Merge pull request #109460 from PeterCLu/plu-designer-updates

Designer updates

Author: ShannonLeavitt

articles/machine-learning/how-to-debug-pipelines.md

@@ -17,7 +17,7 @@ ms.date: 03/18/2020
 In this article, you learn how to debug and troubleshoot [machine learning pipelines](concept-ml-pipelines.md) in the [Azure Machine Learning SDK](https://docs.microsoft.com/python/api/overview/azure/ml/intro?view=azure-ml-py) and [Azure Machine Learning designer (preview)](https://docs.microsoft.com/azure/machine-learning/concept-designer). Information is provided on how to:
 
 * Debug using the Azure Machine Learning SDK
-* Debug using the Azure Machine Learning Designer
+* Debug using the Azure Machine Learning designer
 * Debug using Application Insights
 * Debug interactively using Visual Studio Code (VS Code) and the Python Tools for Visual Studio (PTVSD)
 
@@ -88,7 +88,7 @@ The table below provides information for different debug options for pipelines.
 | Library                    | Type   | Example                                                          | Destination                                  | Resources                                                                                                                                                                                                                                                                                                                    |
 |----------------------------|--------|------------------------------------------------------------------|----------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | Azure Machine Learning SDK | Metric | `run.log(name, val)`                                             | Azure Machine Learning Portal UI             | [How to track experiments](how-to-track-experiments.md#available-metrics-to-track)<br>[azureml.core.Run class](https://docs.microsoft.com/python/api/azureml-core/azureml.core.run(class)?view=experimental)                                                                                                                                                 |
-| Python printing/logging    | Log    | `print(val)`<br>`logging.info(message)`                          | Driver logs, Azure Machine Learning Designer | [How to track experiments](how-to-track-experiments.md#available-metrics-to-track)<br><br>[Python logging](https://docs.python.org/2/library/logging.html)                                                                                                                                                                       |
+| Python printing/logging    | Log    | `print(val)`<br>`logging.info(message)`                          | Driver logs, Azure Machine Learning designer | [How to track experiments](how-to-track-experiments.md#available-metrics-to-track)<br><br>[Python logging](https://docs.python.org/2/library/logging.html)                                                                                                                                                                       |
 | OpenCensus Python          | Log    | `logger.addHandler(AzureLogHandler())`<br>`logging.log(message)` | Application Insights - traces                | [Debug pipelines in Application Insights](how-to-debug-pipelines-application-insights.md)<br><br>[OpenCensus Azure Monitor Exporters](https://github.com/census-instrumentation/opencensus-python/tree/master/contrib/opencensus-ext-azure)<br>[Python logging cookbook](https://docs.python.org/3/howto/logging-cookbook.html) |
 
 #### Logging options example
@@ -133,8 +133,8 @@ For pipelines created in the designer, you can find the **log files** on either
 When you submit a pipeline run and stay in the authoring page, you can find the log files generated for each module.
 
 1. Select any module in the authoring canvas.
-1. In the right pane of the module, go to the  **Outputs+ogs** tab.
-1. Select the log file `70_driver_log.txt`
+1. In the right pane of the module, go to the  **Outputs + logs** tab.
+1. Select the log file `70_driver_log.txt`.
 
     ![Authoring page module logs](./media/how-to-debug-pipelines/pipelinerun-05.png)
 
@@ -145,8 +145,8 @@ You can also find the log files of specific runs in the pipeline run detail page
 1. Select a pipeline run created in the designer.
     ![Pipeline run page](./media/how-to-debug-pipelines/pipelinerun-04.png)
 1. Select any module in the preview pane.
-1. In the right pane of the module, go to the  **Outputs+ogs** tab.
-1. Select the log file `70_driver_log.txt`
+1. In the right pane of the module, go to the  **Outputs + logs** tab.
+1. Select the log file `70_driver_log.txt`.
 
 ## Debug and troubleshoot in Application Insights
 For more information on using the OpenCensus Python library in this manner, see this guide: [Debug and troubleshoot machine learning pipelines in Application Insights](how-to-debug-pipelines-application-insights.md)

articles/machine-learning/how-to-retrain-designer.md

@@ -49,14 +49,14 @@ To retrain a model, you need an initial model. In this section, you learn how to
    For this example, the data is stored in an [Azure datastore](how-to-access-data.md). If you don't already have a datastore, you can create one now by selecting **New datastore**.
 
 1. Specify the path to your data. You can also select **Browse path** to browse to your datastore. 
-1. Select **Run** at the top of the canvas.
+1. Select **Submit** at the top of the canvas.
 
    > [!NOTE]
    > If you have already set a default compute for this pipeline draft, the pipeline will run automatically. Otherwise, you can follow the prompts on the settings pane to set one now.
 
 ### Find your trained model
 
-The designer saves all pipeline outputs, including trained models, to the default storage account. You can also access the trained model directly in the designer:
+The designer saves all pipeline outputs, including trained models, to the default storage account. However, you can also access trained models directly in the designer:
 
 1. Wait for the pipeline to finish running.
 1. Select the **Train Model** module.

articles/machine-learning/samples-designer.md

@@ -9,7 +9,7 @@ ms.topic: sample
 
 author: peterclu
 ms.author: peterlu
-ms.date: 03/10/2020
+ms.date: 03/29/2020
 ---
 # Designer sample pipelines
 
@@ -25,6 +25,8 @@ Use the built-in examples in Azure Machine Learning designer to quickly get star
 
 The designer saves a copy of the sample pipelines to your studio workspace. You can edit the pipeline to adapt it to your needs and save it as your own. Use them as a starting point to jumpstart your projects.
 
