update(pie-basic): altair — comprehensive quality review

[MarkusNeusinger]

Summary

Updated altair implementation for pie-basic.

Changes: Comprehensive review improving code quality, data choice, visual design, spec compliance, and library feature usage.

Test Plan

• Preview images uploaded to GCS staging
• Implementation file passes ruff format/check
• Metadata YAML updated with current versions
• Automated review triggered

---

Generated with Claude Code /update command

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays a pie chart titled "pie-basic · altair · pyplots.ai" with the subtitle "Global Cloud Infrastructure Market Share". Six slices represent cloud providers: AWS (31%, dark blue/Python Blue), Azure (24%, golden yellow), Google Cloud (11%, teal), Alibaba (4%, coral/salmon), Oracle (3%, light teal), and Others (27%, gray). Percentage labels are positioned outside each slice in bold text. White stroke lines separate the slices with subtle corner radius and pad angle for visual separation. A horizontal legend at the bottom lists all six providers with colored circles. The pie occupies the upper portion of the square canvas with significant whitespace between the chart and the bottom legend.

Quality Score: 81/100

Criteria Checklist

Visual Quality (26/30)

• VQ-01: Text Legibility (8/8) — All font sizes explicitly set: title 28pt, subtitle 20pt, legend title 20pt, legend labels 18pt, text labels 21pt. All perfectly readable.
• VQ-02: No Overlap (6/6) — No overlapping text. Percentage labels positioned outside slices with adequate spacing.
• VQ-03: Element Visibility (5/6) — Slices are visible but Alibaba (4%) and Oracle (3%) are quite thin. No exploded slice to add emphasis.
• VQ-04: Color Accessibility (4/4) — Colorblind-safe palette with blue, yellow, teal, coral, light teal, gray. Good contrast between adjacent slices.
• VQ-05: Layout Balance (2/4) — Pie sits in upper portion of canvas with large whitespace gap between chart and bottom legend. Layout feels top-heavy.
• VQ-06: Axis Labels & Title (1/2) — Title and subtitle are descriptive. No axes on pie chart; subtitle provides context but no unit annotation.

Design Excellence (11/20)

• DE-01: Aesthetic Sophistication (5/8) — Custom Python Blue-first palette, padAngle separation, cornerRadius polish, white strokes. Above defaults but not publication-exceptional.
• DE-02: Visual Refinement (4/6) — Clean view with no frame (strokeWidth=0), horizontal legend layout, white slice separators. Some refinement visible.
• DE-03: Data Storytelling (2/6) — Percentages are displayed but no annotations highlight insights (e.g., AWS as market leader, "Others" being second-largest). Viewer must find their own story.

Spec Compliance (13/15)

• SC-01: Plot Type (5/5) — Correct chart type: pie chart with proportional slices.
• SC-02: Required Features (2/4) — Percentage labels ✓, distinct colors ✓, legend ✓. MISSING: "Slightly explode the largest or smallest slice for emphasis" per spec.
• SC-03: Data Mapping (3/3) — Categories mapped to slices, values mapped to angles via theta encoding.
• SC-04: Title & Legend (3/3) — Title format "pie-basic · altair · pyplots.ai" correct. Legend labels match data categories.

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) — Six categories with good range of proportions (3% to 31%). No exploded slice to demonstrate emphasis variation.
• DQ-02: Realistic Context (5/5) — Cloud infrastructure market share is a real, neutral, well-known business scenario with plausible values.
• DQ-03: Appropriate Scale (4/4) — Values sum to 100%, proportions approximate real-world cloud market shares.

Code Quality (9/10)

• CQ-01: KISS Structure (3/3) — Clean flow: imports → data → processing → chart → save. No functions/classes.
• CQ-02: Reproducibility (2/2) — Deterministic hardcoded data, no randomness.
• CQ-03: Clean Imports (2/2) — Only altair and pandas imported, both fully used.
• CQ-04: Code Elegance (1/2) — Clean but the base chart + layering pattern is slightly verbose for this simple pie.
• CQ-05: Output & API (1/1) — Saves as plot.png and plot.html. No deprecated functions.

Library Mastery (8/10)

• LM-01: Idiomatic Usage (5/5) — Declarative encoding, theta with stack=True, alt.layer for text overlay, mark_arc, alt.Title, configure_view. Expertly idiomatic.
• LM-02: Distinctive Features (3/5) — Uses padAngle, cornerRadius, layer composition, and HTML export. These are Altair-specific but fairly standard for pie charts.

