Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: correctly set holiday feature to 1 for all holiday dates #175

Merged
merged 1 commit into from
Nov 20, 2024

Conversation

sd2k
Copy link
Collaborator

@sd2k sd2k commented Nov 20, 2024

Prior to this commit, the holiday feature was only set to 1 for the
first occurrence of a holiday date. This meant that the holiday
effect was only applied to predictions for that single datetime
in the dataframe, rather than all dates in the dataframe that
were on the holidays.

This commit fixes that by iterating over all dates in the dataframe
that are on the holiday, and setting the holiday feature to 1.0 for
those dates.

Summary by CodeRabbit

  • New Features

    • Enhanced holiday feature generation by identifying multiple occurrences of holidays in the dataset, allowing for more accurate modeling.
    • Updated logic ensures all relevant holiday dates are marked correctly in the feature matrix.
  • Documentation

    • Minor adjustments made to comments for clarity on the new holiday occurrence handling logic.

Prior to this commit, the holiday feature was only set to 1 for the
first occurrence of a holiday date. This meant that the holiday
effect was only applied to predictions for that single datetime
in the dataframe, rather than all dates in the dataframe that
were on the holidays.

This commit fixes that by iterating over all dates in the dataframe
that are on the holiday, and setting the holiday feature to 1.0 for
those dates.
Copy link
Contributor

coderabbitai bot commented Nov 20, 2024

Walkthrough

The changes primarily focus on the make_holiday_features method within the Prophet struct in the prep.rs file. The method's logic for identifying holiday occurrences in the dataset has been modified from using a single occurrence check to a loop that allows for multiple indices to be identified. This enables the method to set holiday column values to 1.0 for all relevant occurrences instead of just the first one, improving the accuracy of holiday feature generation. Minor comment adjustments were also made to reflect these changes.

Changes

File Path Change Summary
crates/augurs-prophet/src/prophet/prep.rs Updated make_holiday_features method to identify multiple holiday occurrences and adjust column values accordingly; minor comment updates.

Poem

In the garden where the holidays bloom,
The Prophet now counts each festive room.
With loops and checks, it marks every day,
Ensuring no joy is lost in the fray.
Hopping through data, with features so bright,
Celebrating each moment, a true delight! 🐇✨


📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL

📥 Commits

Reviewing files that changed from the base of the PR and between 1c1f24f and 07d3d73.

📒 Files selected for processing (1)
  • crates/augurs-prophet/src/prophet/prep.rs (1 hunks)
🔇 Additional comments (1)
crates/augurs-prophet/src/prophet/prep.rs (1)

690-694: LGTM! The fix correctly handles multiple holiday occurrences.

The implementation now properly sets the holiday feature to 1.0 for all matching dates by using the positions iterator to find all occurrences of a holiday date. This fixes the issue where only the first occurrence was being marked.

Let's verify the fix by checking for any other holiday-related code:

✅ Verification successful

Let me gather more context about the holiday feature implementation to ensure the fix is comprehensive.


Let me try a different approach to examine the holiday feature implementation.


The holiday feature implementation is correctly handling all occurrences

After examining the complete implementation, the fix is properly implemented and consistent with the rest of the codebase. The code:

  1. Correctly rounds down timestamps to the nearest day for comparison
  2. Properly handles holiday windows through the lower and upper bounds
  3. Uses positions iterator to find all matching dates within the time series
  4. Sets the holiday feature to 1.0 for each matching occurrence
🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Description: Search for holiday-related code to ensure consistent handling.
# Test: Search for holiday-related code. Expect: Only this occurrence of holiday feature setting.

rg -A 5 'holiday.*feature'

Length of output: 2565


Script:

#!/bin/bash
# Search for the complete implementation of make_holiday_features
ast-grep --pattern 'fn make_holiday_features($$$) {
  $$$
}'

Length of output: 62


Script:

#!/bin/bash
# Search for the complete implementation using ripgrep with context
rg -U "fn make_holiday_features" -A 50 "crates/augurs-prophet/src/prophet/prep.rs"

Length of output: 2450


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
🪧 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>, please review it.
    • 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 gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @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 using 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.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

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.

Copy link

Deploying augurs with  Cloudflare Pages  Cloudflare Pages

Latest commit: 07d3d73
Status: ✅  Deploy successful!
Preview URL: https://f451e7d6.augurs.pages.dev
Branch Preview URL: https://prophet-fix-holidays-with-su.augurs.pages.dev

View logs

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant