From 1c4959e0c42848767a7536ac9ed2aafc16eb8939 Mon Sep 17 00:00:00 2001
From: lochen <cloga0216@gmail.com>
Date: Wed, 24 Nov 2021 20:45:55 +0800
Subject: [PATCH 1/2] change pipeline data to pipeline output dataset
---
...l-pipelines-with-data-dependency-steps.ipynb | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb
index 419303a42..9b89c14f7 100644
--- a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb
+++ b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb
@@ -252,8 +252,12 @@
"# is_directory=None)\n",
"\n",
"# Naming the intermediate data as processed_data1 and assigning it to the variable processed_data1.\n",
- "processed_data1 = PipelineData(\"processed_data1\",datastore=def_blob_store)\n",
- "print(\"PipelineData object created\")"
+ "# Promote pipelinedata to pipeline_output_dataset, which will use dataset instead of data reference \n",
+ "\n",
+ "from azureml.pipeline.core.pipeline_output_dataset import PipelineOutputFileDataset\n",
+ "\n",
+ "processed_data1 = PipelineOutputFileDataset(PipelineData(\"processed_data1\",datastore=def_blob_store))\n",
+ "print(\"PipelineOutputFileDataset object created\")"
]
},
{
@@ -544,10 +548,13 @@
"Azure ML"
],
"friendly_name": "Azure Machine Learning Pipelines with Data Dependency",
+ "interpreter": {
+ "hash": "3e9e0e270b75c5e6da2e22113ba4f77b864d68f95da6601809c29e46c73ae6bb"
+ },
"kernelspec": {
"display_name": "Python 3.6",
"language": "python",
- "name": "python36"
+ "name": "python3"
},
"language_info": {
"codemirror_mode": {
@@ -559,7 +566,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.6.7"
+ "version": "3.7.8"
},
"order_index": 2,
"star_tag": [
@@ -572,4 +579,4 @@
},
"nbformat": 4,
"nbformat_minor": 2
-}
\ No newline at end of file
+}
From 96a8e069178c707bfa39cd77f04ba4cde18a1f9b Mon Sep 17 00:00:00 2001
From: lochen <cloga0216@gmail.com>
Date: Thu, 25 Nov 2021 09:24:42 +0800
Subject: [PATCH 2/2] make change to use pipeline_output_dataset
---
.../aml-pipelines-with-data-dependency-steps.ipynb | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb
index 9b89c14f7..587875733 100644
--- a/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb
+++ b/how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-with-data-dependency-steps.ipynb
@@ -230,7 +230,9 @@
"- **output_name:** Name of the output\n",
"- **output_mode:** Specifies \"upload\" or \"mount\" modes for producing output (default: mount)\n",
"- **output_path_on_compute:** For \"upload\" mode, the path to which the module writes this output during execution\n",
- "- **output_overwrite:** Flag to overwrite pre-existing data"
+ "- **output_overwrite:** Flag to overwrite pre-existing data\n",
+ "\n",
+ "As PipelineData is using [DataReference](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.data.data_reference.datareference?view=azure-ml-py) to represent the data, which is not the recommanded approch, we will recommand you to use [pipeline_output_dataset](https://docs.microsoft.com/en-us/python/api/azureml-pipeline-core/azureml.pipeline.core.pipeline_output_dataset?view=azure-ml-py) instead, once promoted to an Azure Machine Learning dataset, it will also be consumed as a Dataset instead of a DataReference in subsequent steps."
]
},
{