feat(plotnine): implement line-stress-strain

[github-actions]

Implementation: line-stress-strain - plotnine

Implements the plotnine version of line-stress-strain.

File: plots/line-stress-strain/implementations/plotnine.py

Parent Issue: #4413

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays an engineering stress-strain curve for mild steel on a clean minimal background. A thick blue (#306998) line traces the characteristic shape: steep elastic rise from origin to ~250 MPa, a brief yield plateau, strain hardening curving up to ~400 MPa (UTS) at strain ~0.22, then necking decline to fracture at ~320 MPa and strain ~0.35. Three large red dots mark Yield Point (0.2% offset), UTS, and Fracture, with italic labels above each. A red dashed line shows the 0.2% offset construction. Gray italic text labels the four regions: "Elastic", "Yield Plateau", "Strain Hardening", and "Necking". A bold blue annotation reads "E = 210 GPa". Title is "line-stress-strain · plotnine · pyplots.ai" in bold at top. X-axis: "Engineering Strain", Y-axis: "Engineering Stress (MPa)". Subtle horizontal grid lines only on y-axis with light alpha.

Score: 86/100

Category	Score	Max
Visual Quality	26	30
Design Excellence	14	20
Spec Compliance	15	15
Data Quality	15	15
Code Quality	10	10
Library Mastery	6	10
Total	86	100

Visual Quality (26/30)

• VQ-01: Text Legibility (7/8) — Font sizes explicitly set for title/axes/ticks; annotation text (size=10-11) is slightly small relative to the canvas
• VQ-02: No Overlap (4/6) — "Elastic" region label at x=0.008 is partially obscured by the steep curve and offset line in the narrow elastic region
• VQ-03: Element Visibility (6/6) — Thick blue line (size=2.5) and large red markers (size=5) are clearly visible
• VQ-04: Color Accessibility (3/4) — Blue/red scheme provides good contrast; red is not ideal for all colorblind types but shape/style distinction (dashed line, filled dots) helps
• VQ-05: Layout & Canvas (4/4) — Good 16:9 proportions, data fills canvas well with balanced margins
• VQ-06: Axis Labels & Title (2/2) — Descriptive labels with units: "Engineering Stress (MPa)"

Design Excellence (14/20)

• DE-01: Aesthetic Sophistication (5/8) — Custom Python Blue color, red accents for key points, theme_minimal base — clearly above defaults but not publication-exceptional
• DE-02: Visual Refinement (4/6) — Removed x-axis grid, subtle y-axis grid with alpha=0.4, minor grid removed, theme_minimal handles spines
• DE-03: Data Storytelling (5/6) — Excellent storytelling: labeled regions create narrative flow from elastic→fracture, critical points marked with visual emphasis, modulus annotation adds engineering context

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) — Correct line plot showing stress-strain curve
• SC-02: Required Features (4/4) — All spec features present: region labels, critical points (yield/UTS/fracture), 0.2% offset line, elastic modulus annotation
• SC-03: Data Mapping (3/3) — X=strain, Y=stress correctly mapped
• SC-04: Title & Legend (3/3) — Title format correct; no legend needed for single-material curve with inline annotations

Data Quality (15/15)

• DQ-01: Feature Coverage (6/6) — Shows all stress-strain regions: elastic, yield plateau, strain hardening, necking, fracture
• DQ-02: Realistic Context (5/5) — Mild steel tensile test with realistic engineering context
• DQ-03: Appropriate Scale (4/4) — E=210 GPa, σ_y=250 MPa, UTS=400 MPa, ε_f=0.35 — all realistic for mild steel

Code Quality (10/10)

• CQ-01: KISS Structure (3/3) — Clean imports → data → plot → save structure, no functions/classes
• CQ-02: Reproducibility (2/2) — np.random.seed(42) set
• CQ-03: Clean Imports (2/2) — All imports are used
• CQ-04: Code Elegance (2/2) — Well-structured data generation with clear region separation, appropriate complexity
• CQ-05: Output & API (1/1) — Saves as plot.png with dpi=300

Library Mastery (6/10)

• LM-01: Idiomatic Usage (4/5) — Good use of ggplot grammar: layered geoms with multiple data frames, aes mappings, annotate(), theme customization
• LM-02: Distinctive Features (2/5) — Uses plotnine's layer composition but nothing that couldn't be replicated in matplotlib with similar effort

Score Caps Applied

• None

Strengths

• Perfect spec compliance — all required features (regions, key points, offset line, modulus) are present and well-executed
• Excellent data generation with physically realistic mild steel properties across all deformation regions
• Clean data storytelling with labeled regions creating a clear narrative flow through the material behavior
• Well-structured, readable code following KISS principles

