feat(plotnine): implement campbell-basic

[github-actions]

Implementation: campbell-basic - plotnine

Implements the plotnine version of campbell-basic.

File: plots/campbell-basic/implementations/plotnine.py

Parent Issue: #4241

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot shows a Campbell Diagram (interference diagram) for rotating machinery analysis. Four natural frequency curves are displayed as solid colored lines: 1st Bending (dark blue, ~18-23 Hz, slightly increasing), 2nd Bending (coral/salmon, ~43-39 Hz, slightly decreasing), 1st Torsional (green, ~65-73 Hz, increasing), and Axial (orange/yellow, ~88-90 Hz, nearly flat). Three engine order excitation lines (1x, 2x, 3x) are shown as gray dashed diagonal lines originating from the origin. Red diamond markers indicate critical speed intersections where engine order lines cross natural frequency curves. Mode labels are positioned at the right edge of each curve, and engine order labels (1x, 2x, 3x) appear in italic gray text near the top of each line. The title "campbell-basic · plotnine · pyplots.ai" is centered at the top. X-axis shows "Rotational Speed (RPM)" from 0-6000, Y-axis shows "Frequency (Hz)" from 0-120. The background uses a minimal theme with subtle light gray grid lines.

Quality Score: 86/100

Criteria Checklist

Visual Quality (28/30)

• VQ-01: Text Legibility (8/8) - All font sizes explicitly set: title 24pt, axis titles 20pt, axis text 16pt, base 14pt. All text clearly readable.
• VQ-02: No Overlap (6/6) - No overlapping text elements. Mode labels well-positioned at right edge, EO labels well-spaced.
• VQ-03: Element Visibility (6/6) - Mode lines at size 2.2, EO lines at 1.2, critical markers at size 5 — all clearly visible and well-adapted.
• VQ-04: Color Accessibility (3/4) - Blue, coral, green, orange palette is mostly distinguishable. However, the coral (2nd Bending) and green (1st Torsional) could be confused by deuteranopic viewers. Not purely red-green dependent due to lightness differences.
• VQ-05: Layout Balance (3/4) - Good 16:9 layout with x-axis extended to 6800 for mode labels. Slight wasted space at top (120 Hz limit when data maxes at ~90 Hz), though this accommodates the EO line labels.
• VQ-06: Axis Labels & Title (2/2) - "Rotational Speed (RPM)" and "Frequency (Hz)" — descriptive with units.

Spec Compliance (13/15)

• SC-01: Plot Type (5/5) - Correct Campbell diagram with natural frequency curves, engine order lines, and critical speed markers.
• SC-02: Required Features (3/4) - All major features present (4 modes, 3 EO lines, critical markers, labels). However, the spec explicitly asks for "a clean legend distinguishing natural frequency curves from engine order lines" — the implementation uses direct labeling instead, which is arguably better but deviates from the spec requirement.
• SC-03: Data Mapping (3/3) - X=RPM, Y=Hz correctly assigned. All data visible.
• SC-04: Title & Legend (2/3) - Title format "campbell-basic · plotnine · pyplots.ai" is correct. No formal legend present (direct labels used instead).

Data Quality (15/15)

• DQ-01: Feature Coverage (6/6) - Shows 4 modes with realistic behaviors (gyroscopic effects: some frequencies increase, some decrease with speed). Multiple critical speed intersections across different EO lines and modes.
• DQ-02: Realistic Context (5/5) - Rotating machinery context with realistic mode names (1st Bending, 2nd Bending, 1st Torsional, Axial).
• DQ-03: Appropriate Scale (4/4) - Speed range 0-6000 RPM and frequencies 18-90 Hz are realistic for industrial rotating equipment.

Design Excellence (13/20)

• DE-01: Aesthetic Sophistication (5/8) - Thoughtful custom color palette starting with Python Blue, gray EO lines, red diamond critical markers, italic EO labels. Clearly above defaults but not quite publication-ready.
• DE-02: Visual Refinement (4/6) - Minimal theme with subtle grid (alpha=0.25), minor grid removed. Good whitespace. Could benefit from further refinement (e.g., tick mark styling).
• DE-03: Data Storytelling (4/6) - Red diamond markers draw attention to critical speeds. Direct labeling creates clear visual hierarchy. Mode curves vs dashed EO lines establish good visual separation. Could improve with annotations explaining significance of key intersections.

