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

Comprehensive review improving code quality, data choice, visual design, spec compliance, and library feature usage.

Author: MarkusNeusinger

plots/dendrogram-basic/implementations/letsplot.py

@@ -1,7 +1,7 @@
-""" pyplots.ai
+"""pyplots.ai
 dendrogram-basic: Basic Dendrogram
-Library: letsplot 4.8.2 | Python 3.13.11
-Quality: 91/100 | Created: 2025-12-23
+Library: letsplot 4.8.2 | Python 3.14.3
+Quality: /100 | Updated: 2026-04-05
 """
 
 import numpy as np
@@ -10,12 +10,14 @@
     LetsPlot,
     aes,
     element_blank,
+    element_line,
     element_text,
     geom_segment,
     geom_text,
     ggplot,
     ggsize,
     labs,
+    layer_tooltips,
     scale_color_manual,
     scale_x_continuous,
     scale_y_continuous,
@@ -24,132 +26,131 @@
 )
 from lets_plot.export import ggsave
 from scipy.cluster.hierarchy import linkage
+from sklearn.datasets import load_iris
 
 
 LetsPlot.setup_html()
 
-# Data - Iris flower measurements (4 features for 15 samples)
+# Data - Iris flower measurements (15 samples, 3 species)
+iris = load_iris()
 np.random.seed(42)
+indices = np.sort(np.concatenate([np.random.choice(np.where(iris.target == k)[0], 5, replace=False) for k in range(3)]))
+features = iris.data[indices]
+species_names = ["Setosa", "Versicolor", "Virginica"]
+labels = [f"{species_names[iris.target[i]]}-{j + 1}" for j, i in enumerate(indices)]
 
-# Simulate iris-like measurements: sepal length, sepal width, petal length, petal width
-# Three species with distinct characteristics
-samples_per_species = 5
-
-labels = []
-data = []
-
-# Setosa: shorter petals, wider sepals
-for i in range(samples_per_species):
-    labels.append(f"Setosa-{i + 1}")
-    data.append(
-        [
-            5.0 + np.random.randn() * 0.3,  # sepal length
-            3.4 + np.random.randn() * 0.3,  # sepal width
-            1.5 + np.random.randn() * 0.2,  # petal length
-            0.3 + np.random.randn() * 0.1,  # petal width
-        ]
-    )
-
-# Versicolor: medium measurements
-for i in range(samples_per_species):
-    labels.append(f"Versicolor-{i + 1}")
-    data.append(
-        [
-            5.9 + np.random.randn() * 0.4,  # sepal length
-            2.8 + np.random.randn() * 0.3,  # sepal width
-            4.3 + np.random.randn() * 0.4,  # petal length
-            1.3 + np.random.randn() * 0.2,  # petal width
-        ]
-    )
-
-# Virginica: longer petals and sepals
-for i in range(samples_per_species):
-    labels.append(f"Virginica-{i + 1}")
-    data.append(
-        [
-            6.6 + np.random.randn() * 0.5,  # sepal length
-            3.0 + np.random.randn() * 0.3,  # sepal width
-            5.5 + np.random.randn() * 0.5,  # petal length
-            2.0 + np.random.randn() * 0.3,  # petal width
-        ]
-    )
-
-data = np.array(data)
-n_samples = len(labels)
-
-# Compute hierarchical clustering using Ward's method
-linkage_matrix = linkage(data, method="ward")
+# Hierarchical clustering (Ward's method)
+linkage_matrix = linkage(features, method="ward")
 
 # Build dendrogram coordinates from linkage matrix
 n = len(labels)
-leaf_positions = {i: i for i in range(n)}
-node_heights = dict.fromkeys(range(n), 0)
+leaf_positions = {i: float(i) for i in range(n)}
+node_heights = dict.fromkeys(range(n), 0.0)
 segments = []
 
-# Color threshold for clustering (similar to matplotlib's default)
+# Color threshold — splits into 3 major clusters
 max_dist = linkage_matrix[:, 2].max()
 color_threshold = 0.7 * max_dist
 
-# Process each merge in the linkage matrix
+# Track cluster identity for each node (leaf or merged)
+palette = {"above": "#306998", "Setosa": "#4DAF4A", "Versicolor": "#FF7F00", "Virginica": "#984EA3"}
+node_cluster = {i: labels[i].split("-")[0] for i in range(n)}
+
 for i, (left, right, dist, _) in enumerate(linkage_matrix):
     left, right = int(left), int(right)
     new_node = n + i
 
-    # Get positions of children
     left_pos = leaf_positions[left]
     right_pos = leaf_positions[right]
-
-    # New node position is midpoint of children
-    new_pos = (left_pos + right_pos) / 2
-    leaf_positions[new_node] = new_pos
+    leaf_positions[new_node] = (left_pos + right_pos) / 2
     node_heights[new_node] = dist
 
-    # Determine color based on height threshold
-    color = "#306998" if dist >= color_threshold else "#FFD43B"
+    # Cluster label: same species if both children match, otherwise "above"
+    left_cl, right_cl = node_cluster[left], node_cluster[right]
+    node_cluster[new_node] = left_cl if left_cl == right_cl else "above"
+    cluster_label = node_cluster[new_node] if dist < color_threshold else "above"
+    color = palette[cluster_label]
+    display_cluster = cluster_label if cluster_label != "above" else "Inter-cluster"
 
     left_height = node_heights[left]
     right_height = node_heights[right]
 
