feat(matplotlib): implement scatter-pitch-events

[github-actions]

Implementation: scatter-pitch-events - matplotlib

Implements the matplotlib version of scatter-pitch-events.

File: plots/scatter-pitch-events/implementations/matplotlib.py

Parent Issue: #4417

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays a soccer pitch event map on a dark navy (#1a1a2e) background with a forest green (#2d6a4f) pitch surface. Standard FIFA pitch markings are drawn in light gray/white, including the outer boundary, halfway line, center circle with center spot, both penalty areas with penalty spots and arcs, goal areas, corner arcs, and goal posts rendered as thick white lines. Four event types are scattered across the pitch: cyan circles with directional arrows for passes (~120, distributed broadly), pink/magenta stars with arrows for shots (~25, concentrated in the right attacking third pointing toward goal), yellow/gold upward triangles for tackles (~40, spread across defensive and midfield zones), and green diamonds for interceptions (~35, distributed across the field). Successful events appear bright and opaque while unsuccessful ones are faded/transparent. A horizontal legend bar at the bottom displays all six categories (Pass, Shot, Tackle, Interception, Successful bright, Unsuccessful faded) against the dark background. The title "scatter-pitch-events · matplotlib · pyplots.ai" appears centered at the top in light gray text.

Score: 83/100

Category	Score	Max
Visual Quality	24	30
Design Excellence	13	20
Spec Compliance	15	15
Data Quality	15	15
Code Quality	9	10
Library Mastery	7	10
Total	83	100

Visual Quality (24/30)

• VQ-01: Text Legibility (6/8) — Title explicitly set at 24pt; legend fontsize 14 is below recommended 16pt; pass arrow linewidth 1.5 is thin for high-res output
• VQ-02: No Overlap (5/6) — Minor overlap among dense pass arrows in central areas, but all text elements are clear and readable
• VQ-03: Element Visibility (5/6) — Events generally visible; 120 pass arrows create some visual clutter; shot stars and other markers well-sized
• VQ-04: Color Accessibility (3/4) — Cyan, pink, yellow, green are distinct, but cyan (#48bfe3) and green (#80ed99) could be problematic for deuteranopia
• VQ-05: Layout & Canvas (4/4) — Pitch fills canvas well with balanced margins, nothing cut off
• VQ-06: Axis Labels & Title (1/2) — Axes appropriately turned off for pitch diagram; title present in correct format; no dimensional context (e.g., meters) indicated

Design Excellence (13/20)

• DE-01: Aesthetic Sophistication (6/8) — Strong custom dark theme with cohesive vibrant palette against dark background; white edge highlighting on markers adds polish; intentional color hierarchy
• DE-02: Visual Refinement (4/6) — Axes off (appropriate for pitch), dark background provides natural framing, pitch markings are subtle, good whitespace around pitch
• DE-03: Data Storytelling (3/6) — Spatial clustering creates natural storytelling (shots near goal, passes spanning field), opacity encoding adds analytical depth, but no explicit focal point or key tactical insight highlighted

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) — Correct scatter plot on accurately scaled pitch diagram
• SC-02: Required Features (4/4) — All features present: pitch markings (penalty areas, goal areas, center circle, halfway line, corner arcs, goals), distinct marker shapes/colors per event type, outcome encoding via opacity, directional arrows for passes and shots, green pitch background, correct aspect ratio
• SC-03: Data Mapping (3/3) — X/Y correctly mapped to 105m × 68m pitch dimensions
• SC-04: Title & Legend (3/3) — Title format "scatter-pitch-events · matplotlib · pyplots.ai" correct; legend shows all event types and outcome encoding

Data Quality (15/15)

• DQ-01: Feature Coverage (6/6) — All 4 event types with both success/failure outcomes, directional arrows, realistic spatial distribution across pitch zones
• DQ-02: Realistic Context (5/5) — Soccer match events with realistic distributions: passes most frequent (78% success), shots in attacking third (35% success), tackles defensive/midfield, interceptions distributed
• DQ-03: Appropriate Scale (4/4) — FIFA-standard 105×68m pitch, realistic event counts (120 passes, 25 shots, 40 tackles, 35 interceptions), plausible success rates

