Docs update

docs/book/.gitbook/assets/cloud/readme.md

@@ -0,0 +1 @@
+Evidently Cloud visual assets.

docs/book/README.md

@@ -9,19 +9,26 @@ Have only 1 minute? Check out this example:
 ["Hello world" example](get-started/hello-world.md). 
 {% endcontent-ref %}
 
-New to Evidently? This tutorial shows how to run ad hoc data and model checks. (15 min).
+New to Evidently? Learn how to run data and model checks. (15 min).
 {% content-ref url="get-started/tutorial.md" %}
 [Get started tutorial](get-started/tutorial.md). 
 {% endcontent-ref %}
 
-Want a dashboard to track metrics over time? (2 min to launch a demo, 15 to complete).
+Want an ML monitoring dashboard to track metrics over time? 
+
+Self-host an ML monitoring dashboard: 
 {% content-ref url="get-started/tutorial-monitoring.md" %}
 [Get started tutorial](get-started/tutorial-monitoring.md). 
 {% endcontent-ref %}
 
-You can explore mode code [examples](examples/examples.md). 
+Get started with Evidently Cloud: 
+{% content-ref url="get-started/tutorial-cloud.md" %}
+[Get started tutorial](get-started/tutorial-cloud.md). 
+{% endcontent-ref %}
+
+You can explore more code [examples](examples/examples.md). 
 
-Don't want to self-host? Sign up for the [Evidently Cloud Waitlist](https://www.evidentlyai.com/product/cloud)!
+Don't want to self-host? Sign up for the [Evidently Cloud](https://www.evidentlyai.com/cloud-signup)!
 
 # How it works 
 

docs/book/SUMMARY.md

@@ -5,7 +5,8 @@
 * [Get Started](get-started/README.md)
   * [Hello World Example](get-started/hello-world.md)
   * [Quickstart for Reports and Tests](get-started/tutorial.md)
-  * [Quickstart for ML Monitoring](get-started/tutorial-monitoring.md)
+  * [Quickstart for Evidently Cloud](get-started/tutorial-cloud.md)
+  * [Self-host ML Monitoring](get-started/tutorial-monitoring.md)
 * [Presets](presets/README.md)
   * [All Presets](presets/all-presets.md)
   * [Data Drift](presets/data-drift.md)

docs/book/customization/feature-importance.md

@@ -2,10 +2,8 @@
 description: How to show feature importance in Data Drift evaluations.
 ---
 
-You can add feature importances to the dataset-level data drift Tests, Metrics and Reports:
+You can add feature importances to the dataset-level data drift Tests and Metrics:
 * `DataDriftTable`
-* `DataDriftPreset`
-* `DataDriftTestPreset`
 * `TestShareOfDriftedColumns`
 
 # Code example

docs/book/get-started/tutorial-monitoring.md

@@ -16,6 +16,10 @@ The tutorial is split into two parts.
 
 **Note**: This guide assumes you run Evidently locally.
 
+{% hint style="info" %}
+**Don't want to self-host the ML monitoring dashboard?** Check out the [Evidently Cloud tutorial](tutorial-cloud.md).
+{% endhint %}
+
 # Part 1. Pre-built demo
 
 ## 1. Create virtual environment

docs/book/get-started/tutorial.md

@@ -1,8 +1,8 @@
-In this tutorial, you will use the Evidently open-source Python library to evaluate **data stability** and **data drift** on tabular data. You will run batch checks on a toy dataset and generate visual Reports and Test Suites.
+In this tutorial, you will use the Evidently open-source Python library to evaluate **data stability** and **data drift** on tabular data. You will run batch checks on a toy dataset and generate visual Reports and Test Suites in your Python environment.
 
-We recommend going through this tutorial once to understand the basic functionality. You can then explore more advanced workflows, like adjusting test parameters, adding custom metrics or hosting an [ML monitoring dashboard](tutorial-monitoring.md) to track the model or data quality over time.
+We recommend going through this tutorial once to understand the basic functionality. Once you complete it, you will be ready to use all Evidently evaluations, including checks for ML model quality or text data.  
 
-After going through this tutorial, you will be ready to use all Evidently evaluations, including checks for model quality or text data.  
+You can run the Evidently Reports and Test Suites separately or use them as a logging layer for Evidently ML Monitoring. You can later self-host an [ML monitoring dashboard](tutorial-monitoring.md) or send the Reports and Test Suite to [Evidently Cloud platform](tutorial-cloud.md) to monitor metrics over time.  
 
