Skip to content

Commit fa54b19

Browse files
GiovanniGiacomettiGiovanniGiacometti
committed
Adapt Monitoring pages to docs style
1 parent 0ac5cb1 commit fa54b19

File tree

4 files changed

+145
-106
lines changed

4 files changed

+145
-106
lines changed

‎md-docs/user_guide/monitoring/detection_event.md‎

Lines changed: 25 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -4,44 +4,47 @@ A Detection Event is raised by the ML cube Platform when a significant change is
44

55
An event is characterized by the following attributes:
66

7-
- `Event Type`: the type of the event. It's possible values are:
8-
<div class="nice-list">
9-
<ul>
10-
<li> `Warning On`: the monitoring entity is experiencing slight changes that might lead to a drift.</li>
11-
<li> `Warning Off`: the monitoring entity has returned to the reference distribution. </li>
12-
<li> `Drift On`: the monitoring entity has drifted from the reference distribution.</li>
13-
<li> `Drift Off`: the monitoring entity has returned to the reference distribution.</li>
14-
</ul>
15-
</div>
16-
- `Severity`: the severity of the event. It's provided only for drift events and it can be `Low`, `Medium`, or `High`.
17-
- `Monitoring Target`: the [Monitoring Target](index.md#monitoring-metrics) being monitored.
18-
- `Monitoring Metric`: the [Monitoring Metric](index.md#monitoring-metrics) being monitored.
19-
- `Model Name`: the name of the model that raised the event. It's present only if the event is related to a model.
20-
- `Model Version`: the version of the model that raised the event. It's present only if the event is related to a model.
21-
- `Insert datetime`: the time when the event was raised.
22-
- `Sample timestamp`: the timestamp of the sample that triggered the event.
23-
- `Sample customer ID`: the id of the customer that triggered the event.
24-
- `User feedback`: the feedback provided by the user on whether the event was expected or not.
7+
| Attribute | Description |
8+
|--------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
9+
| Eventy Type | The type of the event. It's possible values are: <div class="nice-list"><ul><li> `Warning On`: the monitoring entity is experiencing slight changes that might lead to a drift.</li><li> `Warning Off`: the monitoring entity has returned to the reference distribution. </li><li> `Drift On`: the monitoring entity has drifted from the reference distribution.</li><li> `Drift Off`: the monitoring entity has returned to the reference distribution.</li> </ul></div> |
10+
| Severity | The severity of the event. It's provided only for drift events and it can be `Low`, `Medium`, or `High`. |
11+
| Monitoring Target | The [Monitoring Target](index.md#monitoring-metrics) being monitored. |
12+
| Monitoring Metric | The [Monitoring Metric](index.md#monitoring-metrics) being monitored. |
13+
| Model Name | The name of the model that raised the event. It's present only if the event is related to a model. |
14+
| Model Version | The version of the model that raised the event. It's present only if the event is related to a model. |
15+
| Insert datetime | The time when the event was raised. |
16+
| Sample timestamp | The timestamp of the sample that triggered the event. |
17+
| Sample customer ID | The id of the sample that triggered the event. |
18+
| User feedback | The feedback provided by the user on whether the event was expected or not. |
19+
2520

2621
## Retrieve Detection Events
2722

2823
You can access the detection events generated by the Platform in two ways:
2924

3025
- **SDK**: it can be used to retrieve all detection events for a specific task programmatically.
31-
- **WebApp**: navigate to the **`Detection `** section located in the task page's sidebar. Here, all detection events are displayed in a table,
26+
- **WebApp**: navigate to the `Detection` section located in the task page's sidebar. Here, all detection events are displayed in a table,
3227
with multiple filtering options available for useful event management. Additionally, the latest detection events identified are shown in the Task homepage,
3328
in the section named "Latest Detection Events".
3429

30+
??? code-block "SDK Example"
31+
32+
The following code demonstrates how to retrieve all detection events for a specific task.
33+
34+
```python
35+
detection_events = client.get_detection_events(task_id='my-task-id')
36+
```
37+
3538
## User Feedback
3639

