Similarity calculation per use case layers

src/data-hub/role-stage-discovery-microservice/app/configs/swagger.yml

@@ -48,7 +48,7 @@ paths:
             description: "The layer data to be added"
             required: true
             schema:
-                $ref: "#/definitions/Layer-UpperCase"
+                $ref: "#/definitions/Layer"
         responses:
             '201':
                 description: "Successful operation"
@@ -274,16 +274,6 @@ definitions:
     type: array
     items:
         $ref: "#/definitions/Cluster"
-
-  Layer-UpperCase:
-    type: object
-    properties:
-        LayerName:
-            type: string
-        Properties:
-            type: array
-            items: 
-                type: string
     
   Layer:
     type: object

src/data-hub/role-stage-discovery-microservice/app/configs/swagger_local.yml

@@ -45,7 +45,7 @@ paths:
             description: "The layer data to be added"
             required: true
             schema:
-                $ref: "#/definitions/Layer-UpperCase"
+                $ref: "#/definitions/Layer"
         responses:
             '201':
                 description: "Successful operation"
@@ -251,16 +251,6 @@ definitions:
     type: array
     items:
         $ref: "#/definitions/Cluster"
-
-  Layer-UpperCase:
-    type: object
-    properties:
-        LayerName:
-            type: string
-        Properties:
-            type: array
-            items: 
-                type: string
     
   Layer:
     type: object

src/data-hub/role-stage-discovery-microservice/app/db/entities/layer.py

@@ -17,12 +17,14 @@ class Layer:
     def to_serializable_dict(self, for_db=False) -> Dict:
         return {
             "layer_name": self.layer_name,
-            "properties": self.properties
+            "properties": self.properties,
+            "use_case": self.use_case
         }
 
     def from_serializable_dict(self, layer_info: Dict, from_db=False):
         self.layer_name = layer_info['layer_name']
         self.properties = layer_info['properties']
+        self.use_case = layer_info['use_case']
 
     def __repr__(self):
         return json.dumps(self.to_serializable_dict())

src/data-hub/role-stage-discovery-microservice/app/similarityMain.py → src/data-hub/role-stage-discovery-microservice/app/processing/similarityFiles/similarityMain.py

@@ -12,7 +12,7 @@ import os
 import sys
 import math
 import datetime
-from typing import Dict
+from typing import Dict, List
 
 ### init logging ###
 import logging
@@ -22,9 +22,9 @@ LOGGER = logging.getLogger(__name__)
 
 ##################AUX
 
-modules_path = '../../../modules/'
-if os.path.exists(modules_path):
-    sys.path.insert(1, modules_path)
+for modules_path in ['../../../modules/', './']:
+    if os.path.exists(modules_path):
+        sys.path.insert(1, modules_path)
 
 #### TO BE DELETED #### ^
 
@@ -38,8 +38,15 @@ from processing.similarityFiles.miscFunctions import *
 from processing.similarityFiles.dataOutput import *
 
 
-def main():   
-    print("\nEntered Main")
+def main(layerNameList:List[str] = ["Price_Layer","FinishedTime_Layer","Destination_Layer"]):   
+    '''
+    Executes the similarity calculation by calculating weights between clusters in different layers.
+    Then calculating the Euclidean distance between nodes in the same layer based on one other layer each.
+    Everything is loaded from and stored to the database.
+    
+    :param layerNameList: The list of layer names as strings
+    '''
+    print("Entered Similarity Main")
 
     outputToFileFLAG = False
 
@@ -56,14 +63,14 @@ def main():
         StartingTime_Layer
         User_Layer
     """
-    layerNameList = ["Price_Layer","FinishedTime_Layer","Destination_Layer"] #Get it from somewhere else?
+    
     limitNrCluster = -1 #per Layer # 0< equals noLimit
     limitNrNodes = -1 #per Layer
 
 
     layerDict = getClusterDataFromMongo(layerNameList,limitNrCluster,limitNrNodes)
     if layerDict is None or len(layerDict) == 0:
-        LOGGER.error(f"None of the following layers existed: {str(layerNameList)}. Similarity calculation was not performed.")
+        LOGGER.error(f"No data for any of the following layers existed: {str(layerNameList)}. Similarity calculation was not performed.")
         return
 
     #URLlist = None
@@ -116,5 +123,6 @@ def main():
     return
 
 ##########START##########
-main()
+if __name__ is '__main__':
+    main()
 #########FINISH##########

src/data-hub/role-stage-discovery-microservice/app/routes/layers.py

@@ -14,8 +14,8 @@ def post():
 
 def _insert_layer(layer_data: dict):
     '''Converts object keys from external source and inserts into database.'''
-    layer_data['layer_name'] = layer_data.pop('LayerName')
-    layer_data['properties'] = layer_data.pop('Properties')
+    # layer_data['layer_name'] = layer_data.pop('LayerName')
+    # layer_data['properties'] = layer_data.pop('Properties')
 
     repo.add_layer(Layer(layer_data))
 

src/data-hub/role-stage-discovery-microservice/app/run_similarity_calc.py

+import processing.similarityFiles.similarityMain as SimilarityCalc
+from db.repository import Repository
+
+repo = Repository()
+
+
+def run_similarity_calc_per_use_case():
+    layers = repo.get_layers()
+
+    uc_layers = {}
+    for layer in layers:
+        uc = layer.use_case
+        if uc not in uc_layers:
+            uc_layers[uc] = []
+        uc_layers[uc].append(layer.layer_name)
+
+    for key in uc_layers:
+        layers = uc_layers[key]
+        print(f"Running for use case {key} with layers {str(layers)}.")
+        SimilarityCalc.main(layerNameList=layers)
+    
+
+if __name__ == '__main__':
+    run_similarity_calc_per_use_case()
\ No newline at end of file