Strengths

• Excellent text legibility with all font sizes explicitly set
• Idiomatic Altair usage with declarative encoding, layer composition, and proper theta encoding
• Realistic cloud market share data with plausible, well-known values
• Colorblind-safe custom palette anchored with Python Blue
• Polished slice styling with padAngle separation and cornerRadius

Weaknesses

• Missing exploded slice for emphasis as required by specification ("Slightly explode the largest or smallest slice for emphasis")
• Large whitespace gap between pie chart and bottom legend creates unbalanced layout — pie should be more centered or legend closer
• No data storytelling: no annotations highlighting AWS as market leader or calling out that "Others" collectively ranks second
• Small slices (Alibaba 4%, Oracle 3%) are very thin and could benefit from the exploded slice treatment for visibility

Verdict: REJECTED

[Copilot]

Pull request overview

This PR updates the altair implementation for the pie-basic specification with a comprehensive quality review. The changes include improvements to data choice (switching from budget allocation to cloud provider market share), visual design enhancements (padAngle, cornerRadius, horizontal legend), and metadata updates (Python 3.14.0, claude-opus-4-6 generator). Minor specification updates add clarification about data requirements and slice explosion guidance.

Changes:

• Updated altair implementation with improved data, visual polish, and horizontal legend layout
• Modified specification to clarify data requirements and explosion guidance
• Updated metadata with new Python/generator versions and null quality score

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

File	Description
plots/pie-basic/specification.yaml	Added "comparison" feature tag
plots/pie-basic/specification.md	Clarified data requirements and explosion guidance (positive values, meaningful whole, largest/smallest slice)
plots/pie-basic/metadata/altair.yaml	Updated to Python 3.14.0, claude-opus-4-6, set quality_score to null
plots/pie-basic/implementations/altair.py	Comprehensive update: cloud provider data, horizontal legend, visual polish (padAngle, cornerRadius), subtitle added

[Copilot]

The docstring header format is inconsistent with other implementations in the codebase. Other implementations use triple-quotes with a space: """ pyplots.ai while this uses no space: """pyplots.ai. For consistency, the header should match the format seen in matplotlib.py, plotly.py, and other implementations.

[Copilot]

The specification requires "Slightly explode the largest or smallest slice for emphasis" (specification.md line 27), but the implementation does not include any slice explosion. In matplotlib.py this is implemented using the explode parameter, and in plotly.py using the pull parameter. Altair does not have direct explosion support in mark_arc, but this requirement should either be implemented through a workaround or documented as a library limitation.

[github-actions]

🔧 Repair Attempt 1/3

Applied fixes based on AI review feedback.

Status: Repair completed, re-triggering review...

---

🤖 impl-repair

[claude]

AI Review - Attempt 2/3

Image Description

The plot displays a pie chart titled "pie-basic · altair · pyplots.ai" with a subtitle "Global Cloud Infrastructure Market Share" on a square canvas. Six slices represent cloud providers: AWS (dark blue, 31%), Azure (golden yellow, 24%), Others (gray, 27%), Google Cloud (teal, 11%), Alibaba (coral/salmon, 4%), and Oracle (light teal, 3%). The AWS slice is slightly exploded outward for emphasis. Percentage labels (bold, ~21pt) are positioned outside each slice. Two italic annotations provide narrative context: "AWS leads at 31% — largest single provider" in blue near the upper-right, and '"Others" at 27% collectively outpace all but AWS' in gray near the lower-left. A horizontal legend at the bottom lists all six providers with colored dots. White stroke borders separate slices with subtle rounded corners and padding.

