Merge pull request #223972 from ssalgadodev/designerCompV2

V2 component TOC

Author: AnnaMHuff

articles/machine-learning/component-reference-v2/classification.md

@@ -0,0 +1,68 @@
+---
+title:  "AutoML Classification"
+titleSuffix: Azure Machine Learning
+description: Learn how to use the AutoML Classification component in Azure Machine Learning to create a classifier using ML Table data.
+services: machine-learning
+ms.service: machine-learning
+ms.subservice: core
+ms.topic: reference
+ms.author: shoja
+author: shouryaj
+ms.reviewer: ssalgadodev
+ms.date: 12/1/2022
+---
+
+# AutoML Classification
+
+This article describes a component in Azure Machine Learning designer.
+
+Use this component to create a machine learning model that is based on the AutoML Classification.
+
+
+## How to configure 
+
+This component creates a classification model on tabular data.
+
+This model requires a training dataset. Validation and test datasets are optional. 
+
+AutoML creates a number of pipelines in parallel that try different algorithms and parameters for your model. The service iterates through ML algorithms paired with feature selections, where each iteration produces a model with a training score. You are able to choose the metric you want the model to optimize for. The better the score for the chosen metric the better the model is considered to "fit" your data. You are able to define an exit criteria for the experiment. The exit criteria will be model with a specific training score you want AutoML to find. It will stop once it hits the exit criteria defined. This component will then output the best model that has been generated at the end of the run for your dataset.
+
+
+1.  Add the **AutoML Classification** component to your pipeline.
+
+1.  Specify the **Target Column** you want the model to output 
+
+1. For **classification**, you can also enable deep learning.
+    
+If deep learning is enabled, validation is limited to _train_validation split_. [Learn more about validation options](/how-to-configure-cross-validation-data-splits.md).
+
+
+1. (Optional) View addition configuration settings: additional settings you can use to better control the training job. Otherwise, defaults are applied based on experiment selection and data. 
+
+    Additional configurations|Description
+    ------|------
+    Primary metric| Main metric used for scoring your model. [Learn more about model metrics](/how-to-configure-auto-train.md#primary-metric).
+    Explain best model | Select to enable or disable, in order to show explanations for the recommended best model. <br> This functionality is not currently available for [certain forecasting algorithms](/how-to-machine-learning-interpretability-automl.md#interpretability-during-training-for-the-best-model). 
+    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).
+    Exit criterion| When any of these criteria are met, the training job is stopped. <br> *Training job time (hours)*: How long to allow the training job to run. <br> *Metric score threshold*:  Minimum metric score for all pipelines. This ensures that if you have a defined target metric you want to reach, you do not spend more time on the training job than necessary.
+    Concurrency| *Max concurrent iterations*: Maximum number of pipelines (iterations) to test in the training job. The job will not run more than the specified number of iterations. Learn more about how automated ML performs [multiple child jobs on clusters](/how-to-configure-auto-train.md#multiple-child-runs-on-clusters).
+
+
+1. The **[Optional] Validate and test** form allows you to do the following. 
+
+    1. Specify the type of validation to be used for your training job. [Learn more about cross validation](/how-to-configure-cross-validation-data-splits.md#prerequisites). 
+    
+    1. Provide a test dataset (preview) to evaluate the recommended model that automated ML generates for you at the end of your experiment. When you provide test data, a test job is automatically triggered at the end of your experiment. This test job is only job on the best model that was recommended by automated ML. 
+    
+        >[!IMPORTANT]
+        > Providing a test dataset to evaluate generated models is a preview feature. This capability is an [experimental](/python/api/overview/azure/ml/#stable-vs-experimental) preview feature, and may change at any time.
+        
+        * Test data is considered a separate from training and validation, so as to not bias the results of the test job of the recommended model. [Learn more about bias during model validation](/concept-automated-ml.md#training-validation-and-test-data).
+        * You can either provide your own test dataset or opt to use a percentage of your training dataset. Test data must be in the form of an [Azure Machine Learning TabularDataset](../v1/how-to-create-register-datasets.md#tabulardataset).         
+        * The schema of the test dataset should match the training dataset. The target column is optional, but if no target column is indicated no test metrics are calculated.
+        * The test dataset should not be the same as the training dataset or the validation dataset.
+     
+
+## Next steps
+
+See the [set of components available](/component-reference.md) to Azure Machine Learning. 

