172 implement hyperopt phase for casearrivals

.github/workflows/simod.yml

@@ -28,7 +28,7 @@ jobs:
     timeout-minutes: 120
     strategy:
       matrix:
-        python-version: [ '3.9' ]
+        python-version: [ '3.11' ]
     steps:
       - uses: actions/checkout@v3
         with:
@@ -121,7 +121,7 @@ jobs:
     if: github.ref == 'refs/heads/master'
     strategy:
       matrix:
-        python-version: [ '3.9' ]
+        python-version: [ '3.11' ]
     environment:
       name: PyPI
       url: https://pypi.org/p/simod

README.md

@@ -17,7 +17,7 @@ the [Prosimos](https://github.com/AutomatedProcessImprovement/Prosimos) simulato
 
 | Dependency | Version | Notes                                                                                                                                          |
 |------------|---------|------------------------------------------------------------------------------------------------------------------------------------------------|
-| Python     | 3.9     | For Windows, [Python 3.9.13](https://www.python.org/downloads/release/python-3913/) is the last distribution with Windows installers.          |
+| Python     | 3.11    | For Windows, [Python 3.9.13](https://www.python.org/downloads/release/python-3913/) is the last distribution with Windows installers.          |
 | Java       | 1.8     | For example, use [Amazon Corretto 8](https://docs.aws.amazon.com/corretto/latest/corretto-8-ug/downloads-list.html).                           |
 | Poetry     | latest  | If using Docker or compiling from source, use [Poetry](https://python-poetry.org/) for building, installing, and managing Python dependencies. |
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "simod"
-version = "5.1.6"
+version = "5.2.0"
 authors = [
     "Ihar Suvorau <ihar.suvorau@gmail.com>",
     "David Chapela <david.chapela@ut.ee>",
@@ -15,40 +15,40 @@ readme = "README.md"
 packages = [{ include = "simod", from = "src" }]
 
 [tool.poetry.dependencies]
-python = "^3.9,<3.12"
-click = "^8.1.3"
-hyperopt = "^0.2.7"
-lxml = "^5.3.0"
-matplotlib = "^3.6.0"
-networkx = "^3.2.1"
-numpy = "^1.24.23"
-pandas = "^2.1.0"
-pendulum = "^3.0.0"
-pydantic = "^2.3.0"
-python-dotenv = "^1.0.0"
-python-multipart = "^0.0.12"
-pytz = "^2024.2"
-PyYAML = "^6.0"
-requests = "^2.28.2"
-scipy = "^1.13.0"
+python = ">=3.11,<3.13"
+click = "^8.4.2"
+hyperopt = "^0.3.0"
+lxml = "^6.1.1"
+matplotlib = "^3.11.1"
+networkx = "^3.6.1"
+numpy = "^2.4.6"
+pandas = "^2.3.3"
+pendulum = "^3.2.0"
+pydantic = "^2.13.4"
+python-dotenv = "^1.2.2"
+python-multipart = "^0.0.32"
+pytz = "^2026.3"
+PyYAML = "^6.0.3"
+requests = "^2.34.2"
+scipy = "^1.17.1"
 statistics = "^1.0.3.5"
-tqdm = "^4.64.1"
-xmltodict = "^0.13.0"
-prosimos = "^2.0.6"
-extraneous-activity-delays = "^2.1.21"
+tqdm = "^4.70.0"
+xmltodict = "^1.0.4"
+prosimos = "^2.1.0"
+extraneous-activity-delays = "^2.3.0"
 openxes-cli-py = "^0.1.15"
-pix-framework = "^0.13.17"
-log-distance-measures = "^2.0.0"
+pix-framework = "^0.15.0"
+log-distance-measures = "^2.2.0"
 
 [tool.poetry.group.dev.dependencies]
-pytest = "^7.1.3"
-pytest-cov = "^4"
+pytest = "^9.0.1"
+pytest-cov = "^7.0.0"
 memory-profiler = "^0.61.0"
-pylint = "^2.17.4"
-setuptools = "^67.8.0"
-seaborn = "^0.12.2"
-pytest-benchmark = "^4.0.0"
-snakeviz = "^2.2.0"
+pylint = "^4.0.3"
+setuptools = "^80.9.0"
+seaborn = "^0.13.2"
+pytest-benchmark = "^5.2.3"
+snakeviz = "^2.2.2"
 
 [tool.poetry.scripts]
 simod = "simod.cli:main"

resources/config/benchmark/benchmark_pool.yml → resources/config/benchmark/AcademicCredentials_diff.yml

@@ -1,12 +1,12 @@
-version: 5
+version: 5.2
 ##########
 # Common #
 ##########
 common:
   # Path to the event log in CSV format
-  train_log_path: ../../event_logs/BPIC_2012_W_train.csv.gz
+  train_log_path: ../../event_logs/AcademicCredentials_train.csv.gz
   # Event log to evaluate the discovered BPS model with
-  test_log_path: ../../event_logs/BPIC_2012_W_test.csv.gz
+  test_log_path: ../../event_logs/AcademicCredentials_test.csv.gz
   # Specify the name for each of the columns in the CSV file (XES standard by default)
   log_ids:
     case: "case_id"
@@ -23,10 +23,31 @@ common:
     - absolute_event_distribution
     - relative_event_distribution
     - circadian_event_distribution
+    - circadian_workforce_distribution
     - arrival_event_distribution
     - cycle_time_distribution
   # Whether to discover case attributes or not
   discover_data_attributes: false
+######################
+# Case Arrival model #
+######################
+case_arrival:
+  # Metric to guide the optimization process (loss function to minimize)
+  optimization_metric: arrival_event_distribution
+  # Number of optimization iterations over the search space
+  num_iterations: 5
+  # Number of times to evaluate each iteration (using the mean of all of them)
+  num_evaluations_per_iteration: 3
+  # Whether to simulate the arrival times using the distribution of inter-arrival times observed in the training log,
+  # or fitting a parameterized probabilistic distribution (e.g., norm, expon) with these observed values.
+  use_observed_arrival_distribution: false
+  # When fitting a probabilistic distribution, threshold used to filter out outliers in the sample of inter-arrival
+  # times observed in the training event log (fixed or range between two floats). Increasing the outlier threshold
+  # increases the "range" of accepted values, thus, potentially decreasing the number of observations considered
+  # an outlier.
+  outlier_threshold:
+    - 5.0
+    - 50.0
 #################
 # Preprocessing #
 #################
@@ -40,7 +61,7 @@ control_flow:
   # Metric to guide the optimization process (loss function to minimize)
   optimization_metric: two_gram_distance
   # Number of optimization iterations over the search space
-  num_iterations: 30
+  num_iterations: 40
   # Number of times to evaluate each iteration (using the mean of all of them)
   num_evaluations_per_iteration: 5
   # Methods for discovering gateway probabilities
@@ -77,7 +98,7 @@ resource_model:
   # Resource profiles configuration
   resource_profiles:
     # Resource profile discovery type
-    discovery_type: pool
+    discovery_type: differentiated
     # Time granularity (in minutes) for the resource calendar (the higher the density of events in the log, the smaller the granularity can be)
     granularity: 60
     # Minimum confidence of the intervals in the discovered calendar (of a resource or set of resources)
@@ -89,4 +110,4 @@ resource_model:
       - 0.05
       - 0.5
     # Participation of a resource in the process to discover a calendar for them (gathered together otherwise)
-    participation: 0.4
+    participation: 0.4

resources/config/benchmark/AcademicCredentials_diff_extr.yml

@@ -0,0 +1,109 @@
+version: 5.2
+##########
+# Common #
+##########
+common:
+  # Path to the event log in CSV format
+  train_log_path: ../../event_logs/AcademicCredentials_train.csv.gz
+  # Event log to evaluate the discovered BPS model with
+  test_log_path: ../../event_logs/AcademicCredentials_test.csv.gz
+  # Use this process model and skip its discovery
+  process_model_path: ../../../outputs/AcademicCredentials_diff/best_result/AcademicCredentials_train.bpmn
+  # Specify the name for each of the columns in the CSV file (XES standard by default)
+  log_ids:
+    case: "case_id"
+    activity: "activity"
+    resource: "resource"
+    start_time: "start_time"
+    end_time: "end_time"
+  # Number of evaluations of the discovered BPS model
+  num_final_evaluations: 10
+  # Metrics to evaluate the discovered BPS model
+  evaluation_metrics:
+    - 3_gram_distance
+    - 2_gram_distance
+    - absolute_event_distribution
+    - relative_event_distribution
+    - circadian_event_distribution
+    - circadian_workforce_distribution
+    - arrival_event_distribution
+    - cycle_time_distribution
+  # Whether to discover case attributes or not
+  discover_data_attributes: false
+######################
+# Case Arrival model #
+######################
+case_arrival:
+  # Metric to guide the optimization process (loss function to minimize)
+  optimization_metric: arrival_event_distribution
+  # Number of optimization iterations over the search space
+  num_iterations: 5
+  # Number of times to evaluate each iteration (using the mean of all of them)
+  num_evaluations_per_iteration: 3
+  # Whether to simulate the arrival times using the distribution of inter-arrival times observed in the training log,
+  # or fitting a parameterized probabilistic distribution (e.g., norm, expon) with these observed values.
+  use_observed_arrival_distribution: false
+  # When fitting a probabilistic distribution, threshold used to filter out outliers in the sample of inter-arrival
+  # times observed in the training event log (fixed or range between two floats). Increasing the outlier threshold
+  # increases the "range" of accepted values, thus, potentially decreasing the number of observations considered
+  # an outlier.
+  outlier_threshold:
+    - 5.0
+    - 50.0
+#################
+# Preprocessing #
+#################
+preprocessing:
+  multitasking: false
+  enable_time_concurrency_threshold: 0.5
+################
+# Control-flow #
+################
+control_flow:
+  # Metric to guide the optimization process (loss function to minimize)
+  optimization_metric: two_gram_distance
+  # Number of optimization iterations over the search space
+  num_iterations: 1
+  # Number of times to evaluate each iteration (using the mean of all of them)
+  num_evaluations_per_iteration: 1
+  # Methods for discovering gateway probabilities
+  gateway_probabilities: discovery
+##################
+# Resource model #
+##################
+resource_model:
+  # Metric to guide the optimization process (loss function to minimize)
+  optimization_metric: circadian_emd
+  # Number of optimization iterations over the search space
+  num_iterations: 40
+  # Number of times to evaluate each iteration (using the mean of all of them)
+  num_evaluations_per_iteration: 5
+  # Whether to discover prioritization or batching behavior
+  discover_prioritization_rules: false
+  discover_batching_rules: false
+  # Resource profiles configuration
+  resource_profiles:
+    # Resource profile discovery type
+    discovery_type: differentiated
+    # Time granularity (in minutes) for the resource calendar (the higher the density of events in the log, the smaller the granularity can be)
+    granularity: 60
+    # Minimum confidence of the intervals in the discovered calendar (of a resource or set of resources)
+    confidence:
+      - 0.5
+      - 0.85
+    # Minimum support of the intervals in the discovered calendar (of a resource or set of resources)
+    support:
+      - 0.05
+      - 0.5
+    # Participation of a resource in the process to discover a calendar for them (gathered together otherwise)
+    participation: 0.4
+#####################
+# Extraneous delays #
+#####################
+extraneous_activity_delays:
+  # Method to compute the extraneous delay (naive or eclipse-aware)
+  discovery_method: eclipse-aware
+  # Metric to guide the optimization process (loss function to minimize)
+  optimization_metric: relative_emd
+  # Number of optimization iterations over the search space (1 = direct discovery, no optimization stage)
+  num_iterations: 20

resources/config/benchmark/AcademicCredentials_fuzz.yml

@@ -0,0 +1,92 @@
+version: 5.2
+##########
+# Common #
+##########
+common:
+  # Path to the event log in CSV format
+  train_log_path: ../../event_logs/AcademicCredentials_train.csv.gz
+  # Event log to evaluate the discovered BPS model with
+  test_log_path: ../../event_logs/AcademicCredentials_test.csv.gz
+  # Use this process model and skip its discovery
+  process_model_path: ../../../outputs/AcademicCredentials_diff/best_result/AcademicCredentials_train.bpmn
+  # Specify the name for each of the columns in the CSV file (XES standard by default)
+  log_ids:
+    case: "case_id"
+    activity: "activity"
+    resource: "resource"
+    start_time: "start_time"
+    end_time: "end_time"
+  # Number of evaluations of the discovered BPS model
+  num_final_evaluations: 10
+  # Metrics to evaluate the discovered BPS model
+  evaluation_metrics:
+    - 3_gram_distance
+    - 2_gram_distance
+    - absolute_event_distribution
+    - relative_event_distribution
+    - circadian_event_distribution
+    - circadian_workforce_distribution
+    - arrival_event_distribution
+    - cycle_time_distribution
+  # Whether to discover case attributes or not
+  discover_data_attributes: false
+######################
+# Case Arrival model #
+######################
+case_arrival:
+  # Metric to guide the optimization process (loss function to minimize)
+  optimization_metric: arrival_event_distribution
+  # Number of optimization iterations over the search space
+  num_iterations: 5
+  # Number of times to evaluate each iteration (using the mean of all of them)
+  num_evaluations_per_iteration: 3
+  # Whether to simulate the arrival times using the distribution of inter-arrival times observed in the training log,
+  # or fitting a parameterized probabilistic distribution (e.g., norm, expon) with these observed values.
+  use_observed_arrival_distribution: false
+  # When fitting a probabilistic distribution, threshold used to filter out outliers in the sample of inter-arrival
+  # times observed in the training event log (fixed or range between two floats). Increasing the outlier threshold
+  # increases the "range" of accepted values, thus, potentially decreasing the number of observations considered
+  # an outlier.
+  outlier_threshold:
+    - 5.0
+    - 50.0
+#################
+# Preprocessing #
+#################
+preprocessing:
+  multitasking: false
+  enable_time_concurrency_threshold: 0.5
+################
+# Control-flow #
+################
+control_flow:
+  # Metric to guide the optimization process (loss function to minimize)
+  optimization_metric: two_gram_distance
+  # Number of optimization iterations over the search space
+  num_iterations: 1
+  # Number of times to evaluate each iteration (using the mean of all of them)
+  num_evaluations_per_iteration: 1
+  # Methods for discovering gateway probabilities
+  gateway_probabilities: discovery
+##################
+# Resource model #
+##################
+resource_model:
+  # Metric to guide the optimization process (loss function to minimize)
+  optimization_metric: circadian_emd
+  # Number of optimization iterations over the search space
+  num_iterations: 40
+  # Number of times to evaluate each iteration (using the mean of all of them)
+  num_evaluations_per_iteration: 5
+  # Whether to discover prioritization or batching behavior
+  discover_prioritization_rules: false
+  discover_batching_rules: false
+  # Resource profiles configuration
+  resource_profiles:
+    # Resource profile discovery type
+    discovery_type: differentiated_fuzzy
+    # Time granularity (in minutes) for the resource calendar (the higher the density of events in the log, the smaller the granularity can be)
+    granularity: 60
+    fuzzy_angle:
+      - 0.1
+      - 0.9