add pca

src/main.py

@@ -16,6 +16,10 @@ def main():
             "src/rtu/models/kmeans_rtu_1.pkl",
             "src/rtu/models/kmeans_rtu_2.pkl",
         ],
+        pca_model_paths=[
+            "src/rtu/models/pca_rtu_1.pkl",
+            "src/rtu/models/pca_rtu_2.pkl",
+        ],
         num_inputs=rtu_data_pipeline.num_inputs,
         num_outputs=rtu_data_pipeline.num_outputs,
     )
@@ -26,6 +30,10 @@ def main():
             "src/rtu/models/kmeans_rtu_3.pkl",
             "src/rtu/models/kmeans_rtu_4.pkl",
         ],
+        pca_model_paths=[
+            "src/rtu/models/pca_rtu_3.pkl",
+            "src/rtu/models/pca_rtu_4.pkl",
+        ],
         num_inputs=rtu_data_pipeline.num_inputs,
         num_outputs=rtu_data_pipeline.num_outputs,
     )

src/rtu/RTUAnomalizer1.py

@@ -10,11 +10,13 @@ class RTUAnomalizer1:
 
     model = None
     kmeans_models = []
+    pca_models = []
 
     def __init__(
         self,
         prediction_model_path=None,
         clustering_model_paths=None,
+        pca_model_paths=None,
         num_inputs=None,
         num_outputs=None,
     ):
@@ -29,8 +31,9 @@ class RTUAnomalizer1:
         """
         self.num_inputs = num_inputs
         self.num_outputs = num_outputs
-        if prediction_model_path is not None and clustering_model_paths is not None:
-            self.load_models(prediction_model_path, clustering_model_paths)
+        if prediction_model_path is not None and clustering_model_paths is not None and pca_model_paths is not None:
+            self.load_models(prediction_model_path, clustering_model_paths, pca_model_paths)
+            
         self.actual_list, self.pred_list, self.resid_list = self.initialize_lists()
 
     def initialize_lists(self, size=30):
@@ -46,7 +49,7 @@ class RTUAnomalizer1:
         initial_values = [[0]*self.num_outputs] * size
         return initial_values.copy(), initial_values.copy(), initial_values.copy()
 
-    def load_models(self, prediction_model_path, clustering_model_paths):
+    def load_models(self, prediction_model_path, clustering_model_paths, pca_model_paths):
         """
         Load the prediction and clustering models.
 
@@ -58,6 +61,9 @@ class RTUAnomalizer1:
 
         for path in clustering_model_paths:
             self.kmeans_models.append(joblib.load(path))
+            
+        for path in pca_model_paths:
+            self.pca_models.append(joblib.load(path))
 
     def predict(self, df_new):
         """
@@ -158,7 +164,7 @@ class RTUAnomalizer1:
         for i, model in enumerate(self.kmeans_models):
             dist.append(
                 np.linalg.norm(
-                    resid[:, (i * 7) + 1 : (i * 7) + 8] - model.cluster_centers_[0],
+                    self.pca_models[i].transform(resid[:, (i * 7) + 1 : (i * 7) + 8]) - model.cluster_centers_[0],
                     ord=2,
                     axis=1,
                 )

src/rtu/RTUAnomalizer2.py

@@ -10,11 +10,13 @@ class RTUAnomalizer2:
 
     model = None
     kmeans_models = []
+    pca_models = []
 
     def __init__(
         self,
         prediction_model_path=None,
         clustering_model_paths=None,
+        pca_model_paths=None,
         num_inputs=None,
         num_outputs=None,
     ):
@@ -29,8 +31,9 @@ class RTUAnomalizer2:
         """
         self.num_inputs = num_inputs
         self.num_outputs = num_outputs
-        if prediction_model_path is not None and clustering_model_paths is not None:
-            self.load_models(prediction_model_path, clustering_model_paths)
+        if prediction_model_path is not None and clustering_model_paths is not None and pca_model_paths is not None:
+            self.load_models(prediction_model_path, clustering_model_paths, pca_model_paths)
+            
         self.actual_list, self.pred_list, self.resid_list = self.initialize_lists()
 
     def initialize_lists(self, size=30):
@@ -46,7 +49,7 @@ class RTUAnomalizer2:
         initial_values = [[0]*self.num_outputs] * size
         return initial_values.copy(), initial_values.copy(), initial_values.copy()
 
-    def load_models(self, prediction_model_path, clustering_model_paths):
+    def load_models(self, prediction_model_path, clustering_model_paths, pca_model_paths):
         """
         Load the prediction and clustering models.
 
@@ -58,6 +61,9 @@ class RTUAnomalizer2:
 
         for path in clustering_model_paths:
             self.kmeans_models.append(joblib.load(path))
+            
+        for path in pca_model_paths:
+            self.pca_models.append(joblib.load(path))
 
     def predict(self, df_new):
         """
@@ -158,7 +164,7 @@ class RTUAnomalizer2:
         for i, model in enumerate(self.kmeans_models):
             dist.append(
                 np.linalg.norm(
-                    resid[:, (i * 7) + 1 : (i * 7) + 8] - model.cluster_centers_[0],
+                    self.pca_models[i].transform(resid[:, (i * 7) + 1 : (i * 7) + 8]) - model.cluster_centers_[0],
                     ord=2,
                     axis=1,
                 )

src/rtu/models/kmeans_rtu_1.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42621b20e5f4048526e82615e92de0031ba42c540fbaba637efe0b4506f13ff4
-size 2065925
+oid sha256:eb67ee66d9eff490b1ab8668a29c2ac428f1f2ac0e4adab479a50dfb4109d914
+size 2065909

src/rtu/models/kmeans_rtu_2.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1c07513633ff899c5b1fa46bdf750420ee95593282f79bc4564db06c2dfb601
-size 2065925
+oid sha256:5ff364f579e10cc8ec951cfae8ef4f0c658e5e5a39a94ffdaf0984aad526726b
+size 2065909

src/rtu/models/kmeans_rtu_3.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31d6d81362dde61976f0617e51239a67c6962c1ea84f6c301970bafdb8406146
-size 2065881
+oid sha256:985814b63e8649991cbf7c68f659ea3d34ba1d452e8f8b53ab04e2257547d83f
+size 2065865

src/rtu/models/kmeans_rtu_4.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a5a1799b4546825815d9833598bcce7fb3241f9c15a3c03c3d0c28e5010b33
-size 2065881
+oid sha256:5390875e07cc929502f0eec1fe7e1751479ecfa928a8196176996141dbf86dc5
+size 2065865

src/rtu/models/pca_rtu_1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec1b50bc380f48a59de90ae3a8a45923816e24848dceeb353299c0407e2e34c
+size 1083

src/rtu/models/pca_rtu_2.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0e68e14251682befa07845b614e545a97074ac5390b8bc6cfa85540211175e
+size 1083

src/rtu/models/pca_rtu_3.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4599b4e582432c9de20e501d5d28c582d9df8dd71a3006f975469fb819e9a0e
+size 1083

src/rtu/models/pca_rtu_4.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efeca9febf06e512ab41e93ded97b978569cf5f531094cd777e82289ecf9856f
+size 1083