Moved n_components from cluster estimation into config.yml

config.yaml

@@ -38,6 +38,7 @@ geolocation:
 cluster_estimation:
     min_activation_threshold: 25
     min_new_points_to_run: 5
+    max_num_components: 10
     random_state: 0
 
 communications:

main_2024.py

@@ -116,6 +116,7 @@ def main() -> int:
 
         MIN_ACTIVATION_THRESHOLD = config["cluster_estimation"]["min_activation_threshold"]
         MIN_NEW_POINTS_TO_RUN = config["cluster_estimation"]["min_new_points_to_run"]
+        MAX_NUM_COMPONENTS = config["cluster_estimation"]["max_num_components"]
         RANDOM_STATE = config["cluster_estimation"]["random_state"]
 
         COMMUNICATIONS_TIMEOUT = config["communications"]["timeout"]
@@ -303,7 +304,7 @@ def main() -> int:
     result, cluster_estimation_worker_properties = worker_manager.WorkerProperties.create(
         count=1,
         target=cluster_estimation_worker.cluster_estimation_worker,
-        work_arguments=(MIN_ACTIVATION_THRESHOLD, MIN_NEW_POINTS_TO_RUN, RANDOM_STATE),
+        work_arguments=(MIN_ACTIVATION_THRESHOLD, MIN_NEW_POINTS_TO_RUN, MAX_NUM_COMPONENTS, RANDOM_STATE),
         input_queues=[geolocation_to_cluster_estimation_queue],
         output_queues=[cluster_estimation_to_communications_queue],
         controller=controller,

modules/cluster_estimation/cluster_estimation.py

@@ -28,6 +28,9 @@ class ClusterEstimation:
     min_new_points_to_run: int
         Minimum number of new data points that must be collected before running model.
 
+    max_num_components: int
+        Max number of real landing pads.
+
     random_state: int
         Seed for randomizer, to get consistent results.
 
@@ -62,8 +65,8 @@ class ClusterEstimation:
     __MEAN_PRECISION_PRIOR = 1e-6
     __MAX_MODEL_ITERATIONS = 1000
 
-    # Real-world scenario Hyperparameters
-    __MAX_NUM_COMPONENTS = 10  # assumed maximum number of real landing pads
+    # # Real-world scenario Hyperparameters
+    # __MAX_NUM_COMPONENTS = 10  # assumed maximum number of real landing pads
 
     # Hyperparameters to clean up model outputs
     __WEIGHT_DROP_THRESHOLD = 0.1
@@ -74,6 +77,7 @@ def create(
         cls,
         min_activation_threshold: int,
         min_new_points_to_run: int,
+        max_num_components: int,
         random_state: int,
         local_logger: logger.Logger,
     ) -> "tuple[bool, ClusterEstimation | None]":
@@ -92,6 +96,7 @@ def create(
             cls.__create_key,
             min_activation_threshold,
             min_new_points_to_run,
+            max_num_components,
             random_state,
             local_logger,
         )
@@ -101,6 +106,7 @@ def __init__(
         class_private_create_key: object,
         min_activation_threshold: int,
         min_new_points_to_run: int,
+        max_num_components: int, 
         random_state: int,
         local_logger: logger.Logger,
     ) -> None:
@@ -112,7 +118,7 @@ def __init__(
         # Initializes VGMM
         self.__vgmm = sklearn.mixture.BayesianGaussianMixture(
             covariance_type=self.__COVAR_TYPE,
-            n_components=self.__MAX_NUM_COMPONENTS,
+            n_components = max_num_components,
             init_params=self.__MODEL_INIT_PARAM,
             weight_concentration_prior=self.__WEIGHT_CONCENTRATION_PRIOR,
             mean_precision_prior=self.__MEAN_PRECISION_PRIOR,

modules/cluster_estimation/cluster_estimation_worker.py

@@ -14,6 +14,7 @@
 def cluster_estimation_worker(
     min_activation_threshold: int,
     min_new_points_to_run: int,
+    max_num_components: int,
     random_state: int,
     input_queue: queue_proxy_wrapper.QueueProxyWrapper,
     output_queue: queue_proxy_wrapper.QueueProxyWrapper,
@@ -30,6 +31,9 @@ def cluster_estimation_worker(
     min_new_points_to_run: int
         Minimum number of new data points that must be collected before running model.
 
+    max_num_components: int
+        Max number of real landing pads.
+
     random_state: int
         Seed for randomizer, to get consistent results.
 
@@ -56,6 +60,7 @@ def cluster_estimation_worker(
     result, estimator = cluster_estimation.ClusterEstimation.create(
         min_activation_threshold,
         min_new_points_to_run,
+        max_num_components,
         random_state,
         local_logger,
     )