#25 make the plots better

[Asifdotexe]

This PR aims to improve the plot's aesthetics.

Plot type	Old	New
Barplot
Histogram
Boxplot (Univariate)
Scatterplot
Boxplot (Bivariate)
Multivariate analysis

Summary by CodeRabbit

• New Features

  • Unified plot styling for a consistent look across all charts.
  • Chart directory can be provided as a string or path-like object; outputs now return relative file paths.

• Style

  • Enhanced visuals: clearer titles and axis labels, improved scatter transparency, diverging heatmap colormap with gridlines, consistent primary color usage, and bar annotations for categorical plots.

• Refactor

  • Standardized path handling for chart generation and saving.
  • Early checks and warnings when no numeric columns are available for multivariate plots.

[coderabbitai]

Walkthrough

Adds a new styling module and integrates it across univariate, bivariate, and multivariate plotting. All three plot generators now accept Path-like directories, use pathlib for path construction, return relative string paths, and apply standardized styling. Visual tweaks were made per plot type, and multivariate adds a guard for missing numeric columns.

Changes

Cohort / File(s)	Summary
Plot generation API and path handling src/dora/plots/bivariate.py, src/dora/plots/multivariate.py, src/dora/plots/univariate.py	Update generate_plots signatures to accept Union[str, Path] and return list[str]; convert charts_dir to Path; build save paths via pathlib; return relative string paths; invoke styling setup at start.
Per-plot visual adjustments src/dora/plots/bivariate.py	Add scatter alpha, titles/axis labels, and PRIMARY_COLOR for categorical plots; collect relative plot paths.
Heatmap and guards src/dora/plots/multivariate.py	Use diverging colormap, linewidths, descriptive title; compute relative path via Path.relative_to; add early exit with warning if no numeric columns.
Univariate aesthetics and annotations src/dora/plots/univariate.py	Apply PRIMARY_COLOR to hist/box/bar; enhanced titles/labels/grid; annotate bar counts; construct paths via Path and return relative strings.
Styling module introduction src/dora/plots/styling.py	Add constants PRIMARY_COLOR, GRAY_COLOR, BACKGROUND_COLOR, TEXT_COLOR; add apply_custom_styling() configuring seaborn style/palette and matplotlib rcParams.

Sequence Diagram(s)

sequenceDiagram
    autonumber
    participant Caller
    participant PlotModule as generate_plots(...)
    participant Styling as apply_custom_styling()
    participant FS as Filesystem
    participant Viz as Matplotlib/Seaborn

    Caller->>PlotModule: generate_plots(df, charts_dir, config_params)
    Note over PlotModule: New/changed: Path-like handling
    PlotModule->>Styling: apply_custom_styling()
    Styling-->>PlotModule: rcParams/seaborn configured

    PlotModule->>PlotModule: charts_dir_path = Path(charts_dir)
    alt For each feature/plot type
        PlotModule->>Viz: create plot (titles/labels/colors updated)
        Viz-->>PlotModule: Axes/Figure
        PlotModule->>FS: savefig(charts_dir_path / "...png")
        FS-->>PlotModule: file saved
        PlotModule->>PlotModule: collect relative string path
    end

    Note over PlotModule: Multivariate: guard if no numeric columns → early return
    PlotModule-->>Caller: list[str] of relative plot paths

Loading

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Poem

I hop through paths of Path and string,
With palettes set, I style everything.
A grid of plots, neat titles shine,
Heatmaps hum in a diverging line.
I nibble warnings, save each chart—
A tidy warren, artisanal art. 🐇🖼️

Pre-merge checks and finishing touches

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Title Check	❓ Inconclusive	The title “#25 make the plots better” references an issue and broadly indicates improvements to plotting, but it is too generic to convey the key updates such as adding custom styling, type-flexible path handling, and enhanced annotations across univariate, bivariate, and multivariate plots.	Please update the title to clearly summarize the main change in one concise sentence, for example: “Enhance plot generation with custom styling, Path support, and improved annotations.”

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

✨ Finishing touches

• 📝 Generate docstrings

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch 25-make-the-plots-better

---

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 48f74fa and b28bcd3.

📒 Files selected for processing (4)

• src/dora/plots/bivariate.py (3 hunks)
• src/dora/plots/multivariate.py (3 hunks)
• src/dora/plots/styling.py (1 hunks)
• src/dora/plots/univariate.py (3 hunks)

🧰 Additional context used

🧬 Code graph analysis (3)

src/dora/plots/univariate.py (3)

src/dora/plots/styling.py (1)

• apply_custom_styling (19-62)

src/dora/plots/bivariate.py (1)

• generate_plots (16-85)

src/dora/plots/multivariate.py (1)

• generate_plots (16-63)

src/dora/plots/bivariate.py (3)

src/dora/plots/styling.py (1)

• apply_custom_styling (19-62)

src/dora/plots/multivariate.py (1)

• generate_plots (16-63)

src/dora/plots/univariate.py (1)

• generate_plots (16-100)

src/dora/plots/multivariate.py (3)

src/dora/plots/styling.py (1)

• apply_custom_styling (19-62)

src/dora/plots/bivariate.py (1)

• generate_plots (16-85)

src/dora/plots/univariate.py (1)

• generate_plots (16-100)

🔇 Additional comments (14)

src/dora/plots/styling.py (3)

1-9: LGTM! Clear documentation and appropriate imports.

