feat(pygal): implement scatter-basic (#5315)

## Implementation: `scatter-basic` - python/pygal

Implements the **python/pygal** version of `scatter-basic`.

**File:** `plots/scatter-basic/implementations/python/pygal.py`

**Parent Issue:** #611

---
:robot: *[impl-generate
workflow](https://github.com/MarkusNeusinger/anyplot/actions/runs/24853810841)*

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Author: github-actions[bot]

plots/scatter-basic/implementations/python/pygal.py

@@ -1,141 +1,100 @@
-""" pyplots.ai
+""" anyplot.ai
 scatter-basic: Basic Scatter Plot
-Library: pygal 3.1.0 | Python 3.14
-Quality: 87/100 | Created: 2025-12-22
+Library: pygal 3.1.0 | Python 3.14.4
+Quality: 87/100 | Created: 2026-04-23
 """
 
-import numpy as np
-import pygal
-from pygal.style import Style
+import os
+import sys
 
 
-# Data — study hours vs exam scores with realistic positive correlation
-np.random.seed(42)
-n = 115
-study_hours = np.random.uniform(2, 14, n)
-exam_scores = study_hours * 4.5 + np.random.normal(0, 5.5, n) + 25
-exam_scores = np.clip(exam_scores, 15, 100)
+# Script filename shadows the installed `pygal` package when run as `python pygal.py`;
+# dropping the script directory from sys.path lets the real package resolve.
+sys.path.pop(0)
+
+import numpy as np  # noqa: E402
+import pygal  # noqa: E402
+from pygal.style import Style  # noqa: E402
+
 
-# Add deliberate outliers showcasing scatter diversity (high/low performers)
-outlier_hours = np.array([3.0, 12.5, 7.0, 11.0, 4.5])
-outlier_scores = np.array([82.0, 42.0, 95.0, 48.0, 78.0])
-study_hours = np.concatenate([study_hours, outlier_hours])
-exam_scores = np.concatenate([exam_scores, outlier_scores])
+# Theme tokens
+THEME = os.getenv("ANYPLOT_THEME", "light")
+PAGE_BG = "#FAF8F1" if THEME == "light" else "#1A1A17"
+INK = "#1A1A17" if THEME == "light" else "#F0EFE8"
+INK_SOFT = "#4A4A44" if THEME == "light" else "#B8B7B0"
+INK_MUTED = "#8A8A82" if THEME == "light" else "#6E6D66"
 
-# Compute trend line (linear regression) for data storytelling
-coeffs = np.polyfit(study_hours, exam_scores, 1)
-slope, intercept = coeffs
-r = np.corrcoef(study_hours, exam_scores)[0, 1]
-trend_x = np.linspace(study_hours.min(), study_hours.max(), 50)
-trend_y = slope * trend_x + intercept
+OKABE_ITO = ("#009E73", "#D55E00", "#0072B2", "#CC79A7", "#E69F00", "#56B4E9", "#F0E442")
+
+# Data — study hours vs exam scores, moderate positive correlation
+np.random.seed(42)
+n = 180
+study_hours = np.random.uniform(1.5, 13.5, n)
+exam_scores = study_hours * 4.8 + np.random.normal(0, 6.5, n) + 26
+exam_scores = np.clip(exam_scores, 20, 100)
 
-# Identify notable outliers for annotation
-residuals = exam_scores - (slope * study_hours + intercept)
-top_outlier_idx = int(np.argmax(residuals))
-bottom_outlier_idx = int(np.argmin(residuals))
+# Visual hierarchy: split at conventional 70% passing threshold to guide the
+# viewer's eye and convey the "hours → outcome" narrative beyond a raw cloud.
+PASSING = 70.0
+above = [(float(h), float(s)) for h, s in zip(study_hours, exam_scores, strict=True) if s >= PASSING]
+below = [(float(h), float(s)) for h, s in zip(study_hours, exam_scores, strict=True) if s < PASSING]
 
-# Shared font family
 font = "DejaVu Sans, Helvetica, Arial, sans-serif"
 
