feat(letsplot): implement line-reaction-coordinate

[github-actions]

Implementation: line-reaction-coordinate - letsplot

Implements the letsplot version of line-reaction-coordinate.

File: plots/line-reaction-coordinate/implementations/letsplot.py

Parent Issue: #4409

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays a reaction coordinate energy diagram with a smooth blue curve (#306998) tracing the energy profile from reactants (50 kJ/mol) through a transition state peak (120 kJ/mol) to products (20 kJ/mol). The title "line-reaction-coordinate · letsplot · pyplots.ai" is centered at the top. The y-axis is labeled "Potential Energy (kJ/mol)" ranging from 0 to 140, and the x-axis is labeled "Reaction Coordinate" with no tick marks (appropriate for arbitrary units). A red double-headed arrow on the left side indicates Ea = 70.0 kJ/mol between the reactant level and transition state. A green double-headed arrow on the right side indicates ΔH = -30.0 kJ/mol between reactant and product levels. Horizontal gray dashed lines mark the reactant (50) and product (20) energy levels. The background is clean white with subtle horizontal grid lines on the y-axis only. Text labels identify Reactants, Transition State, and Products with their energy values.

Score: 80/100

Category	Score	Max
Visual Quality	24	30
Design Excellence	13	20
Spec Compliance	15	15
Data Quality	14	15
Code Quality	10	10
Library Mastery	4	10
Total	80	100

Visual Quality (24/30)

• VQ-01: Text Legibility (7/8) - Font sizes explicitly set (title 24, axis title 20, axis text 16, annotation text 16). All readable, though annotation text could be slightly larger for the energy labels.
• VQ-02: No Overlap (5/6) - Minor overlap: "Ea = 70.0 kJ/mol" label overlaps slightly with the red arrow line; "Reactants" label is very close to the left edge and y-axis.
• VQ-03: Element Visibility (5/6) - Curve and arrows are visible and well-sized. The ΔH arrow is relatively short visually (spanning only 30 kJ/mol) compared to the Ea arrow, making it slightly less prominent.
• VQ-04: Color Accessibility (2/4) - Red (#C0392B) and green (#2E7D32) arrows are the classic red-green combination that is problematic for colorblind users (deuteranopia/protanopia). While contextual labels help, the color choice itself is not colorblind-safe.
• VQ-05: Layout & Canvas (3/4) - Good proportions overall. The curve and annotations use the canvas well, though there is some unused space in the lower-left quadrant.
• VQ-06: Axis Labels & Title (2/2) - Y-axis has "Potential Energy (kJ/mol)" with units. X-axis has "Reaction Coordinate" (unitless by nature).

Design Excellence (13/20)

• DE-01: Aesthetic Sophistication (5/8) - Thoughtful color choices for curve and annotations, clean theme with removed backgrounds. Above defaults but not publication-level exceptional.
• DE-02: Visual Refinement (4/6) - Panel/plot backgrounds removed, y-axis-only subtle grid, x-axis ticks removed, axis lines styled light gray. Good refinement effort.
• DE-03: Data Storytelling (4/6) - The diagram tells a clear chemistry story with labeled energy states and annotated energy differences. The visual hierarchy guides the viewer from reactants through the barrier to products.

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) - Correct reaction coordinate energy diagram with smooth curve and clear transition state maximum.
• SC-02: Required Features (4/4) - All spec features present: labeled reactants/products/transition state, Ea double-headed arrow, ΔH double-headed arrow, horizontal dashed lines, smooth curve, clean minimal style.
• SC-03: Data Mapping (3/3) - X=reaction coordinate, Y=potential energy. Correctly mapped.
• SC-04: Title & Legend (3/3) - Title follows exact format "line-reaction-coordinate · letsplot · pyplots.ai". No legend needed for single-series.

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) - Shows single-step exothermic reaction with activation barrier. Could additionally show an intermediate or catalyzed pathway for fuller coverage, but matches the spec example well.
• DQ-02: Realistic Context (5/5) - Chemistry context with plausible energy values. Neutral scientific topic.
• DQ-03: Appropriate Scale (4/4) - Values (50, 120, 20 kJ/mol) are realistic for a chemical reaction energy profile.

