update(dendrogram-basic): seaborn — comprehensive quality review

plots/dendrogram-basic/implementations/seaborn.py

@@ -1,81 +1,117 @@
 """ pyplots.ai
 dendrogram-basic: Basic Dendrogram
-Library: seaborn 0.13.2 | Python 3.13.11
-Quality: 91/100 | Created: 2025-12-23
+Library: seaborn 0.13.2 | Python 3.14.3
+Quality: 89/100 | Updated: 2026-04-05
 """
 
 import matplotlib.pyplot as plt
 import numpy as np
+import pandas as pd
 import seaborn as sns
-from scipy.cluster.hierarchy import dendrogram, linkage
-from sklearn.datasets import load_iris
 
 
-# Set seaborn style for better aesthetics
-sns.set_theme(style="whitegrid")
+# Style - leverage seaborn's distinctive theming
+sns.set_theme(style="white", rc={"axes.linewidth": 0.8, "font.family": "sans-serif"})
 sns.set_context("talk", font_scale=1.2)
 
-# Load iris dataset - use subset for readability (spec recommends 10-50 items)
-np.random.seed(42)
-iris = load_iris()
+# Custom palette starting with Python Blue
+species_palette = sns.color_palette(["#306998", "#E8843C", "#4EA86B"])
 species_names = ["Setosa", "Versicolor", "Virginica"]
+species_colors = dict(zip(species_names, species_palette, strict=True))
 
-# Select 10 samples from each species (30 total) for clearer visualization
-indices = np.concatenate([np.random.choice(np.where(iris.target == i)[0], 10, replace=False) for i in range(3)])
-
-X = iris.data[indices]
-
-# Create clear labels: Species-Number format using vectorized approach
-species_ids = iris.target[indices]
-labels = [f"{species_names[sid]}-{np.sum(species_ids[: i + 1] == sid)}" for i, sid in enumerate(species_ids)]
-
-# Compute linkage matrix using Ward's method
-linkage_matrix = linkage(X, method="ward")
+# Data - use seaborn's iris dataset (30 samples for readable dendrogram)
+np.random.seed(42)
+iris = sns.load_dataset("iris")
+samples = (
+    iris.groupby("species").apply(lambda g: g.sample(10, random_state=42), include_groups=False).reset_index(level=0)
+)
 
-# Create figure
-fig, ax = plt.subplots(figsize=(16, 9))
+feature_cols = ["sepal_length", "sepal_width", "petal_length", "petal_width"]
+features = samples[feature_cols].copy()
+
+# Build sample labels: Species-Number
+counters = dict.fromkeys(["setosa", "versicolor", "virginica"], 0)
+labels = []
+species_list = []
+for species in samples["species"]:
+    counters[species] += 1
+    labels.append(f"{species.title()}-{counters[species]}")
+    species_list.append(species.title())
+
+features.index = labels
+
+# Rename columns to readable format
+features.columns = ["Sepal Length", "Sepal Width", "Petal Length", "Petal Width"]
+
+# Row colors by species - seaborn distinctive feature for annotating clusters
+row_colors = pd.Series([species_colors[sp] for sp in species_list], index=labels, name="Species")
+
+# sns.clustermap - seaborn's distinctive hierarchical clustering + dendrogram
+# This IS the idiomatic seaborn way to visualize dendrograms with data context
+g = sns.clustermap(
+    features,
+    method="ward",
+    row_colors=row_colors,
+    col_cluster=True,
+    cmap=sns.color_palette("viridis", as_cmap=True),
+    figsize=(16, 9),
+    dendrogram_ratio=(0.25, 0.12),
+    linewidths=0.5,
+    linecolor="white",
+    cbar_kws={"label": "Feature Value"},
+    tree_kws={"linewidths": 1.8, "colors": "#666666"},
+    xticklabels=True,
+    yticklabels=True,
+)
 
