You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/machine-learning/service/azure-machine-learning-release-notes.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -471,7 +471,7 @@ At the time of this release, the following browsers are supported: Chrome, Firef
471
471
+ Fixed transformations argument forLIME explainer for raw feature importance in azureml-contrib-explain-model package
472
472
+ added segmentations to image explanations in image explainer for AzureML-contrib-explain-model package
473
473
+ add scipy sparse support for LimeExplainer
474
-
+add batch_size to mimic explainer when include_local=Falsefor streaming global explanations in batches to improve execution time of DecisionTreeExplainableModel
474
+
+added `batch_size` to mimic explainer when `include_local=False`,for streaming global explanations in batches to improve execution time of DecisionTreeExplainableModel
475
475
+**azureml-contrib-featureengineering**
476
476
+ Fix for calling set_featurizer_timeseries_params(): dict value type change and null check - Add notebook for timeseries featurizer
477
477
+ Update NimbusML dependency to 1.2.0 version (current latest).
@@ -500,7 +500,7 @@ At the time of this release, the following browsers are supported: Chrome, Firef
500
500
+for mimic explainer in explain model library, fixed error when include_local=Falsefor sparse data input
501
501
+ add expected values to automl output
502
502
+ fixed permutation feature importance when transformations argument supplied to get raw feature importance
503
-
+add batch_size to mimic explainer when include_local=Falsefor streaming global explanations in batches to improve execution time of DecisionTreeExplainableModel
503
+
+added `batch_size` to mimic explainer when `include_local=False`,for streaming global explanations in batches to improve execution time of DecisionTreeExplainableModel
504
504
+for model explainability library, fixed blackbox explainers where pandas dataframe inputis required for prediction
505
505
+ Fixed a bug where `explanation.expected_values` would sometimes return a float rather than a listwith a floatin it.
0 commit comments