sample | ||
| - name: upload notebook's working folder as an artifact | ||
| if: ${{ always() }} | ||
| uses: actions/upload-artifact@v2 | ||
| with: | ||
| name: test_featurestore_sdk_samples | ||
| path: sdk/python/featurestore_sample |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,26 @@ | ||
| from pyspark.sql import SparkSession | ||
|
|
||
| spark = SparkSession.builder.appName("AccessData").getOrCreate() | ||
|
|
||
| print("=======Test Notebook 1============") | ||
| with open( | ||
| "notebooks/sdk_only/1. Develop a feature set and register with managed feature store.py" | ||
| ) as f: | ||
| exec(f.read()) | ||
|
|
||
| ## Enable test for notebook 1 first | ||
| # print("=======Test Notebook 2============") | ||
| # with open( | ||
| # "notebooks/sdk_only/2. Enable materialization and backfill feature data.py" | ||
| # ) as f: | ||
| # exec(f.read()) | ||
|
|
||
| # print("=======Test Notebook 3============") | ||
| # with open("notebooks/sdk_only/3. Experiment and train models using features.py") as f: | ||
| # exec(f.read()) | ||
|
|
||
| # print("=======Test Notebook 3============") | ||
| # with open( | ||
| # "notebooks/sdk_only/4. Enable recurrent materialization and run batch inference.py" | ||
| # ) as f: | ||
| # exec(f.read()) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,36 @@ | ||
| pip install --upgrade jupytext | ||
|
|
||
| # <create_variables> | ||
| SUBSCRIPTION_ID=$(az account show --query id -o tsv) | ||
| LOCATION=$(az ml workspace show --query location -o tsv) | ||
| RESOURCE_GROUP=$(az group show --query name -o tsv) | ||
| AML_WORKSPACE_NAME=$(az configure -l --query "[?name=='workspace'].value" -o tsv) | ||
| OUTPUT_COMMAND="print" | ||
| FEATURE_STORAGE_ACCOUNT_NAME=${RESOURCE_GROUP}fs | ||
| USER_ID="36b5b70a-a2b2-45e6-a496-df3c2ffde085" | ||
|
|
||
| # </create_variables> | ||
|
|
||
| # <convert_notebook_to_py> | ||
| NOTEBOOK_1="notebooks/sdk_only/1. Develop a feature set and register with managed feature store" | ||
| NOTEBOOK_2="notebooks/sdk_only/2. Enable materialization and backfill feature data" | ||
| NOTEBOOK_3="notebooks/sdk_only/3. Experiment and train models using features" | ||
| NOTEBOOK_4="notebooks/sdk_only/4. Enable recurrent materialization and run batch inference" | ||
| jupytext --to py "${NOTEBOOK_1}.ipynb" | ||
| jupytext --to py "${NOTEBOOK_2}.ipynb" | ||
| jupytext --to py "${NOTEBOOK_3}.ipynb" | ||
| jupytext --to py "${NOTEBOOK_4}.ipynb" | ||
| # <convert_notebook_to_py> | ||
|
|
||
| #<replace_template_values> | ||
| sed -i "s/<SUBSCRIPTION_ID>/$SUBSCRIPTION_ID/g; | ||
| s/<RESOURCE_GROUP>/$RESOURCE_GROUP/g; | ||
| s/<AML_WORKSPACE_NAME>/$AML_WORKSPACE_NAME/g;" $1 | ||
|
|
||
| #<replace_template_values> | ||
| sed -i "s/display/$OUTPUT_COMMAND/g;s/.\/Users\/<your_user_alias>\/featurestore_sample/.\//g;" "${NOTEBOOK_1}.py" | ||
| sed -i "s/display/$OUTPUT_COMMAND/g;s/.\/Users\/<your_user_alias>\/featurestore_sample/.\//g; | ||
| s/<FEATURE_STORAGE_ACCOUNT_NAME>/$FEATURE_STORAGE_ACCOUNT_NAME/g; | ||
| s/<USER_AAD_OBJECTID>/$USER_ID/g;" "${NOTEBOOK_2}.py" | ||
| sed -i "s/display/$OUTPUT_COMMAND/g;s/.\/Users\/<your_user_alias>\/featurestore_sample/.\//g;" "${NOTEBOOK_3}.py" | ||
| sed -i "s/display/$OUTPUT_COMMAND/g;s/.\/Users\/<your_user_alias>\/featurestore_sample/.\//g;" "${NOTEBOOK_4}.py" |
88 changes: 88 additions & 0 deletions
88
sdk/python/featurestore_sample/test_featurestore_sdk_samples.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,88 @@ | ||
| { | ||
| "cells": [ | ||
| { | ||
| "attachments": {}, | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Use a serverless Spark compute" | ||
| ] | ||
| }, | ||
| { | ||
| "attachments": {}, | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "You should have an attached Synapse Spark pool available in your workspace. Please see documentation page: [Attach and manage a Synapse Spark pool in Azure Machine Learning (preview)](https://learn.microsoft.com/azure/machine-learning/how-to-manage-synapse-spark-pool) for more details.\n", | ||
