docs: add reassignZinggId & model diff guides#1283
Open
padam-prakash wants to merge 2 commits intozinggAI:mainfrom
Open
docs: add reassignZinggId & model diff guides#1283padam-prakash wants to merge 2 commits intozinggAI:mainfrom
padam-prakash wants to merge 2 commits intozinggAI:mainfrom
Conversation
Expand and improve documentation for explainOutput, persistent ZINGG ID reassignments, and model diff. Changes include: - docs/explainoutput/README.md: rename incrementalRun->runIncremental and add an "Important Notes" section clarifying that explainOutput focuses on probabilistic matches (deterministic matches are not included and may produce empty results for some clusters). - docs/persistentZinggId.md: fix title typo and replace placeholder with a full guide for the reassignZinggId phase (motivation, how it works, CLI and Python usage examples, configuration wrappers, example JSON configs, and output/usage notes). - docs/stepbystep/createtrainingdata/modeldiff.md: replace placeholder with a comprehensive model diff guide (purpose, how it works, CLI and Python examples, configuration samples, output format, and use cases).
Contributor
There was a problem hiding this comment.
Pull request overview
This PR expands Enterprise documentation for understanding model evolution and operational continuity by adding full guides for model diff, persistent ZINGG ID reassignment, and clarifying explainOutput behavior.
Changes:
- Added a comprehensive guide for the
diffphase, including CLI/Python usage and config examples. - Replaced the placeholder persistent ID page with a full
reassignZinggIdguide (motivation, workflow, usage examples, configs). - Updated
explainOutputdocs to userunIncrementaland added notes clarifying its current focus on probabilistic matches.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
| docs/stepbystep/createtrainingdata/modeldiff.md | Replaces placeholder with an end-to-end “diff” guide (usage, configs, output). |
| docs/persistentZinggId.md | Fixes page title and adds a detailed “reassignZinggId” guide (usage, configs, behavior). |
| docs/explainoutput/README.md | Renames incremental phase reference and documents explainOutput scope/limitations. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+366
to
+379
| "deterministicMatching": [ | ||
| { | ||
| "matchCondition": [ | ||
| {"fieldName": "fname"}, | ||
| {"fieldName": "stNo"}, | ||
| {"fieldName": "add1"} | ||
| ] | ||
| }, | ||
| { | ||
| "matchCondition": [ | ||
| {"fieldName": "ssn"} | ||
| ] | ||
| } | ||
| ], |
There was a problem hiding this comment.
The narrative/Python example says deterministic matching rules are added in the new configuration, but in the JSON samples the deterministicMatching block appears under the Original Configuration (configBaseline.json). Please align the examples (either move deterministicMatching to the updated config sample or adjust the explanation) to avoid misleading readers about what changed between the models.
Suggested change
| "deterministicMatching": [ | |
| { | |
| "matchCondition": [ | |
| {"fieldName": "fname"}, | |
| {"fieldName": "stNo"}, | |
| {"fieldName": "add1"} | |
| ] | |
| }, | |
| { | |
| "matchCondition": [ | |
| {"fieldName": "ssn"} | |
| ] | |
| } | |
| ], |
Update documentation to clarify the required wrapper configuration for CLI operations and update example files/names. Key changes: use the sparkIncremental reassign example in persistentZinggId.md; explain that --conf must point to a wrapper config containing transformedOutputPath and that its name is an arbitrary internal identifier; change transformedOutputPath names to reassignedOutput and diffOutput in examples; add explanatory notes about wrapper usage; add deterministicMatching to the updated model example and remove the duplicate block from the baseline example; and clarify wording for ZINGG_ID_UPDATED/ORIGINAL in the diff output description.
This file contains hidden or 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
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.
Expand and improve documentation for explainOutput, persistent ZINGG ID reassignments, and model diff. Changes include:
closes #1272