The module docstring effectively communicates the design philosophy, and the imports are minimal and well-chosen.

---

11-16: LGTM! Well-chosen color palette.

The color constants provide a cohesive, professional palette with good contrast and visual hierarchy.

---

19-61: LGTM! Well-structured styling configuration.

The function effectively centralizes visual styling with thoughtful choices:

• Removes chart clutter (top/right spines, tick marks)
• Adds appropriate padding for readability
• Uses accessible font choices with fallbacks

Note: The grid color is set to white ("grid.color": "#ffffff" on line 30) matching the white background, making the grid invisible. This appears intentional per the "de-cluttering" principle in the module docstring.

src/dora/plots/bivariate.py (3)

6-7: LGTM! Improved type annotations and imports.

The function signature now accepts both string and Path objects for charts_dir, improving flexibility while maintaining backward compatibility. The explicit return type annotation list[str] clarifies the API contract.

Also applies to: 13-13, 16-21

---

30-30: LGTM! Proper styling initialization and path handling.

The styling is applied early, ensuring consistent visual appearance. Converting charts_dir to a Path object enables robust path operations throughout the function.

Also applies to: 39-39

---

51-72: LGTM! Enhanced plot aesthetics and proper path handling.

The visual improvements are well-executed:

• Alpha transparency on scatter plots helps with overplotting
• Consistent title formatting across plot types
• Proper use of pathlib for path construction and relative path conversion

Note: The scatter plot doesn't explicitly use PRIMARY_COLOR like the boxplot does (line 64). This appears intentional to rely on matplotlib's default color cycle, which provides automatic color variation when multiple features are plotted.

Also applies to: 76-76, 80-80

src/dora/plots/multivariate.py (3)

6-7: LGTM! Consistent type annotations and imports.

The function signature now accepts both string and Path objects, aligning with the other plotting modules (univariate and bivariate) for a consistent API across the plotting subsystem.

Also applies to: 13-13, 16-18

---

27-27: LGTM! Consistent initialization pattern.

The styling application and path conversion follow the same pattern established in the univariate and bivariate modules, promoting consistency.

Also applies to: 29-29

---

47-54: LGTM! Effective heatmap styling improvements.

The visual enhancements are well-chosen:

• Diverging color palette (blue-to-red) is a standard, intuitive choice for correlation matrices
• Cell line widths improve readability by separating values
• Title formatting is consistent with the other plotting modules

The path operations correctly use pathlib's / operator and convert to relative paths for the return value.

Also applies to: 57-57, 60-60

src/dora/plots/univariate.py (5)

6-7: LGTM! Consistent API improvements.

The function signature and imports align perfectly with the patterns established in the bivariate and multivariate modules, ensuring a unified API across all plotting functions.

Also applies to: 13-13, 16-18

---

27-27: LGTM! Standard initialization pattern.

Consistent with the other plotting modules in applying styling early and converting the directory path.

Also applies to: 29-29

---

39-48: LGTM! Well-styled histogram with clear labeling.

The enhancements effectively improve readability:

• PRIMARY_COLOR ensures consistent visual branding
• Title formatting matches the other plot types
• Axis labels and grid aid interpretation

The grid is a particularly good addition for histograms, helping viewers align bins with the frequency axis.

---

51-58: LGTM! Effective boxplot styling.

The styling improvements are well-applied. Note that unlike the histogram (line 48), no grid is added for the boxplot. This is appropriate since boxplots are less dependent on precise axis alignment than histograms.

---

60-60: LGTM! Comprehensive barplot improvements and proper path handling.

The changes significantly enhance the barplot:

• Capturing the axes object (ax = sns.countplot(...)) enables the value annotations
• The annotations (lines 84-92) display count values directly on bars, improving accessibility
• Removing the y-axis label (line 82) is appropriate since the category names are self-explanatory
• Path operations correctly use pathlib throughout

This is a particularly effective enhancement, as the direct labeling reduces cognitive load for readers.

Also applies to: 64-64, 71-92, 94-94, 97-97

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[Asifdotexe]

@coderabbitai help

[coderabbitai]

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.
  • 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.
• 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 the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

CodeRabbit commands

These commands are invoked using PR/Issue 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 evaluate custom pre-merge check --instructions <custom-checks-instructions> --name <custom-checks-title> [--mode <error|warning>] to validate the custom pre-merge checks instructions. Defaults to error when --mode is omitted.
  • @coderabbitai ignore pre-merge checks to override pre-merge checks and get an approval on PR.
  • @coderabbitai run pre-merge checks to run pre-merge checks on the pull request.
• @coderabbitai generate docstrings to generate docstrings for this PR.
• @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
• @coderabbitai generate unit tests to generate unit tests for this PR.
• @coderabbitai resolve to 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 or @coderabbit 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

Status, support, documentation and community

• Visit our status page to check the current availability of CodeRabbit.
• Create a ticket on our support page for assistance with any issues or questions.
• Visit our documentation site for detailed information on how to use CodeRabbit.
• Join our Discord community to connect with other users and get help from the community.
• Follow us on X/Twitter for updates and announcements.