Enhanced Summarization for DataFrames and Series #75
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Outdated suggestions cannot be applied.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 improves how we summarize
DataFrame
s andSeries
. The enhanced summarization allows GPT to understand the data structure and content better. This summarized format takes up about ~1,600 tokens, depending largely on how big the fields are in the sample. Long text fields do pose a problem. However, that's no different than the current implementation! Another thing that is hopefully a help to GPT -- we specify what level of sampling we're doing as well as the real size.Key Changes:
summarize_dataframe
andsummarize_series
functions to generate detailed summaries forDataFrame
s andSeries
respectively.DataFrame
s includes:Series
includes:Example output
Dataframe Summary
Number of Rows: 806
Number of Columns: 14
Column Information
Numerical Summary
Categorical Summary
Sample Data (5x14)