Aggregated metrics visualization

Breaking Changes:
#601
Since this version, the following metrics will render aggregated plots instead of raw data plots:

• ColumnDriftMetric
• DataDriftTable
• ColumnValuePlot
• TextDescriptorsDriftMetric
• ColumnSummaryMetric
• RegressionPredictedVsActualScatter
• RegressionPredictedVsActualPlot
• RegressionErrorPlot
• RegressionAbsPercentageErrorPlot
• RegressionErrorNormality
• RegressionTopErrorMetric
• ClassificationClassSeparationPlot
• ClassificationQualityByFeatureTable
• RegressionErrorBiasTable
• TargetByFeaturesTable

To return raw data plots use render option :

• On a metric level:

report = Report(
	metrics=[
	RegressionPredictedVsActualScatter(options={"render": {"raw_data": True}}),
])

• On a report level:

report = Report(
    metrics=[
      RegressionQualityMetric(),
      RegressionPredictedVsActualScatter(),
    ],
    options={"render": {"raw_data": True}}
  )

Updates:
#588
#589
#597

Fixes:
#593

Support for Text Descriptors in Column Tests and Embedding Drift Test

Breaking Changes:
#585
Drift detection method
text_content_drift was renamed to perc_text_content_drift
This happened because an additional text data drift detection method was added: abs_text_content_drift. This drift detection technique works more efficiently with large datasets.

Updates:
#562
#564
#566
#567
#569
#570
#587

Fixes:
#568
#572
#573
#574
#575
#579
#580
#582
#583
#586

Dashboards API is no longer supported! JSON output customisation & Embeddings Drift Metric

Breaking Changes:
Old API is no longer supported! There are no more Dashboards, Model Profiles, Tabs, and Profile Sections!
#550

Updates:
JSON output customisation:
#543
#545
#548

Text descriptors support in column metrics and tests:
#542
#546
#553
#557

Embeddings Drift Metric
#558

Fixes:
#560

New Examples:
How to customize JSON output for Reports and TestSuites?
How to calculate drift for embeddings?
How to apply column metrics for text descriptors?

Fix for reports json generation

Fixes:
#536
#537
#541

MetricResult structuring (to be used for JSON adjustment later)

Updates:
#517
#533

Streamlit Integration Example:
#531

Fixes:
#523
#528
#529
#532
#534
#535

Text Descriptors Customisation for Text-specific Metrics and Preset

Updates:

1. Added text descriptor TriggerWordsPresence
2. Added an option to specify which text descriptors should be used in the following metrics:

• TextDescriptorsDriftMetric
• TextDescriptorsDistribution
• TextDescriptorsCorrelationMetric

3. Added an option to specify which text descriptors should be used in the TextOverviewPreset

Fixes:
#512
#519
#520
#521
#522

Fix for Correlation Tests

Updates:
Instead of using just Pearson correlation, the following tests automatically choose the correlation method depending on target and prediction types:

• TestTargetPredictionCorrelation
• TestTargetFeaturesCorrelations
• TestPredictionFeaturesCorrelations

Fixes:
#446
#499
#504
#505
#511

Compatibility with Python 3.11

Updated project build to be compatible with python 3.11

Conda-compatible project build

Conda-compatible project build: prebuilt UI is stored in the repo; there is no need to build it locally.

Text data support in Reports and TestSuites

Breaking Changes:

• Python 3.6 is no longer supported

Updates:

• New parameter “text_features” was added to ColumnMapping. text_features parameter takes a list with feature names: “column_mapping.text_features=[’text_feature_1’, ‘text_feature_2’, …, ‘text_feature_k’]”
• The following metrics now support text features:
  • DatasetSummaryMetric()
  • DatasetMissingValuesMetric()
  • ColumnSummaryMetric(column_name="name")
  • ColumnMissingValuesMetric(column_name="name")
  • ColumnRegExpMetric(column_name="name", reg_exp=r".ticket.")
  • ConflictPredictionMetric()
  • ConflictTargetMetric()
  • DatasetCorrelationsMetric()
  • DatasetDriftMetric()
  • DataDriftTable()
  • ColumnDriftMetric(column_name=”name”)
  • TargetByFeaturesTable(columns=columns)
  • ClassificationQualityByFeatureTable()
  • RegressionErrorBiasTable()
• All metric presets now support text features
• All tests based on metrics that support text features also support texts
• The following test presets now support text features:
  • NoTargetPerformanceTestPreset
  • DataStabilityTestPreset
  • DataQualityTestPreset
  • DataDriftTestPreset
• Added metric TextDescriptorsDriftMetric for text data
• Added metric TextDescriptorsDistribution for text data
• Added metric TextDescriptorsCorrelationMetric for text data
• Added TextOverviewPreset(column_name=”name”) for text data. The preset includes:
  • ColumnSummaryMetric
  • TextDescriptorsDistribution
  • TextDescriptorsCorrelation
  • ColumnDriftMetric (if reference dataset is provided)
  • TextDescriptorsDriftMetric (if reference dataset is provided)

Changes:

• Method get_parameters(self) -> Optional[tuple] from Metric(Generic[TResult]) class was updated and became optional. The algorithm to determine metric parameters and create a tuple with metric parameters and its values is updated to cover more parameter types. Since the algorithm has been significantly updated, get_parameters method should be implemented in a custom metric class only if specific behaviour is needed. For most standard scenarios, the default version is sufficient.
• Metric deduplication now includes not only metric calculation parameters but features as well. This helps to deduplicate calculations of the same metrics on top of the same features and as a result, reduce calculation time.

Fixes:

• #484
• #490