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

Update unintelligibility algorithm #242

Merged
merged 2 commits into from
Jan 6, 2025
Merged

Update unintelligibility algorithm #242

merged 2 commits into from
Jan 6, 2025

Conversation

dthaler
Copy link
Collaborator

@dthaler dthaler commented Jan 6, 2025

Treat any multiple of 60 as a hum frequency

Summary by CodeRabbit

  • New Features

    • Enhanced frequency detection logic with more precise hum frequency identification
    • Updated signal threshold for frequency analysis
  • Tests

    • Added unit test for verifying hum frequency detection across various input frequencies
  • Improvements

    • Adjusted minimum signal percentage from 30% to 25%
    • Made frequency detection method publicly accessible

Treat any multiple of 60 as a hum frequency

Signed-off-by: Dave Thaler <[email protected]>
Copy link

coderabbitai bot commented Jan 6, 2025

Walkthrough

The pull request introduces modifications to the FrequencyInfo class in the OrcanodeMonitor.Core namespace. The changes include updating the _defaultMinSignalPercent constant from 30 to 25 and modifying the IsHumFrequency method. The method's access modifier has been changed from private to public, and its implementation now includes a more detailed frequency checking mechanism with a tolerance constant. Additionally, a new test method named TestHumFrequencies has been added to validate the functionality of the updated method.

Changes

File Change Summary
OrcanodeMonitor/Core/FfmpegCoreAnalyzer.cs - Updated _defaultMinSignalPercent constant from 30 to 25
- Modified IsHumFrequency method implementation
- Changed method access modifier from private to public
Test/UnintelligibilityTests.cs - Added new test method TestHumFrequencies
- Includes assertions for various frequency values

Sequence Diagram

sequenceDiagram
    participant Caller
    participant FrequencyInfo
    Caller->>FrequencyInfo: IsHumFrequency(frequency)
    FrequencyInfo-->>Caller: Boolean result
    Note over FrequencyInfo: Check frequency against<br>hum frequency tolerance
Loading

Possibly related PRs

Poem

🐰 Frequencies dance, a musical delight,
Hum detection now shines so bright!
From private to public, the method takes flight,
Tolerance whispers, frequencies just right,
A rabbit's code melody, pure and tight! 🎵


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 generate docstrings to generate docstrings for this PR. (Beta)
  • @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

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

🧹 Nitpick comments (3)
Test/UnintelligibilityTests.cs (2)

40-40: Remove async if there are no asynchronous operations.

This test method is declared async but does not perform any awaits. Consider removing async to avoid potential confusion, or introduce asynchronous operations if required.


43-52: Add boundary test coverage near tolerance thresholds.

Currently, the tolerance is 1.0. You already test frequencies at 59.1 and 60.9, which are close to 60±1.0, but also consider more granular edges like 59.99 or 60.01 to ensure complete coverage of edge cases.

OrcanodeMonitor/Core/FfmpegCoreAnalyzer.cs (1)

128-133: Consider negative or unexpected frequency inputs.

This function doesn’t handle negative frequencies or zero, which may be irrelevant in normal usage, but either validate inputs or document assumptions that frequencies will always be positive.

📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 3fd7e39 and 2d5c271.

📒 Files selected for processing (2)
  • OrcanodeMonitor/Core/FfmpegCoreAnalyzer.cs (2 hunks)
  • Test/UnintelligibilityTests.cs (1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms (3)
  • GitHub Check: build_windows (Release)
  • GitHub Check: build_windows (Debug)
  • GitHub Check: Analyze (csharp)
🔇 Additional comments (2)
OrcanodeMonitor/Core/FfmpegCoreAnalyzer.cs (2)

101-102: Confirm or adjust the new minimum signal percent value.

The comment notes that known-unintelligible peaks at 21% and known-good is at 29%. Setting the default to 25% is in between, but confirm through testing that it doesn’t cause misclassification on borderline cases.


135-135: Good extension of method visibility.

Exposing IsHumFrequency(double frequency) publicly allows for accurate, reusable hum checks across the codebase and in tests.

Signed-off-by: Dave Thaler <[email protected]>
Copy link

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

🧹 Nitpick comments (1)
OrcanodeMonitor/Core/FfmpegCoreAnalyzer.cs (1)

129-136: Consider documenting and parameterizing the frequency tolerance.

The implementation looks solid, but a few improvements could make it more maintainable:

  1. Document why 1.0 Hz was chosen as the tolerance value
  2. Consider making the tolerance configurable via environment variable, similar to other thresholds in the class

Here's a suggested implementation:

+        // Tolerance in Hz for considering a frequency as a multiple of the hum frequency
+        const double _defaultHumFrequencyTolerance = 1.0;
+        private static double HumFrequencyTolerance
+        {
+            get
+            {
+                string? toleranceString = Environment.GetEnvironmentVariable("ORCASOUND_HUM_FREQUENCY_TOLERANCE");
+                return double.TryParse(toleranceString, out var tolerance) ? tolerance : _defaultHumFrequencyTolerance;
+            }
+        }

         private static bool IsHumFrequency(double frequency, double humFrequency)
         {
             Debug.Assert(frequency >= 0.0);
             Debug.Assert(humFrequency >= 0.0);
-            const double tolerance = 1.0;
+            double tolerance = HumFrequencyTolerance;
             double remainder = frequency % humFrequency;
             return (remainder < tolerance || remainder > (humFrequency - tolerance));
         }
📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 2d5c271 and 006ac02.

📒 Files selected for processing (2)
  • OrcanodeMonitor/Core/FfmpegCoreAnalyzer.cs (3 hunks)
  • Test/UnintelligibilityTests.cs (1 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
  • Test/UnintelligibilityTests.cs
⏰ Context from checks skipped due to timeout of 90000ms (3)
  • GitHub Check: build_windows (Release)
  • GitHub Check: build_windows (Debug)
  • GitHub Check: Analyze (csharp)
🔇 Additional comments (3)
OrcanodeMonitor/Core/FfmpegCoreAnalyzer.cs (3)

8-8: LGTM!

The addition of the System.Diagnostics import is necessary for the Debug.Assert statements used in the modified IsHumFrequency method.


102-103: LGTM! Well-documented threshold adjustment.

The new threshold of 25% is well-justified by the documented observations: it provides a balanced separation between known-unintelligible samples (max 21%) and known-good samples (min 29%).


138-138: LGTM! Implementation aligns with PR objectives.

The method correctly implements the requirement to treat multiples of both 50 Hz and 60 Hz as hum frequencies, maintaining compatibility with different power line frequencies worldwide.

@dthaler dthaler merged commit 5afcb66 into main Jan 6, 2025
8 checks passed
@dthaler dthaler deleted the hum branch January 6, 2025 16:03
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