Merge branch 'feature/community-prediction' into 'develop'

CA-CEP

See merge request !44

src/data-hub/proactive-community-detection-microservice/Dockerfile

@@ -2,13 +2,15 @@ FROM python:3
 LABEL maintainer="Alexander Lercher"
 
 RUN apt-get update
-RUN pip install flask
-RUN pip install connexion[swagger-ui]
 
 EXPOSE 5000
 
 WORKDIR /app
 
+COPY src/data-hub/role-stage-discovery-microservice/app/requirements.txt /app/
+RUN pip install -r requirements.txt
+
+COPY src/modules/ /app/
 COPY src/data-hub/proactive-community-detection-microservice/app/ /app/
 RUN chmod a+x main.py
 

src/data-hub/proactive-community-detection-microservice/app/.gitignore

+# contains raw data for machine learning
+data/

src/data-hub/proactive-community-detection-microservice/app/configs/routes.yml

+paths:
+  /debug:
+    post:
+      operationId: "debug.echo"
+      tags:
+        - "Echo"
+      summary: "Echo function for debugging purposes"
+      description: "Echoes the input back to the caller."
+      parameters:
+        - in: body
+          name: "Object"
+          required: true
+          schema:
+            type: object
+      responses:
+        '200':
+          description: "Successful echo of request data"
+          
+  /use-cases/{use_case}/tables/{table}/layers/{layer_name}/predictions:
+    get:
+      operationId: "routes.predictions.get"
+      security:
+        - JwtRegular: []
+      tags:
+          - "Predictions"
+      summary: "Get predictions"
+      parameters: 
+        - name: "use_case"
+          in: "path"
+          description: "Name of the use-case"
+          required: true
+          type: "string"
+        - name: "table"
+          in: "path"
+          description: "Name of the table"
+          required: true
+          type: "string"
+        - name: "layer_name"
+          in: "path"
+          description: "Name of the layer"
+          required: true
+          type: "string"
+      responses:
+        '200':
+            description: "Successful operation"
+            schema: 
+                $ref: "#/definitions/Prediction"
+        '404':
+            description: "Predictions not found"
+
+
+definitions:
+  Prediction:
+    type: object
+    properties:
+        use_case:
+            type: string
+        table:
+            type: string
+        method:
+            type: string
+        layer:
+            type: string
+        reference_layer:
+            type: string
+        cluster_label:
+            type: string
+        time_window:
+            type: string
+        prediction:
+            type: integer

src/data-hub/proactive-community-detection-microservice/app/configs/swagger.yml

@@ -11,20 +11,9 @@ produces:
 
 basePath: "/api"
 
+# Import security definitions from global security definition
+securityDefinitions:
+  $ref: '../security/security.yml#securityDefinitions'
+
 paths:
-  /debug:
-    post:
-      operationId: "debug.echo"
-      tags:
-        - "Echo"
-      summary: "Echo function for debugging purposes"
-      description: "Echoes the input back to the caller."
-      parameters:
-        - in: body
-          name: "Object"
-          required: true
-          schema:
-            type: object
-      responses:
-        200:
-          description: "Successful echo of request data"
+  $ref: 'routes.yml#paths'

src/data-hub/proactive-community-detection-microservice/app/configs/swagger_local.yml

+swagger: "2.0"
+info:
+  title: Proactive Community Detection microservice
+  description: This is the documentation for the proactive community detection microservice.
+  version: "1.0.0"
+
+consumes:
+  - "application/json"
+produces:
+  - "application/json"
+
+basePath: "/api"
+
+# Import security definitions from global security definition
+securityDefinitions:
+  $ref: '../../../../modules/security/security_local.yml#securityDefinitions'
+
+paths:
+  $ref: 'routes.yml#paths'
+
+

src/data-hub/proactive-community-detection-microservice/app/db/dao/__init__.py

+from db.dao.cluster import Cluster as ClusterDao
+from db.dao.layer import Layer as LayerDao
+from db.dao.timeslice import TimeSlice as TimeSliceDao
+from db.dao.layer_pair import LayerPair as LayerPairDao
+from db.dao.prediction_result import PredictionResult

src/data-hub/proactive-community-detection-microservice/app/db/dao/cluster.py

+import json
+from typing import List, Dict
+from datetime import date, datetime
+
+
+class Cluster:
+    '''
+    A cluster for an arbitrary layer containing some nodes.
+
+    :param use_case: The use-case of the layer
+    :param use_case_table: The use-case table of the layer
+    :param layer_name: The name of the layer in which the cluster is located
+    :param cluster_label: The label of the cluster unique for the layer
+    :param nodes: The individual nodes of the cluster
+    :param label: A human readable label
+    '''
+
+    def __init__(self, use_case: str = None, use_case_table: str = None, layer_name: str = None, 
+                 cluster_label: int = None, nodes: List[Dict] = None, label: str = None,
+                 cluster_dict: Dict = None, from_db=False):
+        self.use_case = use_case
+        self.use_case_table = use_case_table
+        self.layer_name = layer_name
+        self.cluster_label = cluster_label
+        self.nodes = nodes
+        self.label = label
+
+        if cluster_dict is not None:
+            self.from_serializable_dict(cluster_dict, from_db)
+
+    def to_serializable_dict(self, for_db=False) -> Dict:
+        return {
+            "use_case": self.use_case,
+            "use_case_table": self.use_case_table,
+            "layer_name": self.layer_name,
+            "cluster_label": self.cluster_label,
+            "nodes": json.dumps(self.nodes) if for_db else self.nodes,
+            "label": self.label,
+        }
+
+    def from_serializable_dict(self, cluster_dict: Dict, from_db=False):
+        self.use_case = cluster_dict["use_case"]
+        self.use_case_table = cluster_dict["use_case_table"]
+        self.layer_name = cluster_dict["layer_name"]
+        self.cluster_label = cluster_dict["cluster_label"]
+        self.nodes = json.loads(cluster_dict["nodes"]) \
+            if from_db else cluster_dict["nodes"]
+        self.label = cluster_dict["label"]
+
+    def __repr__(self):
+        return json.dumps(self.to_serializable_dict())
+
+    def __str__(self):
+        return f"Cluster({self.__repr__()})"

src/data-hub/proactive-community-detection-microservice/app/db/dao/layer.py

+import json
+from datetime import datetime
+from typing import Dict
+
+class Layer:
+    '''
+    This class represents a single layer of the Multilayer Graph.
+
+    :param layer_info: Information as dictionary to restore the layer object.
+    '''
+
+    def __init__(self, layer_info: Dict = None, from_db=False):
+        if layer_info is not None:
+            self.from_serializable_dict(layer_info, from_db)
+
+    def to_serializable_dict(self, for_db=False) -> Dict:
+        return {
+            "layer_name": self.layer_name,
+            "properties": self.properties,
+            "use_case": self.use_case,
+            "use_case_table": self.use_case_table,
+            "total_properties": self.total_properties,
+        }
+
+    @staticmethod
+    def from_business_logic_dict(layer_info: Dict):
+        layer = Layer()
+        layer.layer_name = layer_info["name"]
+        layer.properties = layer_info["cluster_properties"]
+        layer.total_properties = layer_info["properties"]
+        layer.use_case = layer_info["use_case"]
+        layer.use_case_table = layer_info["table"]
+        return layer
+
+    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"]
+        self.use_case_table = layer_info["use_case_table"]
+        self.total_properties = layer_info["total_properties"] if "total_properties"in layer_info.keys() else None 
+
+    def __repr__(self):
+        return json.dumps(self.to_serializable_dict())
+
+    def __str__(self):
+        return f"Layer({self.__repr__()})"

