feat(pygal): implement indicator-rsi

[github-actions]

Implementation: indicator-rsi - pygal

Implements the pygal version of indicator-rsi.

File: plots/indicator-rsi/implementations/pygal.py

Parent Issue: #3229

---

🤖 impl-generate workflow

[claude]

AI Review - Attempt 1/3

Image Description

The plot displays an RSI (Relative Strength Index) technical indicator chart on a white background. The title "indicator-rsi · pygal · pyplots.ai" is shown at the top in a legible font. The Y-axis is labeled "RSI Value (0-100)" with a proper 0-100 scale. The X-axis is labeled "Trading Period (120 days, 14-period RSI lookback)". A blue RSI line oscillates across 120 periods, showing values ranging roughly from 25 to 65, with typical momentum indicator behavior. Three horizontal threshold lines are displayed: a green dashed line at 70 (overbought), a red dashed line at 30 (oversold), and a gray dashed line at 50 (centerline). The legend at the bottom clearly identifies all four series: RSI (14), Overbought (70), Oversold (30), and Centerline (50). The chart uses cubic interpolation for smooth lines and has subtle horizontal grid lines.

Quality Score: 85/100

Criteria Checklist

Visual Quality (33/40 pts)

• VQ-01: Text Legibility (8/10) - Title and axis labels are readable, but Y-axis label uses monospace font that could be cleaner
• VQ-02: No Overlap (8/8) - No overlapping text elements
• VQ-03: Element Visibility (6/8) - RSI line is visible but could be thicker; threshold lines are somewhat thin
• VQ-04: Color Accessibility (5/5) - Blue/green/red/gray are distinguishable and colorblind-safe
• VQ-05: Layout Balance (3/5) - Good use of canvas but legend placement at bottom creates extra whitespace
• VQ-06: Axis Labels (2/2) - Descriptive labels with units (0-100 scale)
• VQ-07: Grid & Legend (1/2) - Grid is subtle but legend could be more prominent

Spec Compliance (24/25 pts)

• SC-01: Plot Type (8/8) - Correct line chart for RSI indicator
• SC-02: Data Mapping (5/5) - RSI values correctly mapped over time periods
• SC-03: Required Features (5/5) - Has overbought (70), oversold (30), and optional centerline (50)
• SC-04: Data Range (3/3) - Y-axis properly fixed from 0-100
• SC-05: Legend Accuracy (2/2) - Legend labels correctly identify all series
• SC-06: Title Format (1/2) - Uses correct format but title font could be larger

Data Quality (16/20 pts)

• DQ-01: Feature Coverage (6/8) - RSI shows variation but doesn't cross into overbought zone (>70); only approaches oversold
• DQ-02: Realistic Context (7/7) - Technical trading indicator with realistic RSI calculation using 14-period lookback
• DQ-03: Appropriate Scale (3/5) - RSI values are valid (0-100) but data never demonstrates overbought condition

Code Quality (9/10 pts)

• CQ-01: KISS Structure (3/3) - Simple imports → data → plot → save structure
• CQ-02: Reproducibility (3/3) - Uses np.random.seed(42)
• CQ-03: Clean Imports (2/2) - Only numpy, pygal, and Style are imported
• CQ-04: No Deprecated API (1/1) - Current pygal API used
• CQ-05: Output Correct (0/1) - Saves plot.png but specification recommends considering if shading would enhance clarity

Library Features (3/5 pts)

• LF-01: Uses distinctive library features (3/5) - Uses pygal's custom Style, cubic interpolation, and stroke_style for dashed lines, but doesn't utilize fill_between or other advanced features

Strengths

• Correct RSI calculation using EMA method with 14-period lookback
• All three threshold lines (30, 50, 70) properly implemented with distinct colors and dashed styling
• Clean, readable layout with proper axis labeling including lookback period info
• Good use of pygal's interpolation for smooth RSI line
• Proper Y-axis range fixed at 0-100 as required

Weaknesses

• RSI data never enters overbought zone (>70), limiting demonstration of full indicator utility
• Specification suggests shading overbought/oversold zones for visual clarity, which is not implemented
• Legend at bottom with small box sizes could be more prominent
• RSI line and threshold lines could be slightly thicker for better visibility

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 an RSI (Relative Strength Index) line chart on a white background. The blue RSI line oscillates between approximately 26 and 66 over 120 trading periods, using cubic interpolation for smooth curves. Horizontal dashed reference lines are present: green at 70 (overbought threshold), red at 30 (oversold threshold), and gray at 50 (centerline). The Y-axis is correctly fixed from 0 to 100 with label "RSI Value (0-100)". The X-axis shows "Trading Period (120 days, 14-period RSI lookback)". Title correctly formatted as "indicator-rsi · pygal · pyplots.ai". Legend at bottom shows RSI (14), Overbought (70), Oversold (30), and Centerline (50). However, the overbought/oversold zone shading is NOT visible despite being coded, and the RSI line never enters the overbought zone (>70).

Quality Score: 78/100

Criteria Checklist

Visual Quality (32/40)

• VQ-01: Text Legibility (8/10) - Text is readable but title and labels could be larger for 4800x2700 canvas
• VQ-02: No Overlap (8/8) - No overlapping text elements
• VQ-03: Element Visibility (6/8) - RSI line is visible with good stroke width, but zone shading is not rendering
• VQ-04: Color Accessibility (5/5) - Blue RSI line, red/green thresholds with dashed patterns distinguish them
• VQ-05: Layout Balance (3/5) - Good use of canvas but legend items appear incomplete (missing zone entries)
• VQ-06: Axis Labels (2/2) - Descriptive labels with context: "RSI Value (0-100)" and "Trading Period (120 days, 14-period RSI lookback)"
• VQ-07: Grid & Legend (0/2) - Zone fill series are in the code but not visible; legend is missing the zone entries

Spec Compliance (18/25)

• SC-01: Plot Type (8/8) - Correct line chart for RSI indicator
• SC-02: Data Mapping (5/5) - RSI values correctly mapped to Y-axis over time periods
• SC-03: Required Features (2/5) - Missing: visible zone shading for overbought (70-100) and oversold (0-30) zones as specified
• SC-04: Data Range (3/3) - Y-axis correctly fixed 0-100
• SC-05: Legend Accuracy (0/2) - Legend missing the zone fill entries that are in the code
• SC-06: Title Format (2/2) - Correct format "indicator-rsi · pygal · pyplots.ai"

Data Quality (15/20)

• DQ-01: Feature Coverage (5/8) - RSI enters oversold zone but NEVER enters overbought zone (max ~66), should show both extremes
• DQ-02: Realistic Context (7/7) - Plausible RSI scenario with trending periods
• DQ-03: Appropriate Scale (3/5) - Values within valid 0-100 RSI range but missing overbought excursions

Code Quality (10/10)

• CQ-01: KISS Structure (3/3) - Linear structure: imports → data generation → chart creation → save
• CQ-02: Reproducibility (3/3) - Uses np.random.seed(42)
• CQ-03: Clean Imports (2/2) - Only numpy, pygal, and Style imported
• CQ-04: No Deprecated API (1/1) - Current pygal API usage
• CQ-05: Output Correct (1/1) - Saves as plot.png and plot.html

Library Features (3/5)

• LF-01: Uses distinctive library features (3/5) - Uses pygal Style customization, cubic interpolation, stroke_style options; but fill=True for zones not working as intended

Strengths

• Correct RSI calculation using EMA method with 14-period lookback
• Clean code structure following KISS principles
• Proper title format and descriptive axis labels
• Good use of dashed lines for threshold visualization
• Reproducible with fixed random seed

Weaknesses

• Zone shading (overbought 70-100 red, oversold 0-30 green) is not visible in output despite being coded - the fill=True approach creates filled area from 0 to the line value, not a horizontal band
• RSI data never enters overbought zone (>70) - maximum value is approximately 66, missing half of the key feature demonstration
• Legend is incomplete - zone fill series entries not showing

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 an RSI (Relative Strength Index) technical indicator chart rendered as a smooth blue line (cubic interpolation) showing RSI values over 120 trading periods. The Y-axis is correctly fixed from 0 to 100. Three horizontal reference lines are present: a red dashed line at 70 (overbought threshold), a green dashed line at 30 (oversold threshold), and a gray dotted line at 50 (centerline). The RSI line clearly enters both overbought territory (peaking at ~97) and oversold territory (dipping to ~14), demonstrating the full range of RSI momentum behavior. The title "indicator-rsi · pygal · pyplots.ai" is displayed at the top. A legend at the bottom identifies all four elements with appropriate color coding. The layout has good proportions with the plot filling the canvas well.

Quality Score: 85/100

Criteria Checklist

Visual Quality (34/40)

• VQ-01: Text Legibility (9/10) - Title, axis labels, and legend text are clearly readable with appropriately scaled font sizes for the 4800x2700 canvas
• VQ-02: No Overlap (8/8) - No overlapping text elements; legend at bottom is well-spaced
• VQ-03: Element Visibility (7/8) - RSI line is clearly visible with good stroke width; threshold lines appropriately styled as dashed
• VQ-04: Color Accessibility (4/5) - Red/green threshold lines could be problematic for red-green colorblind users, though the dashed styling helps differentiate
• VQ-05: Layout Balance (4/5) - Good canvas utilization; slight excess whitespace at bottom due to legend placement
• VQ-06: Axis Labels (2/2) - Y-axis labeled "RSI Value (0-100)" with range info; X-axis labeled "Trading Period (120 days, 14-period RSI lookback)" with context
• VQ-07: Grid & Legend (0/2) - Y-guides are visible but legend uses colored squares that match line colors well; however grid lines are somewhat sparse

Spec Compliance (21/25)

• SC-01: Plot Type (8/8) - Correct line chart for RSI oscillator
• SC-02: Data Mapping (5/5) - RSI values correctly plotted on 0-100 scale over time
• SC-03: Required Features (3/5) - Has threshold lines at 30, 70, and centerline at 50; missing zone shading/highlighting for overbought (70-100) and oversold (0-30) regions mentioned in spec notes
• SC-04: Data Range (3/3) - Y-axis shows full 0-100 range as required
• SC-05: Legend Accuracy (2/2) - Legend correctly identifies all elements
• SC-06: Title Format (2/2) - Uses correct format "indicator-rsi · pygal · pyplots.ai"

Data Quality (18/20)

• DQ-01: Feature Coverage (8/8) - Excellent! RSI enters both overbought (>70, peaks ~97) and oversold (<30, dips ~14) zones multiple times, demonstrating full indicator behavior
• DQ-02: Realistic Context (5/7) - Trading context is appropriate; RSI calculation uses proper EMA method with 14-period lookback
• DQ-03: Appropriate Scale (5/5) - RSI values are mathematically correct (0-100 bounded) with realistic momentum patterns

Code Quality (9/10)

• CQ-01: KISS Structure (3/3) - Clean linear structure: imports → data generation → RSI calculation → chart config → save
• CQ-02: Reproducibility (3/3) - Uses np.random.seed(42)
• CQ-03: Clean Imports (2/2) - Only necessary imports (numpy, pygal, Style)
• CQ-04: No Deprecated API (1/1) - Uses current pygal API
• CQ-05: Output Correct (0/0) - Saves as plot.png and plot.html correctly

Library Features (3/5)

• LF-01: Uses distinctive library features - Custom Style with scaled fonts, stroke_style for dashed lines, cubic interpolation, legend_at_bottom; however pygal's SVG nature and interactive tooltips are not fully leveraged (show_dots=False removes hover points)

Strengths

• Y-axis correctly fixed 0-100 with all three reference lines (70, 30, 50) as horizontal thresholds
• RSI data demonstrates excellent feature coverage entering both overbought and oversold zones multiple times
• Proper RSI calculation using EMA method with 14-period lookback
• Good use of pygal's Style customization for large canvas rendering
• Clean, smooth cubic interpolation makes the RSI trend easy to follow

Weaknesses

• Missing zone shading/highlighting for overbought (70-100) and oversold (0-30) regions as suggested in spec notes
• Red/green color scheme for threshold lines could be improved for colorblind accessibility

Verdict: APPROVED

Score of 85/100 on attempt 3/3 exceeds the 50-point threshold for merge. The implementation correctly renders an RSI indicator with proper threshold lines and demonstrates the oscillator entering both extreme zones. While zone shading would enhance visual clarity, the core requirements are met.

[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 an RSI (Relative Strength Index) technical indicator chart on a white background. A blue line (RSI 14-period) smoothly oscillates across 120 trading days, reaching peaks above 90 (overbought territory) twice and dropping below 15 (deeply oversold) twice. Three horizontal threshold lines are clearly visible: a red dashed line at 70 (overbought), a green dashed line at 30 (oversold), and a gray dotted line at 50 (centerline). The Y-axis is correctly fixed from 0 to 100 with clear labels. The X-axis title indicates "Trading Period (120 days, 14-period RSI lookback)". The title follows the correct format "indicator-rsi · pygal · pyplots.ai". A legend at the bottom identifies all four series. The layout shows good canvas utilization with the plot area filling most of the available space.

Quality Score: 90/100

Criteria Checklist

Visual Quality (36/40 pts)

• VQ-01: Text Legibility (9/10) - Title, axis labels, and legend are clearly readable. Font sizes appropriately scaled for 4800x2700.
• VQ-02: No Overlap (8/8) - No overlapping text elements anywhere in the plot.
• VQ-03: Element Visibility (7/8) - RSI line is clearly visible with good stroke width. Threshold lines are distinguishable.
• VQ-04: Color Accessibility (5/5) - Blue RSI line, red overbought, green oversold, gray centerline - all distinguishable including for colorblind users.
• VQ-05: Layout Balance (5/5) - Good canvas utilization, plot fills appropriate portion of space, legend well-positioned at bottom.
• VQ-06: Axis Labels (1/2) - Y-axis has descriptive label with range but no units (RSI is unitless so acceptable). X-axis describes the trading period well.
• VQ-07: Grid & Legend (1/2) - Y-guides present and subtle, legend clear but positioned at bottom taking extra space.

Spec Compliance (24/25 pts)

• SC-01: Plot Type (8/8) - Correct line chart for RSI indicator
• SC-02: Data Mapping (5/5) - RSI values correctly mapped to Y-axis over time on X-axis
• SC-03: Required Features (5/5) - All required features present: 0-100 Y-axis, 70 overbought line, 30 oversold line, 50 centerline, RSI line clearly visible
• SC-04: Data Range (3/3) - Y-axis correctly fixed 0-100, all data visible
• SC-05: Legend Accuracy (1/2) - Legend labels correct but uses "(70)", "(30)", "(50)", "(14)" format which is functional but slightly verbose
• SC-06: Title Format (2/2) - Correct format: "indicator-rsi · pygal · pyplots.ai"

Data Quality (18/20 pts)

• DQ-01: Feature Coverage (7/8) - RSI enters both overbought (>70) and oversold (<30) zones multiple times, showing momentum oscillation. Could show more subtle divergence patterns.
• DQ-02: Realistic Context (7/7) - Trading context is realistic, RSI calculation uses proper 14-period EMA method
• DQ-03: Appropriate Scale (4/5) - RSI values realistic for stock momentum, though some peaks are quite extreme (~97)

Code Quality (9/10 pts)

• CQ-01: KISS Structure (3/3) - Imports → Data → Plot → Save structure, no functions/classes
• CQ-02: Reproducibility (3/3) - np.random.seed(42) set
• CQ-03: Clean Imports (2/2) - Only numpy, pygal, and Style imported - all used
• CQ-04: No Deprecated API (1/1) - Current pygal API used
• CQ-05: Output Correct (0/1) - Saves as plot.png and plot.html (correct)

Library Features (3/5 pts)

• LF-01: Uses distinctive library features (3/5) - Uses pygal Style customization, stroke_style for dashed lines, interpolate="cubic" for smooth curves, legend_at_bottom. Could leverage more pygal-specific features like tooltips.

Strengths

• Correct RSI calculation using EMA method with 14-period lookback
• All required threshold lines (30, 50, 70) clearly visible with appropriate styling
• RSI enters both overbought and oversold zones demonstrating full indicator range
• Good color differentiation between RSI line and threshold lines
• Clean canvas utilization with proper margins
• Correct title format following pyplots.ai convention

Weaknesses

• Legend at bottom takes significant vertical space; could be more compact
• No shading/highlighting of overbought (70-100) and oversold (0-30) zones as suggested in spec (pygal limitation)
• X-axis labels hidden (show_x_labels=False) - could show periodic date markers

Verdict: APPROVED