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) - np.random.seed(42) set.
• CQ-03: Clean Imports (2/2) - All imports used, no unused imports.
• CQ-04: Code Elegance (2/2) - Appropriate complexity. Linear interpolation for critical speed calculation is well-implemented.
• CQ-05: Output & API (1/1) - Saves as plot.png, no deprecated functions.

Library Mastery (7/10)

• LM-01: Idiomatic Usage (4/5) - Good grammar-of-graphics layer composition. Uses scale_color_identity for manual color mapping, separate DataFrames per geom layer. Could leverage more plotnine-specific patterns.
• LM-02: Distinctive Features (3/5) - Uses ggplot-specific patterns: layer composition with different data frames, scale_color_identity, fontstyle parameter in geom_text. Somewhat generic ggplot usage that could translate to other gg-libraries.

Strengths

• Excellent data quality with realistic rotordynamic context and appropriate scale values
• Clean critical speed intersection calculation using linear interpolation with sign-change detection
• Good visual hierarchy: solid colored mode curves vs dashed gray EO lines vs red diamond markers
• Direct labeling of mode curves at right edge is effective and avoids legend clutter
• All font sizes explicitly set following library guidelines for 4800×2700 output

Weaknesses

• Missing a formal legend as requested by the spec — while direct labeling works well, a small legend distinguishing "Natural Frequency Modes" from "Engine Order Lines" would satisfy the spec requirement
• Color palette includes coral-red and green which may be problematic for colorblind viewers — consider using a more colorblind-safe palette (e.g., blue, orange, purple, brown)
• The y-axis range extends to 120 Hz when data maxes around 90 Hz, leaving unused space at the top of the plot
• Engine order label placement could be improved — the 3x label sits very close to the top edge, and labels could be rotated to follow the line angle for better association

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 Campbell Diagram for rotating machinery analysis. Four natural frequency mode curves are drawn as thick solid lines: 1st Bending (dark blue, ~18-23 Hz), 2nd Bending (amber/gold, ~42-39 Hz declining), 1st Torsional (purple, ~65-72 Hz rising), and Axial (teal/green, ~88-90 Hz nearly flat). Three gray dashed engine order lines (1x, 2x, 3x) radiate from the origin with increasing slopes. Red diamond markers with pink fill highlight critical speed intersections where engine order lines cross natural frequency curves (~10 intersection points visible). Mode names are labeled in bold matching colors at the right edge of the plot. Engine order labels (1x, 2x, 3x) appear in gray italic along each diagonal line. A dotted red vertical line drops from the 1x/1st Bending intersection down to the x-axis with an annotation reading "1127 RPM" in red italic, highlighting the most operationally significant critical speed. The background is light gray (#FAFAFA) with subtle grid lines. A horizontal legend at the bottom lists all four modes with colored solid line swatches plus one dashed gray "Engine Order (1x, 2x, 3x)" entry.

Quality Score: 85/100

Criteria Checklist

Visual Quality (26/30)

• VQ-01: Text Legibility (8/8) - All font sizes explicitly set: title 24pt, axis titles 20pt bold, tick labels 16pt, legend 14pt. All perfectly readable.
• VQ-02: No Overlap (5/6) - The "3x" engine order label partially overlaps with the Axial mode line near ~1300 RPM. Minor but visible.
• VQ-03: Element Visibility (5/6) - Lines thick at 1.8, diamond markers visible. Engine order labels (gray italic size=10) are slightly faint against gray dashed lines.
• VQ-04: Color Accessibility (4/4) - Colorblind-safe palette: blue (#306998), amber (#E69F00), purple (#882D9E), teal (#009E73). No red-green distinction issues.
• VQ-05: Layout Balance (2/4) - x-axis extended to 7200 for right-edge mode labels creates asymmetric whitespace. Bottom legend + right labels slightly unbalanced.
• VQ-06: Axis Labels & Title (2/2) - "Rotational Speed (RPM)" and "Frequency (Hz)" — descriptive with units.

Design Excellence (14/20)

• DE-01: Aesthetic Sophistication (6/8) - Strong design with custom palette, styled panel (#FAFAFA), intentional typography hierarchy, solid/dashed distinction. Above defaults but not FiveThirtyEight-level.
• DE-02: Visual Refinement (4/6) - Minor grid disabled, subtle major grid, panel background customized, axis lines styled. Legend title hidden via size=1/white hack is inelegant.
• DE-03: Data Storytelling (4/6) - The "1127 RPM" critical speed annotation creates a clear focal point. Diamond markers and right-edge labels build visual hierarchy. Good emphasis on the most operationally significant intersection.