articles/machine-learning/component-reference-v2/component-reference-v2.md

@@ -0,0 +1,49 @@
+---
+title:  "Algorithm & component reference (v2)"
+description: Learn about the Azure Machine Learning designer components that you can use to create your own machine learning projects. (v2)
+titleSuffix: Azure Machine Learning
+services: machine-learning
+ms.service: machine-learning
+ms.subservice: core
+ms.topic: reference
+ms.author: shoja
+author: shouryaj
+ms.reviewer: ssalgadodev
+ms.date: 01/17/2023
+---
+# Algorithm & component reference for Azure Machine Learning designer (v2)
+
+Azure Machine Learning designer components (Designer) allows users to create machine learning projects using a drag and drop interface. Follow this link to reach the Designer studio. Follow this link to [learn more about Designer.] (..//concept-designer)
+
+
+This reference content provides the technical background on each of the custom components (v2) available in Azure Machine Learning designer.
+
+The below image shows how you would navigate to Custom components in AzureML Studio
+
+:::image type="content" source="media/designer-new-pipeline.png" alt-text="Diagram showing the Designer UI for selecting a custom component.":::
+
+
+Each component represents a set of code that can run independently and perform a machine learning task, given the required inputs. A component might contain a particular algorithm, or perform a task that is important in machine learning, such as missing value replacement, or statistical analysis.
+
+For help with choosing algorithms, see 
+* [How to select algorithms](..//how-to-select-algorithms.md)
+
+> [!TIP]
+> In any pipeline in the designer, you can get information about a specific component. Select the **Learn more** link in the component card when hovering on the component in the component list, or in the right pane of the component.
+
+
+## AutoML Algorithms
+
+| Functionality | Description | component |
+| --- |--- | --- |
+| Classification | Component that executes an AutoML Classification task model training in a pipeline. |  [AutoML Classification](classification.md) |
+| Regression | Predict a value | [AutoML Regression](regression.md) |
+| Forecasting | Predict a value | [AutoML Forecasting](forecasting.md) |
+| Computer Vision | Image data preprocessing and Image recognition related components. |  [Image Object Detection](image-object-detection.md) <br/> [Image Classification](image-classification.md) <br/> [Image Classification Multilabel](image-classification-multilabel.md) <br/> [Image Instance Segmentation](image-instance-segmentation.md) |
+| Multilabel Text Classification | Component that executes an AutoML Multilabel Text Classification task model training in a pipeline. | [AutoML Multilabel Text Classification](text-classification-multilabel.md)|
+| Text Classification | Component that executes an AutoML Text Classification Model | [AutoML Text Classification](text-classification.md)|
+| Text Ner | Component that executes an AutoML Text NER (Named Entity Recognition) | [AutoML Text Ner](text-ner.md)|
+
+## Next steps
+
+* [Tutorial: Build a model in designer to predict auto prices](../tutorial-designer-automobile-price-train-score.md)

