feat(seaborn): implement forest-basic

[github-actions]

Implementation: forest-basic - seaborn

Implements the seaborn version of forest-basic.

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

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The forest plot displays a meta-analysis of 10 clinical studies showing treatment effect (mean difference) with horizontal confidence intervals. The plot uses a blue color scheme (#306998) for study markers and CI lines. Each study is represented with a circular marker whose size varies proportionally to study weight. Study names are listed on the left (e.g., "Johnson et al. 2019", "Brown et al. 2020"), while effect sizes with 95% CIs are shown on the right in monospace font (e.g., "-0.52 [-0.77, -0.27]"). A dashed vertical reference line at x=0 indicates the null effect. At the bottom, a yellow diamond shows the pooled estimate (-0.31 [-0.37, -0.24]). The title "forest-basic · seaborn · pyplots.ai" is prominently displayed at the top. Directional annotations "← Favors Treatment" and "Favors Control →" appear at the top of the plot area.

Quality Score: 92/100

Criteria Checklist

Visual Quality (37/40 pts)

• VQ-01: Text Legibility (10/10) - All text perfectly readable: title at 24pt, axis labels at 20pt, study names at 14pt, tick labels at 16pt
• VQ-02: No Overlap (8/8) - No overlapping elements; study labels, CIs, and effect sizes are well-spaced
• VQ-03: Element Visibility (8/8) - Marker sizes appropriately scaled by weight, CI lines clearly visible with good linewidth
• VQ-04: Color Accessibility (5/5) - Blue/yellow color scheme is colorblind-safe with good contrast
• VQ-05: Layout Balance (3/5) - Good use of canvas but some unused space on the right side could be reduced
• VQ-06: Axis Labels (2/2) - Descriptive x-axis label "Mean Difference (Treatment - Control)" with parenthetical context
• VQ-07: Grid & Legend (1/2) - Grid is subtle and appropriate; no legend needed for this plot type

Spec Compliance (25/25 pts)

• SC-01: Plot Type (8/8) - Correct forest plot with point estimates and confidence intervals
• SC-02: Data Mapping (5/5) - Effect sizes on x-axis, studies on y-axis with proper ordering
• SC-03: Required Features (5/5) - All required: diamond for pooled estimate, vertical reference line, weighted markers, CI whiskers
• SC-04: Data Range (3/3) - All data visible within axis limits
• SC-05: Legend Accuracy (2/2) - No legend needed; directional annotations serve informational purpose
• SC-06: Title Format (2/2) - Correct format: "forest-basic · seaborn · pyplots.ai"

Data Quality (18/20 pts)

• DQ-01: Feature Coverage (7/8) - Shows studies favoring treatment AND control, various CI widths, weighted markers, pooled estimate
• DQ-02: Realistic Context (7/7) - Realistic meta-analysis scenario with plausible study names and chronological years
• DQ-03: Appropriate Scale (4/5) - Effect sizes (-0.52 to +0.12) and CI widths are realistic for mean differences

Code Quality (9/10 pts)

• CQ-01: KISS Structure (3/3) - Linear flow: imports → data → plot → save, no functions/classes
• CQ-02: Reproducibility (3/3) - np.random.seed(42) is set
• CQ-03: Clean Imports (2/2) - All imports are used (matplotlib.patches, plt, np, pd, sns)
• CQ-04: No Deprecated API (0/1) - sns.set_style called after figure creation (order doesn't affect output but not idiomatic)
• CQ-05: Output Correct (1/1) - Saves as plot.png with correct parameters

Library Features (3/5 pts)

• LF-01: Uses distinctive library features (3/5) - Uses sns.scatterplot with size mapping and sns.despine, but CI lines use matplotlib directly

Strengths

• Excellent implementation of all forest plot requirements: diamond pooled estimate, weighted markers, reference line, CI whiskers
• Clear, professional layout with study labels and effect sizes displayed in readable format
• Good use of seaborn's scatterplot for weighted point estimates with size mapping
• Proper directional annotations help interpret the plot
• Realistic meta-analysis data with chronological study names and varied effect sizes

Weaknesses

• sns.set_style called after plt.subplots (should be called before for idiomatic seaborn usage)
• Layout could be slightly tighter on the right side to reduce whitespace

Verdict: APPROVED