Spec Compliance (14/15)

• SC-01: Plot Type (5/5) - Correct Campbell diagram: frequency curves + engine order excitation lines + critical speed markers.
• SC-02: Required Features (3/4) - All major features present (4 modes, 3 engine orders, critical markers, labels). Spec suggests 4-5 modes; only 4 provided. Optional shading around critical zones not implemented.
• SC-03: Data Mapping (3/3) - X=Speed (RPM), Y=Frequency (Hz) correctly assigned.
• SC-04: Title Format (3/3) - "campbell-basic · plotnine · pyplots.ai" correct. Legend consolidates EO lines cleanly as one entry.

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) - Shows modes with different speed-dependent behaviors (some increasing, some decreasing). Multiple engine order intersections. Could show a 5th mode for fuller coverage.
• DQ-02: Realistic Context (5/5) - Real rotating machinery scenario with proper mode names (1st Bending, 2nd Bending, 1st Torsional, Axial).
• DQ-03: Appropriate Scale (4/4) - Frequencies 18-90 Hz, speed 0-6000 RPM — realistic turbomachinery values. Gyroscopic effects properly modeled.

Code Quality (9/10)

• CQ-01: KISS Structure (3/3) - Linear flow: imports → data → plot → save. No functions or classes.
• CQ-02: Reproducibility (2/2) - np.random.seed(42) set.
• CQ-03: Clean Imports (2/2) - All imports used.
• CQ-04: Code Elegance (1/2) - Loop-based record construction is verbose. Legend title hidden via size=1/white color hack instead of proper suppression.
• CQ-05: Output & API (1/1) - Saves as plot.png, dpi=300.

Library Mastery (8/10)

• LM-01: Idiomatic Usage (5/5) - Excellent ggplot grammar: aes mapping, scale_manual for colors/linetypes, guide_legend(override_aes), annotate layers, theme composition.
• LM-02: Distinctive Features (3/5) - Uses plotnine-specific patterns: guide_legend override_aes, scale_linetype_manual, annotate("segment"), element_blank/element_rect layering. Could go further with stat layers or coord transforms.

Strengths

• Colorblind-safe custom palette with strong color differentiation across all four modes
• Critical speed intersection calculation using sign-change interpolation is mathematically sound
• "1127 RPM" annotation creates effective data storytelling with a clear focal point
• Clean legend design consolidating 3 engine order lines into one entry
• Idiomatic plotnine grammar-of-graphics composition with proper aes mapping and scale layering

Weaknesses

• Right-edge mode labels push x-axis to 7200 creating asymmetric layout; consider positioning labels within the plot area or using a secondary legend
• Engine order labels (3x, 2x) partially overlap with mode lines making them hard to read
• Legend title suppression uses a hack (size=1, white color) rather than a clean approach
• Only 4 modes when spec suggests 4-5; adding a 5th mode would improve feature coverage

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 a Campbell Diagram plotting natural frequency (Hz) on the Y-axis against rotational speed (RPM) on the X-axis, ranging from 0-6000 RPM and 0-110 Hz. Five solid-colored natural frequency mode curves are shown: 1st Bending (blue, ~18-23 Hz, slightly increasing), 2nd Bending (amber/yellow, ~42-39 Hz, slightly decreasing), 1st Torsional (purple, ~55-62 Hz, increasing), 2nd Torsional (orange, ~72-76 Hz, slightly increasing), and Axial (teal/green, ~88-90 Hz, nearly flat). Three dashed gray engine order lines (1x, 2x, 3x) radiate from the origin with increasing slopes, labeled in bold italic text along the lines. Red diamond markers highlight approximately 10+ critical speed intersections where engine order lines cross natural frequency curves. A dotted vertical red line at approximately 1127 RPM with a red italic label annotates the most significant critical speed (1x crossing 1st Bending). The title "campbell-basic · plotnine · pyplots.ai" is centered and bold at the top. A horizontal legend at the bottom lists all five modes and a consolidated "Engine Order (1x, 2x, 3x)" entry in a white-bordered box. The background is light gray (#FAFAFA) with subtle major gridlines.

