FEAT-#7254: Support right merge/join

[korbit-ai]

User description

What do these changes do?

Blocked on modin-project/modin#7251

Performance: 1.7 sec (the PR) vs 3.1 sec (on main) on Ray (8 cores)

import modin.pandas as pd
from time import time
import numpy as np
from modin.utils import execute

np.random.seed(42)

df1 = pd.DataFrame(np.random.randint(0, 100_000,size=(400_000, 64)))
df2 = pd.DataFrame(np.random.randint(0, 100_000,size=(400_000, 64)))
execute(df1)
execute(df2)


for _ in range(3):
    start = time()
    result = pd.merge(df1, df2, how="right", on=1)
    execute(result)
    print(f"{result.shape=}")
    print(f"merge time: {time()-start}")

• first commit message and PR title follow format outlined here

  NOTE: If you edit the PR title to match this format, you need to add another commit (even if it's empty) or amend your last commit for the CI job that checks the PR title to pick up the new PR title.

• passes flake8 modin/ asv_bench/benchmarks scripts/doc_checker.py
• passes black --check modin/ asv_bench/benchmarks scripts/doc_checker.py
• signed commit with git commit -s
• Resolves #7254
• tests added and passing
• module layout described at docs/development/architecture.rst is up-to-date

Description by Korbit AI

Note

This feature is in early access. You can enable or disable it in the Korbit Console.

What change is being made?

Add support for right merge/join in the row_axis_merge function within the Modin library.

Why are these changes being made?

This change addresses the need for right merge/join functionality, which was previously unsupported. The implementation ensures that the merge operation correctly handles the right join by swapping the left and right dataframes when necessary and adjusting the metadata computation accordingly. This approach maintains consistency and correctness in the merge results.

---

PR Type

enhancement

---

Description

• Added support for right merge/join by swapping the left and right operands when necessary.
• Introduced a reverted flag to manage operand swapping during the merge operation.
• Adjusted the computation of result metadata to account for the order of operands.
• Optimized the merge operation for cases where the left operand has a single partition.

---

Changes walkthrough 📝

	Relevant files
Enhancement	merge.py Add support for right merge/join with operand swapping      modin/core/storage_formats/pandas/merge.py Added logic to handle right merge/join by swapping operands. Introduced a reverted flag to track operand swapping. Adjusted metadata computation based on operand order. Optimized merge operation for specific conditions. +27/-4

---

💡 PR-Agent usage:
Comment /help on the PR to get a list of all available PR-Agent tools and their descriptions

Summary by CodeRabbit

• New Features

  • Enhanced DataFrame merging capabilities to optimize performance when merging single-partition DataFrames.
  • Added flexibility in merging logic by allowing for conditional swapping of input DataFrames based on predefined scenarios.

• Bug Fixes

  • Improved metadata computation for merged DataFrames, ensuring accurate representation of columns and data types regardless of merge order.

[korbit-ai]

Clone of the PR modin-project/modin#7226

[korbit-ai]

My review is in progress 📖 - I will have feedback for you in a few minutes!

[coderabbitai]

Important

Review skipped

Auto reviews are disabled on this repository.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Walkthrough

The changes to the row_axis_merge function in Modin enhance its efficiency by introducing a mechanism to swap input DataFrames during merge operations. This is particularly applicable for "inner" joins when the left DataFrame has only one partition. The adjustments streamline merging logic, potentially optimizing performance, while also ensuring accurate metadata computation based on the order of merged DataFrames.

Changes

Files	Change Summary
modin/core/storage_formats/pandas/merge.py	Updated row_axis_merge to introduce a reverted flag for swapping DataFrames in specific conditions, enhancing merging efficiency and ensuring accurate metadata calculation.

Sequence Diagram(s)

sequenceDiagram
    participant User
    participant MergeFunction
    participant MapFunc

    User->>MergeFunction: Call row_axis_merge(left, right)
    MergeFunction->>MapFunc: Check if "inner" join and single partition
    alt Condition met
        MergeFunction->>MergeFunction: Set reverted = True
        MergeFunction->>MapFunc: Call map_func(right, left)
    else
        MergeFunction->>MapFunc: Call map_func(left, right)
    end
    MapFunc->>MergeFunction: Return merged DataFrame
    MergeFunction->>User: Return result

Loading

Poem

In the burrow where data hops,
A merge so swift, it never stops.
With a twist and a turn, oh what a sight,
Data dances, left and right!
One partition, a clever swap,
Efficiency blooms, we all cheer and hop! 🐇✨

---

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

Share

• X
• Mastodon
• Reddit
• LinkedIn

Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai generate interesting stats about this repository and render them as a table.
  • @coderabbitai show all the console.log statements in this repository.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (invoked as PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Additionally, you can add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[korbit-ai]

I have reviewed your code and did not find any issues!

---

Please note that I can make mistakes, and you should still encourage your team to review your code as well.