 To complete the tutorial, you need basic knowledge of Python. You should be able to complete it in **about 15 minutes**.
 

docs/book/reference/all-metrics.md

@@ -28,27 +28,18 @@ We are doing our best to maintain this page up to date. In case of discrepancies
 
 # Metric Presets
 
-<details>
-
-<summary>Metric Preset composition</summary>
-
-
 **Defaults**: each Metric in a Preset uses the default parameters for this Metric. You can see them in the tables below. 
 
 | Preset name and Description | Parameters |
 |---|---|
 | **`DataQualityPreset`**<br><br>Evaluates the data quality and provides descriptive stats. <br><br>Input features are required. Prediction and target are optional. <br><br>**Contents:**<ul><li>`DatasetSummaryMetric()`</li><li>`ColumnSummaryMetric(column_name=column_name)` for `all` or `сolumns` if provided</li><li>`DatasetMissingValuesMetric()`</li><li>`DatasetCorrelationsMetric()`</li></ul> | **Optional**:<br>`columns`<br> |
 | **`DataDriftPreset`**<br> Evaluates the data drift in the individual columns and the dataset. <br><br> Input features are required. <br><br>**Contents**:<ul><li>`DataDriftTable(сolumns=сolumns)` or `all` if not listed</li><li>`DatasetDriftMetric(сolumns=сolumns)` or `all` if not listed</li></ul>| **Optional**:<ul><li>`columns`</li><li>`stattest`</li><li>`cat_stattest`</li><li>`num_stattest`</li><li>`per_column_stattest`</li><li>`text_stattest`</li><li>`stattest_threshold`</li><li>`cat_stattest_threshold`</li><li>`num_stattest_threshold`</li><li>`per_column_stattest_threshold`</li><li>`text_stattest_threshold`</li><li>`embeddings`</li><li>`embeddings_drift_method`</li><li>`drift_share`</li></ul> [How to set data drift parameters](../customization/options-for-statistical-tests.md), [embeddings drift parameters](../customization/embeddings-drift-parameters.md).|
-| **`TargetDriftPreset`** <br><br>Evaluates the prediction or target drift. <br><br>Target or prediction is required. Input features are optional.<br><br>**Contents**:<ul><li>`ColumnDriftMetric(column_name=target, prediction)`</li><li>`ColumnCorrelationsMetric(column_name=target, prediction)`</li><li>`TargetByFeaturesTable(columns=columns)` or `all` if not listed</li></ul>
-If regression:<ul><li>`ColumnValuePlot(column_name=target, prediction)`</li></ul> | **Optional**:<ul><li>`columns`</li><li>`stattest`</li><li>`cat_stattest`</li><li>`num_stattest`</li><li>`per_column_stattest`</li><li>`stattest_threshold`</li><li>`cat_stattest_threshold` </li><li>`num_stattest_threshold`</li><li>`per_column_stattest_threshold`</li></ul> [How to set data drift parameters](../customization/options-for-statistical-tests.md). |
+| **`TargetDriftPreset`** <br><br>Evaluates the prediction or target drift. <br><br>Target or prediction is required. Input features are optional.<br><br>**Contents**:<ul><li>`ColumnDriftMetric(column_name=target, prediction)`</li><li>`ColumnCorrelationsMetric(column_name=target, prediction)`</li><li>`TargetByFeaturesTable(columns=columns)` or `all` if not listed</li></ul> If regression:<ul><li>`ColumnValuePlot(column_name=target, prediction)`</li></ul> | **Optional**:<ul><li>`columns`</li><li>`stattest`</li><li>`cat_stattest`</li><li>`num_stattest`</li><li>`per_column_stattest`</li><li>`stattest_threshold`</li><li>`cat_stattest_threshold` </li><li>`num_stattest_threshold`</li><li>`per_column_stattest_threshold`</li></ul> [How to set data drift parameters](../customization/options-for-statistical-tests.md). |
 | **`RegressionPreset`**<br> Evaluates the quality of a regression model. <br><br>Prediction and target are required. Input features are optional.<br><br>**Contents**:<ul><li>`RegressionQualityMetric()`</li><li>`RegressionPredictedVsActualScatter()`</li><li>`RegressionPredictedVsActualPlot()`</li><li>`RegressionErrorPlot()`</li><li>`RegressionAbsPercentageErrorPlot()`</li><li>`RegressionErrorDistribution()`</li><li>`RegressionErrorNormality()`</li><li>`RegressionTopErrorMetric()`</li><li>`RegressionErrorBiasTable(columns=columns)` or `all` if not listed</li></ul>| **Optional**:<br>`columns` |
-| **`ClassificationPreset`** <br>Evaluates the quality of a classification model. <br><br>Prediction and target are required. Input features are optional.<br><br>**Contents**:<ul><li>`ClassificationQualityMetric()`</li><li>`ClassificationClassBalance()`</li><li>`ClassificationConfusionMatrix()`</li><li>`ClassificationQualityByClass()`</li></ul>If probabilistic classification, also:<ul><li>`ClassificationClassSeparationPlot()`</li><li>`ClassificationProbDistribution()`</li><li>`ClassificationRocCurve()`</li><li>`ClassificationPRCurve()`</li><li>`ClassificationPRTable()`</li><li>`ClassificationQualityByFeatureTable(columns=columns)` or `all` if not listed</li></ul>
- | **Optional**:<ul><li>`columns`</li><li>`probas_threshold`</li><li>`k`</li></ul> |
+| **`ClassificationPreset`** <br>Evaluates the quality of a classification model. <br><br>Prediction and target are required. Input features are optional.<br><br>**Contents**:<ul><li>`ClassificationQualityMetric()`</li><li>`ClassificationClassBalance()`</li><li>`ClassificationConfusionMatrix()`</li><li>`ClassificationQualityByClass()`</li></ul>If probabilistic classification, also:<ul><li>`ClassificationClassSeparationPlot()`</li><li>`ClassificationProbDistribution()`</li><li>`ClassificationRocCurve()`</li><li>`ClassificationPRCurve()`</li><li>`ClassificationPRTable()`</li><li>`ClassificationQualityByFeatureTable(columns=columns)` or `all` if not listed</li></ul>| **Optional**:<ul><li>`columns`</li><li>`probas_threshold`</li><li>`k`</li></ul> |
 |**`TextOverviewPreset(column_name=”text”)`** <br>Evaluates data drift and descriptive statistics for text data. <br><br>Input features (text) are required.<br><br>**Contents**:<ul><li>`ColumnSummaryMetric()`</li><li>`TextDescriptorsDistribution()`</li><li>`TextDescriptorsCorrelation()`</li></ul>If reference data is provided, also:<ul><li> `ColumnDriftMetric()`</li><li>`TextDescriptorsDriftMetric()`</li></ul>| **Required**:<br>`column_name` | 
 |**`RecsysPreset`** <br>Evaluates the quality of the recommender system. <br><br>Recommendations and true relevance scores are required. For some metrics, training data and item features are required. <br><br>**Contents**:<ul><li>`PrecisionTopKMetric()`</li><li>`RecallTopKMetric()`</li><li>`FBetaTopKMetric()`</li><li>`MAPKMetric()`</li><li>`NDCGKMetric()`</li><li>`MRRKMetric()`</li><li>`HitRateKMetric()`</li><li>`PersonalizationMetric()`</li><li>`PopularityBias()` </li><li>`RecCasesTable()`</li><li>`ScoreDistribution()`</li><li>`DiversityMetric()`</li><li>`SerendipityMetric()`</li><li>`NoveltyMetric()`</li><li>`ItemBiasMetric()` (pass column as a parameter)</li><li>`UserBiasMetric()`(pass column as a parameter)</li></ul>| **Required**:<br>`k` <br> **Optional**:<ul><li>`min_rel_score: Optional[int]`</li><li>`no_feedback_users: bool`</li><li>`normalize_arp: bool`</li><li>`user_ids: Optional[List[Union[int, str]]]`</li><li>`display_features: Optional[List[str]]`</li><li>`item_features: Optional[List[str]]`</li><li>`user_bias_columns: Optional[List[str]]`</li><li>`item_bias_columns: Optional[List[str]]`</li></ul>
 
