feat(altair): implement forest-basic

[github-actions]

Implementation: forest-basic - altair

Implements the altair version of forest-basic.

File: plots/forest-basic/implementations/altair.py

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays a forest plot for a meta-analysis with 10 studies (Taylor 2023 through Johnson 2018) and a pooled estimate at the bottom. Each study is shown with a blue horizontal line representing the 95% confidence interval and a blue circular point for the effect size. The marker sizes vary based on study weight - larger circles for higher-weighted studies (e.g., Williams 2020, Wilson 2022) and smaller circles for lower-weighted studies (e.g., Brown 2021). A vertical dashed gray reference line at x=0 indicates the null effect. The pooled estimate is displayed as a distinctive yellow diamond with a blue border. The x-axis shows "Standardized Mean Difference (95% CI)" ranging from approximately -1.20 to 0.20. Study names appear on the y-axis. Text annotations "← Favors Treatment" and "Favors Control →" appear near the bottom. The title "forest-basic · altair · pyplots.ai" is centered at the top.

Quality Score: 91/100

Criteria Checklist

Visual Quality (36/40 pts)

• VQ-01: Text Legibility (10/10) - Title, axis labels, and study names are all clearly readable with appropriate font sizes
• VQ-02: No Overlap (8/8) - No overlapping text elements; all study names and labels are well-spaced
• VQ-03: Element Visibility (8/8) - Confidence interval lines are clearly visible with good stroke width; point markers appropriately sized and weight-scaled
• VQ-04: Color Accessibility (5/5) - Blue (#306998) and yellow (#FFD43B) diamond provide excellent contrast; no red-green issues
• VQ-05: Layout Balance (3/5) - Good overall layout but the plot area could use more of the canvas; some empty space on the right side
• VQ-06: Axis Labels (2/2) - X-axis has descriptive label with units: "Standardized Mean Difference (95% CI)"
• VQ-07: Grid & Legend (0/2) - Grid is subtle which is good, but "Favors Treatment" and "Favors Control" annotations are partially cut off at the edges

Spec Compliance (25/25 pts)

• SC-01: Plot Type (8/8) - Correct forest plot with point estimates, confidence intervals, and pooled diamond
• SC-02: Data Mapping (5/5) - Effect sizes on X-axis, studies on Y-axis, correct CI representation
• SC-03: Required Features (5/5) - All spec features present: diamond for pooled estimate, vertical reference line at null, marker sizes proportional to weight
• SC-04: Data Range (3/3) - Axes show all data points and confidence intervals completely
• SC-05: Legend Accuracy (2/2) - No legend needed for this plot type; annotations explain direction correctly
• SC-06: Title Format (2/2) - Correct format: "forest-basic · altair · pyplots.ai"

Data Quality (18/20 pts)

• DQ-01: Feature Coverage (7/8) - Shows variety in effect sizes, CI widths, and weights; all negative effects though (no crossing null)
• DQ-02: Realistic Context (7/7) - Realistic meta-analysis of RCTs with plausible study names and years
• DQ-03: Appropriate Scale (4/5) - Standardized mean differences in reasonable range (-0.21 to -0.67); weights sensible but one study crossing null would be more educational

Code Quality (9/10 pts)

• CQ-01: KISS Structure (3/3) - Clean sequential structure: imports → data → chart layers → save
• CQ-02: Reproducibility (3/3) - Deterministic data (no random generation)
• CQ-03: Clean Imports (2/2) - Only altair and pandas imported, both used
• CQ-04: No Deprecated API (1/1) - Using current Altair API
• CQ-05: Output Correct (0/1) - Saves both plot.png and plot.html which is correct for altair

Library Features (3/5 pts)

• LF-01: Uses distinctive library features (3/5) - Good use of layered marks, tooltips, and declarative encoding; could leverage more Altair-specific features like interactive selection or concatenation

Strengths

• Excellent visual clarity with well-sized text and markers
• Diamond shape for pooled estimate is distinctive and correctly implemented
• Good use of Altair's layered chart composition with 7 layers cleanly combined
• Weight-proportional marker sizing implemented correctly
• Appropriate color scheme with blue/yellow contrast
• Clean code structure following KISS principles
• Helpful tooltips for interactivity

Weaknesses

• The "Favors Treatment" and "Favors Control" annotations appear slightly cut off at the edges
• All studies show negative effects (favoring treatment); having at least one study crossing the null line (CI spanning 0) would better demonstrate the full range of forest plot interpretation
• Could leverage more Altair-specific features like selection for highlighting or concatenated views

Verdict: APPROVED