Code Quality (10/10)

• CQ-01: KISS Structure (3/3) - Linear flow: imports → data generation → plot construction → save. No functions or classes.
• CQ-02: Reproducibility (2/2) - Fully deterministic data (mathematical curve, no randomness).
• CQ-03: Clean Imports (2/2) - All imports used (numpy, pandas, lets_plot, ggsave).
• CQ-04: Code Elegance (2/2) - Clean implementation with well-structured Gaussian-based curve generation. Appropriate complexity.
• CQ-05: Output & API (1/1) - Saves as plot.png via ggsave with scale=3.

Library Mastery (4/10)

• LM-01: Idiomatic Usage (3/5) - Uses ggplot grammar correctly (aes, geom_line, geom_segment, geom_text, theme, labs). Correct but straightforward usage without leveraging advanced lets-plot patterns.
• LM-02: Distinctive Features (1/5) - Generic ggplot-style usage. The arrow() function in geom_segment is standard ggplot grammar, not distinctive to lets-plot. No lets-plot-specific features used.

Score Caps Applied

• None

Strengths

• Complete spec compliance with all required features (labels, arrows, dashed lines, smooth curve)
• Clean, deterministic data generation producing a scientifically accurate energy profile
• Good visual refinement with removed backgrounds, subtle grid, and clean axis styling
• Effective data storytelling with clear visual hierarchy for a chemistry diagram

Weaknesses

• Red-green color combination for Ea and ΔH arrows is not colorblind-safe
• Generic lets-plot usage without leveraging library-distinctive features
• Minor label positioning issues (Ea label overlaps arrow, Reactants label near edge)

Issues Found

1. VQ-04 LOW: Red-green arrow colors are problematic for colorblind users
   • Fix: Replace red/green with colorblind-safe alternatives (e.g., blue/orange, or dark red/dark blue)
2. LM-01 LOW: Straightforward ggplot usage without advanced lets-plot patterns
   • Fix: Consider using lets-plot-specific features like geom_label() for styled annotations, or theme_minimal2() for refined theming
3. LM-02 LOW: No distinctive lets-plot features used
   • Fix: Leverage lets-plot unique capabilities (e.g., geom_label with label_padding, interactive HTML tooltips via ggsave HTML export)
4. VQ-02 MINOR: Slight label positioning issues
   • Fix: Adjust annotation positions to avoid overlap with arrows and axes

AI Feedback for Next Attempt

Fix colorblind accessibility by replacing red/green arrows with colorblind-safe colors (e.g., #C0392B → #E67E22 orange, #2E7D32 → #2C3E50 dark). Improve library mastery by using lets-plot distinctive features like geom_label() for annotation boxes or flavor_*() theming. Adjust label positions to eliminate minor overlaps — move "Reactants" label slightly right and "Ea" label away from the arrow line.

Verdict: REJECTED

[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 reaction coordinate energy diagram with a smooth blue curve (#306998) tracing the energy profile from reactants (50 kJ/mol) on the left, rising through a Gaussian-shaped transition state peak (120 kJ/mol) near center, then descending to products (20 kJ/mol) on the right. A subtle light blue shaded area fills beneath the curve. An orange double-headed arrow on the left shows Ea = 70 kJ/mol with a bold white-on-orange label. A steel blue double-headed arrow on the right shows ΔH = -30 kJ/mol with a white-on-blue label. Reactants, Transition State, and Products are labeled in rounded boxes with light gray fill. Two horizontal dashed gray lines mark the 50 and 20 kJ/mol energy levels. The x-axis reads "Reaction Coordinate" with no tick marks (appropriate), the y-axis reads "Potential Energy (kJ/mol)" with values 0-140. The title "line-reaction-coordinate · letsplot · pyplots.ai" is centered and bold at the top. The panel background is a very subtle off-white (#FAFBFC) with faint horizontal gridlines.

Score: 91/100

Category	Score	Max
Visual Quality	29	30
Design Excellence	16	20
Spec Compliance	15	15
Data Quality	14	15
Code Quality	10	10
Library Mastery	7	10
Total	91	100

Visual Quality (29/30)

• VQ-01: Text Legibility (7/8) — All font sizes explicitly set (title=24, axis_title=20, axis_text=16, geom_label=15-16). All text clearly readable at output resolution.
• VQ-02: No Overlap (6/6) — All labels well-separated with no collisions. Strategic placement avoids curve overlap.
• VQ-03: Element Visibility (6/6) — Main curve at size=2.5 is prominent. Arrows at size=1.3 are clearly visible. Label boxes stand out with fill backgrounds.
• VQ-04: Color Accessibility (4/4) — Colorblind-safe palette: orange (#D35400) for Ea, steel blue (#2471A3) for ΔH. No red-green distinction.
• VQ-05: Layout & Canvas (4/4) — Good canvas utilization. Curve fills the central area well, labels positioned in available space without crowding.
• VQ-06: Axis Labels & Title (2/2) — "Potential Energy (kJ/mol)" with units, "Reaction Coordinate" descriptive and appropriate without units.