-</details>
-
 # Data Integrity
 
 **Defaults for Missing Values**. The metrics that calculate the number or share of missing values detect four types of the values by default: Pandas nulls (None, NAN, etc.), "" (empty string), Numpy "-inf" value, Numpy "inf" value. You can also pass a custom missing values as a parameter and specify if you want to replace the default list. Example:

docs/book/reference/all-tests.md

@@ -26,6 +26,7 @@ You can use the menu on the right to navigate the sections. We organize individu
   * No reference: the test conditions that apply if you do not provide the reference. They are based on heuristics.
 
 **Test visualizations**. Each test also includes a default render. If you want to see the visualization, navigate to the [example notebooks](../examples/examples.md).
+
 </details>
 
 {% hint style="info" %} 
@@ -34,10 +35,6 @@ We are doing our best to maintain this page up to date. In case of discrepancies
 
 # Test Presets
 
-<details>
-
-<summary>Test Preset Composition</summary>
-
 Default conditions for each Test in the Preset match the Test's defaults. You can see them in the tables below. The listed Preset parameters apply to the relevant individual Tests inside the Preset.
 
 | Preset name and Description | Parameters |
@@ -52,8 +49,6 @@ Default conditions for each Test in the Preset match the Test's defaults. You ca
 | **`BinaryClassificationTestPreset`** <br><ul><li>`TestColumnDrift(column_name=target)`</li><li>`TestPrecisionScore()`</li><li>`TestRecallScore()`</li><li>`TestF1Score()`</li><li>`TestAccuracyScore()`</li></ul>If probabilistic classification, also:<ul><li>`TestRocAuc()`</li></ul> | **Optional**:<ul><li>`stattest`</li><li>`stattest_threshold`</li><li>`probas_threshold`</li></ul> [How to set data drift parameters](../customization/options-for-statistical-tests.md)|
 | **`RecsysTestPreset`** <br><ul><li>`TestPrecisionTopK()`</li><li>`TestRecallTopK()`</li><li>`TestMAPK()`</li><li>`TestNDCGK()`</li><li>`TestHitRateK()`</li></ul> | **Required:**<ul><li>`k`</li></ul> **Optional:**<ul><li>`min_rel_score: Optional[int]`</li><li>`no_feedback_users: bool`</li></ul>
 
-</details>
-
 # Data Integrity
 
 **Defaults for Data Integrity**. If there is no reference data or defined conditions, data integrity will be checked against a set of heuristics. If you pass the reference data, Evidently will automatically derive all relevant statistics (e.g., number of columns, rows, share of missing values etc.) and apply default test conditions. You can also pass custom test conditions.