Improve readability of anomaly detection feature plots

Author: JohT

domains/anomaly-detection/explore/AnomalyDetectionIsolationForestExploration.ipynb

@@ -367,9 +367,6 @@
     "def plot_feature_correlation_matrix(features: pd.DataFrame) -> None:\n",
     "    \"\"\"\n",
     "    Plots the correlation matrix of the features in the DataFrame.\n",
-    "    \n",
-    "    :param java_package_anomaly_detection_features: DataFrame containing the features.\n",
-    "    :param java_package_features_to_standardize: List of feature names to include in the correlation matrix.\n",
     "    \"\"\"\n",
     "    correlation_matrix = features.corr()\n",
     "\n",
@@ -381,7 +378,7 @@
     "    axis.set_xticklabels(correlation_matrix.columns, rotation=90)\n",
     "    axis.set_yticklabels(correlation_matrix.index)\n",
     "    for (i, j), correlation_value in np.ndenumerate(correlation_matrix.values):\n",
-    "        axis.text(j, i, f\"{correlation_value:.2f}\", ha='center', va='center', color='black', bbox=dict(facecolor='white', alpha=0.3, edgecolor='none'))\n",
+    "        axis.text(j, i, f\"{correlation_value:.2f}\", ha='center', va='center', color='black', bbox=dict(facecolor='white', alpha=0.3, edgecolor='none'), fontsize=6)\n",
     "    plot.title(\"Feature Correlation Matrix (excluding embeddings)\", fontsize=10)\n",
     "    plot.tight_layout()\n",
     "    plot.show()"
@@ -946,8 +943,8 @@
     "    x_position_column: str = 'embeddingVisualizationX',\n",
     "    y_position_column: str = 'embeddingVisualizationY',\n",
     "    annotate_top_n_anomalies: int = 10,\n",
-    "    annotate_top_n_non_anomalies: int = 5,\n",
-    "    annotate_top_n_clusters: int = 20,\n",
+    "    annotate_top_n_non_anomalies: int = 3,\n",
+    "    annotate_top_n_clusters: int = 10,\n",
     "    percentile_of_distance_to_center: float = 0.8,\n",
     "    no_cluster_coloring: bool = False,\n",
     ") -> None:\n",
@@ -995,7 +992,11 @@
     "    cluster_non_noise = cluster_without_anomalies[cluster_without_anomalies[cluster_label_column] != -1]\n",
     "\n",
     "    plot.figure(figsize=(10, 10))\n",
-    "    plot.title(f\"{title_prefix} (size={size_column}, main-color=cluster, red=anomaly, green=non-anomaly)\", pad=20)\n",
+    "    plot.title(\n",
+    "        label=f\"{title_prefix} (size={size_column}, main-color=cluster, red=anomaly, green=non-anomaly)\", \n",
+    "        pad=30,\n",
+    "        bbox=dict(facecolor='white', edgecolor='none', pad=2, alpha=0.6)\n",
+    "    )\n",
     "\n",
     "    # Plot noise (from clustering)\n",
     "    plot.scatter(\n",
@@ -1111,6 +1112,8 @@
     "            **plot_annotation_style\n",
     "        )\n",
     "\n",
+    "    plot.tight_layout(pad=0.2)\n",
+    "    plot.axis('off')\n",
     "    plot.show()"
    ]
   },
@@ -1263,6 +1266,8 @@
     "            **plot_annotation_style\n",
     "        )\n",
     "\n",
+    "    plot.tight_layout(pad=0.2)\n",
+    "    plot.axis('off')\n",
     "    plot.show()"
    ]
   },

domains/anomaly-detection/tunedAnomalyDetectionExplained.py

@@ -621,8 +621,8 @@ def plot_anomalies(
         return
 
     annotate_top_n_anomalies: int = 10
-    annotate_top_n_non_anomalies: int = 5
-    annotate_top_n_clusters: int = 20
+    annotate_top_n_non_anomalies: int = 3
+    annotate_top_n_clusters: int = 10
 
     features_to_visualize_zoomed=zoom_into_center_while_preserving_top_scores(
         features_to_visualize, 
@@ -647,8 +647,11 @@ def get_common_plot_parameters(data: pd.DataFrame) -> dict:
     cluster_non_noise = cluster_without_anomalies[cluster_without_anomalies[cluster_label_column] != -1]
 
     plot.figure(figsize=(10, 10))
-    plot.title(f"{title_prefix} Anomalies (size={size_column}, main-color=cluster, red=anomaly, green=non-anomaly)", pad=20)
-
+    plot.title(
+        label=f"{title_prefix} Anomalies (size={size_column}, main-color=cluster, red=anomaly, green=non-anomaly)", 
+        pad=30,
+        bbox=dict(facecolor='white', edgecolor='none', pad=2, alpha=0.6)
+    )
     # Plot noise (from clustering)
     plot.scatter(
         **get_common_plot_parameters(cluster_noise),
@@ -712,6 +715,9 @@ def get_common_plot_parameters(data: pd.DataFrame) -> dict:
         color="red",
     )
 
+    plot.tight_layout(pad=0.2)
+    plot.axis('off')
+    
     plot.savefig(plot_file_path)
     plot.close()