Design Excellence (16/20)

• DE-01: Aesthetic Sophistication (6/8) — Strong design with intentional color coding: orange for Ea, blue for ΔH, cohesive dark slate for text labels. Color-filled annotation badges for energy values are a professional touch. Clearly above library defaults.
• DE-02: Visual Refinement (5/6) — Subtle y-axis-only grid (#EEEEEE), x-axis ticks/text removed (appropriate for reaction coordinate), custom panel background (#FAFBFC), light axis lines (#CCCCCC). Good whitespace and clean composition.
• DE-03: Data Storytelling (5/6) — Color-coded annotations create clear visual hierarchy. The orange Ea badge and blue ΔH badge immediately draw attention to the key thermodynamic quantities. Labels with energy values guide the viewer through the energy landscape. The exothermic nature is immediately apparent.

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) — Correct reaction coordinate energy diagram with smooth curve showing energy landscape.
• SC-02: Required Features (4/4) — All required: labeled reactants/products/transition state, Ea double-headed arrow, ΔH double-headed arrow, horizontal dashed reference lines, smooth curve with clear maximum, clean minimal style.
• SC-03: Data Mapping (3/3) — X = reaction coordinate (0-1), Y = potential energy (kJ/mol). Correct mapping.
• SC-04: Title & Legend (3/3) — Title "line-reaction-coordinate · letsplot · pyplots.ai" in correct format. No legend needed for single-series plot.

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) — Shows activation energy barrier, enthalpy change, transition state peak, reactant/product plateaus. Single-step exothermic reaction as specified. Could show additional reaction types for full coverage but matches spec example well.
• DQ-02: Realistic Context (5/5) — Chemistry educational context with realistic energy values. Neutral, scientific topic.
• DQ-03: Appropriate Scale (4/4) — Reactants 50, TS 120, Products 20 kJ/mol — all realistic for a chemical reaction. Ea=70 and ΔH=-30 are sensible values.

Code Quality (10/10)

• CQ-01: KISS Structure (3/3) — Clean Imports → Data → Plot → Save structure. No functions or classes.
• CQ-02: Reproducibility (2/2) — Fully deterministic data generation (no randomness).
• CQ-03: Clean Imports (2/2) — All imports used: numpy, pandas, lets_plot, ggsave.
• CQ-04: Code Elegance (2/2) — Appropriate complexity. Gaussian+sigmoid approach for smooth curve is clean and effective. No over-engineering.
• CQ-05: Output & API (1/1) — Saves as plot.png with scale=3 per library guidelines. Also saves HTML.

Library Mastery (7/10)

• LM-01: Idiomatic Usage (4/5) — Good ggplot2-style grammar of graphics with proper layer composition. Uses aes mappings, geom layers, scales, and theme customization idiomatically.
• LM-02: Distinctive Features (3/5) — Uses flavor_high_contrast_light() (lets-plot specific flavor system), geom_label with label_padding/label_r/label_size parameters (lets-plot specific), ggsize(), and arrow() with type parameter.

Score Caps Applied

• None — no caps triggered.

Strengths

• Excellent color-coded annotation system: orange badges for Ea, blue badges for ΔH create immediate visual distinction
• Smooth, scientifically accurate energy curve using Gaussian+sigmoid construction
• Clean, educational layout with all spec-required features present and well-positioned
• Thoughtful use of lets-plot features (flavor system, geom_label parameters)

Weaknesses

• Minor: geom_label text sizes (15) are slightly smaller than ideal — could be 16-18 for maximum legibility at the output resolution

Issues Found

None critical. Implementation meets all requirements with strong design execution.

AI Feedback for Next Attempt

N/A — implementation approved. Strong execution with thoughtful color coding, clean layout, and all spec features present. The color-coded energy annotation badges are a particularly effective design choice.

Verdict: APPROVED