src/data-hub/proactive-community-detection-microservice/app/db/dao/layer_pair.py

+from typing import List, Dict
+
+class LayerPair:
+    def __init__(self, use_case: str, table: str, layer: str, reference_layer: str):
+        self.use_case = use_case
+        self.table = table
+        self.layer = layer
+        self.reference_layer = reference_layer
+    
+    @staticmethod
+    def create_from_dict(dict_) -> 'LayerPair':
+        lp = LayerPair(None, None, None, None)
+        lp.__dict__.update(dict_)
+        return lp

src/data-hub/proactive-community-detection-microservice/app/db/dao/prediction_result.py

+from typing import List, Dict
+
+class PredictionResult:
+    def __init__(self, use_case: str, table: str, method: str, 
+                 layer: str, reference_layer: str, cluster_id: str, 
+                 time_window: str, prediction: int):
+        self.use_case = use_case
+        self.table = table
+        self.method = method
+        self.layer = layer
+        self.reference_layer = reference_layer
+
+        self.cluster_id = cluster_id
+        self.time_window = time_window
+        self.prediction = prediction
+        
+    
+    @staticmethod
+    def create_from_dict(dict_) -> 'PredictionResult':
+        obj = PredictionResult(None, None, None, None, None, None, None, None)
+        obj.__dict__.update(dict_)
+        return obj

src/data-hub/proactive-community-detection-microservice/app/db/dao/timeslice.py

+import json
+from typing import List, Dict, NewType, Any
+from datetime import date, datetime
+
+Node = NewType('Node', dict)
+
+class TimeSlice:
+    '''
+    A time slice for a single layer containing all nodes for that time.
+
+    :param time: The tag indicating the time
+    :param layer_name: The name of the layer the nodes belong to
+    '''
+
+    def __init__(self, time: Any = None, use_case: str = None, use_case_table: str = None, layer_name: str = None,
+                 time_slice_dict: Dict = None, from_db = False):
+        self.time = str(time)
+        self.use_case = use_case
+        self.use_case_table = use_case_table
+        self.layer_name = layer_name
+        self.clusters: Dict[str, List[Node]] = {}
+
+        if time_slice_dict is not None:
+            self.from_serializable_dict(time_slice_dict, from_db)
+
+    def init_all_clusters(self, cluster_labels: List[str]):
+        '''Initializes internal clusters for all labels with an empty list.'''
+        for cluster_label in cluster_labels:
+            # only string keys can be stored in json
+            cluster_label = str(cluster_label)
+            self.clusters[cluster_label] = []
+
+    def add_node_to_cluster(self, cluster_label: str, node):
+        # only string keys can be stored in json
+        cluster_label = str(cluster_label)
+
+        if cluster_label not in self.clusters:
+            # self.clusters[cluster_label] = []
+            raise KeyError(f"self::init_all_clusters must be used to add all global cluster labels beforehand (got {cluster_label})")
+
+        # node = self._get_unique_id(node)
+        self.clusters[cluster_label].append(node)
+
+    def get_nodes_for_cluster(self, cluster_label: str):
+        if cluster_label in self.clusters:
+            return self.clusters[cluster_label]
+        else:
+            return []
+        
+    def _get_unique_id(self, node : Dict) -> Dict:
+        '''Returns a new dict with the unique id only.'''
+        uid_key = 'UniqueID'
+        if uid_key in node:
+            return {uid_key: node[uid_key]}
+
+
+    def to_serializable_dict(self, for_db=False) -> Dict:
+        return {
+            "time": self.time,
+            "use_case": self.use_case,
+            "use_case_table": self.use_case_table,
+            'layer_name': self.layer_name,
+            "clusters": json.dumps(self.clusters) if for_db else self.clusters
+        }
+
+    def from_serializable_dict(self, dict: Dict, from_db=False):
+        self.time = dict["time"]
+        self.use_case = dict["use_case"]
+        self.use_case_table = dict["use_case_table"]
+        self.layer_name = dict['layer_name']
+        self.clusters = json.loads(dict['clusters']) if from_db else dict['clusters']
+
+    def __repr__(self):
+        return json.dumps(self.to_serializable_dict())
+
+    def __str__(self):
+        return f"TimeSlice({self.__repr__()})"

