Add Treemap visualization to anomaly detection

Author: JohT

domains/anomaly-detection/anomalyDetectionPython.sh

@@ -20,7 +20,7 @@ REPORTS_DIRECTORY=${REPORTS_DIRECTORY:-"reports"}
 # CDPATH reduces the scope of the cd command to potentially prevent unintended directory changes.
 # This way non-standard tools like readlink aren't needed.
 ANOMALY_DETECTION_SCRIPT_DIR=${ANOMALY_DETECTION_SCRIPT_DIR:-$(CDPATH=. cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)}
-echo "anomalyDetectionPipeline: ANOMALY_DETECTION_SCRIPT_DIR=${ANOMALY_DETECTION_SCRIPT_DIR}"
+echo "anomalyDetectionPython: ANOMALY_DETECTION_SCRIPT_DIR=${ANOMALY_DETECTION_SCRIPT_DIR}"
 # Get the "scripts" directory by taking the path of this script and going one directory up.
 SCRIPTS_DIR=${SCRIPTS_DIR:-"${ANOMALY_DETECTION_SCRIPT_DIR}/../../scripts"} # Repository directory containing the shell scripts
 # Get the "cypher" query directory for gathering features.
@@ -49,7 +49,7 @@ while [[ $# -gt 0 ]]; do
       verboseMode="--verbose"
       ;;
     *)
-      echo -e "${COLOR_ERROR}anomalyDetectionPipeline: Error: Unknown option: ${key}${COLOR_DEFAULT}" >&2
+      echo -e "${COLOR_ERROR}anomalyDetectionPython: Error: Unknown option: ${key}${COLOR_DEFAULT}" >&2
       usage
       ;;
   esac
@@ -72,10 +72,10 @@ is_sufficient_data_available() {
     query_result=$( execute_cypher "${ANOMALY_DETECTION_QUERY_CYPHER_DIR}/AnomalyDetectionNodeCount.cypher" "${@}" )
     node_count=$(get_csv_column_value "${query_result}" "node_count")
     if [ "${node_count}" -lt 15 ]; then
-        echo "anomalyDetectionPipeline: Warning: Skipping anomaly detection. Only ${node_count} ${language} ${nodeLabel} nodes. At least 15 required."
+        echo "anomalyDetectionPython: Warning: Skipping anomaly detection. Only ${node_count} ${language} ${nodeLabel} nodes. At least 15 required."
         false
     else
-        echo "anomalyDetectionPipeline: Info: Running anomaly detection with ${node_count} ${language} ${nodeLabel} nodes."
+        echo "anomalyDetectionPython: Info: Running anomaly detection with ${node_count} ${language} ${nodeLabel} nodes."
         true
     fi
 }
@@ -92,7 +92,7 @@ is_sufficient_data_available() {
 anomaly_detection_features() {
     local nodeLabel
     nodeLabel=$( extractQueryParameter "projection_node_label" "${@}" )
-    echo "anomalyDetectionPipeline: $(date +'%Y-%m-%dT%H:%M:%S%z') Collecting features for ${nodeLabel} nodes..."
+    echo "anomalyDetectionPython: $(date +'%Y-%m-%dT%H:%M:%S%z') Collecting features for ${nodeLabel} nodes..."
 
     # Determine the Betweenness centrality (with the directed graph projection) if not already done
     execute_cypher_queries_until_results "${ANOMALY_DETECTION_FEATURE_CYPHER_DIR}/AnomalyDetectionFeature-Betweenness-Exists.cypher" \
@@ -127,7 +127,7 @@ anomaly_detection_using_python() {
     local language
     language=$( extractQueryParameter "projection_language" "${@}" )
 
-    echo "anomalyDetectionPipeline: $(date +'%Y-%m-%dT%H:%M:%S%z') Executing Python scripts for ${language} ${nodeLabel} nodes..."
+    echo "anomalyDetectionPython: $(date +'%Y-%m-%dT%H:%M:%S%z') Executing Python scripts for ${language} ${nodeLabel} nodes..."
 