-# Refined style for 4800x2700 px canvas — subtle, professional palette
 custom_style = Style(
-    background="white",
-    plot_background="#f7f7f7",
-    foreground="#2a2a2a",
-    foreground_strong="#2a2a2a",
-    foreground_subtle="#e0e0e0",
-    guide_stroke_color="#e0e0e0",
-    guide_stroke_dasharray="4, 4",
-    colors=("#306998", "#d64541", "#e8a838"),
+    background=PAGE_BG,
+    plot_background=PAGE_BG,
+    foreground=INK_SOFT,
+    foreground_strong=INK,
+    foreground_subtle=INK_MUTED,
+    colors=OKABE_ITO,
     font_family=font,
     title_font_family=font,
-    title_font_size=56,
-    label_font_size=42,
-    major_label_font_size=38,
-    legend_font_size=34,
+    label_font_family=font,
+    major_label_font_family=font,
     legend_font_family=font,
-    value_font_size=28,
-    tooltip_font_size=28,
     tooltip_font_family=font,
-    opacity=0.65,
+    title_font_size=52,
+    label_font_size=40,
+    major_label_font_size=36,
+    legend_font_size=34,
+    tooltip_font_size=28,
+    value_font_size=26,
+    opacity=0.7,
     opacity_hover=0.95,
     stroke_opacity=1,
     stroke_opacity_hover=1,
 )
 
-# Axis range tightened to data bounds for better canvas utilization
-x_min, x_max = float(np.floor(study_hours.min())), float(np.ceil(study_hours.max()))
-y_min = float(max(0, np.floor(exam_scores.min() / 5) * 5))
-y_max = float(min(100, np.ceil(exam_scores.max() / 5) * 5 + 5))
-
-# Create XY chart
 chart = pygal.XY(
     width=4800,
     height=2700,
     style=custom_style,
-    title="scatter-basic \u00b7 pygal \u00b7 pyplots.ai",
+    title="scatter-basic · pygal · anyplot.ai",
     x_title="Study Hours per Week (hrs)",
     y_title="Exam Score (%)",
+    stroke=False,
+    dots_size=17,
     show_legend=True,
     legend_at_bottom=True,
-    legend_at_bottom_columns=3,
-    legend_box_size=24,
-    stroke=False,
-    dots_size=9,
+    legend_at_bottom_columns=2,
+    legend_box_size=32,
     show_x_guides=True,
     show_y_guides=True,
-    x_value_formatter=lambda x: f"{x:.0f}",
-    value_formatter=lambda y: f"{y:.0f}%",
-    margin_bottom=100,
-    margin_left=60,
-    margin_right=40,
-    margin_top=50,
-    x_label_rotation=0,
-    truncate_legend=-1,
-    range=(y_min, y_max),
-    xrange=(x_min, x_max),
+    x_value_formatter=lambda v: f"{v:.0f}",
+    value_formatter=lambda v: f"{v:.0f}%",
+    range=(15, 100),
+    xrange=(1, 14),
     x_labels_major_count=7,
     y_labels_major_count=9,
+    margin=60,
     print_values=False,
-    print_zeroes=False,
     js=[],
 )
 
-# Add scatter data as list of (x, y) tuples
-points = [(float(h), float(s)) for h, s in zip(study_hours, exam_scores, strict=True)]
-chart.add(
-    f"Students (n={len(points)})",
-    points,
-    stroke=False,
-    formatter=lambda x: f"({x[0]:.1f} hrs, {x[1]:.0f}%)" if isinstance(x, (tuple, list)) else f"{x:.0f}",
-)
-
-# Add trend line — dashed stroke for visual contrast
-trend_points = [(float(x), float(y)) for x, y in zip(trend_x, trend_y, strict=True)]
-chart.add(
-    f"Trend (r = {r:.2f})",
-    trend_points,
-    stroke=True,
-    show_dots=False,
-    stroke_style={"width": 14, "dasharray": "32, 14", "linecap": "round", "linejoin": "round"},
-)
-
-# Annotate notable outliers — pygal per-point metadata with label styling
-oh = float(study_hours[top_outlier_idx])
-os_ = float(exam_scores[top_outlier_idx])
-bh = float(study_hours[bottom_outlier_idx])
-bs = float(exam_scores[bottom_outlier_idx])
-chart.add(
-    "Outliers",
-    [
-        {"value": (oh, os_), "label": f"High performer ({oh:.0f}h \u2192 {os_:.0f}%)"},
-        {"value": (bh, bs), "label": f"Low performer ({bh:.0f}h \u2192 {bs:.0f}%)"},
-    ],
-    stroke=False,
-    dots_size=16,
-    formatter=lambda x: f"{x[1]:.0f}%" if isinstance(x, (tuple, list)) else f"{x:.0f}",
-)
+chart.add("Passing (≥ 70%)", above)
+chart.add("Below 70%", below)
 
-# Save outputs — dual format leverages pygal's SVG-native + PNG capability
-chart.render_to_png("plot.png")
-chart.render_to_file("plot.html")
+chart.render_to_png(f"plot-{THEME}.png")
+with open(f"plot-{THEME}.html", "wb") as f:
+    f.write(chart.render())