Merge pull request #241903 from MicrosoftDocs/main

Publish to live, Sunday 4 PM

Author: American-Dipper

articles/azure-monitor/data-sources.md

@@ -216,7 +216,7 @@ In addition to the standard tiers of an application, you may need to monitor oth
 
 | Destination | Method | Description | Reference |
 |:---|:---|:---|:---|
-| Azure Monitor Logs | Logs ingestion API | Collect log data from any REST client and store in Log Analytics workspace using a data collection rule. | [Logs ingestion API in Azure Monitor (preview)](logs/logs-ingestion-api-overview.md) |
+| Azure Monitor Logs | Logs ingestion API | Collect log data from any REST client and store in Log Analytics workspace using a data collection rule. | [Logs ingestion API in Azure Monitor](logs/logs-ingestion-api-overview.md) |
 |                    | Data Collector API | Collect log data from any REST client and store in Log Analytics workspace. | [Send log data to Azure Monitor with the HTTP Data Collector API (preview)](logs/data-collector-api.md) |
 | Azure Monitor Metrics | Custom Metrics API | Collect metric data from any REST client and store in Azure Monitor metrics database. | [Send custom metrics for an Azure resource to the Azure Monitor metric store by using a REST API](essentials/metrics-store-custom-rest-api.md) |
 

articles/cognitive-services/Anomaly-Detector/How-to/postman.md

@@ -1,5 +1,5 @@
 ---
-title: How to run Multivariate Anomaly Detection API (GA version) in Postman?
+title: How to run Multivariate Anomaly Detector API (GA version) in Postman?
 titleSuffix: Azure Cognitive Services
 description: Learn how to detect anomalies in your data either as a batch, or on streaming data with Postman.
 services: cognitive-services
@@ -12,7 +12,7 @@ ms.date: 12/20/2022
 ms.author: mbullwin
 ---
 
-# How to run Multivariate Anomaly Detection API in Postman?
+# How to run Multivariate Anomaly Detector API in Postman?
 
 This article will walk you through the process of using Postman to access the Multivariate Anomaly Detection REST API.
 
@@ -22,7 +22,7 @@ Select this button to fork the API collection in Postman and follow the steps in
 
 [![Run in Postman](../media/postman/button.svg)](https://app.getpostman.com/run-collection/18763802-b90da6d8-0f98-4200-976f-546342abcade?action=collection%2Ffork&collection-url=entityId%3D18763802-b90da6d8-0f98-4200-976f-546342abcade%26entityType%3Dcollection%26workspaceId%3De1370b45-5076-4885-884f-e9a97136ddbc#?env%5BMVAD%5D=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)
 
-## Multivariate Anomaly Detection API
+## Multivariate Anomaly Detector API
 
 1. Select environment as **MVAD**.
 

articles/cognitive-services/Anomaly-Detector/concepts/best-practices-multivariate.md

@@ -14,9 +14,9 @@ ms.author: mbullwin
 keywords: anomaly detection, machine learning, algorithms
 ---
 
-# Best practices for using the Multivariate Anomaly Detection API
+# Best practices for using the Multivariate Anomaly Detector API
 
-This article will provide guidance around recommended practices to follow when using the multivariate Anomaly Detection (MVAD) APIs. 
+This article provides guidance around recommended practices to follow when using the multivariate Anomaly Detector (MVAD) APIs. 
 In this tutorial, you'll:
 
 > [!div class="checklist"]
@@ -27,7 +27,7 @@ In this tutorial, you'll:
 
 ## API usage
 
-Follow the instructions in this section to avoid errors while using MVAD. If you still get errors, please refer to the [full list of error codes](./troubleshoot.md) for explanations and actions to take.
+Follow the instructions in this section to avoid errors while using MVAD. If you still get errors, refer to the [full list of error codes](./troubleshoot.md) for explanations and actions to take.
 
 [!INCLUDE [mvad-input-params](../includes/mvad-input-params.md)]
 
@@ -49,7 +49,7 @@ Now you're able to run your code with MVAD APIs without any error. What could be
 * The underlying model of MVAD has millions of parameters. It needs a minimum number of data points to learn an optimal set of parameters. The empirical rule is that you need to provide **5,000 or more data points (timestamps) per variable** to train the model for good accuracy. In general, the more the training data, better the accuracy. However, in cases when you're not able to accrue that much data, we still encourage you to experiment with less data and see if the compromised accuracy is still acceptable.
 * Every time when you call the inference API, you need to ensure that the source data file contains just enough data points. That is normally `slidingWindow` + number of data points that **really** need inference results. For example, in a streaming case when every time you want to inference on **ONE** new timestamp, the data file could contain only the leading `slidingWindow` plus **ONE** data point; then you could move on and create another zip file with the same number of data points (`slidingWindow` + 1) but moving ONE step to the "right" side and submit for another inference job. 
 
-    Anything beyond that or "before" the leading sliding window won't impact the inference result at all and may only cause performance downgrade.Anything below that may lead to an `NotEnoughInput` error.
+    Anything beyond that or "before" the leading sliding window won't impact the inference result at all and may only cause performance downgrade. Anything below that may lead to an `NotEnoughInput` error.
 
 
 ### Timestamp round-up
@@ -76,9 +76,9 @@ In a group of variables (time series), each variable may be collected from an in
 | 12:01:34  | 1.7   |
 | 12:02:04  | 2.0   |
 
-We have two variables collected from two sensors which send one data point every 30 seconds. However, the sensors aren't sending data points at a strict even frequency, but sometimes earlier and sometimes later. Because MVAD will take into consideration correlations between different variables, timestamps must be properly aligned so that the metrics can correctly reflect the condition of the system. In the above example, timestamps of variable 1 and variable 2 must be properly 'rounded' to their frequency before alignment.
+We have two variables collected from two sensors which send one data point every 30 seconds. However, the sensors aren't sending data points at a strict even frequency, but sometimes earlier and sometimes later. Because MVAD takes into consideration correlations between different variables, timestamps must be properly aligned so that the metrics can correctly reflect the condition of the system. In the above example, timestamps of variable 1 and variable 2 must be properly 'rounded' to their frequency before alignment.
 
-Let's see what happens if they're not pre-processed. If we set `alignMode` to be `Outer` (which means union of two sets), the merged table will be
+Let's see what happens if they're not pre-processed. If we set `alignMode` to be `Outer` (which means union of two sets), the merged table is:
 
 | timestamp | Variable-1 | Variable-2 |
 | --------- | -------- | -------- |
@@ -93,9 +93,9 @@ Let's see what happens if they're not pre-processed. If we set `alignMode` to be
 | 12:02:04  | `nan`    | 2.0      |
 | 12:02:08  | 1.3      | `nan`    |
 
-`nan` indicates missing values. Obviously, the merged table isn't what you might have expected. Variable 1 and variable 2 interleave, and the MVAD model can't extract information about correlations between them. If we set `alignMode` to `Inner`, the merged table will be empty as there's no common timestamp in variable 1 and variable 2.
+`nan` indicates missing values. Obviously, the merged table isn't what you might have expected. Variable 1 and variable 2 interleave, and the MVAD model can't extract information about correlations between them. If we set `alignMode` to `Inner`, the merged table is empty as there's no common timestamp in variable 1 and variable 2.
 
-Therefore, the timestamps of variable 1 and variable 2 should be pre-processed (rounded to the nearest 30-second timestamps) and the new time series are
+Therefore, the timestamps of variable 1 and variable 2 should be pre-processed (rounded to the nearest 30-second timestamps) and the new time series are:
 
 *Variable-1*
 
@@ -149,7 +149,7 @@ There are some limitations in both the training and inference APIs, you should b
 ## Model quality
 
 ### How to deal with false positive and false negative in real scenarios?
-We have provided severity which indicates the significance of anomalies. False positives may be filtered out by setting up a threshold on the severity. Sometimes too many false positives may appear when there are pattern shifts in the inference data. In such cases a model may need to be retrained on new data. If the training data contains too many anomalies, there could be false negatives in the detection results. This is because the model learns patterns from the training data and anomalies may bring bias to the model. Thus proper data cleaning may help reduce false negatives.
+We have provided severity that indicates the significance of anomalies. False positives may be filtered out by setting up a threshold on the severity. Sometimes too many false positives may appear when there are pattern shifts in the inference data. In such cases a model may need to be retrained on new data. If the training data contains too many anomalies, there could be false negatives in the detection results. This is because the model learns patterns from the training data and anomalies may bring bias to the model. Thus proper data cleaning may help reduce false negatives.
 