src/data-hub/proactive-community-detection-microservice/app/db/repository.py

+import pymongo
+import network_constants as netconst
+from database.MongoRepositoryBase import MongoRepositoryBase
+import json
+
+from db.dao import *
+from typing import List
+
+import logging
+LOGGER = logging.getLogger(__name__)
+
+
+class Repository(MongoRepositoryBase):
+    '''This is a repository for MongoDb.'''
+
+    def __init__(self):
+        super().__init__(netconst.PROACTIVE_COMMUNITY_DETECTION_DB_HOSTNAME,
+                         netconst.PROACTIVE_COMMUNITY_DETECTION_DB_PORT,
+                         'proactiveCommunityDb')
+
+        self._use_case_collection = 'use_cases'
+        self._layer_collection = 'layers'
+        self._layer_pair_collection = 'layer_pairs'
+        self._clusters_collection = 'clusters'
+        self._time_slice_collection = 'time_slices'
+        self._prediction_result_collection = 'prediction_results'
+       
+
+    def DROP(self, confirm:bool=False):
+        assert confirm, 'WONT DELETE WHOLE DB WITHOUT CONFIRMATION'
+
+        for collection_ in [self._use_case_collection, self._layer_collection, self._layer_pair_collection, 
+                            self._clusters_collection, self._time_slice_collection]:
+            super().drop_collection(collection_)
+    
+
+#region LayerPair
+    def add_use_case(self, use_case: str):
+        super().insert_entry(self._use_case_collection, {'name':use_case})
+
+    def get_use_cases(self) -> List[str]:
+        entries = super().get_entries(self._use_case_collection)
+        return [e['name'] for e in entries]
+
+#endregion 
+
+#region Layers
+    def add_layer(self, layer: LayerDao):
+        super().insert_entry(self._layer_collection, layer.to_serializable_dict())
+
+    def get_layers(self) -> List[LayerDao]:
+        '''Retrieves all layers from the db, independent of use-case.'''
+        entries = super().get_entries(self._layer_collection, projection={'_id': 0})
+        return [LayerDao(e) for e in entries]
+
+    def get_layers_for_use_case(self, use_case: str) -> LayerDao:
+        entries = super().get_entries(self._layer_collection, selection={'use_case': use_case})
+        return [LayerDao(e) for e in entries]
+
+    def get_layers_for_table(self, use_case: str, use_case_table: str) -> LayerDao:
+        entries = super().get_entries(self._layer_collection, selection={'use_case': use_case, 'use_case_table': use_case_table})
+        return [LayerDao(e) for e in entries]
+
+    def get_layer_by_name(self, use_case:str, use_case_table:str, layer_name:str) -> LayerDao:
+        '''Returns a singe layer for use-case and layer-name.'''
+        entries = super().get_entries(self._layer_collection, selection={'use_case': use_case, 'use_case_table': use_case_table, 'layer_name': layer_name})
+        entries = [LayerDao(e) for e in entries]
+
+        if entries is not None and len(entries) > 0:
+            if len(entries) > 1:
+                LOGGER.error(f"Layer Key {use_case}, {layer_name} is not unique.")
+            return entries[0]
+        else:
+            return None
+    
+    def delete_all_layers(self):
+        super().drop_collection(self._layer_collection)
+#endregion Layers
+
+
+#region Clusters
+    def add_cluster(self, cluster: ClusterDao):
+        super().insert_entry(self._clusters_collection, cluster.to_serializable_dict(for_db=True))
+        
+    def add_clusters(self, clusters: List[ClusterDao]):
+        cluster_dicts = [c.to_serializable_dict(for_db=True) for c in clusters]
+        super().insert_many(self._clusters_collection, cluster_dicts)
+        
+    def get_clusters_for_layer(self, use_case: str, use_case_table: str, layer_name: str) -> List[ClusterDao]:
+        entries = super().get_entries(self._clusters_collection, selection={'use_case': use_case, 'use_case_table': use_case_table, 'layer_name': layer_name}, projection={'_id': 0})
+        return [ClusterDao(cluster_dict=e, from_db=True) for e in entries]
+    
+    def delete_all_clusters(self):
+        super().drop_collection(self._clusters_collection)
+#endregion
+
+
+#region TimeSlice
+    def add_time_slice(self, timeslice: TimeSliceDao):
+        super().insert_entry(self._time_slice_collection, timeslice.to_serializable_dict(for_db=True))
+
+    def get_time_slices(self) -> List[TimeSliceDao]:
+        '''Returns all time slices.'''
+        entries = super().get_entries(self._time_slice_collection)
+        return [TimeSliceDao(None, None, time_slice_dict=e, from_db=True) for e in entries]
+
+    def get_time_slices_for_layer(self, use_case: str, use_case_table: str, layer_name: str) -> List[TimeSliceDao]:
+        '''Returns all time slices with the given layer_name.'''
+        entries = super().get_entries(self._time_slice_collection, selection={'use_case': use_case, 'use_case_table': use_case_table, 'layer_name': layer_name})
+        return [TimeSliceDao(time_slice_dict=e, from_db=True) for e in entries]
+
+    def remove_all_time_slices(self):
+        super().drop_collection(self._time_slice_collection)
+#endregion
+
+
+#region LayerPair
+    def add_layer_pair(self, layer_pair: LayerPairDao):
+        super().insert_entry(self._layer_pair_collection, layer_pair.__dict__)
+
+    def get_layer_pairs(self, use_case: str) -> List[LayerPairDao]:
+        entries = super().get_entries(self._layer_pair_collection, selection={'use_case': use_case})
+        return [LayerPairDao.create_from_dict(e) for e in entries]
+#endregion
+
+
+#region PredictionResult
+    def add_prediction_result(self, prediction_result: PredictionResult):
+        super().insert_entry(self._prediction_result_collection, prediction_result.__dict__)
+
+    def get_prediction_results(self, use_case: str) -> List[PredictionResult]:
+        entries = super().get_entries(self._prediction_result_collection, selection={'use_case': use_case}, projection={'_id': 0})
+        return [PredictionResult.create_from_dict(e) for e in entries]
+
+    def delete_all_prediction_results(self):
+        super().drop_collection(self._prediction_result_collection)
+#endregion

src/data-hub/proactive-community-detection-microservice/app/debug.py

 from flask import request
 
 def echo():
+    import processing.fetching.fetching as f
+    
+    # print(f._fetch_use_cases())
+    print(f._fetch_use_cases())
+
     return request.json
 
 
+ 
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/entities/__init__.py

+from entities.timewindow import TimeWindow
+from entities.cluster import Cluster
+from entities.layer import Layer
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/entities/cluster.py

+# from __future__ import annotations
+from typing import Dict, List, Iterable, Any, Tuple
+from entities.timewindow import TimeWindow
+import numpy as np
+import scipy
+from processing import ClusterMetricsCalculatorFactory
+
+
+class Cluster:
+    '''A cluster from one time window containing all metrics used for machine learning.'''
+
+    def __init__(self, time_window_id: Any, cluster_id: Any, cluster_nodes: List[dict], cluster_feature_names: List[str], nr_layer_nodes: int, layer_diversity: int, 
+        global_cluster_center, global_center_distance=None):
+        self.time_window_id = time_window_id
+        self.cluster_id = cluster_id
+
+        metrics_calculator = ClusterMetricsCalculatorFactory.create_metrics_calculator(cluster_nodes, cluster_feature_names, nr_layer_nodes, layer_diversity)
+
+        self.size = metrics_calculator.get_size()
+        self.std_dev = metrics_calculator.get_standard_deviation()
+        self.scarcity = metrics_calculator.get_scarcity()
+        
+        self.importance1 = metrics_calculator.get_importance1()
+        self.importance2 = metrics_calculator.get_importance2()
+        
+        self.range_ = metrics_calculator.get_range()
+        self.center = metrics_calculator.get_center()
+
+        self.global_center_distance = \
+            scipy.spatial.distance.euclidean(self.center, global_cluster_center) \
+            if self.size > 0 \
+            else  0
+
+    def get_time_info(self) -> int:
+        '''Returns the week of the time tuple str, eg. 25 for "(2014, 25)".'''
+        return eval(self.time_window_id)[1]
+
+    def __repr__(self):
+        return str(self.__dict__)
+
+    def __str__(self):
+        return f"Cluster({self.time_window_id}, {self.cluster_id}, " \
+        f"{self.size}, {self.std_dev}, {self.scarcity}, " \
+        f"{self.importance1}, {self.importance2}, " \
+        f"{self.range_}, {self.center})"
+
+    @staticmethod
+    def create_multiple_from_time_window(time_window: TimeWindow, cluster_feature_names: List[str], global_cluster_centers: Dict[str, Tuple[float]]) -> Iterable['Cluster']:
+        total_layer_nodes = sum([len(nodes) for nodes in time_window.clusters.values()])
+        
+        layer_diversity = len([nodes for nodes in time_window.clusters.values() if len(nodes) > 0])
+
+        for cluster_nr, cluster_nodes in time_window.clusters.items():
+            yield Cluster(time_window.time, cluster_nr, cluster_nodes, cluster_feature_names, total_layer_nodes, layer_diversity, global_cluster_centers[cluster_nr])
+
+    @staticmethod
+    def create_from_dict(dict_) -> 'Cluster':
+        cl = Cluster(0, 0, [], 'None', 0, 0, None)
+        cl.__dict__.update(dict_)
+        return cl