Code Quality (9/10)

• CQ-01: KISS Structure (3/3) — Clean imports → data → plot → save flow, no functions or classes
• CQ-02: Reproducibility (2/2) — np.random.seed(42) set
• CQ-03: Clean Imports (2/2) — All imports used (matplotlib.patches, matplotlib.pyplot, numpy)
• CQ-04: Code Elegance (1/2) — Slightly verbose with individual for-loops for pass/shot arrows and duplicated scatter calls for success/fail variants of tackles and interceptions
• CQ-05: Output & API (1/1) — Saves as plot.png with dpi=300, bbox_inches='tight'

Library Mastery (7/10)

• LM-01: Idiomatic Usage (4/5) — Good use of Axes methods, patches module for pitch geometry, annotate for directional arrows, scatter for grouped events
• LM-02: Distinctive Features (3/5) — Leverages matplotlib-specific patches (Rectangle, Circle, Arc) for pitch markings, custom legend construction with Line2D proxy artists, annotate with arrowprops for directional visualization

Score Caps Applied

• None — no cap conditions triggered

Strengths

• Excellent pitch rendering with all FIFA-standard markings accurately positioned (penalty areas, arcs, center circle, corner arcs, goals)
• Cohesive dark theme design with vibrant, well-chosen event colors that stand out against the green pitch
• Perfect spec compliance — all required features implemented including directional arrows and outcome encoding
• Realistic data generation with plausible event counts, spatial distributions, and success rates

Weaknesses

• Legend fontsize (14pt) is below the recommended 16pt for high-resolution output
• Pass arrows at 120 events create visual clutter — could benefit from reduced count or thinner/shorter arrows
• Cyan and green markers may be difficult to distinguish for colorblind viewers
• No visual emphasis or focal point to guide tactical insight (e.g., highlighting a key zone or pattern)
• Duplicated scatter calls for success/fail variants could be more concise

Issues Found

1. VQ-01 MEDIUM: Legend fontsize 14 below recommended 16pt threshold
   • Fix: Increase legend fontsize to 16
2. VQ-04 MEDIUM: Cyan (#48bfe3) and green (#80ed99) may confuse deuteranopic viewers
   • Fix: Replace one color to increase perceptual distance (e.g., use orange or purple instead of green)
3. DE-03 LOW: No visual hierarchy or focal point guiding the viewer to a tactical insight
   • Fix: Add subtle zone shading, highlight a key attacking corridor, or vary marker sizes to create emphasis
4. CQ-04 LOW: Duplicated scatter calls and verbose individual arrow loops
   • Fix: Consolidate success/fail scatter calls or use vectorized approaches where possible

AI Feedback for Next Attempt

Increase legend fontsize to 16pt. Replace the green interception color (#80ed99) with a more colorblind-distinguishable alternative (e.g., orange or purple) to improve accessibility alongside the cyan passes. Add visual storytelling through subtle zone highlighting, a heat-density overlay, or size variation to create a focal point that guides tactical interpretation. Consider consolidating the duplicated success/fail scatter calls to reduce code verbosity.

Verdict: REJECTED

[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 soccer pitch on a dark green (#2d6a4f) background with a dark navy (#1a1a2e) frame. Standard FIFA pitch markings are drawn in light gray — penalty areas, goal areas, center circle, halfway line, corner arcs, and goal posts (white). Four event types are plotted with distinct markers and colors: passes (cyan circles with directional arrows), shots (magenta/pink stars with bold arrows concentrated in the attacking third), tackles (gold triangles spread across defensive/midfield zones), and interceptions (orange diamonds distributed broadly). Successful events appear at high opacity while unsuccessful ones are faded. A subtle amber-highlighted zone in the right third is labeled "Attacking Third" in yellow text. The legend at the bottom displays all four event types plus success/failure encoding. Title reads "scatter-pitch-events · matplotlib · pyplots.ai" in light gray with a dark stroke effect.

