feat(seaborn): implement line-realtime

[github-actions]

Implementation: line-realtime - seaborn

Implements the seaborn version of line-realtime.

File: plots/line-realtime/implementations/seaborn.py

Parent Issue: #3073

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays a real-time CPU usage monitoring chart with a blue line (#306998) showing CPU usage percentage over approximately 6 seconds (14:30:04 to 14:30:10). The line has a gradient fade effect where older data points on the left appear more transparent than recent data. Key features visible: a red "LIVE" indicator in the top-left corner, an arrow showing "Old data scrolls off" direction, the current value annotated as "Latest: 40.7%" in a yellow box with arrow pointing to the most recent data point (larger marker), scattered data points at key intervals along the line, Y-axis labeled "CPU Usage (%)" ranging 0-100, X-axis labeled "Time (HH:MM:SS)", a subtitle showing "Sliding window: 60 samples (6 sec)" in the bottom-right. The title follows the correct format. Background has a subtle light gray (#fafafa) with dotted grid lines.

Quality Score: 91/100

Criteria Checklist

Visual Quality (37/40 pts)

• VQ-01: Text Legibility (10/10) - Title 24pt bold, axis labels 20pt, tick labels 16pt - all perfectly readable
• VQ-02: No Overlap (8/8) - No overlapping text elements, rotated x-axis labels prevent overlap
• VQ-03: Element Visibility (7/8) - Line width 3 is good, alpha gradient effective, but some scatter points in the middle could be more prominent
• VQ-04: Color Accessibility (5/5) - Single blue color (#306998) with yellow accent - colorblind safe
• VQ-05: Layout Balance (5/5) - Plot fills canvas well, balanced margins, annotations well-placed
• VQ-06: Axis Labels (2/2) - "CPU Usage (%)" and "Time (HH:MM:SS)" both descriptive with units
• VQ-07: Grid & Legend (0/2) - Grid alpha 0.3 is good, but no legend present (only inline annotation)

Spec Compliance (24/25 pts)

• SC-01: Plot Type (8/8) - Correct line chart for real-time monitoring
• SC-02: Data Mapping (5/5) - Timestamp on X, CPU value on Y correctly assigned
• SC-03: Required Features (4/5) - Sliding window ✓, fade effect ✓, scroll direction indicator ✓, latest value annotation ✓. Missing: smooth animation (static image limitation acknowledged)
• SC-04: Data Range (3/3) - Y-axis 0-100% appropriate for CPU usage, X-axis shows full time window
• SC-05: Legend Accuracy (2/2) - Latest value label accurate (40.7%)
• SC-06: Title Format (2/2) - "line-realtime · seaborn · pyplots.ai" matches required format

Data Quality (18/20 pts)

• DQ-01: Feature Coverage (7/8) - Shows variation, spikes, baseline drift - good coverage but data somewhat monotonous in the 35-55% range for most of the window
• DQ-02: Realistic Context (7/7) - CPU usage monitoring is a real, neutral, practical scenario
• DQ-03: Appropriate Scale (4/5) - Values 35-70% realistic for CPU, though the one spike to ~68% is the only outlier - could show more dramatic variation

Code Quality (9/10 pts)

• CQ-01: KISS Structure (3/3) - Flat structure: imports → data → plot → save
• CQ-02: Reproducibility (3/3) - np.random.seed(42) set
• CQ-03: Clean Imports (2/2) - All imports used (matplotlib.pyplot, numpy, pandas, seaborn, DateFormatter)
• CQ-04: No Deprecated API (0/1) - Using segment-by-segment sns.lineplot in a loop is inefficient and not idiomatic seaborn
• CQ-05: Output Correct (1/1) - Saves as plot.png

Library Features (3/5 pts)

• LF-01: Uses distinctive library features (3/5) - Uses sns.lineplot but in a loop for gradient effect which is not idiomatic. The gradient fade is achieved by calling lineplot 59 times which is computationally inefficient. A more seaborn-idiomatic approach would use matplotlib LineCollection or a single line with different styling.

Strengths

• Excellent visual communication of real-time concept with LIVE indicator and scroll direction arrow
• Latest value annotation with contrasting yellow background draws attention effectively
• Alpha gradient fade effect successfully conveys older data visually
• Proper sliding window implementation showing 60 of 100 generated points
• Clean title format and axis labels with units
• Realistic CPU monitoring scenario with appropriate value ranges

Weaknesses

• Calling sns.lineplot 59 times in a loop is inefficient; consider using matplotlib LineCollection for gradient or a single seaborn call with post-processing
• Data lacks dramatic variation - mostly hovers around 35-50% with only one visible spike

Verdict: APPROVED