src/data-hub/proactive-community-detection-microservice/app/entities/layer.py

+from typing import Dict, List, Tuple, Any
+import scipy.spatial
+from entities.timewindow import TimeWindow
+from processing import ClusterMetricsCalculatorFactory
+
+
+class InternalCluster:
+    def __init__(self, cluster_id, cluster_nodes: List[dict], feature_names:List[str], global_cluster_center: Tuple[float], n_layer_nodes: int):
+        self.cluster_id = cluster_id
+
+        metrics_calculator = ClusterMetricsCalculatorFactory.create_metrics_calculator(cluster_nodes, feature_names, n_layer_nodes, None)
+
+        self.size = metrics_calculator.get_size()
+        self.relative_size = metrics_calculator.get_importance1()
+        self.center = metrics_calculator.get_center()
+
+        if self.size > 0:
+            self.global_center_distance = scipy.spatial.distance.euclidean(self.center, global_cluster_center)
+        else:
+            self.global_center_distance = 0
+
+    @staticmethod
+    def create_many_from_cluster_nodes(clusters: Dict[str, List[dict]], feature_names: List[str], global_cluster_centers: Dict[str, Tuple[float]]) -> List['InternalCluster']:
+        res_clusters = []
+        total_layer_nodes = sum([len(nodes) for nodes in clusters.values()])
+
+        for key, value in clusters.items():
+
+            # ignore noise as it contains no meaningful cluster information
+            if key == '-1':
+                continue
+
+            res_clusters.append(InternalCluster(key, value, feature_names, global_cluster_centers[key], total_layer_nodes))
+        return res_clusters
+
+
+class Layer:
+    '''Represents metrics for one layer for a single time window.'''
+    def __init__(self, time_window_id: Any, clusters: List[InternalCluster]):
+        self.time_window_id = time_window_id
+
+        active_clusters = [c for c in clusters if c.size > 0]
+                
+        self.n_nodes = sum([c.size for c in clusters])
+        self.n_clusters = len(active_clusters)
+
+        self.relative_cluster_sizes = self.get_relative_cluster_sizes(active_clusters)
+        self.cluster_size_agg_metrics = self.get_size_min_max_avg_sum(active_clusters)
+        self.cluster_relative_size_agg_metrics = self.get_relative_size_min_max_avg_sum(active_clusters)
+        self.entropy = self.get_entropy(active_clusters)
+
+        self.centers = [c.center for c in active_clusters]
+        self.distances_from_global_centers = self.get_distances_from_global_center(active_clusters)
+        self.cluster_center_distance_agg_metrics = self.get_center_distance_min_max_avg_sum(active_clusters)
+
+    def get_time_info(self) -> int:
+        '''Returns the week of the time tuple str, eg. 25 for "(2014, 25)".'''
+        return eval(self.time_window_id)[1]
+        
+    def get_size_min_max_avg_sum(self, clusters: List[InternalCluster]) -> dict:
+        '''Returns min, max, avg, and sum of the cluster's absolute sizes.'''
+        if len(clusters) == 0:
+            return {'min':0, 'max':0, 'avg':0, 'sum':0}
+
+        min_ = clusters[0].size
+        max_ = clusters[0].size
+        sum_ = 0
+
+        for c in clusters:
+            value = c.size
+            min_ = min(min_, value)
+            max_ = max(max_, value)
+            sum_ += value
+        avg_ = sum_ / len(clusters)
+        return {'min': min_, 'max': max_, 'avg': avg_, 'sum': sum_}
+        
+    def get_relative_size_min_max_avg_sum(self, clusters: List[InternalCluster]) -> dict:
+        '''Returns min, max, avg, and sum of the cluster's relative sizes.'''
+        if len(clusters) == 0:
+            return {'min':0, 'max':0, 'avg':0, 'sum':0}
+
+        min_ = clusters[0].relative_size
+        max_ = clusters[0].relative_size
+        sum_ = 0
+
+        for c in clusters:
+            value = c.relative_size
+            min_ = min(min_, value)
+            max_ = max(max_, value)
+            sum_ += value
+        avg_ = sum_ / len(clusters)
+        return {'min': min_, 'max': max_, 'avg': avg_, 'sum': sum_}
+
+    def get_center_distance_min_max_avg_sum(self, clusters: List[InternalCluster]) -> dict:
+        '''Returns min, max, avg, and sum of the cluster's center distances.'''
+        if len(clusters) == 0:
+            return {'min':0, 'max':0, 'avg':0, 'sum':0}
+
+        min_ = clusters[0].global_center_distance
+        max_ = clusters[0].global_center_distance
+        sum_ = 0
+
+        for c in clusters:
+            value = c.global_center_distance
+            min_ = min(min_, value)
+            max_ = max(max_, value)
+            sum_ += value
+        avg_ = sum_ / len(clusters)
+        return {'min': min_, 'max': max_, 'avg': avg_, 'sum': sum_}
+
+    def get_relative_cluster_sizes(self, clusters: List[InternalCluster]):
+        return [c.relative_size for c in clusters]
+        
+    def get_entropy(self, clusters: List[InternalCluster]):
+        '''
+        Returns the entropy over all clusters C, 
+        where P(c_i) is the probability that a node belongs to cluster c_i.
+        '''
+        return scipy.stats.entropy(self.get_relative_cluster_sizes(clusters), base=2)
+
+    def get_distances_from_global_center(self, clusters: List[InternalCluster]):
+        return [cluster.global_center_distance for cluster in clusters]
+
+    def __repr__(self):
+        return str(self.__dict__)
+
+    def __str__(self):
+        return f"Layer({self.time_window_id}, " \
+        f"{self.n_nodes}, {self.n_clusters}, {self.relative_cluster_sizes}, " \
+        f"{self.entropy}, {self.centers}, {self.distances_from_global_centers})"
+
+    @staticmethod
+    def create_from_time_window(time_window: TimeWindow, feature_names:List[str], global_cluster_centers: Dict[str, Tuple[float]]) -> 'Layer':
+        clusters: List[InternalCluster] = InternalCluster.create_many_from_cluster_nodes(time_window.clusters, feature_names, global_cluster_centers)
+        return Layer(time_window.time, clusters)
+    
+    @staticmethod
+    def create_from_dict(dict_) -> 'Layer':
+        l = Layer(0, [])
+        l.__dict__.update(dict_)
+        return l
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/entities/timewindow.py

