feat(seaborn): implement psychrometric-basic

[github-actions]

Implementation: psychrometric-basic - seaborn

Implements the seaborn version of psychrometric-basic.

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

Parent Issue: #4583

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays a psychrometric chart with dry-bulb temperature (-10 to 50°C) on the x-axis and humidity ratio (0-30 g/kg dry air) on the y-axis. Blue curves represent relative humidity lines from 10% to 100%, with the saturation curve (100% RH) drawn thicker. Purple dashed diagonal lines show constant wet-bulb temperatures (0-30°C). Red dash-dot diagonal lines show constant enthalpy values (10-110 kJ/kg). Green dotted near-vertical lines show constant specific volume (0.78-0.94 m³/kg). A light blue shaded rectangle marks the comfort zone (~20-26°C, 30-60% RH) with bold "Comfort Zone" label. An orange HVAC process path with arrows connects three labeled state points: A (35°C, 50%) → B (13°C, 100%) → C (24°C, 50%), illustrating cooling, dehumidification, and reheat. A legend in the upper left explains line types. The title reads "psychrometric-basic · seaborn · pyplots.ai". Top and right spines are removed, with subtle grid lines on both axes.

Score: 0/100

AUTO-REJECT: AR-05 — Library Not Used

The implementation does not import or use seaborn at all. All plotting is done with raw matplotlib (ax.plot(), ax.fill(), ax.annotate(), ax.text()). For a seaborn implementation, seaborn plotting functions (e.g., sns.lineplot(), sns.scatterplot()) must be used — styling-only usage (sns.set_style()) is not sufficient.

Category	Score	Max
Visual Quality	0	30
Design Excellence	0	20
Spec Compliance	0	15
Data Quality	0	15
Code Quality	0	10
Library Mastery	0	10
Total	0	100

Visual Quality (0/30)

• VQ-01: Text Legibility (0/8) — AR-05 override
• VQ-02: No Overlap (0/6) — AR-05 override
• VQ-03: Element Visibility (0/6) — AR-05 override
• VQ-04: Color Accessibility (0/4) — AR-05 override
• VQ-05: Layout & Canvas (0/4) — AR-05 override
• VQ-06: Axis Labels & Title (0/2) — AR-05 override

Design Excellence (0/20)

• DE-01: Aesthetic Sophistication (0/8) — AR-05 override
• DE-02: Visual Refinement (0/6) — AR-05 override
• DE-03: Data Storytelling (0/6) — AR-05 override

Spec Compliance (0/15)

• SC-01: Plot Type (0/5) — AR-05 override
• SC-02: Required Features (0/4) — AR-05 override
• SC-03: Data Mapping (0/3) — AR-05 override
• SC-04: Title & Legend (0/3) — AR-05 override

Data Quality (0/15)

• DQ-01: Feature Coverage (0/6) — AR-05 override
• DQ-02: Realistic Context (0/5) — AR-05 override
• DQ-03: Appropriate Scale (0/4) — AR-05 override

Code Quality (0/10)

• CQ-01: KISS Structure (0/3) — AR-05 override
• CQ-02: Reproducibility (0/2) — AR-05 override
• CQ-03: Clean Imports (0/2) — AR-05 override
• CQ-04: Code Elegance (0/2) — AR-05 override
• CQ-05: Output & API (0/1) — AR-05 override

Library Mastery (0/10)

• LM-01: Idiomatic Usage (0/5) — AR-05 override
• LM-02: Distinctive Features (0/5) — AR-05 override

Score Caps Applied

• AR-05: Library not used — seaborn is not imported or used anywhere in the implementation

Strengths

• Comprehensive psychrometric calculations using ASHRAE-based formulas
• All spec-required property lines are present (RH, wet-bulb, enthalpy, specific volume)
• HVAC process path with labeled state points tells a clear engineering story
• Comfort zone is properly highlighted
• Good color differentiation between curve types
• Direct labeling of property lines on the chart

Weaknesses

• CRITICAL: No seaborn usage — the entire implementation uses only matplotlib and numpy
• Uses 5 helper functions violating KISS structure (CQ-01)
• Specific volume calculation uses inefficient brute-force search instead of analytical solution
• Some label overlap in the upper-right area where RH% labels crowd together
• Some annotations (specific volume at 6pt, enthalpy at 6pt) are very small

Issues Found

1. AR-05 CRITICAL: No seaborn import or usage — implementation is pure matplotlib
   • Fix: Import seaborn, use sns.lineplot() for drawing curves, use sns.set_theme() or sns.set_style() for styling, use sns.scatterplot() for state points
2. CQ-01 LOW: Code uses 5 helper functions instead of flat KISS structure
   • Fix: Inline the simpler calculations or reduce to minimum necessary functions
3. VQ-02 MODERATE: Some label overlap in upper chart area
   • Fix: Adjust label positions or reduce label density for crowded regions

AI Feedback for Next Attempt

CRITICAL: This implementation must use seaborn plotting functions — not just matplotlib. Import seaborn and use sns.lineplot() for the property curves, sns.scatterplot() for state points, and sns.set_theme()/sns.set_style() for styling. The underlying chart logic and data are good, but the library requirement is non-negotiable. Additionally, flatten the code structure to avoid helper functions (KISS principle), and fix label overlap in crowded regions.

Verdict: REJECTED

[github-actions]

❌ AI Review Failed

The AI review action completed but did not produce valid output files.

What happened:

• The Claude Code Action ran
• No quality_score.txt file was created
• No review data was extracted

Action required:
Re-run the impl-review workflow manually:

gh workflow run impl-review.yml -f pr_number=4886

---

🤖 impl-review