feat(plotnine): implement line-interactive

[github-actions]

Implementation: line-interactive - plotnine

Implements the plotnine version of line-interactive.

File: plots/line-interactive/implementations/plotnine.py

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays a server response time line chart spanning approximately one week (Jan 01-08, 2024). A blue line (#306998) with small scatter points shows response time variations ranging from ~90ms to ~270ms. Key visual elements include:

• Yellow tooltip box demonstrating hover functionality at "Time: 2024-01-04 03:00, Response: 161.9 ms"
• Teal shaded "Zoom Region" highlighting a data segment with "(use scroll/drag)" label
• Three red triangle markers indicating anomaly spikes
• Gray dashed horizontal line showing the average (~133 ms) with label
• Footer text explaining interactive controls: "Hover points for values • Scroll to zoom • Click-drag to pan • Home to reset"
• Title: "line-interactive · plotnine · pyplots.ai"
• X-axis: "Time" with datetime labels, Y-axis: "Response Time (ms)"

Quality Score: 85/100

Criteria Checklist

Visual Quality (34/40 pts)

• VQ-01: Text Legibility (9/10) - Title large and bold, axis labels readable, tick labels clear. Slight deduction: tooltip text could be slightly larger for optimal readability.
• VQ-02: No Overlap (8/8) - No overlapping text elements, all annotations well-positioned
• VQ-03: Element Visibility (7/8) - Line and markers visible, scatter points well-sized. Minor: anomaly markers could be slightly larger for emphasis.
• VQ-04: Color Accessibility (5/5) - Blue line, teal highlight, red anomalies, yellow tooltip - colorblind-safe palette
• VQ-05: Layout Balance (3/5) - Good canvas utilization but some wasted space at top; bottom footer slightly cramped
• VQ-06: Axis Labels (2/2) - Descriptive with units: "Response Time (ms)" and "Time"
• VQ-07: Grid & Legend (0/2) - Grid visible but no legend present (though this plot doesn't strictly need one, the anomaly markers and average line could benefit from legend entries)

Spec Compliance (20/25 pts)

• SC-01: Plot Type (8/8) - Correct line chart type
• SC-02: Data Mapping (5/5) - Datetime on X, response time on Y correctly mapped
• SC-03: Required Features (3/5) - Spec asks for actual interactivity (hover tooltips, zoom/pan, range selector). This is a static plotnine PNG that only simulates interactivity with annotations. Plotnine cannot produce true interactive output - this is AR-06 borderline.
• SC-04: Data Range (3/3) - All data visible within axes
• SC-05: Legend Accuracy (0/2) - No legend present for anomaly markers or average line
• SC-06: Title Format (2/2) - Correct format: "line-interactive · plotnine · pyplots.ai"

Data Quality (18/20 pts)

• DQ-01: Feature Coverage (7/8) - Shows time series patterns (daily cycles, weekly trends, spikes/anomalies). Missing: demonstration of range selection filtering
• DQ-02: Realistic Context (7/7) - Server response time monitoring is an excellent realistic scenario
• DQ-03: Appropriate Scale (4/5) - Response times 90-270ms are realistic; spike anomalies slightly high but plausible

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 appropriately
• CQ-04: No Deprecated API (1/1) - Current plotnine API
• CQ-05: Output Correct (1/1) - Saves as plot.png

Library Features (3/5 pts)

• LF-01: Uses distinctive library features (3/5) - Good use of ggplot grammar with geom_line, geom_point, geom_rect, geom_hline, annotate. However, plotnine's strengths (grammar of graphics, faceting, statistical transforms) aren't fully leveraged. The plot is essentially matplotlib-style annotated chart built with plotnine syntax.

Strengths

• Creative solution to demonstrate interactivity concepts in a static format using annotations
• Excellent realistic scenario (server response time monitoring)
• Clean, well-structured code following KISS principles
• Good use of visual hierarchy with tooltip, zoom region, and anomaly markers
• Proper datetime handling with scale_x_datetime
• Colorblind-safe color palette

Weaknesses

• plotnine is fundamentally a static plotting library and cannot provide actual interactivity (hover, zoom, pan) - the implementation simulates these with static annotations rather than delivering true interactive features
• No legend for the anomaly markers (red triangles) or average line (dashed gray)
• Bottom footer text is somewhat cramped and may be hard to read
• The "Interactive Controls" footer is misleading since this is a static PNG

Verdict: REJECTED

Reason for Rejection: The specification explicitly requires interactive features (hover tooltips, zoom/pan, range selection). While the implementation cleverly simulates these concepts with static annotations, plotnine cannot produce true interactive output. The score of 85 reflects good visual quality and code but the fundamental mismatch with spec requirements means this needs reconsideration.