+import json
+from typing import List, Dict, NewType, Any
+from datetime import date, datetime
+
+class TimeWindow:
+    '''
+    A time slice for a single layer containing all nodes for that time.
+
+    :param time: The tag indicating the time
+    :param layer_name: The name of the layer the nodes belong to
+    '''
+
+    def __init__(self, time: Any = None, use_case: str = None, use_case_table: str = None, layer_name: str = None,
+                 time_slice_dict: Dict = None, from_db = False):
+        self.time = str(time)
+        self.use_case = use_case
+        self.use_case_table = use_case_table
+        self.layer_name = layer_name
+        self.clusters: Dict[str, List[dict]] = {}
+
+        if time_slice_dict is not None:
+            self.from_serializable_dict(time_slice_dict, from_db)
+
+    def add_node_to_cluster(self, cluster_label: str, node):
+        # only string keys can be stored in json
+        cluster_label = str(cluster_label)
+
+        if cluster_label not in self.clusters:
+            self.clusters[cluster_label] = []
+
+        # node = self._get_unique_id(node)
+        self.clusters[cluster_label].append(node)
+
+    def get_nodes_for_cluster(self, cluster_label: str):
+        if cluster_label in self.clusters:
+            return self.clusters[cluster_label]
+        else:
+            return []
+        
+    def _get_unique_id(self, node : Dict) -> Dict:
+        '''Returns a new dict with the unique id only.'''
+        uid_key = 'UniqueID'
+        if uid_key in node:
+            return {uid_key: node[uid_key]}
+
+
+    def to_serializable_dict(self, for_db=False) -> Dict:
+        return {
+            "time": self.time,
+            "use_case": self.use_case,
+            "use_case_table": self.use_case_table,
+            'layer_name': self.layer_name,
+            "clusters": json.dumps(self.clusters) if for_db else self.clusters
+        }
+
+    def from_serializable_dict(self, dict: Dict, from_db=False):
+        self.time = dict["time"]
+        self.use_case = dict["use_case"]
+        self.use_case_table = dict["use_case_table"]
+        self.layer_name = dict['layer_name']
+        self.clusters = json.loads(dict['clusters']) if from_db else dict['clusters']
+
+    @staticmethod
+    def create_from_serializable_dict(dict: Dict, from_db=False):
+        ts = TimeWindow()
+        ts.from_serializable_dict(dict, from_db)
+        return ts
+
+    def __repr__(self):
+        return json.dumps(self.to_serializable_dict())
+
+    def __str__(self):
+        return f"TimeWindow({self.__repr__()})"

src/data-hub/proactive-community-detection-microservice/app/main.py

+# add modules folder to interpreter path
+import sys
+import os
+modules_path = '../../../modules/'
+if os.path.exists(modules_path):
+    sys.path.insert(1, modules_path)
+
+
+### init logging ###
+import logging
+LOG_FORMAT = ('%(levelname) -5s %(asctime)s %(name)s:%(funcName) -35s %(lineno) -5d:  %(message)s')
+logging.basicConfig(level=logging.INFO, format=LOG_FORMAT)
+LOGGER = logging.getLogger(__name__)
+
+
+#############################
 import connexion
+from security import swagger_util
+from pathlib import Path
+import env_info
+from flask import request
+from flask import redirect
+from flask_cors import CORS
+
 
 # load swagger config
 app = connexion.App(__name__, specification_dir='configs/')
-app.add_api('swagger.yml')
+CORS(app.app)
 
 @app.route('/', methods=['GET'])
 def api_root():
-    return 'Endpoint of proactive-community-detection-microservice!'
+    return redirect('/api/ui')
+
+
+if not env_info.is_running_locally():
+    swagger_path = "configs/swagger.yml"
+
+    # SSL configuration
+    certificate_path = env_info.get_resources_path()
+    context = (os.path.normpath(f'{certificate_path}/articonf1.crt'), os.path.normpath(f'{certificate_path}/articonf1.key')) # certificate and key files
+                    
+else:
+    print("Running locally...")
+    swagger_path = "configs/swagger_local.yml"
+    context = None
+  
+    
+app.add_api(swagger_util.get_bundled_specs(Path(swagger_path)),
+                resolver = connexion.RestyResolver("cms_rest_api"))
+
 
 # start app
 if __name__ == '__main__':
-    app.run(host='0.0.0.0', port=5000, debug=True)
+    app.run(host='0.0.0.0', port=5000, ssl_context=context, debug=True)

src/data-hub/proactive-community-detection-microservice/app/processing/ClusterMetricsCalculator.py