Weaknesses

• "Elastic" region label is partially obscured by the curve and offset line in the narrow elastic region — needs repositioning
• Annotation text sizes (10-11) could be slightly larger for better readability at full resolution
• Color palette is functional but limited to blue+red — a more refined color strategy could elevate design sophistication
• Library mastery could be improved by leveraging more plotnine-specific features

Issues Found

1. VQ-02 MEDIUM: "Elastic" region label at x=0.008, y=140 is partially obscured by the steep elastic curve and 0.2% offset line
   • Fix: Reposition the "Elastic" label or use an arrow annotation to place it in clear space
2. LM-02 LOW: Generic library usage — implementation doesn't leverage plotnine-distinctive features
   • Fix: Consider using plotnine-specific features like scale_color_identity, stat layers, or more sophisticated theme customization
3. DE-01 MEDIUM: Color scheme limited to blue + red accents
   • Fix: Consider a more nuanced color palette or gradient approach for the curve to encode additional information (e.g., strain rate regions)

AI Feedback for Next Attempt

Reposition the "Elastic" region label to avoid overlap with the curve in the narrow elastic region — consider placing it with an offset or arrow. Increase annotation text sizes from 10-11 to 12-13 for better legibility. Explore a more refined color strategy — possibly using color gradients along the curve to encode region transitions, or a warmer accent color instead of pure red. Leverage plotnine-specific features more distinctively.

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 an engineering stress-strain curve for mild steel on a white background. The main curve is a thick blue (#306998) line showing stress (MPa) vs strain. Four distinct regions are shaded with subtle colored rectangles: Elastic (light cyan/green, very narrow on the left), Yield Plateau (light green), Strain Hardening (light orange), and Necking (light pink/red). Three critical points are marked with red (#C0392B) dots: "Yield Point (0.2% offset)" at ~250 MPa, "UTS" at ~400 MPa / strain ~0.22, and "Fracture" at ~320 MPa / strain ~0.35. A red dashed line shows the 0.2% offset construction. Region labels appear in gray italic text. The elastic modulus "E = 210 GPa" is annotated in bold blue. The title reads "line-stress-strain · plotnine · pyplots.ai" in bold dark text. Axes are labeled "Engineering Strain" (x) and "Engineering Stress (MPa)" (y), with y-axis gridlines only.

Score: 86/100

Category	Score	Max
Visual Quality	26	30
Design Excellence	13	20
Spec Compliance	15	15
Data Quality	15	15
Code Quality	10	10
Library Mastery	7	10
Total	86	100

Visual Quality (26/30)

• VQ-01: Text Legibility (7/8) - Font sizes explicitly set (title 24, axis titles 20, ticks 16, annotations 13/12). All readable, though annotation text could be slightly larger for the canvas size.
• VQ-02: No Overlap (5/6) - No direct text collisions, but the elastic region is extremely narrow making the yield point label, offset line, and "Elastic" region label appear cramped together.
• VQ-03: Element Visibility (5/6) - Main curve is thick (size=2.5) and clearly visible. Key points well-sized. Region shading is very subtle (alpha=0.06) — effective but borderline faint.
• VQ-04: Color Accessibility (4/4) - Blue curve with red accents, gray labels. No red-green distinction issues. Good contrast throughout.
• VQ-05: Layout & Canvas (3/4) - Good 16:9 utilization overall. The elastic region (strain 0–0.0012) is extremely compressed on the left, making offset line details hard to discern at this scale.
• VQ-06: Axis Labels & Title (2/2) - "Engineering Strain" and "Engineering Stress (MPa)" — descriptive with units.

Design Excellence (13/20)

• DE-01: Aesthetic Sophistication (5/8) - Custom color scheme with blue curve, red accents, and color-coded region shading. Intentional typography with italic labels and bold modulus annotation. Above defaults but not publication-grade polish.
• DE-02: Visual Refinement (4/6) - theme_minimal with x-grid removed, subtle y-grid with alpha=0.4, white background. Good refinement but could push further (e.g., tick mark styling).
• DE-03: Data Storytelling (4/6) - Plot tells a clear engineering story: regions are color-coded and labeled, critical points annotated, modulus called out. Viewer immediately understands the material behavior progression.

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) - Correct line/curve plot showing stress-strain relationship.
• SC-02: Required Features (4/4) - All spec features present: labeled regions (elastic, yield plateau, strain hardening, necking), yield point via 0.2% offset method, UTS, fracture point, elastic modulus annotation, 0.2% offset line.
• SC-03: Data Mapping (3/3) - X=strain, Y=stress, correctly mapped with appropriate axis ranges.
• SC-04: Title & Legend (3/3) - Title format "line-stress-strain · plotnine · pyplots.ai" correct. No legend needed for single-series plot.

