update(box-basic): letsplot — comprehensive quality review and improvement (#4240)

## Summary

Updated **letsplot** implementation for **box-basic**.

**Changes:** Comprehensive quality review — improved data quality,
visual design, code style, and library feature usage.

## Test Plan

- [x] Preview images uploaded to GCS staging
- [x] Implementation file passes ruff format/check
- [x] Metadata YAML updated with current versions
- [ ] Automated review triggered

---
Generated with [Claude Code](https://claude.com/claude-code) `/update`
command

---------

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: MarkusNeusinger

plots/box-basic/implementations/letsplot.py

@@ -1,23 +1,31 @@
 """ pyplots.ai
 box-basic: Basic Box Plot
-Library: letsplot 4.8.1 | Python 3.13.11
-Quality: 98/100 | Created: 2025-12-23
+Library: letsplot 4.8.2 | Python 3.14
+Quality: 90/100 | Created: 2025-12-23
 """
 
 import numpy as np
 import pandas as pd
 from lets_plot import (
     LetsPlot,
     aes,
+    as_discrete,
+    element_blank,
+    element_line,
+    element_rect,
     element_text,
+    flavor_high_contrast_light,
     geom_boxplot,
+    geom_hline,
+    geom_text,
     ggplot,
     ggsave,
     ggsize,
     labs,
+    layer_tooltips,
     scale_fill_manual,
+    scale_y_continuous,
     theme,
-    theme_minimal,
 )
 
 
@@ -27,7 +35,6 @@
 np.random.seed(42)
 categories = ["Engineering", "Marketing", "Sales", "HR", "Finance"]
 data = []
-# Realistic salary distributions for each department
 distributions = {
     "Engineering": (85000, 15000),
     "Marketing": (65000, 12000),
@@ -40,27 +47,111 @@
     mean, std = distributions[cat]
     n = np.random.randint(50, 100)
     values = np.random.normal(mean, std, n)
-    # Add a few outliers
     outliers = np.random.choice([mean + 3.5 * std, mean - 2.5 * std], size=3)
     values = np.concatenate([values, outliers])
     data.extend([(cat, v) for v in values])
 
-df = pd.DataFrame(data, columns=["category", "value"])
+df = pd.DataFrame(data, columns=["department", "salary"])
+
+# Compute medians for annotation labels
+medians = df.groupby("department")["salary"].median().reset_index()
+medians.columns = ["department", "median_salary"]
+medians["label"] = medians["median_salary"].apply(lambda x: f"${x:,.0f}")
+
+# Insight: compare highest vs lowest median departments
+sorted_medians = medians.sort_values("median_salary")
+low_dept = sorted_medians.iloc[0]
+high_dept = sorted_medians.iloc[-1]
+pct_diff = (high_dept["median_salary"] - low_dept["median_salary"]) / low_dept["median_salary"]
+insight_text = f"+{pct_diff:.0%} vs. {low_dept['department']}"
+
+# Overall mean for reference line
+overall_mean = df["salary"].mean()
+
+# Annotation dataframes
+insight_df = pd.DataFrame(
+    {
+        "department": [high_dept["department"]],
+        "y": [high_dept["median_salary"] + 22000],
+        "lbl": [f"{high_dept['department'][:3]}. {insight_text}"],
+    }
+)
+mean_label_df = pd.DataFrame(
+    {"department": [high_dept["department"]], "y": [overall_mean + 3000], "lbl": [f"Avg: ${overall_mean:,.0f}"]}
+)
 
 # Plot
-colors = ["#306998", "#FFD43B", "#DC2626", "#16A34A", "#9333EA"]
+# Wong colorblind-safe palette (no two similar blues)
+colors = ["#0072B2", "#E69F00", "#D55E00", "#009E73", "#CC79A7"]
 
 plot = (
-    ggplot(df, aes(x="category", y="value", fill="category"))
-    + geom_boxplot(alpha=0.8, size=1.5, outlier_size=4)
+    ggplot(df, aes(x=as_discrete("department", order=1, order_by="..middle.."), y="salary", fill="department"))
+    + geom_boxplot(
+        alpha=0.85,
+        size=1.2,
+        outlier_size=5,
+        outlier_shape=21,
+        outlier_color="#333333",
+        width=0.72,
+        tooltips=layer_tooltips()
+        .title("@department")
+        .line("Median|$@{..middle..}")
+        .line("Q1|$@{..lower..}")
+        .line("Q3|$@{..upper..}")
+        .line("Min|$@{..ymin..}")
+        .line("Max|$@{..ymax..}"),
+    )
     + scale_fill_manual(values=colors)
-    + labs(x="Department", y="Salary ($)", title="box-basic · letsplot · pyplots.ai")
-    + theme_minimal()
+    # Median value labels above each box
+    + geom_text(
+        aes(x="department", y="median_salary", label="label"),
+        data=medians,
+        size=11,
+        color="#333333",
+        fontface="bold",
+        nudge_y=5000,
+        inherit_aes=False,
+    )
+    # Overall mean reference line
+    + geom_hline(yintercept=overall_mean, color="#888888", size=0.8, linetype="dashed")
+    + geom_text(
+        aes(x="department", y="y", label="lbl"),
+        data=mean_label_df,
+        size=10,
+        color="#666666",
+        fontface="italic",
+        hjust=0.5,
+        inherit_aes=False,
+    )
+    # Key insight annotation
+    + geom_text(
+        aes(x="department", y="y", label="lbl"),
+        data=insight_df,
+        size=11,
+        color="#1E4F72",
+        fontface="bold italic",
+        inherit_aes=False,
+    )
+    + scale_y_continuous(format="${,.0f}")
+    + labs(
+        x="Department",
+        y="Annual Salary (USD)",
+        title="box-basic \u00b7 letsplot \u00b7 pyplots.ai",
+        subtitle="Salary distributions across five departments, ordered by median",
+    )
+    + flavor_high_contrast_light()
     + theme(
+        plot_title=element_text(size=24, face="bold"),
+        plot_subtitle=element_text(size=16, color="#555555"),
         axis_title=element_text(size=20),
         axis_text=element_text(size=16),
-        plot_title=element_text(size=24),
+        axis_ticks=element_blank(),
+        panel_grid_major_x=element_blank(),
+        panel_grid_minor=element_blank(),
+        panel_grid_major_y=element_line(color="#DDDDDD", size=0.5),
         legend_position="none",
+        plot_background=element_rect(fill="white", color="white"),
+        plot_margin=[10, 35, 10, 10],
     )
     + ggsize(1600, 900)
 )