Quality Score: 85/100

Criteria Checklist

Visual Quality (26/30)

• VQ-01: Text Legibility (8/8) — all font sizes explicitly set: title 28pt, subtitle 20pt, legend title 20pt, legend labels 18pt, percentage labels 21pt, annotations 16pt
• VQ-02: No Overlap (5/6) — mostly clean, but percentage labels for small slices (3%, 4%, 11%) are crowded on the left side
• VQ-03: Element Visibility (6/6) — all slices clearly visible, even the smallest (Oracle 3%)
• VQ-04: Color Accessibility (4/4) — colorblind-safe palette with blue, yellow, teal, coral, gray — no red-green confusion
• VQ-05: Layout Balance (2/4) — pie is shifted upper-left, significant gap between chart and bottom legend, legend feels isolated
• VQ-06: Axis Labels & Title (1/2) — descriptive subtitle, no axes applicable for pie chart

Design Excellence (14/20)

• DE-01: Aesthetic Sophistication (6/8) — custom palette with Python Blue, white stroke borders, cornerRadius, padAngle polish; strong but not quite publication-perfect
• DE-02: Visual Refinement (4/6) — clean view (strokeWidth=0), subtle slice separations, good typography hierarchy; bottom legend spacing could be tighter
• DE-03: Data Storytelling (4/6) — two annotations guide the viewer to key insights (AWS leadership, Others collective size); good narrative, though annotation positioning could be more balanced

Spec Compliance (14/15)

• SC-01: Plot Type (5/5) — correct pie chart with proportional slices
• SC-02: Required Features (3/4) — percentage labels, distinct colors, legend, and exploded slice all present; explosion effect is subtle (radius overlay rather than true displacement)
• SC-03: Data Mapping (3/3) — categories to slices, values to angles, all correct
• SC-04: Title & Legend (3/3) — correct format "pie-basic · altair · pyplots.ai", legend labels match data

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) — good variety of slice sizes from 3% to 31%; demonstrates large, medium, and small slices well
• DQ-02: Realistic Context (5/5) — cloud infrastructure market share is real, well-known, neutral scenario with plausible values
• DQ-03: Appropriate Scale (4/4) — values sum to 100%, realistic for actual cloud market share

Code Quality (9/10)

• CQ-01: KISS Structure (3/3) — imports → data → chart → save, no functions/classes
• CQ-02: Reproducibility (2/2) — deterministic hardcoded data
• CQ-03: Clean Imports (2/2) — only altair and pandas, both used
• CQ-04: Code Elegance (1/2) — slightly verbose: exploded slice duplicates encoding logic in a separate Chart layer
• CQ-05: Output & API (1/1) — saves plot.png and plot.html

Library Mastery (8/10)

• LM-01: Idiomatic Usage (4/5) — good declarative API use with layered composition, theta encoding, transform_filter
• LM-02: Distinctive Features (4/5) — leverages Altair-specific features: declarative layer composition, transform_filter for exploded slice, mark_arc with padAngle/cornerRadius, tooltip encoding

Strengths

• Explicit font sizing across all text elements ensures excellent readability at target resolution
• Thoughtful annotations add data storytelling with AWS leadership and "Others" collective insight
• Custom color palette with Python Blue lead, cohesive and colorblind-safe
• Good use of Altair's layered composition pattern for the exploded slice effect
• Realistic, neutral data context (cloud market share) with plausible values
• Visual polish: white stroke borders, cornerRadius, padAngle create refined slice separation

Weaknesses

• Layout balance is off — pie chart sits upper-left with too much empty space below it before the legend; the legend feels detached from the chart
• Percentage labels for small adjacent slices (3%, 4%, 11%) crowd together on the left side of the pie, reducing readability
• The exploded slice effect for AWS is quite subtle — it's hard to distinguish the "explosion" visually; consider increasing the offset or using a different approach for more emphasis

Verdict: REJECTED

[github-actions]

🔧 Repair Attempt 2/3

Applied fixes based on AI review feedback.

Status: Repair completed, re-triggering review...

---

🤖 impl-repair

[claude]

AI Review - Attempt 3/3

Image Description

The plot displays a pie chart titled "pie-basic · altair · pyplots.ai" with subtitle "Global Cloud Infrastructure Market Share". Six slices represent cloud providers: AWS (dark blue, 31%), Azure (yellow, 24%), Google Cloud (teal, 11%), Alibaba (coral/pink, 4%), Oracle (light green, 3%), and Others (gray, 27%). The AWS slice is visibly exploded (offset) from the center to emphasize it as the largest provider. Percentage labels are positioned outside each slice in bold text. Two italic annotations provide narrative: "AWS leads at 31% — largest single provider" in blue (top right) and '"Others" at 27% collectively outpace all but AWS' in gray (bottom left). A horizontal legend at the bottom lists all six providers with colored symbols. The background is clean white with no grid lines or axes.