Data Quality (15/15)

• DQ-01: Feature Coverage (6/6) - Shows all aspects of a tensile test: elastic region, yield plateau (characteristic of mild steel), strain hardening with power law, necking to fracture with stress decrease.
• DQ-02: Realistic Context (5/5) - Mild steel tensile test — a real, neutral engineering scenario used universally in materials science education.
• DQ-03: Appropriate Scale (4/4) - Yield=250 MPa, UTS=400 MPa, E=210 GPa, fracture strain=0.35 — textbook-accurate values for mild steel.

Code Quality (10/10)

• CQ-01: KISS Structure (3/3) - Clean imports → data generation → plot construction → save. No functions or classes.
• CQ-02: Reproducibility (2/2) - np.random.seed(42) set at top.
• CQ-03: Clean Imports (2/2) - All imports are used in the implementation.
• CQ-04: Code Elegance (2/2) - Well-organized with clear section comments. Appropriate complexity for the visualization — data generation naturally requires multiple segments.
• CQ-05: Output & API (1/1) - Saves as plot.png with dpi=300, current plotnine API.

Library Mastery (7/10)

• LM-01: Idiomatic Usage (4/5) - Good grammar-of-graphics composition with layered geoms, identity scales for direct aesthetic mapping, coord_cartesian for view control. Could improve by using aes mapping more idiomatically in places where raw values are passed.
• LM-02: Distinctive Features (3/5) - Uses annotate("rect") for region shading, identity scales (scale_color_identity, scale_size_identity), coord_cartesian, and geom_segment — features that leverage plotnine's ggplot2-style grammar distinctively.

Score Caps Applied

• None

Strengths

• Complete spec compliance — all required features (regions, key points, offset line, modulus annotation) are present and correctly implemented
• Excellent engineering data with textbook-accurate mild steel values
• Good use of plotnine's grammar of graphics with layered annotate("rect") for region shading
• Clean, well-structured code with clear section organization
• Effective data storytelling through color-coded regions and annotated critical points

Weaknesses

• The elastic region (strain 0–0.0012) is extremely compressed, making the 0.2% offset line construction nearly invisible at this scale
• Region shading alpha=0.06 is very faint — could be slightly more visible
• Annotation text sizes (12-13) are adequate but could be larger for better readability at full resolution
• "Yield Plateau" label is placed quite far from the actual plateau region (at strain=0.06, stress=140 which is well below the plateau at 250 MPa)

Issues Found

1. VQ-05 MINOR: Elastic region is extremely compressed horizontally — the offset line construction (a key spec feature) is nearly impossible to see clearly
   • Fix: Consider an inset/zoom or adjust x-axis to give the elastic region more visual space
2. DE-01 MODERATE: Good but not exceptional aesthetic polish — region shading is very faint and could be more intentional
   • Fix: Increase region shading alpha slightly (0.08-0.10), refine annotation positioning
3. LM-01 MINOR: Some raw values passed outside aes() where identity scales could be used more idiomatically
   • Fix: Minor code style improvement

AI Feedback for Next Attempt

The implementation is strong with full spec compliance and excellent data quality. To reach 90+: (1) Address the compressed elastic region — either use an inset plot or adjust scale to make the 0.2% offset construction more visible, (2) Increase region shading alpha slightly for better visibility, (3) Reposition the "Yield Plateau" label closer to the actual plateau stress level, (4) Consider slightly larger annotation text sizes (14-15 instead of 12-13).

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 an engineering stress-strain curve for mild steel on a white background. The title "line-stress-strain · plotnine · pyplots.ai" appears in bold dark text at the top. The x-axis is labeled "Engineering Strain" (0.00–0.35) and the y-axis "Engineering Stress (MPa)" (0–450). A thick dark blue line traces the characteristic stress-strain path from origin through elastic deformation, yield plateau, strain hardening up to ~400 MPa at strain ~0.22 (UTS), then necking down to ~320 MPa at fracture (strain ~0.35). Four color-shaded rectangular regions mark the material behavior zones: light blue (Elastic), light green (Yield Plateau), light yellow/orange (Strain Hardening), and light pink/red (Necking), each with gray italic region labels. Three red dots mark critical points labeled in bold: "Yield Point (0.2% offset)", "UTS", and "Fracture". A red dashed line shows the 0.2% offset construction with a small red italic "0.2% offset" label near the bottom. "E = 210 GPa" appears in bold blue text in the elastic region area. The y-axis grid is subtle light gray; x-axis grid is removed. Layout is 16:9 with good canvas utilization.