Score: 89/100

Category	Score	Max
Visual Quality	26	30
Design Excellence	15	20
Spec Compliance	15	15
Data Quality	15	15
Code Quality	10	10
Library Mastery	8	10
Total	89	100

Visual Quality (26/30)

• VQ-01: Text Legibility (7/8) — All font sizes explicitly set (title 24pt, legend 16pt, zone label 14pt). All text clearly readable. Minor: zone label could be larger.
• VQ-02: No Overlap (5/6) — No text overlap. Some marker clustering in the attacking third is natural for the domain but slightly dense.
• VQ-03: Element Visibility (5/6) — Shots (markersize=16) and scatter markers (s=140-180) are well-sized. Pass origin dots (markersize=4) are small but arrows compensate. Unsuccessful passes at alpha=0.2 are very faint.
• VQ-04: Color Accessibility (3/4) — Cyan, magenta, gold, orange are largely distinguishable. However, gold (#ffd166) and orange (#ff9f1c) are close in hue — saved by distinct marker shapes (triangle vs diamond).
• VQ-05: Layout & Canvas (4/4) — Pitch fills canvas well with 16:9 figsize. Equal aspect ratio maintained. Legend positioned cleanly below.
• VQ-06: Axis Labels & Title (2/2) — Axes appropriately turned off for pitch diagram. Title in correct format.

Design Excellence (15/20)

• DE-01: Aesthetic Sophistication (6/8) — Strong dark theme with custom color palette. Path effects on title and zone text add polish. White edge highlights on markers. Professional appearance clearly above defaults.
• DE-02: Visual Refinement (5/6) — Axes hidden (appropriate), dark background with contrasting pitch, custom legend styling with facecolor/edgecolor, subtle zone highlight with rounded corners. Well-refined.
• DE-03: Data Storytelling (4/6) — "Attacking Third" zone highlight creates a clear focal point. Shots concentrated there with prominent star markers and bold arrows naturally draw the eye. Success/failure opacity encoding tells part of the tactical story.

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) — Correct scatter plot on pitch diagram with event markers.
• SC-02: Required Features (4/4) — All spec requirements met: accurate pitch markings (penalty areas, goal areas, center circle, halfway line, corner arcs, goals), distinct markers/colors per event type, outcome encoding via opacity, directional arrows for passes and shots, green pitch background, correct aspect ratio.
• SC-03: Data Mapping (3/3) — X/Y correctly mapped to pitch coordinates (0–105 × 0–68).
• SC-04: Title & Legend (3/3) — Title format correct. Legend comprehensive with all event types plus success/failure encoding.

Data Quality (15/15)

• DQ-01: Feature Coverage (6/6) — All four event types shown with both successful and unsuccessful outcomes. Good spatial distribution matching real match patterns.
• DQ-02: Realistic Context (5/5) — Soccer match events — neutral, comprehensible domain. Event counts realistic (70 passes, 25 shots, 40 tackles, 35 interceptions). Success rates plausible (78% pass, 35% shot).
• DQ-03: Appropriate Scale (4/4) — FIFA standard pitch (105×68m). Event positions distributed realistically across zones.

Code Quality (10/10)

• CQ-01: KISS Structure (3/3) — Linear flow: imports → data → plot → save. No functions/classes.
• CQ-02: Reproducibility (2/2) — np.random.seed(42) set.
• CQ-03: Clean Imports (2/2) — All imports used: patches, patheffects, pyplot, numpy, to_rgba.
• CQ-04: Code Elegance (2/2) — Clean mix of vectorized scatter calls for tackles/interceptions and loops for arrow-annotated events. Appropriate complexity.
• CQ-05: Output & API (1/1) — Saves as plot.png, dpi=300, bbox_inches='tight'. No deprecated API.

Library Mastery (8/10)

• LM-01: Idiomatic Usage (4/5) — Good use of ax methods, patches (Rectangle, Circle, Arc, FancyBboxPatch), annotate with arrowprops, path_effects. Proper Axes-level API.
• LM-02: Distinctive Features (4/5) — Uses matplotlib-specific features: patches module for pitch shapes, Arc for penalty arcs, FancyBboxPatch for zone highlight, patheffects for text strokes, to_rgba for per-point alpha control.