Note: This may be an AR-06 (Not Feasible) case - plotnine as a ggplot2-based grammar of graphics library generates static plots and does not support true browser interactivity. The implementation should either acknowledge this limitation clearly or consider if plotnine is appropriate for this spec.

[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 line chart showing server response times over approximately one week (Jan 01 - Jan 09, 2024). A blue line with circular scatter points traces the response time data, showing cyclical daily patterns. Three red triangle markers highlight anomaly spikes at different points. A dashed gray horizontal line indicates the average response time (133 ms). A light teal shaded region demonstrates a "zoom region" concept. A yellow tooltip box near the center shows a simulated hover display with "Time: 2024-01-04 03:00, Response: 161.9 ms" with an arrow pointing to the data point. The title reads "line-interactive · plotnine · pyplots.ai", the Y-axis is labeled "Response Time (ms)", and the X-axis shows "Time" with rotated datetime labels. A small text at the bottom describes interactive controls. The background is white with subtle gray grid lines.

Quality Score: 87/100

Criteria Checklist

Visual Quality (34/40 pts)

• VQ-01: Text Legibility (9/10) - Title is bold and large (~24pt), axis labels are clear (~20pt), tick labels readable (~14pt). Slightly smaller than ideal for ticks.
• VQ-02: No Overlap (8/8) - No text overlapping, rotated x-axis labels work well
• VQ-03: Element Visibility (7/8) - Line and points are visible, though scatter points could be slightly larger for 200 data points
• VQ-04: Color Accessibility (4/5) - Blue/gray/red/teal color scheme is mostly accessible, though red triangles on blue could be challenging for some colorblind users
• VQ-05: Layout Balance (4/5) - Good use of canvas space, plot fills approximately 60-70% of canvas. Minor issue: legend is not visible in the rendered image
• VQ-06: Axis Labels (2/2) - "Response Time (ms)" includes units, "Time" is descriptive
• VQ-07: Grid & Legend (0/2) - Grid is subtle and appropriate, BUT legend is missing from the visible plot area

Spec Compliance (22/25 pts)

• SC-01: Plot Type (8/8) - Correct line chart type
• SC-02: Data Mapping (5/5) - X=datetime, Y=response time correctly mapped
• SC-03: Required Features (4/5) - Shows hover tooltip simulation, zoom region demonstration, anomaly markers. Missing: reset zoom button visual, pan demonstration
• SC-04: Data Range (3/3) - All data visible, Y-axis appropriately scaled
• SC-05: Legend Accuracy (0/2) - Legend is not visible in the rendered image despite being coded
• SC-06: Title Format (2/2) - Correct format: "line-interactive · plotnine · pyplots.ai"

Data Quality (18/20 pts)

• DQ-01: Feature Coverage (7/8) - Shows time series with daily patterns, anomaly spikes, average line, zoom region concept. Could show more variety in patterns.
• DQ-02: Realistic Context (7/7) - Server response time monitoring is a realistic, neutral scenario
• DQ-03: Appropriate Scale (4/5) - Response times of 90-260ms are realistic for server metrics

Code Quality (8/10 pts)

• CQ-01: KISS Structure (2/3) - Generally follows imports→data→plot→save, but has multiple DataFrames and complex annotation logic
• CQ-02: Reproducibility (3/3) - np.random.seed(42) is set
• CQ-03: Clean Imports (2/2) - All imports are used
• CQ-04: No Deprecated API (1/1) - No deprecated functions
• CQ-05: Output Correct (0/1) - Saves as 'plot.png' but verbose=False may hide issues

Library Features (5/5 pts)

• LF-01: Uses distinctive library features (5/5) - Good use of plotnine's grammar of graphics: ggplot(), multiple geoms (geom_line, geom_point, geom_rect), scale_color_manual, scale_x_datetime, theme customization, and annotate for simulating interactive features

Strengths

• Excellent creative approach to demonstrating interactive concepts in a static library through annotations (tooltip box, zoom region highlight)
• Realistic server monitoring scenario with daily/weekly patterns and anomaly spikes
• Good use of plotnine's grammar of graphics with layered geoms
• Clean datetime formatting on x-axis with appropriate rotation
• Well-designed color scheme for the main data elements

Weaknesses

• Legend is not visible in the final rendered image despite being coded - needs investigation/fix
• The code structure is complex with multiple DataFrames; could be simplified
• Scatter points could be larger for better visibility on the 4800x2700 canvas

Verdict: REJECTED

The implementation is strong but has a critical issue: the legend is not visible in the rendered output. This needs to be fixed to properly show the legend explaining the Response Time line, Anomaly Spike markers, and Average line. Once the legend visibility is resolved, this would be a high-quality implementation.

