feat(plotly): implement scatter-annotated

[github-actions]

Implementation: scatter-annotated - plotly

Implements the plotly version of scatter-annotated.

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

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays a scatter chart of 12 tech companies comparing Market Cap (x-axis, in Billion USD) vs Annual Revenue (y-axis, in Billion USD). Each blue circular marker represents a company, with connecting arrows pointing to white-background annotation boxes containing company names in bold text. The title "scatter-annotated · plotly · pyplots.ai" appears at the top center. Companies shown include Amazon (highest revenue ~520B), Apple (highest market cap ~2800B), Microsoft, Alphabet, Meta, Tesla, Nvidia, Samsung, TSMC, Oracle, Salesforce, and Netflix. The plot uses a clean white template with subtle grid lines, and annotations are well-positioned with minimal overlap.

Quality Score: 92/100

Criteria Checklist

Visual Quality (37/40 pts)

• VQ-01: Text Legibility (10/10) - Title is large and clear, axis labels are well-sized (24pt), tick fonts are readable (18pt), annotations at 18pt are perfectly legible
• VQ-02: No Overlap (8/8) - All annotations are manually positioned with custom offsets to avoid overlap; each label is clearly readable without collision
• VQ-03: Element Visibility (7/8) - Markers size=20 with opacity=0.7 are well-sized for 12 points; white border provides good contrast. Slightly smaller than optimal for this data density.
• VQ-04: Color Accessibility (5/5) - Single blue color (#306998) is colorblind-safe; good contrast against white background
• VQ-05: Layout Balance (4/5) - Good use of canvas space; plot fills ~60% of canvas; margins are balanced. Minor: bottom-left area has some label clustering
• VQ-06: Axis Labels (2/2) - Descriptive with units: "Market Cap (Billion USD)" and "Annual Revenue (Billion USD)"
• VQ-07: Grid & Legend (1/2) - Grid is subtle (alpha 0.1), no legend needed for this plot type. Grid could be slightly more visible.

Spec Compliance (25/25 pts)

• SC-01: Plot Type (8/8) - Correct scatter plot with annotations
• SC-02: Data Mapping (5/5) - X=market cap (numeric), Y=revenue (numeric), labels=company names (string) - all correctly mapped
• SC-03: Required Features (5/5) - All spec features present: text annotations, connecting arrows from labels to points, moderate transparency (0.7), appropriate font size
• SC-04: Data Range (3/3) - Axes show all data with appropriate padding (range extends beyond min/max values)
• SC-05: Legend Accuracy (2/2) - N/A for this plot type (no legend needed)
• SC-06: Title Format (2/2) - Correct format: "scatter-annotated · plotly · pyplots.ai"

Data Quality (18/20 pts)

• DQ-01: Feature Coverage (7/8) - Shows variety of annotation positions, different data point distributions. Good spread across quadrants. Minor: could show more extreme outliers.
• DQ-02: Realistic Context (7/7) - Real tech companies with plausible market cap and revenue values; neutral business topic
• DQ-03: Appropriate Scale (4/5) - Values are realistic for 2024 tech companies. Minor: Nvidia's low revenue relative to market cap is accurate but some values slightly dated.

Code Quality (10/10 pts)

• CQ-01: KISS Structure (3/3) - Clean structure: imports → data → figure → trace → annotations → layout → save
• CQ-02: Reproducibility (3/3) - np.random.seed(42) is set (though not strictly needed since data is hardcoded)
• CQ-03: Clean Imports (2/2) - Only numpy and plotly.graph_objects imported, both used
• 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 (2/5 pts)

• LF-01: Uses distinctive library features (2/5) - Uses graph_objects annotations with arrows, but doesn't leverage plotly's interactive hover (disabled by using static mode primarily). Hover template is defined but the HTML export is secondary. Could better showcase plotly's interactivity as a core feature.

Strengths

• Excellent manual annotation positioning with custom offsets for each company prevents label overlap
• Clean annotation styling with white background boxes, blue borders, and connecting arrows
• Good use of realistic tech company data that makes the plot immediately comprehensible
• Proper title format and descriptive axis labels with units
• Both PNG and HTML exports provided

Weaknesses

• Does not fully leverage plotly's interactive capabilities as a distinctive feature (hover is secondary to static annotations)
• Grid opacity (0.1) is too subtle and could be slightly more visible (0.2-0.3 recommended)

Verdict: APPROVED