37-
When a detection event is raised, you can provide feedback on whether the event was expected or not. This feedback is then used
40+
When a `Drift On` event is raised, you can provide feedback on whether the event was expected or not. This feedback is then used
3841
to tune the monitoring algorithms and improve their performance. The feedback can be provided through the WebApp, in the
39-
**`Detection `** section of the task page, or through the SDK.
42+
`Detection` section of the task page, or through the SDK.
4043

4144

4245
## Detection Event Rules
4346

44-
To automate actions upon the reception of a detection event, you can set up detection event rules.
47+
To automate actions upon the reception of a detection event, you can set up Detection Event Rules.
4548
You can learn more about how to configure them in the [Detection Event Rules] section.
4649

4750

‎md-docs/user_guide/monitoring/detection_event_rules.md‎

Lines changed: 22 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -2,46 +2,49 @@
22

33
This section outlines how to configure automation to receive notifications or start retraining after a [Detection Event] occurs.
44

5-
When a detection event is produced, the ML cube Platform reviews all the detection event rules you have set
5+
When a Detection Event is produced, the ML cube Platform reviews all the Detection Event Rules you have set
66
and triggers those matching the event.
77

88
Rules are specific to a task and are characterized by the following attributes:
99

10-
- `Name`: a descriptive label of the rule.
11-
- `Detection Event Type`: the type of event that triggers the rule.
12-
- `Severity`: the severity of the event that triggers the rule. It is only applicable to drift events. If not specified, the rule will be triggered by drift events of any severity.
13-
- `Monitoring Target`: the [Monitoring Target](index.md#monitoring-targets) whose event should trigger the rule.
14-
- `Monitoring Metric`: the [Monitoring Metric](index.md#monitoring-metrics) whose event should trigger the rule.
15-
- `Model name`: the name of the model to which the rule applies. This is only required when the monitoring target is related to a model
16-
(such as `ERROR` or `PREDICTION`).
17-
- `Actions`: A list of actions to be executed sequentially when the rule is triggered.
10+
| Attribute | Description |
11+
|----------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
12+
| Name | A descriptive label of the rule. |
13+
| Detection Event Type | The type of event that triggers the rule. |
14+
| Severity | The severity of the event that triggers the rule. It is only applicable to drift events. If not specified, the rule will be triggered by drift events of any severity. |
15+
| Monitoring Target | The [Monitoring Target](index.md#monitoring-targets) whose event should trigger the rule. |
16+
| Monitoring Metric | The [Monitoring Metric](index.md#monitoring-metrics) whose event should trigger the rule. |
17+
| Model name | The name of the model to which the rule applies. This is only required when the monitoring target is related to a model (such as `ERROR` or `PREDICTION`). |
18+
| Actions | A list of actions to be executed sequentially when the rule is triggered. |
1819

1920
## Detection Event Actions
2021
Three types of actions are currently supported: notification, plot configuration and retrain.
2122

2223
### Notifications
2324

24-
These actions send notifications to external services when a detection event is triggered. The following notification actions are available:
25+
These actions send notifications to external services when a detection event is triggered. The following notification options are available:
2526

26-
- `Slack Notification`: sends a notification to a Slack channel via webhook.
27-
- `Discord Notification`: sends a notification to a Discord channel via webhook.
28-
- `Email Notification`: sends an email to the provided email address.
29-
- `Teams Notification`: sends a notification to Microsoft Teams via webhook.
30-
- `Mqtt Notification`: sends a notification to an MQTT broker.
27+
| Channel | Description |
28+
|----------------------|--------------------------------------------------------|
29+
| Slack Notification | Sends a notification to a Slack channel via webhook. |
30+
| Discord Notification | Sends a notification to a Discord channel via webhook. |
31+
| Email Notification | Sends an email to the provided email address. |
32+
| Teams Notification | Sends a notification to Microsoft Teams via webhook. |
33+
| Mqtt Notification | Sends a notification to an MQTT broker. |
3134

3235
### Plot Configuration
3336

34-
This action consists in creating two plot configurations when a detection event is triggered: the first one includes
37+
This action consists in creating two plot configurations when a Detection Event is triggered: the first one includes
3538
data preceding the event, while the second one includes data following the event.
3639

