feat(seaborn): implement candlestick-volume

[github-actions]

Implementation: candlestick-volume - seaborn

Implements the seaborn version of candlestick-volume.

File: plots/candlestick-volume/implementations/seaborn.py

Parent Issue: #3068

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays a professional dual-pane financial chart. The upper pane (approximately 75% of the vertical space) shows a candlestick chart with price data ranging from roughly $125 to $165 over 60 trading days from January to late March 2024. Candlesticks are colored in Python blue (#306998) for bullish days (close ≥ open) and yellow (#FFD43B) for bearish days. The lower pane (25%) shows volume bars using the same color scheme, ranging from 0 to about 7.5M shares. Both panes share a common x-axis with bi-weekly date labels. A legend in the upper-left explains the color coding. The title "candlestick-volume · seaborn · pyplots.ai" is centered at the top. Grid lines are subtle with alpha=0.3.

Quality Score: 76/100

Criteria Checklist

Visual Quality (32/40 pts)

• VQ-01: Text Legibility (10/10) - Title at 24pt, labels at 20pt, ticks at 16pt - all perfectly readable
• VQ-02: No Overlap (8/8) - No overlapping text elements
• VQ-03: Element Visibility (8/8) - Candlesticks and volume bars appropriately sized for 60 data points
• VQ-04: Color Accessibility (5/5) - Excellent colorblind-safe palette using blue/yellow instead of red/green
• VQ-05: Layout Balance (5/5) - Good 75%/25% split as specified, well-balanced margins
• VQ-06: Axis Labels (2/2) - "Price ($)" and "Volume" with units, "Date" for x-axis
• VQ-07: Grid & Legend (2/2) - Grid is subtle, legend well placed - deduct 0 → 2/2

Spec Compliance (18/25 pts)

• SC-01: Plot Type (8/8) - Correct candlestick chart with volume bars
• SC-02: Data Mapping (5/5) - OHLC and volume correctly mapped
• SC-03: Required Features (2/5) - Missing crosshair/cursor spanning both panes (-3)
• SC-04: Data Range (3/3) - All data visible with appropriate padding
• SC-05: Legend Accuracy (2/2) - Legend correctly explains bullish/bearish
• SC-06: Title Format (2/2) - Correct format: candlestick-volume · seaborn · pyplots.ai

Data Quality (18/20 pts)

• DQ-01: Feature Coverage (8/8) - Shows both bullish and bearish candles, varied volume
• DQ-02: Realistic Context (7/7) - Realistic stock price movement with trend and volatility
• DQ-03: Appropriate Scale (3/5) - Prices realistic but volume correlation to price moves somewhat artificial (-2)

Code Quality (8/10 pts)

• CQ-01: KISS Structure (3/3) - Linear script structure without functions/classes
• CQ-02: Reproducibility (3/3) - np.random.seed(42) set
• CQ-03: Clean Imports (2/2) - All imports used
• CQ-04: No Deprecated API (1/1) - Current APIs used
• CQ-05: Output Correct (1/1) - Saves as plot.png → 1/1

Library Features (0/5 pts)

• LF-01: Distinctive Features (0/5) - Critical issue: Only uses sns.set_style() and sns.set_context() for styling. All actual plotting is done with matplotlib (ax.bar, ax.plot). No seaborn plotting functions used.

Strengths

• Professional dual-pane layout with correct 75%/25% vertical split between price and volume
• Good colorblind-safe color scheme using Python blue (#306998) and yellow (#FFD43B) instead of red-green
• Volume bars correctly colored to match candlesticks for visual consistency
• Clean seaborn styling with whitegrid and talk context for readability
• Properly formatted date axis with bi-weekly Monday labels

Weaknesses

• Missing crosshair/cursor spanning both panes as specified in requirements
• Does not use seaborn plotting functions - only uses sns.set_style() and sns.set_context() for styling while actual plotting is done with matplotlib ax.bar() and ax.plot()
• Grid lines are not aligned across both panes - they use different scales and do not share visual alignment

Verdict: REJECTED

The implementation produces a visually appealing candlestick chart but has two significant issues: (1) it does not use seaborn's actual plotting capabilities - only styling functions, which may fail AR-05 library usage check in a stricter review, and (2) the spec-required crosshair feature is missing. While seaborn lacks native candlestick support, the implementation should attempt to leverage seaborn's strengths more (e.g., using seaborn for supplementary statistical overlays or annotations) or acknowledge this is primarily a matplotlib implementation with seaborn styling.