articles/machine-learning/component-reference-v2/forecasting.md

@@ -0,0 +1,65 @@
+---
+title:  "AutoML Forecasting Component in Microsoft Azure Machine Learning Designer"
+titleSuffix: Azure Machine Learning
+description: Learn how to use the AutoML Forecasting component in Azure Machine Learning to create a classifier using ML Table data.
+services: machine-learning
+ms.service: machine-learning
+ms.subservice: core
+ms.topic: reference
+ms.author: shoja
+author: shouryaj
+ms.reviewer: ssalgadodev
+ms.date: 12/1/2022
+---
+
+# AutoML Forecasting
+
+This article describes a component in Azure Machine Learning designer.
+
+Use this component to create a machine learning model that is based on the AutoML Forecasting.
+
+
+## How to configure 
+
+This component creates a forecasting model. Because forecasting is a supervised learning method, you need a *labeled dataset* that includes a label column with a value for all rows. Follow this link to get more information on [how to prepare your dataset.](/how-to-prepare-datasets-for-automl-images) The dataset will need a *labeled dataset* that includes a label column with a value for all rows.
+
+This model requires a training dataset. Validation and test datasets are optional. 
+
+AutoML creates a number of pipelines in parallel that try different algorithms and parameters for your model. The service iterates through ML algorithms paired with feature selections, where each iteration produces a model with a training score. You are able to choose the metric you want the model to optimize for. The better the score for the chosen metric the better the model is considered to "fit" your data. You are able to define an exit criteria for the experiment. The exit criteria will be model with a specific training score you want AutoML to find. It will stop once it hits the exit criteria defined. This component will then output the best model that has been generated at the end of the run for your dataset.
+
+
+1.  Add the **AutoML Forecasting** component to your pipeline.
+
+1. Specify the **training_data** you want the model to use. 
+
+1. Specify the **Primary Metric** you want AutoML to use to measure your model's success.
+
+
+1.  Specify the **Target Column** you want the model to output 
+
+1. On the **Task type and settings** form, select the task type: forecasting. See [supported task types](/concept-automated-ml.md#when-to-use-automl-classification-regression-forecasting-computer-vision--nlp) for more information.
+
+    1. For **forecasting** you can, 
+    
+        1. Enable deep learning.
+    
+        1. Select *time column*: This column contains the time data to be used.
+
+        1. Select *forecast horizon*: Indicate how many time units (minutes/hours/days/weeks/months/years) will the model be able to predict to the future. The further the model is required to predict into the future, the less accurate it becomes. [Learn more about forecasting and forecast horizon](/how-to-auto-train-forecast.md).
+
+1. (Optional) View addition configuration settings: additional settings you can use to better control the training job. Otherwise, defaults are applied based on experiment selection and data. 
+
+    Additional configurations|Description
+    ------|------
+    Primary metric| Main metric used for scoring your model. [Learn more about model metrics](/how-to-configure-auto-train.md#primary-metric).
+    Explain best model | Select to enable or disable, in order to show explanations for the recommended best model. <br> This functionality is not currently available for [certain forecasting algorithms](/how-to-machine-learning-interpretability-automl.md#interpretability-during-training-for-the-best-model). 
+    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).
+    Exit criterion| When any of these criteria are met, the training job is stopped. <br> *Training job time (hours)*: How long to allow the training job to run. <br> *Metric score threshold*:  Minimum metric score for all pipelines. This ensures that if you have a defined target metric you want to reach, you do not spend more time on the training job than necessary.
+    Concurrency| *Max concurrent iterations*: Maximum number of pipelines (iterations) to test in the training job. The job will not run more than the specified number of iterations. Learn more about how automated ML performs [multiple child jobs on clusters](/how-to-configure-auto-train.md#multiple-child-runs-on-clusters).
+
+
+
+
+## Next steps
+
+See the [set of components available](/component-reference.md) to Azure Machine Learning. 

articles/machine-learning/component-reference-v2/image-classification-multilabel.md

@@ -0,0 +1,57 @@
+---
+title:  "AutoML Image Classification Multi-label"
+titleSuffix: Azure Machine Learning
+description: Learn how to use the AutoML Image Classification Multi-label component in Azure Machine Learning to create a classifier using ML Table data.
+services: machine-learning
+ms.service: machine-learning
+ms.subservice: core
+ms.topic: reference
+ms.author: shoja
+author: shouryaj
+ms.reviewer: ssalgadodev
+ms.date: 12/1/2022
+---
+
+# AutoML Image Classification Multi-label
+
+This article describes a component in Azure Machine Learning designer.
+
+Use this component to create a machine learning model that is based on the AutoML Image Classification Multi-label.
+
+Multi-label image classification is a computer vision task where the goal is to predict a set of labels associated with each individual image. You may consider using multi-label classification where you need to determine several properties of a given image.
+
+## How to configure 
+
+[Follow this link](/machine-learning/reference-automl-images-cli-multilabel-classification) for a full list of configurable parameters of this component.
+
+[Follow this link](/machine-learning/reference-automl-images-cli-multilabel-classification) for a full list of configurable parameters of this component.
+
+This component creates a classification model. Because classification is a supervised learning method, you need a *labeled dataset* that includes a label column with a value for all rows.
+
+
+This model requires a training dataset. Validation and test datasets are optional. 
+
+Follow this link to get more information on [how to prepare your dataset.](/how-to-prepare-datasets-for-automl-images) The dataset will need a *labeled dataset* that includes a label column with a value for all rows.
+
+
+AutoML runs a number of trials (specified in `max_trials`) in parallel (`specified in max_concurrent_trial`) that try different algorithms and parameters for your model. The service iterates through ML algorithms paired with hyperparameter selections and each trial produces a model with a training score. You are able to choose the metric you want the model to optimize for. The better the score for the chosen metric the better the model is considered to "fit" your data. You are able to define an exit criteria (termination policy) for the experiment. The exit criteria will be model with a specific training score you want AutoML to find. It will stop once it hits the exit criteria defined. This component will then output the best model that has been generated at the end of the run for your dataset. Visit this link for more information on [exit criteria (termination policy)](/how-to-auto-train-image-models#early-termination-policies).
+
+
+
+1.  Add the **AutoML Image Classification Multi-label** component to your pipeline.
+
+1.  Specify the **Target Column** you want the model to output 
+
+1. Specify the **Primary Metric** you want AutoML to use to measure your model's success. Visit this link for an [explanation on each primary metric for computer vision.](/how-to-auto-train-image-models.md#primary-metric)
+
+1. (Optional) You are able to configure algorithm settings. Visit this link for a {list of supported algorithms for computer vision.](/how-to-auto-train-image-models.md#supported-model-algorithms
+
+1. (Optional) To configure job limits, visit [this link for more explanation.](/how-to-auto-train-image-models.md#job-limits)
+
+1. (Optional) Visit this link for a [list of configurations for Sampling and Early Termination for your Job Sweep.](/how-to-auto-train-image-models.md#sampling-methods-for-the-sweep) You can also find more information on each of the policies and sampling methods. 
+
+    
+
+## Next steps
+
+See the [set of components available](/component-reference.md) to Azure Machine Learning. 

