feat: Add component CSVDocumentCleaner for removing empty rows and columns #8816
+262
−2
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
sjrl
requested review from
dfokina and
vblagoje
and removed request for
a team
Pull Request Test Coverage Report for Build 13157297160Details
💛 - Coveralls |
| from .document_cleaner import DocumentCleaner | ||
| from .document_splitter import DocumentSplitter | ||
| from .recursive_splitter import RecursiveDocumentSplitter | ||
| from .text_cleaner import TextCleaner | ||
|
|
||
| __all__ = ["DocumentSplitter", "DocumentCleaner", "RecursiveDocumentSplitter", "TextCleaner"] | ||
| __all__ = ["DocumentSplitter", "DocumentCleaner", "RecursiveDocumentSplitter", "TextCleaner", "CSVDocumentCleaner"] |
There was a problem hiding this comment.
(nit) suggestion: let's keep this list ordered alphabetically as it grows makes it easier to locate components
| from io import StringIO | ||
| from typing import Dict, List | ||
|
|
||
| import pandas as pd |
There was a problem hiding this comment.
since we are probably removing pandas as a hard dependency, we should start importing it in a lazy way
| --- | ||
| features: | ||
| - | | ||
| Introduced CSVDocumentCleaner component for cleaning CSV documents. |
There was a problem hiding this comment.
Suggested change
| Introduced CSVDocumentCleaner component for cleaning CSV documents. | |
| Introduced `CSVDocumentCleaner` component for cleaning CSV documents. |
| cleaned_documents.append(document) | ||
| continue | ||
|
|
||
| # Save ignored rows |
There was a problem hiding this comment.
I would refactor the save ignored rows (and also save ignored columns) logic into helper functions - too keep this for loop concise.
def _handle_ignored_rows(data_frame) -> Tuple[df_saved_rows | None, bool]:Returning the saved rows/columns or None and True/False depending on the number of rows/columns to ignore is smaller/bigger than the total number of rows
Both use cases (row and columns) can even be handled by a single function.
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.
Related Issues
Proposed Changes:
Adds a new component called
CSVDocumentCleaner.This component is for cleaning CSV documents by removing empty rows and columns. Removing empty rows and columns can help reduce unnecessary token usage when sending this CSV document to an LLM in a RAG pipeline.
It allows for the optional ignoring of a specified number of rows and columns before performing the cleaning operation. This is relevant if you want to ignore header rows or columns (e.g. the header of an Excel file) before removing empty rows or columns.
How did you test it?
Added tests.
Notes for the reviewer
Checklist
fix:,feat:,build:,chore:,ci:,docs:,style:,refactor:,perf:,test:and added!in case the PR includes breaking changes.