feat(plotly): implement subplot-grid-custom

[github-actions]

Implementation: subplot-grid-custom - plotly

Implements the plotly version of subplot-grid-custom.

File: plots/subplot-grid-custom/implementations/plotly.py

Parent Issue: #2856

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays a custom subplot grid with 5 panels arranged in a 2×3 grid. The main title "subplot-grid-custom · plotly · pyplots.ai" is centered at the top in large font. The top-left panel ("Stock Price (2 Columns)") spans 2 columns and shows a blue line chart of stock price over time from January to April 2024, with price declining from ~108 to ~78. The top-right panel ("Category Performance") shows a yellow bar chart with 4 categories (Product A-D) with scores ranging from ~68 to ~91. The bottom row has three equal-width panels: "Trading Volume" (blue bar chart showing volume over time), "Revenue vs Expenses" (blue scatter plot showing positive correlation), and "Daily Returns Distribution" (yellow histogram of returns centered around 0%). All panels use the Python blue (#306998) and yellow (#FFD43B) color scheme. Axis labels include units where appropriate.

Quality Score: 92/100

Criteria Checklist

Visual Quality (36/40 pts)

• VQ-01: Text Legibility (9/10) - all text readable, title size 32pt, subplot titles 20pt, tick labels 14pt - good but tick labels could be slightly larger
• VQ-02: No Overlap (8/8) - no overlapping text anywhere
• VQ-03: Element Visibility (7/8) - line width 3 for main plot, markers size 12 for scatter, bars clearly visible - slightly small markers for scatter
• VQ-04: Color Accessibility (5/5) - blue and yellow are colorblind-safe, good contrast
• VQ-05: Layout Balance (5/5) - excellent use of canvas, subplot grid well proportioned, main plot appropriately larger
• VQ-06: Axis Labels (2/2) - all axes have descriptive labels with units (Price ($), Volume (K), Revenue ($K), etc.)
• VQ-07: Grid & Legend (0/2) - no grid lines visible (plotly_white template), no legend needed

Spec Compliance (25/25 pts)

• SC-01: Plot Type (8/8) - correct custom subplot grid with non-uniform cell sizes (colspan=2 for main plot)
• SC-02: Data Mapping (5/5) - X/Y correctly assigned in all subplots
• SC-03: Required Features (5/5) - has colspan spanning, multiple plot types (line, bar, scatter, histogram), dashboard-style layout
• SC-04: Data Range (3/3) - all data visible within axes
• SC-05: Legend Accuracy (2/2) - no legend needed, subplot titles serve as identifiers
• SC-06: Title Format (2/2) - correct format: "subplot-grid-custom · plotly · pyplots.ai"

Data Quality (18/20 pts)

• DQ-01: Feature Coverage (7/8) - shows multiple plot types and span configurations, but no rowspan demonstrated (only colspan)
• DQ-02: Realistic Context (7/7) - financial dashboard scenario with stock price, volume, revenue/expenses, returns - very realistic
• DQ-03: Appropriate Scale (4/5) - realistic values overall, though stock dropping from 108 to 78 in 4 months is steep

Code Quality (10/10 pts)

• CQ-01: KISS Structure (3/3) - linear structure: imports → data → plot → save
• CQ-02: Reproducibility (3/3) - np.random.seed(42) set
• CQ-03: Clean Imports (2/2) - all imports used (numpy, pandas, plotly.graph_objects, plotly.subplots)
• CQ-04: No Deprecated API (1/1) - using current plotly API
• CQ-05: Output Correct (1/1) - saves as plot.png and plot.html

Library Features (3/5 pts)

• LF-01: Distinctive Features (3/5) - uses make_subplots with specs for custom grid, graph_objects for fine control, but doesn't leverage interactivity features like hover customization

Strengths

• Excellent implementation of custom subplot grid with colspan specification
• Clean, well-structured code following KISS principles
• Realistic financial dashboard scenario with coherent data story
• Proper title format and good use of Python blue/yellow color scheme
• All subplots have clear, descriptive titles and axis labels with units
• Good use of plotly's make_subplots with specs parameter for non-uniform grid

Weaknesses

• No rowspan demonstration (spec mentions both colspan AND rowspan)
• Grid lines not visible (could add subtle grid for better readability)
• Scatter plot markers could be slightly larger for the data density (50 points)

Verdict: APPROVED