Quality Score: 86/100

Criteria Checklist

Visual Quality (26/30)

• VQ-01: Text Legibility (8/8) - All font sizes explicitly set: title 24pt, axis labels 20pt bold, tick labels 16pt, legend 14pt. All text perfectly readable
• VQ-02: No Overlap (5/6) - Very minor near-overlap: "3x" label approaches upper plot boundary; some critical speed markers cluster in lower-left region
• VQ-03: Element Visibility (5/6) - Lines thick at 1.8, diamond markers size 5 are visible. Some marker clustering near origin where EO lines converge with 1st Bending
• VQ-04: Color Accessibility (4/4) - Excellent colorblind-safe palette close to Wong palette: blue, amber, purple, vermilion, green — all distinguishable
• VQ-05: Layout Balance (2/4) - Bottom legend occupies space; negative Y-axis range (-5 to 0) is mostly dead space used only for annotation label; some wasted vertical space
• VQ-06: Axis Labels & Title (2/2) - "Rotational Speed (RPM)" and "Frequency (Hz)" with units

Design Excellence (14/20)

• DE-01: Aesthetic Sophistication (6/8) - Strong design with custom colorblind-safe palette, intentional typography hierarchy, styled panel background. Above defaults but not quite FiveThirtyEight-level
• DE-02: Visual Refinement (4/6) - Good: minor grid removed, panel background #FAFAFA, legend styled with border/alpha, axis lines added. Some room for more polish
• DE-03: Data Storytelling (4/6) - The 1127 RPM annotation highlights the most operationally significant critical speed; red diamonds create visual hierarchy drawing attention to resonance points

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) - Correct Campbell Diagram with natural frequency curves overlaid with engine order excitation lines
• SC-02: Required Features (4/4) - All spec features present: 5 modes, 3 EO lines, critical speed markers, mode labels, EO labels, clean legend
• SC-03: Data Mapping (3/3) - X=RPM, Y=Hz correctly assigned, all data visible
• SC-04: Title & Legend (3/3) - Title "campbell-basic · plotnine · pyplots.ai" correct; legend clear with consolidated EO entry

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) - Shows 5 modes with varying speed dependence (increasing, decreasing, flat), 3 engine orders, many critical speed intersections. Mode variation could be more dramatic
• DQ-02: Realistic Context (5/5) - Real rotordynamic scenario with proper mode names (1st/2nd Bending, 1st/2nd Torsional, Axial), realistic frequency ranges
• DQ-03: Appropriate Scale (4/4) - Realistic values: 0-6000 RPM, 18-90 Hz natural frequencies, appropriate gyroscopic effects

Code Quality (9/10)

• CQ-01: KISS Structure (3/3) - Linear imports → data → plot → save structure, no functions/classes
• CQ-02: Reproducibility (2/2) - np.random.seed(42)
• CQ-03: Clean Imports (2/2) - All imports used
• CQ-04: Code Elegance (1/2) - Clear but somewhat verbose; legend mapping with breaks/labels is complex
• CQ-05: Output & API (1/1) - Saves as plot.png, no deprecated functions

Library Mastery (8/10)

• LM-01: Idiomatic Usage (5/5) - Expert grammar of graphics: proper aes mapping, layer composition, scale_color_manual + scale_linetype_manual, guide_legend with override_aes, annotate, inherit_aes=False
• LM-02: Distinctive Features (3/5) - Uses ggplot-style layer composition, guide_legend(override_aes=...), element theming system. These are grammar-of-graphics features well-used but not deeply unique to plotnine

Strengths

• Excellent spec compliance: all required Campbell Diagram features are present (5 modes, 3 EO lines, critical speed markers, labels, legend)
• Strong colorblind-safe palette with good color choices that are easily distinguishable
• Effective data storytelling with the 1127 RPM critical speed annotation highlighting the most significant resonance
• Realistic rotordynamic data with proper mode names and physically plausible frequency behavior
• Expert use of plotnine's grammar of graphics with proper layering, scale mappings, and theme customization

Weaknesses

• Layout has some wasted vertical space: the Y-axis range extends to -5 Hz mainly for one annotation, leaving dead space below 0
• Legend at bottom is functional but could be more compact or integrated (e.g., direct labels on curves instead of legend)
• Critical speed markers cluster in the lower-left region where multiple EO lines converge with the 1st Bending mode, reducing individual marker visibility
• Code complexity around legend construction (breaks/labels mapping) is somewhat verbose for a KISS script

Verdict: APPROVED

[github-actions]