[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 professional dual-pane stock chart with 60 trading days of data (Jan 01 - Mar 25, 2024). The upper pane (~75% height) shows candlestick OHLC data with Python Blue (#306998) for bullish candles and Python Yellow (#FFD43B) for bearish candles. Each candlestick has a body showing open-close range and wicks showing high-low range. The lower pane (25% height) displays volume bars using the same color scheme. A legend in the upper left identifies "Bullish (Close ≥ Open)" and "Bearish (Close < Open)". The title "candlestick-volume · seaborn · pyplots.ai" appears at top. A static crosshair with price annotation ($145.77) is visible at the midpoint. Axes are labeled "Price ($)" and "Volume" with formatted tick labels (volume in millions format like "5.0M"). Grid lines are subtle and dashed.

Quality Score: 85/100

Criteria Checklist

Visual Quality (33/40 pts)

• VQ-01: Text Legibility (9/10) - Title, labels, and ticks are readable with appropriate sizes. Slight reduction for annotation font being small.
• VQ-02: No Overlap (8/8) - No overlapping text elements
• VQ-03: Element Visibility (6/8) - Candlesticks and volume bars visible, but some candlestick bodies appear thin when price change is small
• VQ-04: Color Accessibility (4/5) - Blue/yellow combination is colorblind-safe but not the most optimal contrast pairing
• VQ-05: Layout Balance (4/5) - Good 75/25 split, balanced margins, slight whitespace on right side
• VQ-06: Axis Labels (2/2) - Descriptive with units: "Price ($)", "Volume", "Date"
• VQ-07: Grid & Legend (0/2) - Legend placement is good but grid appears in front of some chart elements which is distracting

Spec Compliance (22/25 pts)

• SC-01: Plot Type (8/8) - Correct candlestick chart with volume
• SC-02: Data Mapping (5/5) - Date on X, Price/Volume on Y correctly assigned
• SC-03: Required Features (3/5) - Has dual pane, shared x-axis, color scheme, crosshair. Missing: crosshair spanning both panes fully (only vertical line, no horizontal in volume pane)
• SC-04: Data Range (3/3) - All data visible with appropriate padding
• SC-05: Legend Accuracy (2/2) - Legend correctly identifies Bullish/Bearish
• SC-06: Title Format (1/2) - Uses correct format but uses middot (·) which is good

Data Quality (18/20 pts)

• DQ-01: Feature Coverage (7/8) - Shows both bullish and bearish candles, varying volume, price trends. Good variety but some candles have very similar open/close values
• DQ-02: Realistic Context (7/7) - Stock price data with realistic OHLC relationships and volume correlation
• DQ-03: Appropriate Scale (4/5) - Price range ~$125-$165 and volume 1-8M are realistic for a mid-cap stock

Code Quality (9/10 pts)

• CQ-01: KISS Structure (3/3) - No functions/classes, linear flow
• CQ-02: Reproducibility (3/3) - Uses np.random.seed(42)
• CQ-03: Clean Imports (2/2) - All imports used (matplotlib.pyplot, numpy, pandas, seaborn, Patch)
• CQ-04: No Deprecated API (0/1) - Uses seaborn 0.13.2 but some patterns may need review for 0.14+ compatibility
• 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.set_style, sns.set_context, sns.lineplot, sns.barplot, but candlestick bodies are drawn with matplotlib fill_between rather than seaborn

Strengths

• Clean dual-pane layout with proper 75/25 height ratio as specified
• Consistent color scheme (Python Blue/Yellow) applied to both candlesticks and volume bars
• Good use of seaborn styling (whitegrid, talk context) for professional appearance
• Realistic stock data generation with OHLC relationships and volume correlation to price moves
• Shared x-axis with proper date formatting at regular intervals
• Well-implemented crosshair with price annotation

Weaknesses

• Grid lines appear in front of some chart elements (should use set_axisbelow consistently)
• Crosshair horizontal line only in price pane, not spanning to volume pane as spec suggests "cursor that spans both panes"
• Volume bars are rendered as grouped bars (side-by-side) due to hue parameter rather than overlapping single bars per day
• Some thin candlestick bodies when open/close are very close together reduce readability

Verdict: REJECTED

The implementation is good overall with proper structure and styling, but the volume bars appear as grouped/dodged bars instead of single bars per day (visible as pairs of blue/yellow bars side by side). The spec requires volume bars to match candlestick colors, meaning each day should have ONE bar colored based on whether that day was bullish or bearish, not two separate bars. This is a spec compliance issue that should be addressed.

