Merge pull request #118921 from sonalim-0/main

Updating docs related to Unified Job Submission

Author: Jak-MS

articles/machine-learning/how-to-use-automated-ml-for-ml-models.md

@@ -124,13 +124,14 @@ Otherwise, you see a list of your recent automated  ML experiments, including th
     ------|------
     Primary metric| Main metric used for scoring your model. [Learn more about model metrics](how-to-configure-auto-train.md#primary-metric).
     Enable ensemble stacking | Ensemble learning improves machine learning results and predictive performance by combining multiple models as opposed to using single models. [Learn more about ensemble models](concept-automated-ml.md#ensemble).
-    Blocked algorithm| Select algorithms you want to exclude from the training job. <br><br> Allowing algorithms is only available for [SDK experiments](how-to-configure-auto-train.md#supported-algorithms). <br> See the [supported algorithms for each task type](/python/api/azureml-automl-core/azureml.automl.core.shared.constants.supportedmodels).
+    Blocked models| Select models you want to exclude from the training job. <br><br> Allowing models is only available for [SDK experiments](how-to-configure-auto-train.md#supported-algorithms). <br> See the [supported algorithms for each task type](/python/api/azureml-automl-core/azureml.automl.core.shared.constants.supportedmodels).
     Explain best model| Automatically shows explainability on the best model created by Automated ML.
+   Positive class label| Label that Automated ML will use to calculate binary metrics.
 
 
 1. (Optional) View featurization settings: if you choose to enable **Automatic featurization** in the **Additional configuration settings** form, default featurization techniques are applied. In the **View featurization settings**, you can change these defaults and customize accordingly. Learn how to [customize featurizations](#customize-featurization). 
 
-    ![Screenshot shows the Select task type dialog box with View featurization settings called out.](media/how-to-use-automated-ml-for-ml-models/view-featurization-settings.png)
+    ![Screenshot shows the Select task type dialog box with View featurization settings called out.](media/how-to-use-automated-ml-for-ml-models/view-featurization.png)
 
 1. The **[Optional] Limits** form allows you to do the following.
 
@@ -163,7 +164,7 @@ b. Provide a test dataset (preview) to evaluate the recommended model that autom
      * The test dataset shouldn't be the same as the training dataset or the validation dataset.
      * Forecasting jobs don't support train/test split.
         
-![Screenshot shows the form where to select validation data and test data](media/how-to-use-automated-ml-for-ml-models/validate-test-form.png)
+![Screenshot shows the form where to select validation data and test data](media/how-to-use-automated-ml-for-ml-models/validate-and-test.png)
 
 ## Customize featurization
 
@@ -173,11 +174,10 @@ The following table summarizes the customizations currently available via the st
 
 Column| Customization
 ---|---
-Included | Specifies which columns to include for training.
 Feature type| Change the value type for the selected column.
 Impute with| Select what value to impute missing values with in your data.
 
-![Azure Machine Learning studio custom featurization](media/how-to-use-automated-ml-for-ml-models/custom-featurization.png)
+![Screenshot showing Azure Machine Learning studio custom featurization.](media/how-to-use-automated-ml-for-ml-models/updated-featurization.png)
 
 ## Run experiment and view results
 
@@ -192,24 +192,13 @@ The **Job Detail** screen opens to the **Details** tab. This screen shows you a
 
 The **Models** tab contains a list of the models created ordered by the metric score. By default, the model that scores the highest based on the chosen metric is at the top of the list. As the training job tries out more models, they're added to the list. Use this to get a quick comparison of the metrics for the models produced so far.
 
-![Job detail](./media/how-to-use-automated-ml-for-ml-models/explore-models.gif)
-
 ### View training job details
 
-Drill down on any of the completed models to see training job details. In the **Model** tab, you can view details like a model summary and the hyperparameters used for the selected model. 
-
-[![Hyperparameter details](media/how-to-use-automated-ml-for-ml-models/hyperparameter-button.png)](media/how-to-use-automated-ml-for-ml-models/hyperparameter-details.png#lightbox)
-
- You can also see model specific performance metric charts on the **Metrics** tab. [Learn more about charts](how-to-understand-automated-ml.md).
+Drill down on any of the completed models to see training job details. 
 
-![Iteration details](media/how-to-use-automated-ml-for-ml-models/iteration-details-expanded.png)
-
-On the Data transformation tab, you can see a diagram of what data preprocessing, feature engineering, scaling techniques and the machine learning algorithm that were applied to generate this model.
-
->[!IMPORTANT]
-> The Data transformation tab is in preview. This capability should be considered [experimental](/python/api/overview/azure/ml/#stable-vs-experimental) and may change at any time.
+You can see model specific performance metric charts on the **Metrics** tab. [Learn more about charts](how-to-understand-automated-ml.md).
 
-![Data transformation](./media/how-to-use-automated-ml-for-ml-models/data-transformation.png)
+This is also where you can find details on all the properties of the model along with associated code, child jobs, and images.
 
 ## View remote test job results (preview)
 
@@ -280,7 +269,7 @@ To generate a Responsible AI dashboard for a particular model,
 
 
 
-    ![Select Explain best model from the Automated ML job configuration page](media/how-to-use-automated-ml-for-ml-models/best-model-selection.png)
+    ![Screenshot showing the Automated ML job configuration page with Explain best model selected.](media/how-to-use-automated-ml-for-ml-models/best-model-selection-updated.png)
 
 3. Proceed to the **Compute** page of the setup form and choose the **Serverless** option for your compute.