[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 server response time monitoring chart spanning approximately one week (Jan 01-09, 2024). A blue line traces response times ranging from ~80ms to ~260ms with clear daily patterns and three prominent spike anomalies marked with red triangles. A yellow tooltip demonstration box appears near the center showing "Time: 2024-01-04 03:00 / Response: 161.9 ms" with a connecting line to the data point. A teal shaded rectangle highlights a "Zoom Region" with "(use scroll/drag)" label. A gray dashed horizontal line indicates the average (~133 ms) with "Average: 133 ms" annotation. The title "line-interactive · plotnine · pyplots.ai" appears at the top in bold. X-axis shows "Time" with rotated date labels, Y-axis shows "Response Time (ms)". A subtle instructional footer reads "Interactive Controls: Hover points for values • Scroll to zoom • Click-drag to pan • Home to reset".

Quality Score: 88/100

Criteria Checklist

Visual Quality (35/40 pts)

• VQ-01: Text Legibility (9/10) - Title, axis labels, and tick labels are all clearly readable; tooltip text is slightly small but legible
• VQ-02: No Overlap (8/8) - No text overlap issues; rotated x-axis labels are well-spaced
• VQ-03: Element Visibility (7/8) - Line thickness is good, scatter points visible; anomaly markers prominent
• VQ-04: Color Accessibility (4/5) - Blue/red/gray palette is colorblind-friendly; good contrast
• VQ-05: Layout Balance (4/5) - Plot fills canvas well; minor issue with legend missing from view
• VQ-06: Axis Labels (2/2) - "Time" and "Response Time (ms)" with units
• VQ-07: Grid & Legend (1/2) - Grid is subtle; legend not visible in rendered image (may be cut off or not rendered)

Spec Compliance (22/25 pts)

• SC-01: Plot Type (8/8) - Correct line chart for time series
• SC-02: Data Mapping (5/5) - DateTime on X, response time on Y correctly mapped
• SC-03: Required Features (4/5) - Demonstrates tooltip, zoom region, anomaly markers; interactive controls are static demonstrations in plotnine
• SC-04: Data Range (3/3) - Full data range visible
• SC-05: Legend Accuracy (0/2) - Legend not visible in the rendered output
• SC-06: Title Format (2/2) - Uses correct "line-interactive · plotnine · pyplots.ai" format

Data Quality (19/20 pts)

• DQ-01: Feature Coverage (7/8) - Shows daily patterns, weekly trend, anomaly spikes, average reference
• DQ-02: Realistic Context (7/7) - Server response time monitoring is a realistic, neutral scenario
• DQ-03: Appropriate Scale (5/5) - Response times in 80-260ms range are realistic for server metrics

Code Quality (9/10 pts)

• CQ-01: KISS Structure (3/3) - Imports → Data → Plot → Save structure followed
• CQ-02: Reproducibility (3/3) - np.random.seed(42) set
• CQ-03: Clean Imports (2/2) - All imports are used
• CQ-04: No Deprecated API (1/1) - Uses current plotnine API
• CQ-05: Output Correct (0/1) - Saves correctly but verbose=False not standard

Library Features (3/5 pts)

• LF-01: Uses plotnine grammar of graphics (3/5) - Uses ggplot2-style syntax with multiple geoms, annotations, theming; good use of scale_color_manual, theme customization, and datetime scales

Strengths

• Excellent demonstration of interactive concepts (tooltip, zoom region, controls) adapted for static plotnine output
• Realistic server monitoring scenario with appropriate temporal patterns and anomaly spikes
• Clean grammar-of-graphics structure with properly layered geoms and annotations
• Good use of plotnine-specific features: scale_x_datetime, element_text styling, geom_rect for highlighting
• Clear visual hierarchy with main data, anomaly markers, and reference lines distinguished by color and shape

Weaknesses

• Legend is defined in code but not visible in the rendered output - may need legend_position adjustment or the legend is being cut off
• The instructional text at bottom ("Interactive Controls...") could be more prominent or better positioned

Verdict: APPROVED

This is attempt 3/3 and the score is 88/100 (≥50 threshold for final attempt). The implementation effectively demonstrates interactive chart concepts within plotnine's static output limitations. The legend visibility issue is minor and doesn't significantly impact the overall quality of the visualization.