🔧 Repair Attempt 3/3

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 a Campbell diagram for rotating machinery analysis. Five natural frequency curves are plotted against rotational speed (0–6000 RPM): 1st Bending (dark blue, ~18 Hz baseline, slightly increasing), 2nd Bending (amber/yellow, ~45 Hz baseline, decreasing), 1st Torsional (purple, ~52 Hz baseline, increasing), 2nd Torsional (red-orange, ~75 Hz baseline, roughly flat), and Axial (teal/green, ~90 Hz baseline, nearly flat). Three dashed gray engine order lines (1×, 2×, 3×) radiate diagonally from the origin. Red diamond markers are placed at each intersection of an EO line with a natural frequency curve (approximately 10 critical speed points). A dotted red vertical line at ~1180 RPM with an italic annotation "Critical: 1180 RPM" highlights the 1×/1st Bending intersection as the most operationally significant. A very subtle blue-tinted operating range band spans 2000–4500 RPM with a faint "Operating Range" label. The bottom legend is horizontal with a white background and gray border, consolidating all three EO lines into a single "Engine Order (1×, 2×, 3×)" entry. Title reads "campbell-basic · plotnine · pyplots.ai" in bold centered text.

Quality Score: 90/100

Criteria Checklist

Visual Quality (27/30)

• VQ-01: Text Legibility (8/8) — all font sizes explicitly set: title 24pt, axis titles 20pt, ticks 16pt, legend 13pt
• VQ-02: No Overlap (5/6) — minor: "3×" label slightly crowds 2nd Torsional line area
• VQ-03: Element Visibility (6/6) — mode lines at weight 2.0, EO lines at 1.0, diamond markers size 4.5
• VQ-04: Color Accessibility (4/4) — colorblind-safe palette with linetype differentiation
• VQ-05: Layout Balance (2/4) — operating range band extremely subtle (alpha=0.04); 3× EO line extends beyond useful data range; bottom legend compresses plot area
• VQ-06: Axis Labels & Title (2/2) — "Rotational Speed (RPM)" and "Natural Frequency (Hz)"

Design Excellence (16/20)

• DE-01: Aesthetic Sophistication (7/8) — custom colorblind-safe palette, intentional typography hierarchy, refined panel background, publication-quality polish
• DE-02: Visual Refinement (5/6) — subtle grid, minor grid removed, panel background with border, good whitespace; legend border slightly heavy
• DE-03: Data Storytelling (4/6) — "Critical: 1180 RPM" annotation with dotted vertical line creates focal point; operating range band adds context; visual hierarchy via line weights

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) — correct Campbell diagram with frequency curves and EO lines
• SC-02: Required Features (4/4) — 5 modes, 3 EO lines, critical speed markers, mode labels, EO labels, operating range shading
• SC-03: Data Mapping (3/3) — X=Speed (RPM), Y=Frequency (Hz)
• SC-04: Title Format (3/3) — "campbell-basic · plotnine · pyplots.ai"; consolidated EO legend entry

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) — 5 modes with varying speed dependence, multiple intersections; could show more dramatic gyroscopic variation
• DQ-02: Realistic Context (5/5) — real turbomachinery terminology and plausible frequency ranges
• DQ-03: Appropriate Scale (4/4) — realistic RPM and Hz values for rotating machinery

Code Quality (9/10)

• CQ-01: KISS Structure (3/3) — imports → data → plot → save, no functions/classes
• CQ-02: Reproducibility (2/2) — np.random.seed(42)
• CQ-03: Clean Imports (2/2) — all imports used
• CQ-04: Code Elegance (1/2) — duplicate interpolation logic for 1×/1st Bending intersection (lines 87–97 repeat lines 70–83 pattern)
• CQ-05: Output & API (1/1) — saves as plot.png, dpi=300

Library Mastery (9/10)

• LM-01: Idiomatic Usage (5/5) — expert grammar-of-graphics composition with layer stacking, scale_manual, guide_legend, coord_cartesian, annotate
• LM-02: Distinctive Features (4/5) — scale_size_identity for line weight, guide_legend(override_aes=...), coord_cartesian zoom, geom_rect band

Strengths

• Excellent use of plotnine's grammar of graphics with layered composition (operating range band → lines → markers → annotations)
• Strong data storytelling: "Critical: 1180 RPM" annotation with vertical dotted line creates immediate visual focus on the most operationally significant intersection
• Colorblind-safe palette with both color AND linetype differentiation between modes and EO lines
• Consolidated legend entry for all three EO lines reduces clutter while maintaining clarity
• Publication-quality typography with explicitly set font sizes at all levels
• Realistic turbomachinery data with appropriate mode names, frequency ranges, and gyroscopic speed dependence

Weaknesses

• Operating range band is nearly invisible at alpha=0.04 — could benefit from slightly higher opacity
• Duplicate interpolation code for 1×/1st Bending critical speed annotation repeats the general intersection logic
• 3× EO line extends well beyond the plot's useful frequency range, creating visual noise in the upper portion

Verdict: APPROVED