     # Within the absolute (full) report directory for anomaly detection, create a sub directory for every detailed type (Java_Package, Java_Type,...)
     local detail_report_directory="${FULL_REPORT_DIRECTORY}/${language}_${nodeLabel}"
@@ -152,6 +152,8 @@ anomaly_detection_using_python() {
 # Required Parameters:
 # - projection_node_label=...
 #   Label of the nodes that will be used for the projection. Example: "Package"
+# - projection_language=...
+#   Name of the associated programming language. Examples: "Java", "Typescript"
 anomaly_detection_labels() {
     local nodeLabel
     nodeLabel=$( extractQueryParameter "projection_node_label" "${@}" )
@@ -168,6 +170,19 @@ anomaly_detection_labels() {
     execute_cypher_summarized "${ANOMALY_DETECTION_LABEL_CYPHER_DIR}/AnomalyDetectionArchetypeOutlier.cypher" "${@}"
 }
 
+# Visualize results with treemap charts.
+# 
+# Required Parameters:
+# - projection_language=...
+#   Name of the associated programming language. Examples: "Java", "Typescript"
+anomaly_detection_treemap_visualization() {
+    local language
+    language=$( extractQueryParameter "projection_language" "${@}" )
+    
+    echo "anomalyDetectionPython: $(date +'%Y-%m-%dT%H:%M:%S%z') Visualizing ${language} results..."
+    time "${ANOMALY_DETECTION_SCRIPT_DIR}/treemapVisualizations.py" "${@}" "--report_directory" "${FULL_REPORT_DIRECTORY}" ${verboseMode}
+}
+
 # Run the anomaly detection pipeline.
 # 
 # Required Parameters:
@@ -177,6 +192,8 @@ anomaly_detection_labels() {
 #   Label of the nodes that will be used for the projection. Example: "Package"
 # - projection_weight_property=...
 #   Name of the node property that contains the dependency weight. Example: "weight"
+# - projection_language=...
+#   Name of the associated programming language. Examples: "Java", "Typescript"
 anomaly_detection_python_reports() {
     time anomaly_detection_features "${@}"
     anomaly_detection_using_python "${@}"
@@ -229,6 +246,7 @@ if is_sufficient_data_available "${ALGORITHM_NODE}=Type" "${ALGORITHM_WEIGHT}=we
   if createUndirectedJavaTypeDependencyProjection "${PROJECTION_NAME}=type-anomaly-detection"; then
       createDirectedJavaTypeDependencyProjection "${PROJECTION_NAME}=type-anomaly-detection-directed"
       anomaly_detection_python_reports "${ALGORITHM_PROJECTION}=type-anomaly-detection" "${ALGORITHM_NODE}=Type" "${ALGORITHM_WEIGHT}=weight" "${ALGORITHM_LANGUAGE}=Java" "${COMMUNITY_PROPERTY}" "${EMBEDDING_PROPERTY}"
+      anomaly_detection_treemap_visualization "${ALGORITHM_LANGUAGE}=Java"
   fi
 fi
 
@@ -238,6 +256,7 @@ if is_sufficient_data_available "${ALGORITHM_NODE}=Module" "${ALGORITHM_WEIGHT}=
   if createUndirectedDependencyProjection "${PROJECTION_NAME}=typescript-module-embedding" "${PROJECTION_NODE}=Module" "${PROJECTION_WEIGHT}=lowCouplingElement25PercentWeight" "${PROJECTION_LANGUAGE}=Typescript"; then
       createDirectedDependencyProjection "${PROJECTION_NAME}=typescript-module-embedding-directed" "${PROJECTION_NODE}=Module" "${PROJECTION_WEIGHT}=lowCouplingElement25PercentWeight" "${PROJECTION_LANGUAGE}=Typescript"
       anomaly_detection_python_reports "${ALGORITHM_PROJECTION}=typescript-module-embedding" "${ALGORITHM_NODE}=Module" "${ALGORITHM_WEIGHT}=lowCouplingElement25PercentWeight" "${ALGORITHM_LANGUAGE}=Typescript" "${COMMUNITY_PROPERTY}" "${EMBEDDING_PROPERTY}"
+      anomaly_detection_treemap_visualization "${ALGORITHM_LANGUAGE}=Module"
   fi
 fi
 
@@ -246,4 +265,4 @@ fi
 # Clean-up after report generation. Empty reports will be deleted.
 source "${SCRIPTS_DIR}/cleanupAfterReportGeneration.sh" "${FULL_REPORT_DIRECTORY}"
 
-echo "anomalyDetectionPipeline: $(date +'%Y-%m-%dT%H:%M:%S%z') Successfully finished."
+echo "anomalyDetectionPython: $(date +'%Y-%m-%dT%H:%M:%S%z') Successfully finished."