+import warnings
+from abc import ABC, abstractmethod
+from typing import Dict, List, Any, Tuple
+import numpy as np
+from scipy.spatial import ConvexHull, qhull, distance
+from math import sqrt
+from statistics import mean
+
+warnings.simplefilter(action='ignore', category=UserWarning)
+# UserWarning: geopandas not available. Some functionality will be disabled.
+from pointpats.centrography import std_distance 
+warnings.simplefilter(action='default', category=UserWarning)
+
+
+class ClusterMetricsCalculator(ABC):
+    def __init__(self, cluster_nodes: List[dict], nr_layer_nodes: int, layer_diversity: int):
+        self.cluster_nodes = cluster_nodes
+        
+        self.nr_layer_nodes = nr_layer_nodes
+        self.layer_diversity = layer_diversity
+
+    def get_size(self) -> int:
+        '''Returns the size of the cluster.'''
+        return len(self.cluster_nodes)
+
+    @abstractmethod
+    def get_standard_deviation(self) -> float:
+        '''Returns the std dev from the center of the distribution.'''
+        pass
+
+    @abstractmethod
+    def get_scarcity(self) -> float:
+        '''
+        Returns the scarcity of the data points regarding the complete range for possible points.
+        High scarcity indicates low density.
+        '''
+        pass
+
+    @abstractmethod
+    def get_range(self) -> float:
+        '''Returns the range or area of the cluster based on the edge nodes.'''
+        pass
+
+    @abstractmethod
+    def get_center(self) -> (float, float):
+        '''Returns the center of the cluster, output is fixed 2d.'''
+        pass
+
+    def get_importance1(self) -> float:
+        '''Returns the ratio of cluster_nodes to layer_nodes.'''
+        return float(len(self.cluster_nodes)) / self.nr_layer_nodes if len(self.cluster_nodes) > 0 else 0
+
+    def get_importance2(self) -> float:
+        '''Returns the inverse of the layer_diversity, where layer_diversity = number of clusters with #nodes > 0.'''
+        return 1.0 / self.layer_diversity if len(self.cluster_nodes) > 0 else 0
+
+    def _convert_feature_to_float(self, feature_value) -> float:
+        return float(feature_value if feature_value is not "" else 0)
+
+   
+class ClusterMetricsCalculator1D(ClusterMetricsCalculator):
+    '''Metrics calculator for clusters which were clustered based on 1 feature (1d clustering).'''
+
+    def __init__(self, cluster_nodes: List[dict], cluster_feature_name: str, nr_layer_nodes: int, layer_diversity: int):
+        super().__init__(cluster_nodes, nr_layer_nodes, layer_diversity)
+        self.feature_values: List[Any] = [self._convert_feature_to_float(node[cluster_feature_name])
+                                          for node in cluster_nodes]
+        if len(self.feature_values) > 0:
+            self.max_value = max(self.feature_values)
+            self.min_value = min(self.feature_values)
+        else:
+            self.max_value = self.min_value = 0
+
+    def get_standard_deviation(self):
+        return np.std(self.feature_values) if len(self.feature_values) > 0 else 0
+
+    def get_scarcity(self):
+        '''Returns the scarcity as cluster_range / cluster_size, or 0 if len(nodes)=0.'''
+        if len(self.feature_values) == 0:
+            return 0
+
+        return self.get_range() / self.get_size()
+
+    def get_range(self):
+        return float(self.max_value - self.min_value)
+
+    def get_center(self):
+        if len(self.feature_values) == 0:
+            return (0, 0)
+        return (sum(self.feature_values) / len(self.feature_values), 0)
+
+
+class ClusterMetricsCalculator2D(ClusterMetricsCalculator):
+    '''Metrics calculator for clusters which were clustered based on 2 features (2d clustering).'''
+    
+    def __init__(self, cluster_nodes: List[dict], cluster_feature_names: List[str], nr_layer_nodes: int, layer_diversity: int):
+        assert len(cluster_feature_names) == 2, "This class is for 2d cluster results only!"
+        super().__init__(cluster_nodes, nr_layer_nodes, layer_diversity)
+
+        self.feature_values: List[Tuple[Any]] = [
+             (self._convert_feature_to_float(node[cluster_feature_names[0]]), self._convert_feature_to_float(node[cluster_feature_names[1]]))
+             for node in cluster_nodes
+             ]
+
+    def get_standard_deviation(self):
+        if len(self.feature_values) == 0:
+            return 0
+
+        warnings.simplefilter(action='ignore', category=RuntimeWarning)
+        std_dist = std_distance(self.feature_values)
+        warnings.simplefilter(action='default', category=RuntimeWarning)
+        
+        if np.isnan(std_dist):
+            return 0 # somehow std_dist=nan if all feature values are same with many decimals
+            
+        return std_dist
+
+    def get_scarcity(self):
+        '''Returns the scarcity as cluster_range / cluster_size, or 0 if len(nodes)=0.'''
+        if len(self.feature_values) == 0:
+            return 0
+
+        if len(self.feature_values) == 1:
+            # exactly 1 element gives inf density
+            return 0
+
+        range_, twodim = self._get_range()
+        if twodim:
+            return sqrt(range_ / self.get_size())
+        else:
+            return range_ / self.get_size()
+   
+    def _get_range(self):
+        twodim = False
+
+        if len(self.feature_values) == 0 or len(self.feature_values) == 1:
+            range_ = 0
+
+        elif len(self.feature_values) == 2:
+            # cannot calculate area with 2 points - just use 2d distance as range instead
+            range_ = float(distance.euclidean(self.feature_values[0], self.feature_values[1]))
+        
+        else:
+            try:
+                # calculate range as 2d area
+                points = self._get_polygon_border_points(self.feature_values)
+                range_ = self._calc_polygon_area(points)
+                # twodim must be known when calculating scarcity
+                twodim = True
+
+            except qhull.QhullError as err:
+                # possible reasons that there is no hull with real area:
+                # 1. all points are at the same location
+                # 2. all points have the same x or y coordinates (lie on one hori/vert line)
+                points = np.asarray(self.feature_values)
+                same_x = len(set(points[:,0])) == 1
+                if same_x:
+                    # use only y feature
+                    features = points[:,1]
+                    range_ = max(features) - min(features)
+
+                same_y = len(set(points[:,1])) == 1
+                if same_y:
+                    # use only x feature
+                    features = points[:,0]
+                    range_ = max(features) - min(features)
+
+                if not same_x and not same_y:
+                    # assume linear distribution of nodes
+                    points = np.asarray(list(set(self.feature_values)))
+                    min_ = min(points[:,0]), min(points[:,1])
+                    max_ = max(points[:,0]), max(points[:,1])
+                    range_ = float(distance.euclidean(min_, max_))
+
+        return (range_, twodim)
+    
+    def get_range(self):
+        return self._get_range()[0]
+
+    def _get_polygon_border_points(self, points: List[List[float]]) -> 'np.array':
+        points = np.asarray(points)
+        hull = ConvexHull(points)
+        return points[hull.vertices]
+
+    def _calc_polygon_area(self, border_points: 'np.array') -> float:
+        x: 'np.array' = border_points[:,0]
+        y: 'np.array' = border_points[:,1]
+        # https://en.wikipedia.org/wiki/Shoelace_formula
+        area = 0.5 * np.abs(np.dot(x, np.roll(y,1)) - np.dot(y, np.roll(x,1)))
+        return float(area)
+
+    def get_center(self):
+        if len(self.feature_values) == 0:
+            return (0, 0)
+            
+        x = [f[0] for f in self.feature_values]
+        y = [f[1] for f in self.feature_values] 
+        centroid = (sum(x) / len(self.feature_values), sum(y) / len(self.feature_values))
+        return centroid
+
+
+class ClusterMetricsCalculatorFactory:
+    @staticmethod
+    def create_metrics_calculator(cluster_nodes: List[dict], cluster_feature_names: List[str], nr_layer_nodes: int, layer_diversity: int) -> ClusterMetricsCalculator:
+        """
+        This factory creates a class which contains metrics about a single cluster based on 
+        its nodes, feature values, its layer total node number and its layer diversity.
+
+        :param cluster_nodes: all nodes from the cluster
+        :param cluster_feature_names: all field names which where used during clustering
+        :param nr_layer_nodes: the number of total layer nodes
+        :param layer_diversity: the diversity of the layer calculated as: number of clusters with nodes > 0
+        """
+        if isinstance(cluster_feature_names, str):
+            return ClusterMetricsCalculator1D(cluster_nodes, cluster_feature_names, nr_layer_nodes, layer_diversity)
+        if len(cluster_feature_names) == 1:
+            return ClusterMetricsCalculator1D(cluster_nodes, cluster_feature_names[0], nr_layer_nodes, layer_diversity)
+
+        if len(cluster_feature_names) == 2:
+            return ClusterMetricsCalculator2D(cluster_nodes, cluster_feature_names, nr_layer_nodes, layer_diversity)

src/data-hub/proactive-community-detection-microservice/app/processing/DataSampler.py

