feat(altair): implement campbell-basic

[github-actions]

Implementation: campbell-basic - altair

Implements the altair version of campbell-basic.

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

Parent Issue: #4241

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays a Campbell Diagram with five natural frequency curves plotted against rotational speed (0–6000 RPM) on the x-axis and frequency (0–300 Hz) on the y-axis. The five mode curves are: 1st Bending (blue), 2nd Bending (orange), 1st Torsional (green), Axial (purple), and 3rd Bending (red) — each rendered as solid lines with strokeWidth=3. Three dashed grey engine order lines (1x, 2x, 3x) radiate from the origin with lower opacity (0.5) and are labeled near the right edge of the plot. Red diamond markers with white stroke indicate critical speed intersections where engine order lines cross natural frequency curves. A legend titled "Natural Frequencies" is positioned on the right side listing all five modes. The title reads "campbell-basic · altair · pyplots.ai" at the top. Grid lines are subtle (0.15 opacity). The overall color palette is cohesive and colorblind-distinguishable.

Quality Score: 81/100

Criteria Checklist

Visual Quality (24/30)

• VQ-01: Text Legibility (8/8) - All font sizes explicitly set: title 28pt, axis titles 22pt, tick labels 18pt, legend labels 14-16pt. All text clearly readable.
• VQ-02: No Overlap (6/6) - No overlapping text elements anywhere in the plot.
• VQ-03: Element Visibility (5/6) - Mode lines (strokeWidth=3) and diamond markers (size=250) are clear. Engine order lines at opacity=0.5 are appropriately subtle but slightly hard to trace.
• VQ-04: Color Accessibility (4/4) - Blue/orange/green/purple/red palette is colorblind-distinguishable. Grey engine order lines provide clear category separation.
• VQ-05: Layout & Canvas (3/4) - Good canvas use at 1600×900 but legend on the right takes notable space. Minor whitespace inefficiency at top of chart.
• VQ-06: Axis Labels & Title (2/2) - "Rotational Speed (RPM)" and "Frequency (Hz)" with units.

Design Excellence (12/20)

• DE-01: Aesthetic Sophistication (5/8) - Thoughtful custom palette starting with Python blue, clear visual distinction between solid mode lines and dashed grey engine order lines, diamond markers with white stroke. Above defaults but not publication-caliber.
• DE-02: Visual Refinement (4/6) - Subtle grid (0.15 opacity), view stroke removed, well-configured legend. Good refinement but not fully polished.
• DE-03: Data Storytelling (3/6) - Red diamond markers create focal points at critical speeds. Visual hierarchy separates modes from excitation lines. However, no annotations explain what intersections mean, and no operating range highlighting guides interpretation.

Spec Compliance (14/15)

• 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 main features present. Spec requests "clean legend distinguishing natural frequency curves from engine order lines" — the legend only covers natural frequencies; engine order lines are text-labeled but not in the legend. Optional shading of critical speed zones is not implemented.
• SC-03: Data Mapping (3/3) - X=RPM, Y=Hz correctly assigned, all data visible within domain.
• SC-04: Title & Legend (3/3) - Title format "campbell-basic · altair · pyplots.ai" correct. Legend labels match mode names.

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) - Shows 5 modes with realistic variation (some increasing, some decreasing with speed), 3 engine orders, multiple critical intersections. Good variety, though gyroscopic effects could be more pronounced.
• DQ-02: Realistic Context (5/5) - Real rotordynamic engineering scenario with proper mode labels (1st Bending, 2nd Bending, 1st Torsional, Axial, 3rd Bending).
• DQ-03: Appropriate Scale (4/4) - Base frequencies 45–220 Hz and speed range 0–6000 RPM are realistic for rotating machinery.

Code Quality (9/10)

• CQ-01: KISS Structure (3/3) - Imports → Data → Plot → Save with no functions or classes.
• CQ-02: Reproducibility (2/2) - np.random.seed(42) set.
• CQ-03: Clean Imports (2/2) - All imports used (altair, numpy, pandas).
• CQ-04: Code Elegance (1/2) - Somewhat verbose: manual loops for engine order layers and label positioning, dense resampling for intersection finding. Functional but could be more concise.
• CQ-05: Output & API (1/1) - Saves as plot.png and plot.html, no deprecated functions.