Quality Score: 90/100

Criteria Checklist

Visual Quality (27/30)

• VQ-01: Text Legibility (8/8) - All font sizes explicitly set: title 28pt, subtitle 20pt, legend title 20pt, legend labels 18pt, percentage labels 21pt bold. All perfectly readable.
• VQ-02: No Overlap (5/6) - No significant overlap. Minor crowding between the 3% and 4% labels on small slices, but all remain readable.
• VQ-03: Element Visibility (5/6) - All slices visible. Oracle (3%) and Alibaba (4%) slices are thin but distinguishable thanks to stroke borders and padding.
• VQ-04: Color Accessibility (4/4) - Six distinct hues (blue, yellow, teal, coral, light green, gray) with good luminance contrast. No red-green-only distinction.
• VQ-05: Layout Balance (3/4) - Pie chart is well-centered and fills a good portion of the canvas. Slight asymmetry with more whitespace on the left side.
• VQ-06: Axis Labels & Title (2/2) - Descriptive title and subtitle. No axes needed for pie chart.

Design Excellence (16/20)

• DE-01: Aesthetic Sophistication (6/8) - Custom Python Blue-first palette, professional typography hierarchy, white stroke borders with corner radius on arcs, intentional padding. Clearly above defaults.
• DE-02: Visual Refinement (5/6) - View stroke removed, clean background, horizontal legend at bottom, exploded slice adds emphasis, cornerRadius and padAngle polish the arcs.
• DE-03: Data Storytelling (5/6) - Two annotations guide interpretation: AWS as market leader and Others collectively outpacing most providers. Exploded slice reinforces the narrative.

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) - Correct pie chart type.
• SC-02: Required Features (4/4) - Percentage labels on slices ✓, distinct colors ✓, legend ✓, exploded largest slice ✓. All spec features present.
• SC-03: Data Mapping (3/3) - Category mapped to color, value mapped to theta angle. Correct.
• SC-04: Title & Legend (3/3) - Title format "pie-basic · altair · pyplots.ai" correct. Legend labels match data.

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) - Good variation in slice sizes from large (31%) to very small (3%). Shows the range of proportional representation well.
• DQ-02: Realistic Context (5/5) - Cloud infrastructure market share is a real, neutral, comprehensible business scenario.
• DQ-03: Appropriate Scale (4/4) - Values are realistic (approximate actual market data), positive, and sum to 100%.

Code Quality (9/10)

• CQ-01: KISS Structure (3/3) - Follows imports → data → plot → save pattern. No functions or classes.
• CQ-02: Reproducibility (2/2) - Deterministic hardcoded data. No random generation needed.
• CQ-03: Clean Imports (2/2) - Only altair and pandas imported, both used.
• CQ-04: Code Elegance (1/2) - Clean overall but the split into separate AWS/non-AWS layers for both arcs and text labels creates some duplication, though this is necessary for the exploded slice technique.
• CQ-05: Output & API (1/1) - Saves as plot.png with scale_factor=3.0 and plot.html.

Library Mastery (9/10)

• LM-01: Idiomatic Usage (5/5) - Expertly uses Altair's declarative grammar: alt.Chart, mark_arc, encode with Theta/Color/Order, transform_filter, alt.layer composition, Scale with domain/range, Legend configuration.
• LM-02: Distinctive Features (4/5) - Uses radiusOffset for exploded slice (Altair-specific), padAngle and cornerRadius on arcs, alt.datum for filter expressions, alt.value() for absolute positioning. These leverage Altair's declarative approach distinctively.

Strengths

• Excellent use of Altair's radiusOffset for the exploded AWS slice — a clean declarative approach
• Two well-placed annotations that add genuine narrative context to the data
• Custom color palette with Python Blue first, professional typography hierarchy with explicit font sizes
• Perfect spec compliance: all four requirements (percentage labels, distinct colors, legend, exploded slice) are met
• Realistic cloud market share data that makes the chart immediately comprehensible
• Clean visual refinement: cornerRadius, padAngle, white strokes, and removed view borders

Weaknesses

• Minor label crowding between the 3% and 4% percentage labels on the smallest slices
• Some code duplication from splitting AWS and non-AWS into separate arc + text layers (4 layers instead of potentially 2 with conditional encoding)
• Slight layout asymmetry with more whitespace on the left side of the canvas

Verdict: APPROVED