feat(plotly): implement scatter-categorical

[github-actions]

Implementation: scatter-categorical - plotly

Implements the plotly version of scatter-categorical.

File: plots/scatter-categorical/implementations/plotly.py

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays a categorical scatter plot showing the relationship between Marketing Investment (%) on the X-axis and Sales Growth (%) on the Y-axis. Four distinct regions are represented: North (blue/steel blue), South (yellow/gold), West (purple/violet), and East (green/teal). Each region forms a visually distinguishable cluster of approximately 40 data points. The title "scatter-categorical · plotly · pyplots.ai" is centered at the top. The legend is positioned on the right side with a "Region" header and shows all four categories. Grid lines are subtle (light gray), and the background is clean white. Markers have slight transparency (0.7) with white borders, making overlapping points still distinguishable.

Quality Score: 93/100

Criteria Checklist

Visual Quality (37/40 pts)

• VQ-01: Text Legibility (10/10) - Title, axis labels, and tick marks are all clearly readable at the output resolution
• VQ-02: No Overlap (8/8) - No text overlap anywhere; legend is well-separated from data
• VQ-03: Element Visibility (7/8) - Markers are appropriately sized (14px) with good alpha (0.7) for ~160 total points; slight deduction as some points in dense areas could benefit from slightly smaller markers
• VQ-04: Color Accessibility (5/5) - Blue, yellow, purple, and green palette is colorblind-safe; no red-green only distinctions
• VQ-05: Layout Balance (5/5) - Plot fills canvas well with balanced margins; legend positioned neatly to the right
• VQ-06: Axis Labels (2/2) - Descriptive labels with units: "Marketing Investment (%)" and "Sales Growth (%)"
• VQ-07: Grid & Legend (0/2) - Grid is subtle at alpha 0.1 which is good, but legend could use a cleaner appearance (border is visible but thin)

Spec Compliance (25/25 pts)

• SC-01: Plot Type (8/8) - Correct categorical scatter plot
• SC-02: Data Mapping (5/5) - X and Y continuous variables correctly assigned, category mapped to color
• SC-03: Required Features (5/5) - All spec features present: distinct colors per category, legend, transparency for overlapping points
• SC-04: Data Range (3/3) - All data points visible within axes range
• SC-05: Legend Accuracy (2/2) - Legend correctly maps colors to region names with clear "Region" title
• SC-06: Title Format (2/2) - Correctly uses "scatter-categorical · plotly · pyplots.ai" format

Data Quality (18/20 pts)

• DQ-01: Feature Coverage (7/8) - Shows four distinct clusters with different center positions; demonstrates category separation well. Minor deduction: clusters overlap somewhat which is realistic but doesn't show maximum distinction
• DQ-02: Realistic Context (7/7) - Product performance across regions is a believable business scenario; neutral topic
• DQ-03: Appropriate Scale (4/5) - Percentage values are reasonable (20-120%), though some sales growth values above 100% are unusual

Code Quality (10/10 pts)

• CQ-01: KISS Structure (3/3) - Clean imports → data → plot → save structure; no functions or classes
• CQ-02: Reproducibility (3/3) - Uses np.random.seed(42)
• CQ-03: Clean Imports (2/2) - Only numpy and plotly.graph_objects used, both necessary
• CQ-04: No Deprecated API (1/1) - Uses current plotly API
• CQ-05: Output Correct (1/1) - Saves as plot.png and plot.html

Library Features (3/5 pts)

• LF-01: Uses distinctive library features (3/5) - Uses go.Scatter with custom hovertemplate for interactivity (visible in HTML output), white marker borders. Could leverage more plotly-specific features like animations or more advanced hover info

Strengths

• Excellent color palette that is colorblind-accessible (blue, yellow, purple, green)
• Clean layout with proper margins and well-positioned legend
• Good use of hovertemplate for interactive exploration in HTML output
• White marker borders provide visual distinction for overlapping points
• Realistic business context (regional product performance)
• Proper title format following pyplots.ai conventions

Weaknesses

• Grid alpha at 0.1 is perhaps too subtle; 0.2-0.3 would provide better reference without being distracting
• Legend border is minimal but could be removed entirely for cleaner look
• Some sales growth values exceed 100% which is mathematically possible but unusual

Verdict: APPROVED