 ### How to estimate which model is best to use according to training loss and validation loss?
 Generally speaking, it's hard to decide which model is the best without a labeled dataset. However, we can leverage the training and validation losses to have a rough estimation and discard those bad models. First, we need to observe whether training losses converge. Divergent losses often indicate poor quality of the model. Second, loss values may help identify whether underfitting or overfitting occurs. Models that are underfitting or overfitting may not have desired performance. Third, although the definition of the loss function doesn't reflect the detection performance directly, loss values may be an auxiliary tool to estimate model quality. Low loss value is a necessary condition for a good model, thus we may discard models with high loss values.

articles/cognitive-services/Anomaly-Detector/faq.yml

@@ -21,8 +21,8 @@ sections:
       - question: |
           When to use Univariate Anomaly Detection v.s. Multivariate Anomaly Detection?
         answer:  |
-          If your goal is to detect anomalies out of a normal pattern on each individual time series purely based on their own historical data, use the univariate anomaly detection APIs. For example, you want to detect daily revenue anomalies based on revenue data itself, or you want to detect a CPU spike purely based on CPU data.
-          If your goal is to detect system level anomalies from a group of time series data, use multivariate anomaly detection APIs. Particularly, when any individual time series won't tell you much, and you have to look at all signals (a group of time series) holistically to determine a system level issue. For example, you have an expensive physical asset like aircraft, equipment on an oil rig, or a satellite. Each of these assets has tens or hundreds of different types of sensors. You would have to look at all those time series signals from those sensors to decide whether there's system level issue.
+          If your goal is to detect anomalies out of a normal pattern on each individual time series purely based on their own historical data, use the univariate anomaly detector APIs. For example, you want to detect daily revenue anomalies based on revenue data itself, or you want to detect a CPU spike purely based on CPU data.
+          If your goal is to detect system level anomalies from a group of time series data, use multivariate anomaly detector APIs. Particularly, when any individual time series won't tell you much, and you have to look at all signals (a group of time series) holistically to determine a system level issue. For example, you have an expensive physical asset like aircraft, equipment on an oil rig, or a satellite. Each of these assets has tens or hundreds of different types of sensors. You would have to look at all those time series signals from those sensors to decide whether there's system level issue.
       - question: |
           Can the Anomaly Detector service be used in other platforms or applications?
         answer:  |

articles/cognitive-services/Anomaly-Detector/includes/quickstarts/anomaly-detector-client-library-csharp-multivariate.md

@@ -10,7 +10,7 @@ ms.date: 03/30/2023
 ms.author: mbullwin
 ---
 
-Get started with the Anomaly Detector multivariate client library for C#. Follow these steps to install the package and start using the algorithms provided by the service. The new multivariate anomaly detection APIs enable developers by easily integrating advanced AI for detecting anomalies from groups of metrics, without the need for machine learning knowledge or labeled data. Dependencies and inter-correlations between different signals are automatically counted as key factors. This helps you to proactively protect your complex systems from failures.
+Get started with the Anomaly Detector multivariate client library for C#. Follow these steps to install the package and start using the algorithms provided by the service. The new multivariate anomaly detector APIs enable developers by easily integrating advanced AI for detecting anomalies from groups of metrics, without the need for machine learning knowledge or labeled data. Dependencies and inter-correlations between different signals are automatically counted as key factors. This helps you to proactively protect your complex systems from failures.
 
 Use the Anomaly Detector multivariate client library for C# to: