fix(ccmodel-hepheastus): incorporate PR feedback

Authored-by: Bruno Mateus <[email protected]>
Signed-off-by: Rafael Belchior <[email protected]>

.cspell.json

@@ -35,6 +35,8 @@
     "cccs",
     "ccep",
     "ccid",
+    "ccmodel",
+    "cctx",
     "celo",
     "cids",
     "clazz",
@@ -206,6 +208,7 @@
     "undici",
     "unixfs",
     "Unmarshal",
+    "unmodeled",
     "utxoexample",
     "uuidv",
     "vscc",

packages/cactus-plugin-ccmodel-hephaestus/.gitignore

@@ -1,4 +1,3 @@
 cactus-openapi-spec-plugin-consortium-manual.json
 src/main/typescript/generated/openapi/typescript-axios/.npmignore
-src/test/csv
-src/test/json
+src/test/ccLogs

packages/cactus-plugin-ccmodel-hephaestus/README.md

@@ -32,6 +32,16 @@ In the root of the project to install the dependencies execute the command:
 npm run configure
 ```
 
+The plugin requires Python and packages for process mining functionality. Install the following prerequisites:
+1. Python 3.x and pip:
+```sh
+sudo apt install python3 python3-pip
+```
+2. Required Python packages:
+```sh
+pip3 install pm4py pandas
+```
+
 Know how to use the following plugins of the project:
 
   - [cactus-plugin-ledger-connector-besu](https://github.com/hyperledger/cactus/tree/main/packages/cactus-plugin-ledger-connector-besu)

packages/cactus-plugin-ccmodel-hephaestus/src/main/typescript/pm4py-adapter/check_conformance.py → packages/cactus-plugin-ccmodel-hephaestus/src/main/python/check_conformance.py

@@ -11,13 +11,6 @@
 from pm4py.objects.petri_net.obj import PetriNet, Marking
 from pm4py.objects.petri_net.utils import petri_utils
 
-#chage path if necessary
-path = os.getcwd()
-parent = os.path.dirname(path)
-csv_dir = path + "/packages/cactus-plugin-ccmodel-hephaestus/src/test/csv"
-json_dir = path + "/packages/cactus-plugin-ccmodel-hephaestus/src/test/json"
-pnml_file = path + "/packages/cactus-plugin-ccmodel-hephaestus/src/main/typescript/pm4py-adapter/process_models/pnml/petri_output.pnml"
-
 ##################################################################
 
 def import_csv_original(file_path):
@@ -34,17 +27,6 @@ def import_json_original(file_path):
 
 ##################################################################
 
-def unserialize_and_check_conformance_file(ccLog):
-    net, initial_marking, final_marking = pm4py.read_pnml(pnml_file)
-    # pm4py.view_petri_net(net, initial_marking, final_marking)
-
-    # check  conformance:
-    print("\n----diagnostics:")
-    diagnostics = pm4py.conformance_diagnostics_alignments(ccLog, net, initial_marking, final_marking)
-    print(diagnostics)
-
-##################################################################
-
 def divide_model(model):
     split_model = model.split(';')
     return split_model[0], split_model[1], split_model[2], split_model[3], split_model[4]
@@ -112,17 +94,15 @@ def unserialize_model(model):
         (source, target) = get_from_to_arc(arc)
 
         # source is a place, target is a transition
-        if get_place(net.places, source) != None: 
+        if get_place(net.places, source) != None:
             place = get_place(net.places, source)
             transition = get_transition(net.transitions, target)
             petri_utils.add_arc_from_to(place, transition, net)
-
         # target is a place, source is a transition
         elif get_place(net.places, target) != None:
             transition = get_transition(net.transitions, source)
             place = get_place(net.places, target)
             petri_utils.add_arc_from_to(transition, place, net)
-
         # target and source are both a transition or a place - cannot happen
         else:
             print("arcs cannot have the same type in source and target")
@@ -171,13 +151,13 @@ def unserialize_and_check_conformance(ccLog):
     if len(non_conforming_activities) != 0:
         print("NON-CONFORMANCE:")
         print(non_conforming_activities)
-        print(file)
+        print(os.path.basename(log_file_path))
         return
 
     if len(all_activities) == len(conforming_activities):
         print("FULL CONFORMANCE:")
         print(conforming_activities)
-        print(file)
+        print(os.path.basename(log_file_path))
         return
 
     # If there were no skips in the case, then all the conforming activities 
@@ -191,36 +171,36 @@ def unserialize_and_check_conformance(ccLog):
     if ignore_skips == True:
         print("PARTIAL CONFORMANCE:")
         print(conforming_activities)
-        print(file)
+        print(os.path.basename(log_file_path))
     else:
         print("SKIPPED ACTIVITY:")
         print(skipped_activities)
-        print(file)
+        print(os.path.basename(log_file_path))
 
 ##################################################################
 
 def main():
-    file_csv = file + ".csv"
-    file_json = file + ".json"
-
-    file_path_csv = os.path.join(csv_dir, file_csv)
-    file_path_json = os.path.join(json_dir, file_json)
-    if (os.path.exists(file_path_csv)):
-        ccLog = import_csv_original(file_path_csv)
+    if not os.path.exists(log_file_path):
+        print(f"File '{log_file_path}' does not exist")
+        exit(1)
+
+    file_extension = os.path.splitext(log_file_path)[1].lower()
+
+    if file_extension == '.csv':
+        ccLog = import_csv_original(log_file_path)
         unserialize_and_check_conformance(ccLog)
-    elif (os.path.exists(file_path_json)):
-        ccLog = import_json_original(file_path_json)
+    elif file_extension == '.json':
+        ccLog = import_json_original(log_file_path)
         unserialize_and_check_conformance(ccLog)
     else:
-        print(f"File '{file}' does not exist")
-        print(file_path_json)
+        print(f"Unsupported file type: {file_extension}")
         exit(1)
 
 if __name__ == "__main__":
     if len(sys.argv) != 3:
-        print("Usage: python3 check_conformance.py file_with_new_logs serialized_ccmodel")
+        print("Usage: python3 check_conformance.py path_to_log_file serialized_ccmodel")
         exit(1)
 
-    file = sys.argv[1]
+    log_file_path = sys.argv[1]
     serialized_ccmodel = sys.argv[2]
     main()

packages/cactus-plugin-ccmodel-hephaestus/src/main/python/create_model.py

@@ -0,0 +1,59 @@
+import sys
+import os
+# uncomment if problems with dependencies
+#%pip install pm4py
+#%pip install pandas
+import pm4py
+import time
+import pandas
+import pickle
+import json
+
+def import_csv_original(file_path):
+    event_log = pandas.read_csv(file_path, sep=';')
+    event_log = pm4py.format_dataframe(event_log, case_id='caseID', activity_key='methodName', timestamp_key='timestamp')
+    return event_log
+
+def import_json_original(file_path):
+    with open(file_path, 'r') as file:
+        data = json.load(file)
+    event_log = pandas.DataFrame(data)
+    event_log = pm4py.format_dataframe(event_log, case_id='caseID', activity_key='methodName', timestamp_key='timestamp')
+    return event_log
+
+##################################################################
+
+def create_and_serialize_model(ccLog):
+    pn, im, fm = pm4py.discover_petri_net_inductive(ccLog)
+    # pm4py.view_petri_net(pn, im, fm)
+    return str(pn.places) + ";" + str(pn.transitions) + ";" + str(pn.arcs) + ";" + str(im) + ";" + str(fm)
+
+##################################################################
+
+def main():
+    file_path = sys.argv[1]
+
+    if not os.path.exists(file_path):
+        print(f"File '{file_path}' does not exist")
+        exit(1)
+
+    file_extension = os.path.splitext(file_path)[1].lower()
+
+    if file_extension == '.csv':
+        ccLog = import_csv_original(file_path)
+        serialized_model = create_and_serialize_model(ccLog)
+        print(serialized_model)
+    elif file_extension == '.json':
+        ccLog = import_json_original(file_path)
+        serialized_model = create_and_serialize_model(ccLog)
+        print(serialized_model)
+    else:
+        print(f"Unsupported file type: {file_extension}")
+        exit(1)
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: python3 create_model.py path_to_log_file")
+        exit(1)
+
+    main()

packages/cactus-plugin-ccmodel-hephaestus/src/main/typescript/pm4py-adapter/ccmodel-adapter.ts → packages/cactus-plugin-ccmodel-hephaestus/src/main/typescript/ccmodel-adapter.ts

@@ -2,9 +2,9 @@ import { execSync } from "child_process";
 
 import path from "path";
 
-export function createModelPM4PY(file_name: string): string {
-  const createModelScript = path.join(__dirname, "create_model.py");
-  const command = `python3 ${createModelScript} ${file_name}`;
+export function createModelPM4PY(logPath: string): string {
+  const createModelScript = path.join(__dirname, "../python/create_model.py");
+  const command = `python3 ${createModelScript} ${logPath}`;
 
   try {
     const startTime = new Date();
@@ -21,11 +21,14 @@ export function createModelPM4PY(file_name: string): string {
 }
 
 export function checkConformancePM4PY(
-  file_name: string,
+  logPath: string,
   serializedCCModel: string,
 ): string {
-  const checkConformanceScript = path.join(__dirname, "check_conformance.py");
-  const command = `python3 ${checkConformanceScript} ${file_name} \'${serializedCCModel}\'`;
+  const checkConformanceScript = path.join(
+    __dirname,
+    "../python/check_conformance.py",
+  );
+  const command = `python3 ${checkConformanceScript} ${logPath} \'${serializedCCModel}\'`;
 
   // console.log(command);
   try {