-    # Vertical segment from left child to merge height
-    segments.append((left_pos, left_height, left_pos, dist, color))
-    # Vertical segment from right child to merge height
-    segments.append((right_pos, right_height, right_pos, dist, color))
-    # Horizontal segment connecting the two
-    segments.append((left_pos, dist, right_pos, dist, color))
+    # Vertical segment from left child up to merge height
+    segments.append(
+        {
+            "x": left_pos,
+            "y": left_height,
+            "xend": left_pos,
+            "yend": dist,
+            "color": color,
+            "merge_dist": round(dist, 2),
+            "cluster": display_cluster,
+        }
+    )
+    # Vertical segment from right child up to merge height
+    segments.append(
+        {
+            "x": right_pos,
+            "y": right_height,
+            "xend": right_pos,
+            "yend": dist,
+            "color": color,
+            "merge_dist": round(dist, 2),
+            "cluster": display_cluster,
+        }
+    )
+    # Horizontal segment connecting the two children
+    segments.append(
+        {
+            "x": left_pos,
+            "y": dist,
+            "xend": right_pos,
+            "yend": dist,
+            "color": color,
+            "merge_dist": round(dist, 2),
+            "cluster": display_cluster,
+        }
+    )
 
-# Create segment dataframe
-segment_df = pd.DataFrame(segments, columns=["x", "y", "xend", "yend", "color"])
+segment_df = pd.DataFrame(segments)
 
-# Create label dataframe for x-axis labels
-label_data = []
-for i, label in enumerate(labels):
-    label_data.append({"x": leaf_positions[i], "y": -0.8, "label": label})
-label_df = pd.DataFrame(label_data)
+# Leaf labels positioned just below y=0
+label_df = pd.DataFrame([{"x": leaf_positions[i], "y": -0.3, "label": labels[i]} for i in range(n)])
 
 # Plot
+color_values = {v: v for v in palette.values()}
+
 plot = (
     ggplot()
-    + geom_segment(aes(x="x", y="y", xend="xend", yend="yend", color="color"), data=segment_df, size=1.5)
-    + geom_text(aes(x="x", y="y", label="label"), data=label_df, angle=35, hjust=1, vjust=1, size=10, color="#333333")
-    + scale_color_manual(values={"#306998": "#306998", "#FFD43B": "#FFD43B"}, guide="none")
-    + scale_x_continuous(expand=[0.06, 0.02])
-    + scale_y_continuous(expand=[0.18, 0.02])
-    + labs(x="Sample", y="Distance (Ward)", title="dendrogram-basic · letsplot · pyplots.ai")
+    + geom_segment(
+        aes(x="x", y="y", xend="xend", yend="yend", color="color"),
+        data=segment_df,
+        size=1.8,
+        tooltips=layer_tooltips().title("Merge").line("Distance|@merge_dist").line("Cluster|@cluster"),
+    )
+    + geom_text(aes(x="x", y="y", label="label"), data=label_df, angle=40, hjust=1, vjust=1, size=10, color="#444444")
+    + scale_color_manual(values=color_values, guide="none")
+    + scale_x_continuous(expand=[0.05, 0.02])
+    + scale_y_continuous(name="Ward Linkage Distance", expand=[0.14, 0.01], breaks=[0, 2, 4, 6, 8, 10, 12])
+    + labs(x="", title="dendrogram-basic \u00b7 letsplot \u00b7 pyplots.ai")
     + theme_minimal()
     + theme(
-        axis_title=element_text(size=20),
+        plot_title=element_text(size=24, face="bold"),
+        axis_title_y=element_text(size=20),
         axis_text=element_text(size=16),
         axis_text_x=element_blank(),
         axis_ticks_x=element_blank(),
-        plot_title=element_text(size=24),
+        axis_line_x=element_blank(),
+        axis_line_y=element_line(size=0.5, color="#CCCCCC"),
         panel_grid_major_x=element_blank(),
         panel_grid_minor_x=element_blank(),
+        panel_grid_major_y=element_line(size=0.5, color="#E8E8E8"),
+        panel_grid_minor=element_blank(),
+        plot_margin=[40, 20, 20, 20],
     )
     + ggsize(1600, 900)
 )
 
-# Save PNG (scale=3 gives 4800x2700)
+# Save
 ggsave(plot, "plot.png", path=".", scale=3)
-
-# Save HTML for interactivity
 ggsave(plot, "plot.html", path=".")

plots/dendrogram-basic/metadata/letsplot.yaml

@@ -1,15 +1,15 @@
 library: letsplot
 specification_id: dendrogram-basic
 created: '2025-12-23T10:01:23Z'
-updated: '2025-12-23T10:07:42Z'
-generated_by: claude-opus-4-5-20251101
+updated: '2026-04-05T20:00:00+00:00'
+generated_by: claude-opus-4-6
 workflow_run: 20457536578
 issue: 0
-python_version: 3.13.11
+python_version: '3.14.3'
 library_version: 4.8.2
 preview_url: https://storage.googleapis.com/pyplots-images/plots/dendrogram-basic/letsplot/plot.png
 preview_html: https://storage.googleapis.com/pyplots-images/plots/dendrogram-basic/letsplot/plot.html
-quality_score: 91
+quality_score: null
 impl_tags:
   dependencies:
     - scipy