+
+import pandas as pd
+from imblearn.under_sampling import RandomUnderSampler
+from imblearn.over_sampling import SMOTE
+
+class DataSampler:
+    def __init__(self):
+        pass
+
+    def undersample(self, X, y, strategy='not minority') -> ('X', 'y'):
+        '''Undersampling so all class sizes equal minority class size.'''
+        rus = RandomUnderSampler(random_state=42, sampling_strategy=strategy)
+        X_undersampled, y_undersampled = rus.fit_resample(X, y)
+
+        return X_undersampled, y_undersampled
+
+    def oversample(self, X, y) -> ('X', 'y'):
+        '''Oversample based on SMOTE so all class sizes equal majority class size.'''
+        sm = SMOTE(random_state=42)
+        X_oversampled, Y_oversampled = sm.fit_resample(X, y)
+
+        return X_oversampled, Y_oversampled
+
+    def sample_fixed_size(self, X, y, size: int) -> ('X', 'y'):
+        sampling_sizes = {k: min(size, v) for k, v in y.value_counts().items()}
+
+        # undersample the larger classes to size
+        X, y = self.undersample(X, y, strategy=sampling_sizes)
+        
+        # oversample the smaller classes to size
+        X, y = self.oversample(X, y)
+
+        return X, y
+
+    def sample_median_size(self, X, y: pd.Series, max_size:int=None) -> ('X', 'y'):
+        '''Sample the median class size for all classes.'''
+        median = int(y.value_counts().median())
+
+        if max_size is not None:
+            median = min(median, max_size)
+        
+        return self.sample_fixed_size(X, y, size=median)

src/data-hub/proactive-community-detection-microservice/app/processing/__init__.py

+from processing.ClusterMetricsCalculator import ClusterMetricsCalculator, ClusterMetricsCalculator1D, ClusterMetricsCalculator2D, ClusterMetricsCalculatorFactory
+from processing.DataSampler import DataSampler

src/data-hub/proactive-community-detection-microservice/app/processing/data_prep/cluster_metrics_calc.py

+from processing.data_prep.metrics_base import calculate_center, get_cyclic_time_feature, get_evolution_label, convert_metrics_data_to_dataframe, get_cluster_metrics
+from pathlib import Path
+
+#############################
+from typing import List, Dict
+import json
+import os
+from entities import TimeWindow, Cluster
+
+def store_metrics_for_clusters(use_case: str, layer_name: str, feature_names: List[str]):
+    '''
+    :param layer_name: Name of the layer for which multiple time windows exist
+    :param feature_names: Features of the layer
+    '''
+    print(f"Working on {layer_name} cluster metrics")
+
+    # load global cluster centers
+    path_in = f'data/{use_case}/raw/clusters/{layer_name}.json'
+    with open(path_in, 'r') as file:
+        clusters = json.loads(file.read())
+        cluster_centers: Dict[str, Tuple[float]] = { 
+            str(cluster['cluster_label']): calculate_center(cluster, feature_names) 
+            for cluster in clusters 
+            if cluster['label'] != 'noise' 
+            }
+
+    path_in = f'data/{use_case}/raw/timeslices/{layer_name}'
+    Path(f'data/{use_case}/cluster_metrics/').mkdir(parents=True, exist_ok=True)
+    path_out = f'data/{use_case}/cluster_metrics/{layer_name}.json'
+
+    complete_clusters: List[Cluster] = []
+
+    for root, _, files in os.walk(path_in):
+        for f in files:
+            with open(os.path.join(root, f), 'r') as file:
+                # for each time window json
+                json_slice = json.loads(file.read())
+                time_window = TimeWindow.create_from_serializable_dict(json_slice)
+
+                # create all clusters + metrics for one time window
+                clusters = Cluster.create_multiple_from_time_window(time_window, feature_names, cluster_centers)
+                complete_clusters.extend(clusters)
+        
+    # store the cluster metrics
+    with open(path_out, 'w') as file:
+        file.write(json.dumps([cl.__dict__ for cl in complete_clusters]))
+######################
+COLUMNS = ['cluster_size', 'cluster_variance', 'cluster_density', 'cluster_import1', 'cluster_import2', 
+        'cluster_area', 'cluster_center_distance', 'time_f1', 'time_f2']*3 + ['evolution_label']
+######################
+import json
+from entities import Cluster
+import collections
+import numpy as np
+from typing import Iterable, Tuple
+
+def create_metrics_training_data(use_case: str, layer_name: str, N: int = 3) -> Iterable[list]:
+    """
+    Loads the metrics training data for an individual layer from disk.
+    A single metrics training data point should look like this:
+
+    (cluster_size, cluster_std_dev, cluster_scarcity, cluster_import1, cluster_import2, cluster_range, cluster_center_x, cluster_center_y, time_info) ^ N, evolution_label
+    time_info ... the time as 2d cyclic feature, i.e. time_info := (time_f1, time_f2)
+
+    The first tuple represents metrics from the cluster in t_i-(N-1).
+    The Nth tuple represents metrics from the cluster in t_i.
+    The label is one of {continuing, shrinking, growing, dissolving, forming} \ {splitting, merging} and identifies the change for t_i+1.
+    
+    :param N: number of cluster metric tuples
+    :param layer_name: the name of the layer metrics json file
+    """
+    
+    path_in = f"data/{use_case}/cluster_metrics/{layer_name}.json"
+    with open(path_in, 'r') as file:
+        data = [Cluster.create_from_dict(cl_d) for cl_d in json.loads(file.read())]
+
+    data.sort(key=lambda cl: (cl.cluster_id, cl.time_window_id))
+
+    # manually prepare deque with N metric_tuples + evolution label
+    tuples = []
+
+    for i, cur_cluster in enumerate(data[:-1]):
+
+        if cur_cluster.cluster_id != data[i+1].cluster_id:
+            # next cluster slice in list will be another cluster id -> restart deque and skip adding the current (last) cluster slice
+            tuples = []
+            continue
+
+        cur_metrics = get_cluster_metrics(cur_cluster)
+
+        # deque function: adding N+1st element will remove oldest one
+        if len(tuples) == N:
+            tuples.pop(0)
+        tuples.append(cur_metrics)
+
+        if len(tuples) == N:
+            label = get_evolution_label(cur_cluster.size, data[i+1].size)
+            yield list(tuples) + [label]
+############################
+def flatten_metrics_datapoint(datapoint: list) -> Tuple['X', np.array]:
+    '''
+    Flattens a single metrics data point in the form:
+    [(cluster_size, cluster_variance, cluster_density, cluster_import1, cluster_import2, cluster_range, cluster_center, (time_f1, time_f2))^N, evolution_label]
+    to:
+    (X, y: np.array)
+    '''
+    flat_list = []
+    for entry in datapoint[:-1]: # for all x
+        flat_list.extend(entry[:-1]) # add all number features except the time tuple
+        flat_list.extend(entry[-1]) # add time tuple
+
+    flat_list.append(datapoint[-1]) # y
+    return np.asarray(flat_list)
+################################
+import numpy as np
+import pandas as pd
+from pandas import DataFrame
+import collections
+import statistics as stat
+
+def balance_dataset(df: DataFrame) -> DataFrame:
+    # nothing happening here, balance only on real training, not during prep
+    return df
+
+def store_training_data(use_case: str, layer_name: str):
+    # load metrics data from disk
+    data: Iterable = create_metrics_training_data(use_case=use_case, layer_name=layer_name)
+    
+    # flatten and convert to df
+    df = convert_metrics_data_to_dataframe(data, columns=COLUMNS, flattening_method=flatten_metrics_datapoint)
+
+    # balance df
+    df = balance_dataset(df)
+
+    # shuffle
+    df = df.sample(frac=1).reset_index(drop=True)
+    
+    Path(f'data/{use_case}/ml_input/single_context/').mkdir(parents=True, exist_ok=True)
+    df.to_csv(f'data/{use_case}/ml_input/single_context/{layer_name}.csv')
+
+#######################
+
+from db.repository import Repository
+from db.dao import LayerDao
+from pathlib import Path
+
+repo = Repository()
+
+def run(use_case=None):
+    '''
+    Requires raw jsons for clusters and time slices.
+    Working directory: data/
+    '''
+    if use_case is not None:
+        use_cases = [use_case]
+    else:
+        use_cases = repo.get_use_cases()
+
+    for use_case in use_cases:
+        print(f"Executing cluster metrics calc for use case {use_case}")
+        
+        layers = [[l.layer_name, l.properties] for l in repo.get_layers_for_use_case(use_case)]
+    
+        ##################
+        for layer in layers:
+            store_metrics_for_clusters(use_case, layer[0], layer[1])
+        ###################
+        for name, _ in layers:
+            print(f"Storing training data for {name}")
+            store_training_data(use_case, layer_name=name)
+            
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/processing/data_prep/layer_metrics_calc.py