[furwellness]

@coderabbitai review

[coderabbitai]

Actions performed

Review triggered.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

[furwellness]

/review

[codiumai-pr-agent-free]

PR Reviewer Guide 🔍

(Review updated until commit fa0ea6f)

⏱️ Estimated effort to review: 3 🔵🔵🔵⚪⚪

🧪 PR contains tests

🔒 No security concerns identified

⚡ Key issues to review Code Duplication The code for computing result metadata is duplicated with a slight variation. Consider refactoring to reduce duplication. Performance Concern The condition for swapping left and right dataframes might not be optimal. Consider if there are other scenarios where swapping could be beneficial.

[codiumai-pr-agent-free]

Persistent review updated to latest commit fa0ea6f

[furwellness]

@coderabbitai full review

[coderabbitai]

Actions performed

Full review triggered.

[codiumai-pr-agent-free]

PR Code Suggestions ✨

Category	Suggestion	Score
Maintainability	Extract repeated logic into a separate method to reduce duplication Consider extracting the logic for computing result metadata into a separate method to reduce code duplication and improve maintainability. modin/core/storage_formats/pandas/merge.py [181-198] -if not reverted: - new_columns, new_dtypes = cls._compute_result_metadata( - left, - right, - on, - left_on, - right_on, - kwargs.get("suffixes", ("_x", "_y")), - ) -else: - new_columns, new_dtypes = cls._compute_result_metadata( - right, - left, - on, - right_on, - left_on, - kwargs.get("suffixes", ("_x", "_y")), +def compute_metadata(left, right, on, left_on, right_on, suffixes): + return cls._compute_result_metadata( + left, right, on, left_on, right_on, suffixes ) +suffixes = kwargs.get("suffixes", ("_x", "_y")) +if not reverted: + new_columns, new_dtypes = compute_metadata(left, right, on, left_on, right_on, suffixes) +else: + new_columns, new_dtypes = compute_metadata(right, left, on, right_on, left_on, suffixes) + Apply this suggestion Suggestion importance[1-10]: 8 Why: Extracting the logic into a separate method reduces code duplication and enhances maintainability, making the code cleaner and easier to manage.	8
	Use a more descriptive variable name to improve code readability Consider using a more descriptive variable name instead of reverted. A name like is_inner_merge_with_single_left_partition would better explain the condition and improve code readability. modin/core/storage_formats/pandas/merge.py [132-135] -reverted = False +is_inner_merge_with_single_left_partition = False if how == "inner" and left._modin_frame._partitions.shape[0] == 1: left, right = right, left - reverted = True + is_inner_merge_with_single_left_partition = True Apply this suggestion Suggestion importance[1-10]: 7 Why: The suggestion to use a more descriptive variable name improves code readability and maintainability by clearly conveying the purpose of the variable, which is beneficial for future developers.	7
	Add a comment to explain the rationale behind setting the sort parameter to False Consider adding a comment explaining why the sort parameter is set to False when how is "left" or "inner" and both left_index and right_index are False. This would improve code understanding for future maintainers. modin/core/storage_formats/pandas/merge.py [129-130] if how in ["left", "inner"] and left_index is False and right_index is False: + # Setting sort to False for left and inner joins without index merging + # to optimize performance, as sorting is not necessary in these cases kwargs["sort"] = False Apply this suggestion Suggestion importance[1-10]: 5 Why: Adding a comment improves code understanding for future maintainers, but it is a minor enhancement as it does not change the functionality or structure of the code.	5
Enhancement	Simplify conditional logic using a ternary operator Consider using a ternary operator to simplify the conditional logic for the pandas merge operation, making the code more concise and easier to read. modin/core/storage_formats/pandas/merge.py [155-158] -if reverted: - df = pandas.merge(right, left, **kwargs) -else: - df = pandas.merge(left, right, **kwargs) +df = pandas.merge(right, left, **kwargs) if reverted else pandas.merge(left, right, **kwargs) Apply this suggestion Suggestion importance[1-10]: 6 Why: Using a ternary operator simplifies the conditional logic, making the code more concise and slightly easier to read, though the improvement is minor.	6

[coderabbitai]

Actionable comments posted: 0

Review details

Configuration used: CodeRabbit UI
Review profile: CHILL

Commits

Files that changed from the base of the PR and between b236b76 and fa0ea6f.

Files selected for processing (1)

• modin/core/storage_formats/pandas/merge.py (3 hunks)

Additional comments not posted (4)

modin/core/storage_formats/pandas/merge.py (4)

132-135: LGTM: Introduction of reverted flag.

The introduction of the reverted flag is a clear and effective way to handle specific merge conditions.

---

155-158: LGTM: Conditional logic in map_func.

The conditional logic in map_func based on the reverted flag ensures the correct order of DataFrame merging.

---

181-198: LGTM: Metadata computation adjustments.

The adjustments to the metadata computation correctly account for the reverted state, ensuring accurate metadata for the merged DataFrames.

---

Line range hint 199-222: LGTM: Consistency of repartitioning logic.

The repartitioning logic remains consistent with the new changes and optimizations in the merge operation.