| "\n", | ||
| "**Note** - To ensure successful execution of Spark job, the identity being used for the Spark job should be assigned **Contributor** and **Storage Blob Data Contributor** roles on the Azure storage account used for data input and output." | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "from azure.ai.ml import MLClient, spark, Input, Output\n", | ||
| "from azure.identity import DefaultAzureCredential\n", | ||
| "from azure.ai.ml.entities import Environment\n", | ||
| "\n", | ||
| "subscription_id = \"<SUBSCRIPTION_ID>\"\n", | ||
| "resource_group = \"<RESOURCE_GROUP>\"\n", | ||
| "workspace = \"<AML_WORKSPACE_NAME>\"\n", | ||
| "ml_client = MLClient(\n", | ||
| " DefaultAzureCredential(), subscription_id, resource_group, workspace\n", | ||
| ")" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "spark_job = spark(\n", | ||
| " display_name=\"featurestore_sample_test\",\n", | ||
| " code=\"./\",\n", | ||
| " entry={\"file\": \"featurestore_sdk_job.py\"},\n", | ||
| " driver_cores=1,\n", | ||
| " driver_memory=\"1g\",\n", | ||
| " executor_cores=1,\n", | ||
| " executor_memory=\"1g\",\n", | ||
| " executor_instances=1,\n", | ||
| " resources={\n", | ||
| " \"instance_type\": \"Standard_E8S_V3\",\n", | ||
| " \"runtime_version\": \"3.2.0\",\n", | ||
| " },\n", | ||
| " environment=Environment(conda_file=\"project/env/conda.yml\"),\n", | ||
| ")\n", | ||
| "\n", | ||
| "returned_spark_job = ml_client.jobs.create_or_update(spark_job)\n", | ||
| "\n", | ||
| "print(returned_spark_job.id)\n", | ||
| "# Wait until the job completes\n", | ||
| "ml_client.jobs.stream(returned_spark_job.name)" | ||
| ] | ||
| } | ||
| ], | ||
| "metadata": { | ||
| "kernelspec": { | ||
| "display_name": "Python 3.10 - SDK V2", | ||
| "language": "python", | ||
| "name": "python310-sdkv2" | ||
| }, | ||
| "language_info": { | ||
| "name": "python", | ||
| "version": "3.7.10" | ||
| }, | ||
| "orig_nbformat": 4, | ||
| "vscode": { | ||
| "interpreter": { | ||
| "hash": "6aeff17a1aa7735c2f7cb3a6d691fe1b4d4c3b8d2d650f644ad0f24e1b8e3f3f" | ||
| } | ||
| } | ||
| }, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 2 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
33 changes: 33 additions & 0 deletions
33
...hon/foundation-models/system/finetune/Llama-notebooks/text-generation/download-dataset.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,33 @@ | ||
| # import library to parse command line arguments | ||
| import argparse, os | ||
|
|
||
| parser = argparse.ArgumentParser() | ||
| # add an argument to specify a dataset name to download | ||
| parser.add_argument("--dataset", type=str, default="samsum", help="dataset name") | ||
| # add an argument to specify a dataset name to download | ||
| parser.add_argument( | ||
| "--dataset_subset", type=str, default="split", help="dataset subset name" | ||
| ) | ||
| # add an argument to specify the directory to download the dataset to | ||
| parser.add_argument( | ||
| "--download_dir", | ||
| type=str, | ||
| default="data", | ||
| help="directory to download the dataset to", | ||
| ) | ||
| args = parser.parse_args() | ||
|
|
||
| # create the download directory if it does not exist | ||
| if not os.path.exists(args.download_dir): | ||
| os.makedirs(args.download_dir) | ||
|
|
||
|
|
||
| # import hugging face datasets library | ||
| from datasets import load_dataset, get_dataset_split_names | ||
|
|
||
| for split in get_dataset_split_names(args.dataset): | ||
| # load the split of the dataset | ||
| dataset = load_dataset(args.dataset, split=split) | ||
| # save the split of the dataset to the download directory as json lines file | ||
| dataset.to_json(os.path.join(args.download_dir, f"{split}.jsonl")) | ||
| # print dataset features |
1 change: 1 addition & 0 deletions
1
...dation-models/system/finetune/Llama-notebooks/text-generation/text-generation-config.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1 @@ | ||
| {} |
Oops, something went wrong.