Merge pull request #109757 from cartacioS/patch-33

Data guardrails updates

Author: PRMerger19

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

@@ -174,17 +174,27 @@ Automated machine learning offers preprocessing and data guardrails automaticall
 
 ### Data guardrails
 
-Data guardrails are applied automatically to help you identify potential issues with your data (e.g., missing values, class imbalance) and help take corrective actions for improved results. There are many best practices that are available and can be applied to achieve reliable results. 
-
-The following table describes the currently supported data guardrails, and the associated statuses that users may come across when submitting their experiment.
+Data guardrails are applied when automatic featurization is enabled or validation is set to auto. Data guardrails help you identify potential issues with your data (e.g., missing values, class imbalance) and help take corrective actions for improved results. There are many best practices that are available and can be applied to achieve reliable results. Users can review data guardrails in the studio within the **Data guardrails** tab of an Automated ML run or by setting ```show_output=True``` when submitting an experiment using the Python SDK. The following table describes the data guardrails currently supported, and the associated statuses that users may come across when submitting their experiment.
 
 Guardrail|Status|Condition for trigger
 ---|---|---
-Missing&nbsp;values&nbsp;imputation |**Passed** <br> <br> **Fixed**|    No missing value in any of the input&nbsp;columns <br> <br> Some columns have missing values
-Cross validation|**Done**|If no explicit validation set is provided
-High&nbsp;cardinality&nbsp;feature&nbsp;detection|    **Passed** <br> <br>**Done**|    No high cardinality features were detected <br><br> High cardinality input columns were detected
-Class balance detection    |**Passed** <br><br><br>**Alerted** |Classes are balanced in the training data; A dataset is considered balanced if each class has good representation in the dataset, as measured by number and ratio of samples <br> <br> Classes in the training data are imbalanced
-Time-series data consistency|**Passed** <br><br><br><br> **Fixed** |<br> The selected {horizon, lag, rolling window} value(s) were analyzed, and no potential out-of-memory issues were detected. <br> <br>The selected {horizon, lag, rolling window} values were analyzed and will potentially cause your experiment to run out of memory. The lag or rolling window has been turned off.
+Missing feature values imputation |**Passed** <br><br><br> **Done**| No missing feature values were detected in your training data. Learn more about [missing value imputation.](https://docs.microsoft.com/azure/machine-learning/how-to-use-automated-ml-for-ml-models#advanced-featurization-options) <br><br> Missing feature values were detected in your training data and imputed.
+High cardinality feature handling |**Passed** <br><br><br> **Done**| Your inputs were analyzed, and no high cardinality features were detected. Learn more about [high cardinality feature detection.](https://docs.microsoft.com/azure/machine-learning/how-to-use-automated-ml-for-ml-models#advanced-featurization-options) <br><br> High cardinality features were detected in your inputs and were handled.
+Validation split handling |**Done**| *The validation configuration was set to 'auto' and the training data contained **less** than 20,000 rows.* <br> Each iteration of the trained model was validated through cross-validation. Learn more about [validation data.](https://docs.microsoft.com/azure/machine-learning/how-to-configure-auto-train#train-and-validation-data) <br><br> *The validation configuration was set to 'auto' and the training data contained **more** than 20,000 rows.* <br> The input data has been split into a training dataset and a validation dataset for validation of the model.
+Class balancing detection |**Passed** <br><br><br><br> **Alerted** | Your inputs were analyzed, and all classes are balanced in your training data. A dataset is considered balanced if each class has good representation in the dataset, as measured by number and ratio of samples. <br><br><br> Imbalanced classes were detected in your inputs. To fix model bias fix the balancing problem. Learn more about [imbalanced data.](https://docs.microsoft.com/azure/machine-learning/concept-automated-ml#imbalance)
+Memory issues detection |**Passed** <br><br><br><br> **Done** |<br> The selected {horizon, lag, rolling window} value(s) were analyzed, and no potential out-of-memory issues were detected. Learn more about time-series [forecasting configurations.](https://docs.microsoft.com/azure/machine-learning/how-to-auto-train-forecast#configure-and-run-experiment) <br><br><br>The selected {horizon, lag, rolling window} values were analyzed and will potentially cause your experiment to run out of memory. The lag or rolling window configurations have been turned off.
+Frequency detection |**Passed** <br><br><br><br> **Done** |<br> The time series was analyzed and all data points are aligned with the detected frequency. <br> <br> The time series was analyzed and data points that do not align with the detected frequency were detected. These data points were removed from the dataset. Learn more about [data preparation for time-series forecasting.](https://docs.microsoft.com/azure/machine-learning/how-to-auto-train-forecast#preparing-data)
+
+#### Data Guardrail States
+Data guardrails will display one of three states: 'Passed', 'Done, or 'Alerted'.
+
+State| Description
+----|----
+Passed| No data problems were detected and no user action is required. 
+Done| Changes were applied to your data. We encourage users to review the corrective actions Automated ML took to ensure the changes align with the expected results. 
+Alerted| A data issue that could not be remedied was detected. We encourage users to revise and fix the issue. 
+
+Previous version of the Automated ML displayed a fourth state: 'Fixed'. Newer experiments will not display this state, and all guardrails which displayed the 'Fixed' state will now display 'Done'.   
 
 ## Run experiment and view results