Update text insights and error_analysis_manager to handle pd.DataFrame predictions and prediction with type of string #2179
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
tongyu-microsoft
changed the title
tongyu-microsoft
changed the title
RubyZ10
reviewed
Jul 12, 2023
responsibleai_text/responsibleai_text/managers/error_analysis_manager.py
Show resolved
Hide resolved
RubyZ10
approved these changes
Jul 12, 2023
Codecov Report
@@ Coverage Diff @@
## main #2179 +/- ##
==========================================
- Coverage 88.14% 78.34% -9.80%
==========================================
Files 129 26 -103
Lines 7296 2152 -5144
==========================================
- Hits 6431 1686 -4745
+ Misses 865 466 -399
Flags with carried forward coverage won't be shown. Click here to find out more.
|
responsibleai_text/responsibleai_text/rai_text_insights/rai_text_insights.py
Outdated
Show resolved
Hide resolved
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR updates rai_text_insights and error_analysis_manager.
For rai_text_insights, for predict_output and predict_proba_output, since we only support numpy array, this PR adds a check to handle pandas.DataFrame, and convert pd.DataFrame to numpy array.
For error_analysis_manager, in the case where the prediction value is a string, we should output the predictions directly, no need to map it from self.classes.
Description
Here is an example AML pipeline running based on responsibleai-text package with the changes in this PR: https://ml.azure.com/experiments/id/26da27c2-760c-4ae7-af6f-fb35b708e952/runs/teal_owl_t5k6t3v2gv?wsid=/subscriptions/3d6da6ed-6af5-4a74-87c6-da367514f8e0/resourceGroups/ResponsibleAIE2E/providers/Microsoft.MachineLearningServices/workspaces/ResponsibleAIE2ETest&flight=RAIAutomlIntegration&tid=72f988bf-86f1-41af-91ab-2d7cd011db47#
Link to dashboard: https://ml.azure.com/model/analysis/distilbert-base-uncased/be98b4b8-550a-40fc-8410-fc57258184c2?wsid=/subscriptions/3d6da6ed-6af5-4a74-87c6-da367514f8e0/resourceGroups/ResponsibleAIE2E/providers/Microsoft.MachineLearningServices/workspaces/ResponsibleAIE2ETest&flight=RAIAutomlIntegration&tid=72f988bf-86f1-41af-91ab-2d7cd011db47
Checklist