articles/machine-learning/component-reference-v2/image-classification.md

@@ -0,0 +1,52 @@
+---
+title:  "AutoML Image Classification"
+titleSuffix: Azure Machine Learning
+description: Learn how to use the AutoML Image Classification component in Azure Machine Learning to create a classifier using ML Table data.
+services: machine-learning
+ms.service: machine-learning
+ms.subservice: core
+ms.topic: reference
+ms.author: shoja
+author: shouryaj
+ms.reviewer: ssalgadodev
+ms.date: 12/1/2022
+---
+
+# AutoML Image Classification
+
+This article describes a component in Azure Machine Learning designer.
+
+Use this component to create a machine learning model that is based on the AutoML Image Classification.
+
+
+## How to configure 
+
+[Follow this link](/machine-learning/reference-automl-images-cli-classification) for a full list of configurable parameters of this component.
+
+
+This model requires a training dataset. Validation and test datasets are optional. 
+
+Follow this link to get more information on [how to prepare your dataset.](/how-to-prepare-datasets-for-automl-images) The dataset will need a *labeled dataset* that includes a label column with a value for all rows.
+
+
+AutoML runs a number of trials (specified in max_trials) in parallel (specified in max_concurrent_trials) that try different algorithms and parameters for your model. The service iterates through ML algorithms paired with hyperparameter selections and each trial produces a model with a training score. You are able to choose the metric you want the model to optimize for. The better the score for the chosen metric the better the model is considered to "fit" your data. You are able to define an exit criteria (termination policy) for the experiment. The exit criteria will be model with a specific training score you want AutoML to find. It will stop once it hits the exit criteria defined. This component will then output the best model that has been generated at the end of the run for your dataset.
+
+
+
+1.  Add the **AutoML Image Classification** component to your pipeline.
+
+1.  Specify the **Target Column** you want the model to output 
+
+1. Specify the **Primary Metric** you want AutoML to use to measure your model's success. Visit this link for an [explanation on each primary metric for computer vision.](/how-to-auto-train-image-models.md#primary-metric)
+
+1. (Optional) You are able to configure algorithm settings. Visit this link for a {list of supported algorithms for computer vision.](/how-to-auto-train-image-models.md#supported-model-algorithms
+
+1. (Optional) To configure job limits, visit [this link for more explanation.](/how-to-auto-train-image-models.md#job-limits)
+
+1. (Optional) Visit this link for a [list of configurations for Sampling and Early Termination for your Job Sweep.](/how-to-auto-train-image-models.md#sampling-methods-for-the-sweep) You can also find more information on each of the policies and sampling methods. 
+
+    
+
+## Next steps
+
+See the [set of components available](/component-reference.md) to Azure Machine Learning.