[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 time series of server response times over approximately one week (Jan 01 to Jan 08, 2024). The main line is blue (#306998) showing response time fluctuations between ~90ms and ~260ms. Three red triangle markers indicate anomaly spikes at distinct peaks. A horizontal gray dashed line shows the average (~133ms) with a label. A yellow tooltip box demonstrates hover functionality, displaying "Time: 2024-01-04 03:00, Response: 161.9 ms" with a connector line to the data point. A teal/cyan shaded region highlights a "Zoom Region (use scroll/drag)" demonstrating range selection. At the bottom, gray text indicates "Interactive Controls: Hover points for values • Scroll to zoom • Click-drag to pan • Home to reset". The title correctly shows "line-interactive · plotnine · pyplots.ai". The x-axis shows "Time" with date/time labels, y-axis shows "Response Time (ms)".

Quality Score: 90/100

Criteria Checklist

Visual Quality (36/40 pts)

• VQ-01: Text Legibility (10/10) - Title at 24pt bold, axis titles at 20pt, axis text at 14pt, all clearly readable
• VQ-02: No Overlap (8/8) - No overlapping text elements, x-axis labels properly rotated
• VQ-03: Element Visibility (6/8) - Line width appropriate (1.8), scatter points visible but somewhat small at every 5th point
• VQ-04: Color Accessibility (5/5) - Blue main line, gray average, red anomalies, teal highlight - colorblind safe
• VQ-05: Layout Balance (3/5) - Good use of canvas but legend is missing from the visible plot (positioned off-screen or not rendering)
• VQ-06: Axis Labels (2/2) - "Response Time (ms)" includes units, "Time" is descriptive
• VQ-07: Grid & Legend (2/2) - Subtle grid with appropriate alpha

Spec Compliance (22/25 pts)

• SC-01: Plot Type (8/8) - Correct line chart for time series
• SC-02: Data Mapping (5/5) - Time on X, response time on Y correctly mapped
• SC-03: Required Features (4/5) - Demonstrates tooltip, zoom region, anomaly markers; however this is static output - plotnine cannot provide true interactivity
• SC-04: Data Range (3/3) - All data visible, y-axis includes headroom for annotations
• SC-05: Legend Accuracy (0/2) - Legend not visible in output (configured at position 0.85,0.75 but not appearing)
• SC-06: Title Format (2/2) - Correctly uses "line-interactive · plotnine · pyplots.ai"

Data Quality (20/20 pts)

• DQ-01: Feature Coverage (8/8) - Shows time series with daily/weekly patterns, anomaly spikes, average reference line
• DQ-02: Realistic Context (7/7) - Server response time monitoring is an excellent real-world scenario
• DQ-03: Appropriate Scale (5/5) - Response times 90-260ms are realistic for server metrics

Code Quality (9/10 pts)

• CQ-01: KISS Structure (3/3) - Clean imports → data → plot → save structure
• CQ-02: Reproducibility (3/3) - Uses np.random.seed(42)
• CQ-03: Clean Imports (2/2) - All imports used appropriately
• CQ-04: No Deprecated API (0/1) - Minor: size parameter in geom_line is deprecated, should use linewidth
• CQ-05: Output Correct (1/1) - Saves as plot.png

Library Features (3/5 pts)

• LF-01: Uses distinctive features (3/5) - Good use of plotnine's grammar of graphics (ggplot, aes, geoms, scales, themes), annotate for demonstrations, but library inherently cannot do interactivity

Strengths

• Excellent creative approach to demonstrating interactive concepts in a static library
• Realistic server monitoring scenario with meaningful patterns (daily cycles, anomaly spikes)
• Clean demonstration of tooltip, zoom region, and control instructions via annotations
• Proper use of plotnine grammar with well-structured theming
• Good color scheme and visual hierarchy
• Appropriate text sizing for 4800x2700 output

Weaknesses

• Legend not rendering in output despite being configured (legend_position may need adjustment)
• The size parameter in geom_line is deprecated in newer plotnine versions

Verdict: APPROVED

This is Attempt 3/3. The implementation creatively demonstrates interactive concepts within plotnine's static nature. The score of 90 meets the approval threshold, and the missing legend is a minor visual issue that doesn't significantly detract from the educational value of the plot. The implementation shows excellent understanding of both the spec requirements and the library's limitations.