+### Open a sample pipeline
+
 1. Sign in to <a href="https://ml.azure.com?tabs=jre" target="_blank">ml.azure.com</a>, and select the workspace you want to work with.
 
 1. Select **Designer**.
@@ -33,6 +35,31 @@ The designer saves a copy of the sample pipelines to your studio workspace. You
 
     Select **Show more samples** for a complete list of samples.
 
+### Submit a pipeline run
+
+To run a pipeline, you first have to set default compute target to run the pipeline on.
+
+1. In the **Settings** pane to the right of the canvas, select **Select compute target**.
+
+1. In the dialog that appears, select an existing compute target or create a new one. Select **Save**.
+
+1. Select **Submit** at the top of the canvas to submit a pipeline run.
+
+Depending on the sample pipeline and compute settings, runs may take some time to complete. The default compute settings have a minimum node size of 0, which means that the designer must allocate resources after being idle. Repeated pipeline runs will take less time since the compute resources are already allocated. Additionally, the designer uses cached results for each module to further improve efficiency.
+
+
+### Review the results
+
+After the pipeline finishes running, you can review the pipeline and view the output for each module to learn more.
+
+Use the following steps to view module outputs:
+
+1. Select a module in the canvas.
+
+1. In the module details pane to the right of the canvas, select **Outputs + logs**. Select the graph icon ![visualize icon](./media/tutorial-designer-automobile-price-train-score/visualize-icon.png) to see the results of each module. 
+
+Use the samples as starting points for some of the most common machine learning scenarios.
+
 ## Regression samples
 
 Learn more about the built-in regression samples.

articles/machine-learning/toc.yml

@@ -355,6 +355,7 @@
     - name: Trigger a pipeline
       href: how-to-trigger-published-pipeline.md
     - name: Debug & troubleshoot pipelines
+      displayName: designer
       href: how-to-debug-pipelines.md
     - name: Debug pipelines in Application Insights
       displayname: pipelines, log, monitor

articles/machine-learning/tutorial-designer-automobile-price-deploy.md

@@ -54,6 +54,8 @@ To deploy your pipeline, you must first convert the training pipeline into a rea
 
 1. Select **Submit**, and use the same compute target and experiment that you used in part one.
 
+    If is the first run, it may take up to 20 minutes for your pipeline to finish running. The default compute settings have a minimum node size of 0, which means that the designer must allocate resources after being idle. Repeated pipeline runs will take less time since the compute resources are already allocated. Additionally, the designer uses cached results for each module to further improve efficiency.
+
 1. Select **Deploy**.
 
 ## Create an inferencing cluster

articles/machine-learning/tutorial-designer-automobile-price-train-score.md

@@ -99,7 +99,7 @@ You can visualize the data to understand the dataset that you'll use.
 
 1. Select the **Automobile price data (Raw)** module.
 
-1. In the module details pane to the right of the canvas, select **Outputs**.
+1. In the module details pane to the right of the canvas, select **Outputs + log**.
 
 1. Select the graph icon to visualize the data.
 
@@ -265,7 +265,7 @@ Use the **Evaluate Model** module to evaluate how well your model scored the tes
 
 ## Submit the pipeline
 
-Now that your pipeline is all setup, you can submit a pipeline run to train your machine learning model. You can submit a pipeline run at any point while building pipelines in the designer. You can do this to check your work as you go to verify your pipeline works as expected.
+Now that your pipeline is all setup, you can submit a pipeline run to train your machine learning model. You can submit a valid pipeline run at any point, which can be used to review changes to your pipeline during development.
 
 1. At the top of the canvas, select **Submit**.
 
@@ -279,14 +279,16 @@ Now that your pipeline is all setup, you can submit a pipeline run to train your
     1. Select **Submit**.
 
     You can view run status and details at the top right of the canvas.
+    
+    If is the first run, it may take up to 20 minutes for your pipeline to finish running. The default compute settings have a minimum node size of 0, which means that the designer must allocate resources after being idle. Repeated pipeline runs will take less time since the compute resources are already allocated. Additionally, the designer uses cached results for each module to further improve efficiency.
 
 ### View scored labels
 
 After the run completes, you can view the results of the pipeline run. First, look at the predictions generated by the regression model.
 
 1. Select the **Score Model** module to view its output.
 
-1. In the module details pane to the right of the canvas, select **Outputs** > graph icon ![visualize icon](./media/tutorial-designer-automobile-price-train-score/visualize-icon.png) to view results.
+1. In the module details pane to the right of the canvas, select **Outputs + logs** > graph icon ![visualize icon](./media/tutorial-designer-automobile-price-train-score/visualize-icon.png) to view results.
 
     Here you can see the predicted prices and the actual prices from the testing data.
 
@@ -298,7 +300,7 @@ Use the **Evaluate Model** to see how well the trained model performed on the te
 
 1. Select the **Evaluate Model** module to view its output.
 
-1. In the module details pane to the right of the canvas, select **Output** > graph icon ![visualize icon](./media/tutorial-designer-automobile-price-train-score/visualize-icon.png) to view results.
+1. In the module details pane to the right of the canvas, select **Outputs + logs** > graph icon ![visualize icon](./media/tutorial-designer-automobile-price-train-score/visualize-icon.png) to view results.
 
 The following statistics are shown for your model: