feat(pygal): implement scatter-lag

plots/scatter-lag/implementations/pygal.py

@@ -0,0 +1,155 @@
+""" pyplots.ai
+scatter-lag: Lag Plot for Time Series Autocorrelation Diagnosis
+Library: pygal 3.1.0 | Python 3.14.3
+Quality: 87/100 | Created: 2026-04-12
+"""
+
+import numpy as np
+import pygal
+from pygal.style import Style
+
+
+# Data — synthetic AR(1) process with moderate positive autocorrelation
+np.random.seed(42)
+n = 400
+phi = 0.78
+noise = np.random.normal(0, 1.0, n)
+temperature = np.zeros(n)
+temperature[0] = 20.0
+for i in range(1, n):
+    temperature[i] = 20.0 + phi * (temperature[i - 1] - 20.0) + noise[i]
+
+lag = 1
+y_t = temperature[:-lag]
+y_t_lag = temperature[lag:]
+
+# Temporal quartile masks
+time_idx = np.arange(len(y_t))
+q_bounds = np.percentile(time_idx, [25, 50, 75])
+
+# Build scatter series with interactive tooltips (pygal dict format)
+early = [
+    {"value": (float(y_t[i]), float(y_t_lag[i])), "label": f"Day {i + 1}"}
+    for i in range(len(y_t))
+    if time_idx[i] < q_bounds[0]
+]
+mid_early = [
+    {"value": (float(y_t[i]), float(y_t_lag[i])), "label": f"Day {i + 1}"}
+    for i in range(len(y_t))
+    if q_bounds[0] <= time_idx[i] < q_bounds[1]
+]
+mid_late = [
+    {"value": (float(y_t[i]), float(y_t_lag[i])), "label": f"Day {i + 1}"}
+    for i in range(len(y_t))
+    if q_bounds[1] <= time_idx[i] < q_bounds[2]
+]
+late = [
+    {"value": (float(y_t[i]), float(y_t_lag[i])), "label": f"Day {i + 1}"}
+    for i in range(len(y_t))
+    if time_idx[i] >= q_bounds[2]
+]
+
+# Correlation coefficient
+r = np.corrcoef(y_t, y_t_lag)[0, 1]
+
+# Reference geometry
+data_min = float(min(y_t.min(), y_t_lag.min()))
+data_max = float(max(y_t.max(), y_t_lag.max()))
+pad = (data_max - data_min) * 0.05
+ref_start = data_min - pad
+ref_end = data_max + pad
+ref_line = [(ref_start, ref_start), (ref_end, ref_end)]
+
+# ±1σ envelope around y=x to visualise autocorrelation spread
+sigma = float(np.std(y_t_lag - y_t))
+upper_env = [(ref_start, ref_start + sigma), (ref_end, ref_end + sigma)]
+lower_env = [(ref_start, ref_start - sigma), (ref_end, ref_end - sigma)]
+
+# Warm-to-cool temporal palette: terracotta → amber → teal → navy
+font = "DejaVu Sans, Helvetica, Arial, sans-serif"
+custom_style = Style(
+    background="white",
+    plot_background="#f8f7f5",
+    foreground="#2a2a2a",
+    foreground_strong="#1a1a1a",
+    foreground_subtle="#d5d5d3",
+    guide_stroke_color="#e0dfdd",
+    colors=(
+        "#c25a3c",  # Q1 — terracotta
+        "#d4a028",  # Q2 — warm amber
+        "#2a9d8f",  # Q3 — teal
+        "#264653",  # Q4 — deep navy
+        "#c0bebb",  # +1σ envelope
+        "#c0bebb",  # −1σ envelope
+        "#888886",  # y = x reference
+    ),
+    font_family=font,
+    title_font_family=font,
+    title_font_size=56,
+    label_font_size=42,
+    major_label_font_size=38,
+    legend_font_size=32,
+    legend_font_family=font,
+    value_font_size=28,
+    tooltip_font_size=28,
+    tooltip_font_family=font,
+    opacity=0.60,
+    opacity_hover=0.95,
+    stroke_opacity=0.7,
+    stroke_opacity_hover=1,
+)
+
+# Chart — interactivity enabled for SVG hover tooltips
+chart = pygal.XY(
+    width=4800,
+    height=2700,
+    style=custom_style,
+    title=f"Lag Plot (k={lag}, r={r:.2f}) \u00b7 scatter-lag \u00b7 pygal \u00b7 pyplots.ai",
+    x_title="y(t)",
+    y_title=f"y(t+{lag})",
+    show_legend=True,
+    legend_at_bottom=True,
+    legend_at_bottom_columns=5,
+    legend_box_size=24,
+    stroke=False,
+    dots_size=8,
+    show_x_guides=True,
+    show_y_guides=True,
+    x_value_formatter=lambda x: f"{x:.1f}",
+    value_formatter=lambda y: f"{y:.1f}",
+    margin_bottom=100,
+    margin_left=80,
+    margin_right=30,
+    margin_top=40,
+    range=(ref_start, ref_end),
+    xrange=(ref_start, ref_end),
+    x_labels_major_count=8,
+    y_labels_major_count=8,
+    print_values=False,
+    print_zeroes=False,
+    truncate_legend=40,
+)
+
+# Temporal quartile scatter series
+chart.add("Days 1\u2013100", early, stroke=False, dots_size=9)
+chart.add("Days 101\u2013200", mid_early, stroke=False)
+chart.add("Days 201\u2013300", mid_late, stroke=False)
+chart.add("Days 301\u2013399", late, stroke=False, dots_size=9)
+
+# ±1σ envelope (no legend entry)
+env_style = {"width": 3, "dasharray": "6, 8", "linecap": "round"}
+chart.add(None, upper_env, stroke=True, show_dots=False, stroke_style=env_style)
+chart.add(None, lower_env, stroke=True, show_dots=False, stroke_style=env_style)
+
+# Diagonal reference line y = x
+chart.add(
+    "y = x (\u00b11\u03c3)",
+    ref_line,
+    stroke=True,
+    show_dots=False,
+    stroke_style={"width": 6, "dasharray": "24, 12", "linecap": "round"},
+)
+
+# Save
+chart.render_to_png("plot.png")
+chart.render_to_file("plot.html")

plots/scatter-lag/metadata/pygal.yaml

@@ -0,0 +1,227 @@
+library: pygal
+specification_id: scatter-lag
+created: '2026-04-12T18:12:36Z'
+updated: '2026-04-12T18:32:40Z'
+generated_by: claude-opus-4-5-20251101
+workflow_run: 24313009875
+issue: 5251
+python_version: 3.14.3
+library_version: 3.1.0
+preview_url: https://storage.googleapis.com/pyplots-images/plots/scatter-lag/pygal/plot.png
+preview_html: https://storage.googleapis.com/pyplots-images/plots/scatter-lag/pygal/plot.html
+quality_score: 87
+review:
+  strengths:
+  - Intentional warm-to-cool temporal palette (terracotta → amber → teal → navy) creates
+    a compelling visual narrative of time progression within the autocorrelation structure
+  - All required spec features fully implemented plus value-adding ±1σ envelope around
+    the diagonal reference line
+  - Comprehensive explicit font sizing throughout; perfect spec compliance (15/15)
+    and code quality (10/10)
+  weaknesses:
+  - dots_size=8–9 causes overplotting for 400 data points; smaller dots (5–6) with
+    lower opacity (~0.45) would reduce central cluster overlap
+  - Terracotta (#c25a3c) and amber (#d4a028) risk confusion for deuteranopic (red-green
+    colorblind) viewers; palette shift needed for full accessibility
+  image_description: 'The plot shows a lag scatter plot on a light beige (#f8f7f5)
+    background. The title reads "Lag Plot (k=1, r=0.75) · scatter-lag · pygal · pyplots.ai"
+    centered at the top. The X-axis is labeled "y(t)" and the Y-axis "y(t+1)". Four
+    temporal quartile series are plotted: Days 1–100 in terracotta (brick-red), Days
+    101–200 in amber/golden-yellow, Days 201–300 in teal/seafoam, and Days 301–399
+    in deep navy. A dashed gray diagonal reference line (y = x ±1σ) runs from lower-left
+    to upper-right. Subtle dotted grid lines are visible across the plot. The legend
+    sits at the bottom with five labeled entries. A clear positive linear autocorrelation
+    pattern is evident — data points cluster diagonally, confirming the AR(1) process
+    (r=0.75).'
+  criteria_checklist:
+    visual_quality:
+      score: 25
+      max: 30
+      items:
+      - id: VQ-01
+        name: Text Legibility
+        score: 8
+        max: 8
+        passed: true
+        comment: 'All font sizes explicitly set: title=56, labels=42, major=38, legend=32,
+          value=28; fully readable at 4800x2700 px'
+      - id: VQ-02
+        name: No Overlap
+        score: 5
+        max: 6
+        passed: true
+        comment: Text elements clear; minor dot overlap in dense central cluster expected
+          for 400 points
+      - id: VQ-03
+        name: Element Visibility
+        score: 4
+        max: 6
+        passed: false
+        comment: dots_size=8-9 for 400 points causes noticeable overplotting; guidelines
+          suggest size 20-50 with alpha 0.3-0.5 for 300+ points
+      - id: VQ-04
+        name: Color Accessibility
+        score: 3
+        max: 4
+        passed: false
+        comment: Terracotta (#c25a3c) and amber (#d4a028) may be confused by deuteranopic
+          users; rest of palette is good
+      - id: VQ-05
+        name: Layout & Canvas
+        score: 3
+        max: 4
+        passed: true
+        comment: Good proportions; margins tuned; legend well-anchored at bottom
+      - id: VQ-06
+        name: Axis Labels & Title
+        score: 2
+        max: 2
+        passed: true
+        comment: y(t) / y(t+1) are standard lag-plot notation; title is descriptive
+          and complete
+    design_excellence:
+      score: 15
+      max: 20
+      items:
+      - id: DE-01
+        name: Aesthetic Sophistication
+        score: 6
+        max: 8
+        passed: true
+        comment: Intentional warm-to-cool temporal palette with custom beige background;
+          clearly above defaults, but not quite publication-ready
+      - id: DE-02
+        name: Visual Refinement
+        score: 4
+        max: 6
+        passed: true
+        comment: Subtle guide_stroke_color, beige plot background, legend columns,
+          margin tuning; limited further by pygal API (no spine removal)
+      - id: DE-03
+        name: Data Storytelling
+        score: 5
+        max: 6
+        passed: true
+        comment: Temporal color gradient is an effective storytelling device; correlation
+          coefficient in title; ±1σ envelope contextualises autocorrelation spread
+    spec_compliance:
+      score: 15
+      max: 15
+      items:
+      - id: SC-01
+        name: Plot Type
+        score: 5
+        max: 5
+        passed: true
+        comment: Correct XY scatter for lag plot
+      - id: SC-02
+        name: Required Features
+        score: 4
+        max: 4
+        passed: true
+        comment: Diagonal y=x reference line, temporal point coloring, r-value annotation
+          in title, configurable lag; bonus ±1σ envelope
+      - id: SC-03
+        name: Data Mapping
+        score: 3
+        max: 3
+        passed: true
+        comment: y(t) on X, y(t+lag) on Y, all data visible
+      - id: SC-04
+        name: Title & Legend
+        score: 3
+        max: 3
+        passed: true
+        comment: Title includes spec-id, library, pyplots.ai, plus informative k and
+          r values; legend labels match temporal quartiles
+    data_quality:
+      score: 14
+      max: 15
+      items:
+      - id: DQ-01
+        name: Feature Coverage
+        score: 5
+        max: 6
+        passed: true
+        comment: Clear positive autocorrelation pattern demonstrated; temporal coloring
+          reveals consistent structure; could include stronger/weaker autocorrelation
+          variation
+      - id: DQ-02
+        name: Realistic Context
+        score: 5
+        max: 5
+        passed: true
+        comment: Daily temperature readings with AR(1) mean reversion (mu=20C) is
+          natural and neutral
+      - id: DQ-03
+        name: Appropriate Scale
+        score: 4
+        max: 4
+        passed: true
+        comment: Values 16-25C and phi=0.78 are realistic for daily temperatures
+    code_quality:
+      score: 10
+      max: 10
+      items:
+      - id: CQ-01
+        name: KISS Structure
+        score: 3
+        max: 3
+        passed: true
+        comment: Clean imports -> data -> plot -> save; no functions or classes
+      - id: CQ-02
+        name: Reproducibility
+        score: 2
+        max: 2
+        passed: true
+        comment: np.random.seed(42) set
+      - id: CQ-03
+        name: Clean Imports
+        score: 2
+        max: 2
+        passed: true
+        comment: numpy, pygal, Style; all used
+      - id: CQ-04
+        name: Code Elegance
+        score: 2
+        max: 2
+        passed: true
+        comment: Four separate list comprehensions for quartiles are verbose but clear;
+          no fake functionality
+      - id: CQ-05
+        name: Output & API
+        score: 1
+        max: 1
+        passed: true
+        comment: render_to_png('plot.png') correct; HTML export is a pygal bonus
+    library_mastery:
+      score: 8
+      max: 10
+      items:
+      - id: LM-01
+        name: Idiomatic Usage
+        score: 5
+        max: 5
+        passed: true
+        comment: Dict-format data points with label keys for SVG tooltips, stroke_style
+          for line customisation, legend_at_bottom_columns — all idiomatic pygal
+      - id: LM-02
+        name: Distinctive Features
+        score: 3
+        max: 5
+        passed: true
+        comment: Pygal-specific dict tooltip data and stroke_style dasharray are library-distinctive;
+          could leverage pygal interactive SVG more explicitly
+  verdict: REJECTED
+impl_tags:
+  dependencies: []
+  techniques:
+  - hover-tooltips
+  - html-export
+  patterns:
+  - data-generation
+  - iteration-over-groups
+  dataprep:
+  - time-series
+  styling:
+  - alpha-blending