Evidently

**Updates:**
720
727
728
729
730

**Fixes:**
721
723

**Updates:**
711
714

**Fixes:**
681
692
695
696
698
704
707
712
713

Updates:
631
634
633
668
672
677
684
687
690

Fixes:
641
651
665

Breaking Changes:
644

**Updates:**
619
622
628
629

**Experimental:**
600

**Breaking Changes:**
Renamed parameter lemmatisize -> lemmatize in TriggerWordsPresence text descriptor

**Fixes:**
607
611
613
615
618
617
623
624
625
626
630

**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

**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