[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 dual-pane candlestick chart with volume. The upper pane (~75% height) shows 60 candlesticks representing stock price movements from approximately $125 to $165 over January-March 2024. Candlesticks use Python Blue (#306998) for bullish days and Python Yellow (#FFD43B) for bearish days. Each candle shows clear wicks and bodies. The lower pane (~25% height) displays volume bars in matching colors. A legend in the upper-left identifies "Bullish (Close ≥ Open)" and "Bearish (Close &lt; Open)". Both panes share a common x-axis with date labels (Jan 01, Jan 15, Jan 29, Feb 12, Feb 26, Mar 11, Mar 25). The title "candlestick-volume · seaborn · pyplots.ai" is centered at the top. Grid lines are subtle dashed lines. The y-axis shows "Price ($)" for the upper pane and "Volume" (in millions format) for the lower pane.

Quality Score: 86/100

Criteria Checklist

Visual Quality (35/40 pts)

• VQ-01: Text Legibility (10/10) - Title 24pt, labels 20pt, ticks 16pt - all perfectly readable
• VQ-02: No Overlap (8/8) - No overlapping text, date labels properly rotated
• VQ-03: Element Visibility (7/8) - Candlesticks visible with clear wicks and bodies, but some candle bodies are quite thin
• VQ-04: Color Accessibility (5/5) - Blue/yellow palette is colorblind-safe
• VQ-05: Layout Balance (5/5) - Perfect 75/25 split, good use of canvas space
• VQ-06: Axis Labels (0/2) - "Volume" lacks units (should be "Volume (shares)" or similar)
• VQ-07: Grid & Legend (0/2) - Grid subtle ✓, but legend placement in upper-left partially overlaps early data points

Spec Compliance (21/25 pts)

• SC-01: Plot Type (8/8) - Correct candlestick + volume dual-pane chart
• SC-02: Data Mapping (5/5) - Date on x-axis, OHLC and volume correctly mapped
• SC-03: Required Features (2/5) - Missing: static crosshair lines not visible in output; volume bars appear dodged/paired instead of single bars per day
• SC-04: Data Range (3/3) - All data visible within axes
• SC-05: Legend Accuracy (2/2) - Legend correctly identifies bullish/bearish
• SC-06: Title Format (1/2) - Correct format but uses middle dot instead of proper spacing

Data Quality (18/20 pts)

• DQ-01: Feature Coverage (8/8) - Shows both bullish and bearish candles, varying volumes, realistic price trend
• DQ-02: Realistic Context (7/7) - Stock data with realistic price movements and volume patterns
• DQ-03: Appropriate Scale (3/5) - Price range realistic ($125-$165), but volume correlation to price moves may be overly uniform

Code Quality (9/10 pts)

• CQ-01: KISS Structure (3/3) - Linear script structure, no functions/classes
• CQ-02: Reproducibility (3/3) - Uses np.random.seed(42)
• CQ-03: Clean Imports (2/2) - All imports are used
• CQ-04: No Deprecated API (1/1) - Uses current seaborn API
• CQ-05: Output Correct (0/1) - Missing plt.show() but saves correctly

Library Features (3/5 pts)

• LF-01: Uses distinctive library features (3/5) - Uses sns.lineplot, sns.barplot, and sns.set_style/set_context, but candlestick bodies drawn with matplotlib fill_between rather than a seaborn-native approach

Strengths

• Excellent dual-pane layout with proper 75%/25% vertical split
• Colorblind-safe blue/yellow color scheme consistently applied across both panes
• Good use of seaborn for statistical context (lineplot for wicks, barplot for volume)
• Clean code structure with realistic stock data generation
• Proper date formatting and shared x-axis between panes
• Legend clearly explains bullish vs bearish classification

Weaknesses

• Volume bars appear as paired/dodged bars per day instead of single bars (seaborn barplot with hue creates side-by-side bars)
• Crosshair feature from spec not effectively visible in rendered output
• Volume axis label missing units (should indicate "shares" or "M shares")

Verdict: APPROVED

This is Attempt 3/3. Score of 86/100 exceeds the 50-point threshold for final attempt approval. The implementation demonstrates good use of seaborn's styling capabilities and creates a functional candlestick chart with volume. While there are minor issues with the volume bar rendering and missing crosshair visibility, the overall visualization effectively communicates stock price and volume data in a professional format suitable for technical analysis.

[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 professional dual-pane financial chart. The upper pane (approximately 75% of vertical space) shows OHLC candlesticks spanning January to late March 2024, with prices ranging from ~$125 to ~$165. Candlesticks are colored in Python Blue (#306998) for bullish days and Python Yellow (#FFD43B) for bearish days. Wicks extend appropriately above and below candle bodies. The lower pane (25%) shows volume bars using the same color scheme, with values displayed in millions. A legend in the upper left explains the color coding. The title reads "candlestick-volume · seaborn · pyplots.ai". Date labels on the x-axis are rotated 45° and show "Jan 01", "Jan 15", etc. Grid lines are subtle dashed lines (alpha ~0.3). NOTE: The crosshair feature specified in the code (red dashed lines with annotations) is NOT visible in the rendered image.

Quality Score: 88/100

Criteria Checklist

Visual Quality (35/40 pts)

• VQ-01: Text Legibility (10/10) - Title 24pt, axis labels 20pt, tick labels 16pt - all clearly readable
• VQ-02: No Overlap (8/8) - No overlapping elements; rotated date labels prevent x-axis collision
• VQ-03: Element Visibility (7/8) - Candlesticks well-sized for 60 data points; wicks visible; minor: some small candle bodies could be slightly larger
• VQ-04: Color Accessibility (4/5) - Blue/yellow is colorblind-friendly; not using red-green; slight deduction as yellow on white can be lower contrast for some users
• VQ-05: Layout Balance (4/5) - Good 75/25 split; proper margins; minor whitespace on right side
• VQ-06: Axis Labels (2/2) - "Price ($)" and "Volume" with units indicated; "Date" label present
• VQ-07: Grid & Legend (0/2) - Grid is subtle (alpha 0.3, dashed), but legend placement could be better positioned to avoid potential data overlap in different scenarios

Spec Compliance (20/25 pts)

• SC-01: Plot Type (8/8) - Correct dual-pane candlestick + volume chart
• SC-02: Data Mapping (5/5) - OHLC correctly mapped; volume correctly displayed
• SC-03: Required Features (2/5) - Missing: crosshair/cursor feature is coded but NOT rendered in the output image; spec explicitly requires "crosshair or cursor that spans both panes"
• SC-04: Data Range (3/3) - All 60 trading days visible; appropriate axis ranges
• SC-05: Legend Accuracy (0/2) - Legend labels are correct but placed in a position that could overlap with data
• SC-06: Title Format (2/2) - Correctly formatted as "candlestick-volume · seaborn · pyplots.ai"

Data Quality (20/20 pts)

• DQ-01: Feature Coverage (8/8) - Shows both bullish AND bearish candles; varied price movements; volume correlation with price moves
• DQ-02: Realistic Context (7/7) - Stock price scenario from $150 base; realistic daily returns and volatility
• DQ-03: Appropriate Scale (5/5) - Price range ($125-$165) is realistic for a mid-cap stock; volume in millions is appropriate

Code Quality (10/10 pts)

• CQ-01: KISS Structure (3/3) - Linear flow: imports → data → plot → save; uses loop for candles but no classes/functions
• CQ-02: Reproducibility (3/3) - np.random.seed(42) ensures deterministic output
• CQ-03: Clean Imports (2/2) - All imports used (matplotlib, numpy, pandas, seaborn, Patch)
• CQ-04: No Deprecated API (1/1) - Uses current seaborn 0.13+ API
• CQ-05: Output Correct (1/1) - Saves as plot.png with proper dpi and bbox_inches

Library Features (3/5 pts)

• LF-01: Uses distinctive library features (3/5) - Uses sns.set_style, sns.set_context, sns.lineplot for wicks; however, candlestick bodies drawn with matplotlib fill_between, not pure seaborn

Strengths

• Excellent dual-pane layout with proper 75/25 height ratio as specified
• Good color scheme using Python blue/yellow that is colorblind accessible
• Clean seaborn styling with whitegrid and talk context provides professional appearance
• Realistic stock data generation with price-volume correlation
• Well-formatted axis labels with units and proper tick formatting for millions

Weaknesses

• Crosshair feature appears in code but is not visible in the rendered output image
• Legend placement in upper left may overlap with price data in some scenarios
• Volume axis label shows just "Volume" instead of "Volume (M shares)" as coded

Verdict: APPROVED

This is attempt 3/3. The score of 88/100 meets the ≥50 threshold for merge after 3 attempts. While the crosshair rendering issue remains unresolved, the core candlestick-volume visualization is well-executed with proper layout, readable text, and good data representation.

[github-actions]

AI Review - Final Status

Score: 88/100 (Acceptable)

After 3 repair attempts, seaborn reached 88/100.

Score ≥ 50 is acceptable for the repository. Merging.

---

🤖 impl-review