Library Mastery (8/10)

• LM-01: Idiomatic Usage (4/5) - Good declarative encoding, layered composition, Scale/Legend config. Manual loop for engine order layers is less idiomatic than using a single chart with color encoding.
• LM-02: Distinctive Features (4/5) - Uses Altair-specific layered composition (+ operator), declarative encoding types (:Q, :N), alt.value() for fixed aesthetics, interactive tooltips on critical points, HTML export, and configure_* methods.

Strengths

• Excellent text legibility with all font sizes explicitly configured (title 28pt, axes 22pt, ticks 18pt, legend 14-16pt)
• Realistic rotordynamic engineering data with proper mode labels and plausible frequency/speed ranges
• Clear visual hierarchy: solid colored lines for modes vs. dashed grey for engine orders, with red diamond critical speed markers as focal points
• Good use of Altair's layered composition and interactive tooltips on critical speed markers
• Clean KISS code structure with no unnecessary abstractions

Weaknesses

• Legend only shows natural frequency modes; engine order lines are not included in the legend, making it harder for unfamiliar viewers to understand the diagram
• Engine order lines at opacity 0.5 are slightly too faint — could be more visible while still remaining secondary to mode lines
• No annotations or context around critical speed intersections to help tell the data story (e.g., labeling key intersections or highlighting an operating range)
• Code is verbose with separate loops for each engine order layer instead of a more idiomatic Altair approach

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 titled "campbell-basic · altair · pyplots.ai" at the top left. The X-axis is "Rotational Speed (RPM)" (0–6000) and the Y-axis is "Frequency (Hz)" (0–310). Five solid colored lines represent natural frequency modes: 1st Bending (blue, ~45 Hz rising), 2nd Bending (orange, ~95 Hz slightly decreasing), 1st Torsional (green, ~130 Hz rising), Axial (purple, ~175 Hz nearly flat), and 3rd Bending (red, ~220 Hz decreasing). Three dashed gray diagonal lines from the origin represent engine orders labeled "1x", "2x", and "3x" near the right edge. Red diamond markers with white stroke highlight critical speed intersections. Three text annotations in dark red label "1st Bending / 3x", "1st Bending / 2x", and "1st Bending / 1x" near their respective intersections. A light blue semi-transparent vertical band marks the "Operating Range" (3000–5000 RPM) with an italic label at the bottom. Two separate legends on the right distinguish Natural Frequencies (5 colored lines) and Excitation (dashed engine order line). The grid is subtle with low opacity. Overall layout is clean and professional.

Quality Score: 86/100

Criteria Checklist

Visual Quality (26/30)

• VQ-01: Text Legibility (8/8) - All font sizes explicitly set: title 28pt, axis title 22pt, tick labels 18pt, legend 14-16pt, annotations 12-16pt
• VQ-02: No Overlap (5/6) - Minor: "1st Bending / 1x" annotation slightly crowded near data lines; mostly clean
• VQ-03: Element Visibility (6/6) - Lines at strokeWidth=3 well differentiated, engine orders dashed at 1.5, diamond markers size=280 with white stroke clearly visible
• VQ-04: Color Accessibility (3/4) - Blue (#306998) and purple (#8172B2) may be hard to distinguish for some colorblind viewers; other colors well separated
• VQ-05: Layout Balance (2/4) - Right-side legends consume significant space, plot area doesn't fill canvas optimally; some wasted whitespace
• 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) - Custom 5-color palette, dashed gray engine orders, diamond markers with white stroke, operating range band — clearly above defaults but not quite FiveThirtyEight-level
• DE-02: Visual Refinement (4/6) - Subtle grid (opacity 0.12), removed view stroke, clean axis styling with light domain/tick colors
• DE-03: Data Storytelling (4/6) - Operating range band and critical speed annotations create clear narrative; visual hierarchy (solid vs dashed) guides the reader to distinguish modes from excitations

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) - Correct Campbell Diagram with frequency vs RPM, engine order overlay lines, and critical speed identification
• SC-02: Required Features (4/4) - All spec features present: engine order lines from origin, natural frequency curves with speed-dependent variation, critical speed diamond markers, mode labels, EO labels, operating range highlight, clean legend
• SC-03: Data Mapping (3/3) - X=RPM, Y=Frequency(Hz), correctly mapped
• SC-04: Title & Legend (3/3) - Title "campbell-basic · altair · pyplots.ai" correct; two legends properly distinguish natural frequencies from excitation lines

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) - Shows 5 modes with varying behavior (some increase, some decrease with speed), 3 engine orders, multiple intersections; could show slightly more pronounced gyroscopic effects
• DQ-02: Realistic Context (5/5) - Plausible rotordynamic scenario with realistic mode names (1st Bending, 2nd Bending, 1st Torsional, Axial, 3rd Bending)
• DQ-03: Appropriate Scale (4/4) - Frequencies 45-220 Hz base, RPM 0-6000, engine orders 1x-3x — all physically plausible for rotating machinery

Code Quality (9/10)

• CQ-01: KISS Structure (3/3) - Imports → data generation → plot → save, no functions/classes
• CQ-02: Reproducibility (2/2) - np.random.seed(42) set
• CQ-03: Clean Imports (2/2) - Only altair, numpy, pandas — all used
• CQ-04: Code Elegance (1/2) - Well-organized but verbose with multiple DataFrames and a dummy chart for the EO legend entry
• CQ-05: Output & API (1/1) - Saves plot.png and plot.html

Library Mastery (8/10)

• LM-01: Idiomatic Usage (4/5) - Good use of declarative encoding, layered composition with +, resolve_scale, configure_* chains; intersection math necessarily done in numpy
• LM-02: Distinctive Features (4/5) - resolve_scale(color="independent") for separate legends, layered composition operator, mark_rect for range band, tooltip encoding on critical points, dual HTML+PNG export

Strengths

• Excellent spec compliance: all required Campbell Diagram elements present (engine order lines, natural frequency curves, critical speed markers, mode labels, operating range band)
• Strong data storytelling: operating range band and critical speed annotations create clear narrative for engineering analysis
• Good Altair idiom usage: layered composition, independent color scale resolution, and declarative encoding
• Visually polished: custom color palette, subtle grid, diamond markers with white stroke, dashed engine order lines differentiated from solid mode curves
• Realistic rotordynamic data with physically plausible mode frequencies and engine order intersections

Weaknesses

• Layout balance: legends on the right consume too much space, reducing the effective plot area; consider making the legend more compact or repositioning
• Blue (#306998) and purple (#8172B2) mode lines are somewhat hard to distinguish, especially for colorblind viewers; consider increasing color distance between these two
• The "1st Bending / 1x" annotation near RPM 4400 is slightly crowded near the data; annotation placement could be refined
• The dummy chart for the engine order legend entry is a workaround that adds code complexity; could explore if Altair has a cleaner way to add custom legend entries

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 titled "campbell-basic · altair · pyplots.ai" with subtitle "Natural Frequency Modes vs Engine Order Excitations". The X-axis shows "Rotational Speed (RPM)" ranging from 0 to ~6200, and the Y-axis shows "Frequency (Hz)" from 0 to 310. Five natural frequency mode curves are drawn as thick solid lines in distinct colors: blue (1st Bending), orange (2nd Bending), green (1st Torsional), purple (Axial), and red (3rd Bending). Three dashed gray engine order lines (1x, 2x, 3x) emanate diagonally from the origin, with text labels at the right edge. Red diamond markers identify critical speed intersections where engine order lines cross natural frequency curves — larger diamonds highlight intersections within the operating range. A translucent light-blue shaded band marks the "Operating Range" (3000–5000 RPM) with an italic label at the bottom. Three text annotations in dark red identify key critical speeds: "1st Bending / 3x", "1st Bending / 1x", and "2nd Bending / 1x". Two separate legends on the right distinguish "Engine Orders" (dashed gray lines) from "Natural Frequencies" (colored solid lines). The grid is very subtle and the overall design is clean and professional.

Quality Score: 85/100

Criteria Checklist

Visual Quality (26/30)

• VQ-01: Text Legibility (8/8) — All font sizes explicitly set: title 28pt, axis titles 22pt, tick labels 18pt, legend 13–14pt. All text clearly readable.
• VQ-02: No Overlap (5/6) — The "1st Bending / 1x" and "2nd Bending / 1x" annotations are very close together and partially overlap each other.
• VQ-03: Element Visibility (6/6) — Mode lines at strokeWidth=3, engine order lines at 1.5 with dashing, critical diamonds at 200–380 size — all well visible and proportioned.
• VQ-04: Color Accessibility (4/4) — Colorblind-safe palette with good perceptual separation between modes; engine orders use neutral gray.
• VQ-05: Layout & Canvas (2/4) — Legend occupies considerable right-side space. Upper region of the plot is largely empty. Acceptable but not optimal canvas utilization.
• 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) — Custom color palette, intentional dashed/solid distinction, size-differentiated critical markers, operating range band. Clearly above defaults but not quite publication-level polish.
• DE-02: Visual Refinement (4/6) — Subtle grid (opacity 0.10), view stroke removed, subdued axis styling. Legend layout could be tighter.
• DE-03: Data Storytelling (4/6) — Operating range band draws attention, larger diamonds highlight in-range critical speeds, text annotations identify key intersections. Viewer is guided to the most important information.