Score Caps Applied

• None — no cap conditions triggered.

Strengths

• Excellent pitch rendering with accurate FIFA dimensions and all required markings
• Professional dark theme with cohesive custom color palette and path effects
• "Attacking Third" zone highlight creates genuine data storytelling and focal point
• All spec requirements fully satisfied with comprehensive legend
• Clean, well-structured code with good use of matplotlib-specific features

Weaknesses

• Gold (#ffd166) and orange (#ff9f1c) tackle/interception colors are too similar in hue — relies on shape distinction alone
• Pass origin markers (markersize=4) are small; unsuccessful passes at alpha=0.2 are nearly invisible
• Zone label "Attacking Third" at 14pt could be slightly larger for the canvas size

Issues Found

1. VQ-04 MINOR: Gold and orange colors are close in hue
   • Fix: Increase color contrast between tackle and interception markers (e.g., use a green-teal or purple for one)
2. VQ-03 MINOR: Unsuccessful pass markers nearly invisible at alpha=0.2 with markersize=4
   • Fix: Raise unsuccessful pass alpha to 0.3 and/or increase pass origin marker size to 5-6
3. VQ-01 MINOR: Zone label at 14pt is slightly undersized
   • Fix: Increase "Attacking Third" label to 16pt

AI Feedback for Next Attempt

Score is 89 — very close to approval. To reach 90+: (1) Differentiate tackle/interception colors more — replace one with a distinctly different hue like teal or purple to improve colorblind accessibility. (2) Increase unsuccessful pass visibility — raise alpha from 0.2 to 0.3 and pass origin markersize from 4 to 5. (3) Bump zone label fontsize from 14 to 16. These small refinements should push the score over the threshold.

Verdict: REJECTED

[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 soccer pitch event map on a dark navy background (#1a1a2e) with a dark green (#2d6a4f) pitch surface. Standard FIFA pitch markings (penalty areas, goal areas, center circle, halfway line, corner arcs, goals) are drawn in light gray (#e0e0e0). Four event types are scattered across the pitch: cyan circles with directional arrows for passes (distributed across the full pitch), magenta/pink star markers with bold arrows for shots (concentrated in the attacking third), gold triangle markers for tackles, and purple diamond markers for interceptions. A subtle "Attacking Third" zone highlight with golden text labels the right third of the pitch. Successful events appear bright (higher alpha) while unsuccessful events are faded (lower alpha). The title "scatter-pitch-events · matplotlib · pyplots.ai" appears at the top with a text stroke effect. A 6-item legend at the bottom identifies all event types plus the success/failure encoding. The pitch maintains correct 105:68 aspect ratio.

Score: 90/100

Category	Score	Max
Visual Quality	27	30
Design Excellence	15	20
Spec Compliance	15	15
Data Quality	15	15
Code Quality	10	10
Library Mastery	8	10
Total	90	100

Visual Quality (27/30)

• VQ-01: Text Legibility (7/8) — Title 24pt, legend 16pt, "Attacking Third" 18pt all explicitly set and readable. Minor: no axis labels to evaluate (axes off, appropriate for pitch diagram).
• VQ-02: No Overlap (5/6) — Minor overlap of pass arrows and markers in dense areas (especially attacking third), but expected with 170 events and doesn't impair readability.
• VQ-03: Element Visibility (5/6) — Markers well-sized (circles 6px, stars 16px, triangles s=180, diamonds s=140). Alpha distinction between success/failure works well. Slightly dense in the attacking third.
• VQ-04: Color Accessibility (4/4) — Cyan, magenta, gold, purple palette is colorblind-safe with excellent contrast against dark green pitch.
• VQ-05: Layout & Canvas (4/4) — Pitch fills canvas well with correct aspect ratio. Balanced margins, legend positioned neatly below.
• VQ-06: Axis Labels & Title (2/2) — Axes appropriately hidden for pitch diagram. Title in correct format.