3740
### Retrain
3841

3942
Retrain Action enables the automatic retraining of your model. Therefore, it is only available when the target of the rule is related to a model.
40-
The retrain action does not need any parameter because it is automatically inferred from the `Model Name` attribute of the rule.
43+
The retrain action does not need any parameter because it is automatically inferred from the `model name` attribute of the rule.
4144
Of course, the model must already have a retrain trigger associated before setting up this action.
4245

43-
!!! example
44-
The following code snippet demonstrates how to create a rule that matches high severity drift events on the error of a model.
46+
??? code-block "SDK Example"
47+
The following code demonstrates how to create a rule that matches high severity drift events on the error of a model.
4548
When triggered, it first sends a notification to the `ml3-platform-notifications` channel on your Slack workspace, using the
4649
provided webhook URL, and then starts the retraining of the model.
4750

‎md-docs/user_guide/monitoring/drift_explainability.md‎

Lines changed: 9 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -5,12 +5,12 @@ ensuring the model continues to function as expected. However, monitoring only i
55

66
In order to make the right decisions, you need to understand what were the main factors that led to the drift in the first place, so that
77
the correct actions can be taken to mitigate it.
8-
9-
The ML cube Platform supports this process by offering what we refer to as **Drift Explainability Reports**,
8+
s
9+
The ML cube Platform supports this process by providing what we refer to as **Drift Explainability Report**,
1010
automatically generated upon the detection of a drift and containing several elements that should help you diagnose the root causes
1111
of the change occurred.
1212

13-
You can access the reports in the WebApp, by navigating to the `Drift Explainability` tab in the sidebar of the Task page.
13+
You can access the reports in the WebApp, by navigating to the `Drift Explainability` tab in the sidebar of the [Task] page.
1414

1515
## Structure
1616

@@ -20,13 +20,13 @@ after the drift, in order to ensure statistical reliability of the results.
2020
If the data distribution moves back to the reference before enough samples are collected, the report might not be generated.
2121

2222
Each report is composed of several entities, each providing a different perspective on the data and the drift occurred.
23-
Most of them are specific to a certain `Data Structure`, so they might not be available for all tasks.
23+
Most of them are specific to a certain Data Structure, so they might not be available for all Tasks.
2424

2525
These entities can take the form of tables, plots, or textual explanations.
2626
Observed and analyzed together, they should provide a comprehensive understanding of the drift and its underlying causes.
2727
These are the entities currently available:
2828

29-
- `Feature Importance`: it's a barplot that illustrates how the significance of each feature differs between the reference
29+
- **`Feature Importance`**: it's a barplot that illustrates how the significance of each feature differs between the reference
3030
and the production datasets. Variations in a feature's values might suggest that its contribution to the model's predictions
3131
has changed over time. This entity is available only for tasks with tabular data.
3232

@@ -35,7 +35,7 @@ These are the entities currently available:
3535
<figcaption>Example of a feature importance plot.</figcaption>
3636
</figure>
3737

38-
- `Variable discriminative power`: it's also a bar plot displays the influence of each feature, as well as the target,
38+
- **`Variable discriminative power`**: it's also a bar plot displays the influence of each feature, as well as the target,
3939
in differentiating between the reference and the production datasets.
4040
The values represent how strongly a given feature helps to distinguish the datasets, with higher values representing stronger
4141
separating power. This entity is available only for tasks with tabular data.
@@ -45,7 +45,7 @@ These are the entities currently available:
4545
<figcaption>Example of a variable discriminative power plot.</figcaption>
4646
</figure>
4747

48-
- `Drift Score`: it's a line plot that shows the evolution of the drift score over time. The drift score is a
48+
- **`Drift Score`**: it's a line plot that shows the evolution of the drift score over time. The drift score is a
4949
measure of the statistical distance between a sliding window of the production data and the reference data. It also shows the threshold,
5050
which is the value that the drift score must exceed to raise a drift alarm, and all the [Detection Events] that were triggered in
5151
the time frame of the report. This plot helps in understanding how the drift evolved over time and the moments in which the difference
@@ -61,4 +61,5 @@ These are the entities currently available:
6161
</figure>
6262

6363
[Monitoring]: index.md
64-
[Detection Events]: detection_event.md
64+
[Detection Events]: detection_event.md
65+
[Task]: ../task.md

0 commit comments

Comments
 (0)