Score: 90/100

Category	Score	Max
Visual Quality	28	30
Design Excellence	15	20
Spec Compliance	15	15
Data Quality	15	15
Code Quality	10	10
Library Mastery	7	10
Total	90	100

Visual Quality (28/30)

• VQ-01: Text Legibility (7/8) — All major text sizes explicitly set (title=26, axis_title=22, axis_text=16). The "0.2% offset" annotation at size=11 is noticeably smaller than other text.
• VQ-02: No Overlap (5/6) — No actual text-on-text overlap, but the elastic region is horizontally compressed causing visual density with multiple labels ("Elastic", "Yield Point", "Yield Plateau", "0.2% offset", "E = 210 GPa") in a narrow horizontal band.
• VQ-03: Element Visibility (6/6) — Main curve at size=2.8 is clearly visible, key points at size=6 are prominent, offset line at size=1.2 is distinguishable.
• VQ-04: Color Accessibility (4/4) — Blue curve with red accents; pastel region shading provides contrast without red-green dependency. Colorblind-safe.
• VQ-05: Layout & Canvas (4/4) — Good 16:9 proportions with plot filling the canvas well. Balanced margins.
• VQ-06: Axis Labels & Title (2/2) — "Engineering Strain" and "Engineering Stress (MPa)" are descriptive with units.

Design Excellence (15/20)

• DE-01: Aesthetic Sophistication (6/8) — Color-coded region shading adds visual richness beyond defaults. Custom color palette (blue curve, red accents, harmonious pastel regions). Intentional typographic hierarchy with bold titles, italic region labels, and bold key points.
• DE-02: Visual Refinement (4/6) — X-axis major grid and all minor grid removed, subtle y-only grid with low alpha. White background, clean panel. Some room for further polish (e.g., the dense left region could benefit from spacing adjustments).
• DE-03: Data Storytelling (5/6) — The colored regions guide the viewer through the material's mechanical behavior story. Key points create clear focal points (UTS as the peak, fracture as the endpoint). The 0.2% offset construction demonstrates a real engineering method. Strong visual hierarchy.

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) — Correct engineering stress-strain curve as a line plot.
• SC-02: Required Features (4/4) — All spec features present: labeled regions (elastic, plastic/strain hardening, necking), marked critical points (yield, UTS, fracture), elastic modulus annotation, 0.2% offset line.
• SC-03: Data Mapping (3/3) — X=strain, Y=stress correctly mapped; axes show full data range.
• SC-04: Title & Legend (3/3) — Title follows exact format "line-stress-strain · plotnine · pyplots.ai". No legend needed for single-series plot.

Data Quality (15/15)

• DQ-01: Feature Coverage (6/6) — Shows all aspects: elastic region, yield plateau (characteristic of mild steel), strain hardening with power-law curve, necking with stress decrease, and fracture. Excellent coverage of stress-strain curve features.
• DQ-02: Realistic Context (5/5) — Mild steel tensile test is a classic, neutral engineering scenario. Real-world plausible and educational.
• DQ-03: Appropriate Scale (4/4) — Young's modulus 210 GPa, yield stress 250 MPa, UTS 400 MPa, fracture strain 0.35 — all realistic values for mild steel.

Code Quality (10/10)

• CQ-01: KISS Structure (3/3) — Clean linear flow: imports → data generation → plot construction → save. No functions or classes.
• CQ-02: Reproducibility (2/2) — np.random.seed(42) set at the start.
• CQ-03: Clean Imports (2/2) — All imports are used in the implementation.
• CQ-04: Code Elegance (2/2) — Well-organized with clear section comments. Appropriate complexity for the visualization. No fake UI elements.
• CQ-05: Output & API (1/1) — Saves as plot.png with dpi=300. Uses current plotnine API.

Library Mastery (7/10)

• LM-01: Idiomatic Usage (4/5) — Good grammar-of-graphics pattern with layered composition (ggplot + geom_line + geom_point + geom_text + annotate). Uses aes() mapping, scale_*_identity() for direct aesthetic control, and theme customization.
• LM-02: Distinctive Features (3/5) — Uses annotate("rect") for region shading (plotnine-distinctive), coord_cartesian() for view control, identity scales for direct aesthetic mapping, and geom_segment for the offset line. These leverage plotnine's grammar-of-graphics approach.

Score Caps Applied

• None

Strengths

• Excellent data storytelling through color-coded region shading that guides the viewer through material behavior phases
• All spec-required features implemented: region labels, critical points, elastic modulus annotation, 0.2% offset line
• Realistic mild steel data with appropriate engineering values
• Clean, well-structured code following KISS principles
• Good use of plotnine's grammar-of-graphics approach with layered composition

Weaknesses

• The elastic region is horizontally compressed, creating visual density with multiple labels in a narrow space
• The "0.2% offset" annotation text (size=11) is noticeably smaller than other text elements

Issues Found

None critical — minor visual density in the elastic region does not significantly impact readability.

AI Feedback for Next Attempt

Plot meets quality threshold. The color-coded region shading, comprehensive annotations, and realistic data create a publication-quality engineering stress-strain visualization. Minor improvements could include adjusting label positions in the elastic region and making the "0.2% offset" text larger, but these are not blocking issues.

Verdict: APPROVED