Design Excellence (15/20)

• DE-01: Aesthetic Sophistication (6/8) — Strong design: dark theme with custom color palette, path effects on text, white edge highlights on markers, intentional visual hierarchy. Clearly above defaults but not quite publication-perfect.
• DE-02: Visual Refinement (5/6) — Axes off (appropriate), dark background polished, path effects on text, white marker edges, generous whitespace. The attacking zone highlight with FancyBboxPatch adds polish.
• DE-03: Data Storytelling (4/6) — The "Attacking Third" zone highlight creates a focal point. Shots concentrated there with distinctive star markers and bold arrows guide the viewer's eye. Alpha variation conveys success/failure narrative.

Spec Compliance (15/15)

• SC-01: Plot Type (5/5) — Scatter plot on accurately scaled pitch diagram with event markers — correct.
• SC-02: Required Features (4/4) — All spec requirements met: pitch markings (penalty areas, goal areas, center circle, halfway line, corner arcs, goals), distinct marker shapes/colors per event type, outcome encoding via opacity, directional arrows for passes and shots, green pitch background, correct aspect ratio.
• SC-03: Data Mapping (3/3) — X (0–105m) and Y (0–68m) correctly mapped to pitch coordinates.
• SC-04: Title & Legend (3/3) — Title "scatter-pitch-events · matplotlib · pyplots.ai" correct. Legend clearly identifies all 4 event types plus success/failure encoding.

Data Quality (15/15)

• DQ-01: Feature Coverage (6/6) — All 4 event types shown with both successful and unsuccessful outcomes. Passes distributed across pitch, shots in attacking third, tackles/interceptions spread realistically.
• DQ-02: Realistic Context (5/5) — Soccer match event data with realistic distributions: 70 passes (78% success), 25 shots (35% success), 40 tackles (65% success), 35 interceptions (80% success). Plausible match segment.
• DQ-03: Appropriate Scale (4/4) — 170 total events, FIFA pitch dimensions (105×68m), realistic event counts and success rates.

Code Quality (10/10)

• CQ-01: KISS Structure (3/3) — Linear flow: imports → data generation → pitch drawing → event plotting → styling → save. No functions/classes.
• CQ-02: Reproducibility (2/2) — np.random.seed(42) set at the start.
• CQ-03: Clean Imports (2/2) — All imports used: matplotlib.patches, matplotlib.patheffects, pyplot, numpy, to_rgba.
• CQ-04: Code Elegance (2/2) — Clean and well-organized. Uses vectorized scatter for tackles/interceptions, loops only where needed (arrows). No fake UI.
• CQ-05: Output & API (1/1) — Saves as plot.png with dpi=300, bbox_inches='tight'.

Library Mastery (8/10)

• LM-01: Idiomatic Usage (4/5) — Uses ax-level methods throughout, patches API for pitch elements, annotate with arrowprops for directional arrows, scatter with RGBA arrays for per-point alpha.
• LM-02: Distinctive Features (4/5) — Leverages matplotlib-specific features: patches (Rectangle, Circle, Arc, FancyBboxPatch), patheffects for text stroke, annotate arrowprops, to_rgba for per-point color arrays.

Score Caps Applied

• None — no score caps triggered.

Strengths

• Excellent pitch rendering with accurate FIFA dimensions and all required markings
• Strong dark theme with colorblind-safe palette and good visual hierarchy
• "Attacking Third" zone highlight adds tactical storytelling context
• All spec requirements fully implemented including directional arrows and outcome encoding
• Clean, well-structured code with good use of matplotlib-specific features

Weaknesses

• Minor marker overlap in dense areas (attacking third) could benefit from slight size reduction for shots
• Pass arrow density is high in some midfield zones, slightly reducing clarity

Issues Found

None — implementation meets all requirements at high quality.

AI Feedback for Next Attempt

N/A — implementation approved at 90/100. Strong design, full spec compliance, and good use of matplotlib features.

Verdict: APPROVED