-# Define custom colors using seaborn colorblind palette for species
-palette = sns.color_palette("colorblind", n_colors=3)
-species_color_map = dict(zip(species_names, palette, strict=True))
+# Customize the row dendrogram (main dendrogram showing sample clustering)
+row_dendro_ax = g.ax_row_dendrogram
+row_dendro_ax.set_xlabel("Distance (Ward)", fontsize=14)
 
-# Create dendrogram
-dendrogram(
-    linkage_matrix,
-    labels=labels,
-    leaf_rotation=45,
-    leaf_font_size=14,
-    ax=ax,
-    above_threshold_color="#888888",
-    color_threshold=0.7 * max(linkage_matrix[:, 2]),
-)
+# Customize heatmap axis labels
+g.ax_heatmap.set_xlabel("Iris Features", fontsize=20)
+g.ax_heatmap.set_ylabel("Iris Samples (by Species)", fontsize=20)
+g.ax_heatmap.tick_params(axis="both", labelsize=13)
 
-# Color the x-axis labels by species using exact palette colors
-for lbl in ax.get_xticklabels():
-    text = lbl.get_text()
-    species = text.rsplit("-", 1)[0]
-    if species in species_color_map:
-        lbl.set_color(species_color_map[species])
+# Color y-axis (sample) labels by species
+for lbl in g.ax_heatmap.get_yticklabels():
+    species = lbl.get_text().rsplit("-", 1)[0]
+    if species in species_colors:
+        lbl.set_color(species_colors[species])
         lbl.set_fontweight("bold")
 
-# Style the plot with seaborn-compatible settings
-ax.set_xlabel("Iris Samples (by Species)", fontsize=20)
-ax.set_ylabel("Distance (Ward Linkage)", fontsize=20)
-ax.set_title("dendrogram-basic · seaborn · pyplots.ai", fontsize=24)
-ax.tick_params(axis="y", labelsize=16)
-ax.tick_params(axis="x", labelsize=14)
-
-# Make grid subtle
-ax.grid(True, alpha=0.3, linestyle="--", axis="y")
-ax.set_axisbelow(True)
+# Color x-axis (feature) labels
+for lbl in g.ax_heatmap.get_xticklabels():
+    lbl.set_fontsize(14)
+    lbl.set_rotation(30)
+    lbl.set_ha("right")
+
+# Style the colorbar
+cbar = g.cax
+cbar.tick_params(labelsize=12)
+cbar.set_ylabel("Feature Value", fontsize=14)
+
+# Add species legend using scatter proxies
+legend_handles = [
+    plt.Line2D([0], [0], marker="s", color="w", markerfacecolor=c, markersize=12, label=n)
+    for n, c in species_colors.items()
+]
+g.ax_heatmap.legend(
+    handles=legend_handles,
+    title="Species",
+    loc="upper left",
+    bbox_to_anchor=(1.15, 1.0),
+    fontsize=12,
+    title_fontsize=13,
+    framealpha=0.95,
+    edgecolor="#cccccc",
+    fancybox=True,
+)
 
-# Add legend using scatter plot handles for exact color matching
-for i, species in enumerate(species_names):
-    ax.scatter([], [], c=[palette[i]], s=150, label=species, marker="s")
-ax.legend(title="Species", loc="upper right", fontsize=14, title_fontsize=16, framealpha=0.9)
+# Title - placed on the figure
+g.figure.suptitle("dendrogram-basic \u00b7 seaborn \u00b7 pyplots.ai", fontsize=24, fontweight="medium", y=1.02)
 
-# Remove top and right spines for cleaner look
-sns.despine(ax=ax)
+# Visual refinement
+sns.despine(ax=g.ax_heatmap, left=False, bottom=False)
 
-plt.tight_layout()
-plt.savefig("plot.png", dpi=300, bbox_inches="tight")
+g.figure.savefig("plot.png", dpi=300, bbox_inches="tight")