Spec Compliance (14/15)

• 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: engine order lines from origin, mode curves with gyroscopic variation, critical speed markers, mode labels, EO labels, legend, operating range shading.
• SC-03: Data Mapping (3/3) — X=RPM, Y=Hz, correctly mapped.
• SC-04: Title & Legend (2/3) — Title format correct. Two separate legends correctly distinguish modes from engine orders; engine order legend entries are all the same gray, which while accurate is slightly redundant.

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) — Five modes, varied gyroscopic behavior (increasing/decreasing), three engine orders, critical speeds in and out of operating range. Good coverage.
• DQ-02: Realistic Context (5/5) — Realistic rotordynamic scenario with correct terminology: 1st/2nd/3rd Bending, 1st Torsional, Axial modes.
• DQ-03: Appropriate Scale (4/4) — Frequency range (45–220 Hz base), speed range (0–6000 RPM), gyroscopic curvature are all realistic for rotating machinery.

Code Quality (9/10)

• CQ-01: KISS Structure (3/3) — Linear flow: imports → data → chart layers → compose → save.
• 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) — Generally clean but somewhat verbose with per-annotation DataFrame creation and offset handling.
• CQ-05: Output & API (1/1) — Saves plot.png and plot.html, no deprecated functions.

Library Mastery (8/10)

• LM-01: Idiomatic Usage (4/5) — Good declarative grammar: layered composition, encoding types, scales, resolve_scale(color="independent") for separate legends.
• LM-02: Distinctive Features (4/5) — Uses Altair-distinctive features: + layer composition, resolve_scale(color="independent") for multiple legends, alt.Title with subtitle, mark_rect for bands, tooltips on critical markers.

Strengths

• Comprehensive Campbell Diagram with all spec-required features: 5 modes, 3 engine orders, critical speed markers, and operating range shading
• Strong data storytelling through size-differentiated critical speed markers (larger in operating range) and targeted text annotations
• Clean colorblind-safe palette with good perceptual distinction between mode curves and engine order lines
• Effective use of Altair's layer composition and independent scale resolution for dual legends
• Realistic rotordynamic data with plausible gyroscopic effects (modes increasing and decreasing with speed)

Weaknesses

• The "1st Bending / 1x" and "2nd Bending / 1x" annotation labels are very close together and partially overlap, reducing readability
• Canvas utilization could be improved — the legend consumes significant right-side space and the upper plot region is largely empty
• Engine order legend entries are all identical gray, making the legend somewhat redundant (though direct labels on the right edge mitigate this)
• Per-annotation DataFrame creation in the code is verbose; a single DataFrame with dx/dy columns and a single mark_text layer would be cleaner

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 titled "campbell-basic · altair · pyplots.ai" with subtitle "Natural Frequency Modes vs Engine Order Excitations". The X-axis shows "Rotational Speed (RPM)" from 0 to 6,000 and the Y-axis shows "Frequency (Hz)" from 0 to 310. Five natural frequency mode curves are plotted as thick solid colored lines: 1st Bending (blue, gently rising), 2nd Bending (orange, gently falling), 1st Torsional (green, rising), Axial (purple, nearly flat), and 3rd Bending (red, falling). Three engine order excitation lines (1x, 2x, 3x) appear as dashed gray diagonal lines from the origin, labeled at the right edge. Red diamond markers indicate critical speed intersections where engine order lines cross mode curves — larger diamonds highlight intersections within the 3000–5000 RPM operating range, which is shown as a light blue shaded vertical band with an italic "Operating Range" label at the bottom. Three key critical speeds are annotated in dark red text: "1st Bending / 3x" (~988 RPM), "1st Bending / 1x" (~4273 RPM), and "1st Torsional / 2x" (~4747 RPM). A legend on the right lists all five natural frequency modes. The grid is very subtle and the overall appearance is clean and professional.

Quality Score: 85/100

Criteria Checklist

Visual Quality (26/30)

• VQ-01: Text Legibility (8/8) - All font sizes explicitly set: title 28pt, axis titles 22pt, tick labels 18pt, legend 13-14pt. All perfectly readable.
• VQ-02: No Overlap (5/6) - Mostly clean layout. Annotations are positioned to avoid overlap with smart dx/dy offsets. Minor tightness near right-edge engine order labels.
• VQ-03: Element Visibility (5/6) - Mode lines at strokeWidth=3 are clear. Critical speed diamonds well-sized (200/380). Engine order lines slightly faint at opacity 0.55.
• VQ-04: Color Accessibility (4/4) - Colorblind-safe palette with good contrast between all five mode colors. No red-green only distinction.
• VQ-05: Layout Balance (2/4) - Plot fills canvas reasonably but legend positioned outside to the right takes space. Operating range band extends full height appropriately. Some wasted space.
• VQ-06: Axis Labels & Title (2/2) - Descriptive labels with units: "Rotational Speed (RPM)" and "Frequency (Hz)".

Design Excellence (14/20)

• DE-01: Aesthetic Sophistication (6/8) - Strong design with custom palette, operating range shading, size-differentiated critical markers, direct engine order labels. Clearly above defaults but not quite publication-level polish.
• DE-02: Visual Refinement (4/6) - Subtle grid (opacity 0.10), view stroke removed, domain styled. Good refinement but not fully polished.
• DE-03: Data Storytelling (4/6) - Operating range highlight + size-differentiated markers + key annotations create clear visual hierarchy. Viewer immediately sees which critical speeds matter for the operating range.

Spec Compliance (14/15)

• SC-01: Plot Type (5/5) - Correct Campbell diagram with mode curves and engine order lines.
• SC-02: Required Features (3/4) - All major features present: EO lines, mode curves, critical markers, labels, legend. Operating range band present. No specific critical speed zone shading around individual intersections.
• SC-03: Data Mapping (3/3) - X=RPM, Y=Hz correctly assigned. All data visible within scale.
• SC-04: Title & Legend (3/3) - Title format correct. Legend shows "Natural Frequencies" with all 5 mode labels.

Data Quality (14/15)

• DQ-01: Feature Coverage (5/6) - 5 modes with varied behavior (rising/falling per gyroscopic effects), 3 engine orders, multiple critical speed intersections, operating range context.
• DQ-02: Realistic Context (5/5) - Realistic rotordynamics scenario with plausible mode names and frequency ranges for rotating machinery.
• DQ-03: Appropriate Scale (4/4) - Realistic values: 0-6000 RPM, 45-220 Hz base frequencies, sensible for turbomachinery analysis.

Code Quality (9/10)

• CQ-01: KISS Structure (3/3) - Imports → Data → Plot → Save. No functions or classes.
• CQ-02: Reproducibility (2/2) - np.random.seed(42) set.
• CQ-03: Clean Imports (2/2) - Only altair, numpy, pandas imported — all used.
• CQ-04: Code Elegance (1/2) - Slightly verbose annotation handling (individual chart layers per annotation). Critical speed detection is well-implemented but adds complexity.
• CQ-05: Output & API (1/1) - Saves as plot.png and plot.html correctly.

Library Mastery (8/10)

• LM-01: Idiomatic Usage (4/5) - Good declarative grammar usage: layer composition with +, encoding channels, scales, legends. Annotation loop is less idiomatic.
• LM-02: Distinctive Features (4/5) - Uses Altair-distinctive features: declarative layer composition, alt.Title with subtitle, detail encoding for grouping, mark_rect for bands, tooltip encoding. Grammar-of-graphics approach.

Strengths

• Excellent data storytelling through size-differentiated critical speed markers (larger in operating range) and targeted annotations for key intersections
• Clean colorblind-safe palette with good visual distinction between all five mode curves
• Direct engine order labeling at right edge instead of legend avoids clutter and improves readability
• Operating range shaded band provides immediate context for which critical speeds matter in practice
• Realistic rotordynamics data with physically plausible mode behaviors (gyroscopic stiffening/softening effects)
• Smart critical speed detection algorithm using sign-change method on dense interpolation grid

Weaknesses

• Engine order lines are slightly too faint at opacity 0.55 — increasing to 0.65-0.70 would improve visibility without overwhelming mode curves
• Layout balance could be improved — the legend takes significant space on the right side
• Annotation placement uses per-row chart layers which is verbose; could be consolidated into fewer layers
• No specific critical speed zone highlighting around individual intersections (spec mentions this as optional)

Verdict: APPROVED