+from processing.data_prep.metrics_base import calculate_center, get_cyclic_time_feature, get_evolution_label,convert_metrics_data_to_dataframe, get_layer_metrics
+from pathlib import Path
+
+#################
+from typing import List, Tuple
+import statistics as stat
+import json
+import os
+from entities import TimeWindow, Layer
+from processing import ClusterMetricsCalculatorFactory
+
+def store_metrics_for_layers(use_case: str, layer_name: str, feature_names: List[str]):
+    print(f"Working on {layer_name} layer metrics")
+
+    # load global cluster centers
+    path_in = f'data/{use_case}/raw/clusters/{layer_name}.json'
+    with open(path_in, 'r') as file:
+        clusters = json.loads(file.read())
+        cluster_centers: Dict[str, Tuple[float]] = { 
+            str(cluster['cluster_label']): calculate_center(cluster, feature_names) 
+            for cluster in clusters 
+            if cluster['label'] != 'noise' 
+            }
+
+    # load time windows 
+    all_layers: List[Layer] = []
+    path_in = f'data/{use_case}/raw/timeslices/{layer_name}'
+    for root, _, files in os.walk(path_in):
+        for f in files:
+            with open(os.path.join(root, f), 'r') as file:
+                json_time_slice = json.loads(file.read())
+                time_window = TimeWindow.create_from_serializable_dict(json_time_slice)
+
+                layer = Layer.create_from_time_window(time_window, feature_names, cluster_centers)
+                all_layers.append(layer)
+        
+    # store the layer metrics
+    Path(f'data/{use_case}/layer_metrics/').mkdir(parents=True, exist_ok=True)
+    path_out = f'data/{use_case}/layer_metrics/{layer_name}.json'
+    with open(path_out, 'w') as file:
+        file.write(json.dumps([l.__dict__ for l in all_layers]))
+#########################
+from typing import List
+
+def get_columns(N) -> List[str]:
+    '''Returns columns for the data depending on sizes of N (number time windows) independent of M (number of clusters in L_R).'''
+
+    cols = ['n_nodes', 'n_clusters', 'entropy']
+
+    for v in ['sizes', 'relative_sizes', 'center_dist']:
+        cols += [f'{v}_min', f'{v}_max', f'{v}_avg', f'{v}_sum']
+
+    # cols.extend(['relative_cluster_sizes']*M)
+    # cols.extend(['cluster_centers']*M)
+    # cols.extend(['distance_from_global_centers']*M)
+
+    cols.extend(['time_f1', 'time_f2'])
+
+    cols = cols * N 
+    return cols + ['cluster_id'] + ['evolution_label']
+######################
+from typing import Iterable, List, Dict, Any
+import json
+from entities import Layer, Cluster
+
+def create_layer_metrics_training_data(use_case: str, layer_name: str, reference_layer: str, N: int = 2) -> Iterable:
+    """
+    Loads the metrics training data for an individual layer from disk.
+    
+    A single metrics training data point should look like this:
+
+    [(n_nodes, n_clusters, entropy,
+     (relative_cluster_size)^M, (cluster_centers)^M, (distance_from_global_centers)^M, 
+     (time1, time2))^N, 
+     cluster_number, evolution_label]
+     
+    The first tuple represents metrics from the reference layer in t_i-(N-1).
+    The Nth tuple represents metrics from the reference layer in t_i.
+    The reference_layer has M clusters in total, this might differ from the number of clusters in layer_name.
+    The cluster number identifies the cluster for which the evolution_label holds. 
+    The label is one of {continuing, shrinking, growing, dissolving, forming} \ {splitting, merging} and identifies the change for a cluster in the layer layer_name for t_i.
+    """
+    if N != 2:
+        raise NotImplementedError("N is not implemented and fixed to 2!")
+    
+    with open(f'data/{use_case}/cluster_metrics/{layer_name}.json') as file:
+        cluster_metrics: List[Cluster] = [Cluster.create_from_dict(e) for e in json.loads(file.read())]
+        cluster_ids = {c.cluster_id for c in cluster_metrics}
+        cluster_metrics: Dict[Any, Cluster] = {(c.time_window_id, c.cluster_id): c for c in cluster_metrics}
+        
+    with open(f'data/{use_case}/layer_metrics/{reference_layer}.json') as file:
+        layer_metrics: List[Layer] = [Layer.create_from_dict(e) for e in json.loads(file.read())]
+        layer_metrics: Dict[Any, Layer] = {l.time_window_id: l for l in layer_metrics}
+
+    # load the time keys chronologically
+    ordered_time_keys = list(layer_metrics.keys())
+    ordered_time_keys.sort(key=lambda x: [int(v) for v in x.replace('(', '').replace(')', '').split(',')])
+    
+    # go through all time windows once...
+    prev_time_key = ordered_time_keys[0]
+    for current_time_key in ordered_time_keys[1:]:
+        # ...and load the current and previous layer metrics in the reference_layer
+        current_layer_metric = layer_metrics[current_time_key]
+        prev_layer_metric = layer_metrics[prev_time_key]
+
+        current_layer_metric_tuple = get_layer_metrics(current_layer_metric)
+        prev_layer_metric_tuple = get_layer_metrics(prev_layer_metric)
+
+        # ...then load the current and previous cluster metrics for all clusters in the layer_name
+        for cluster_id in cluster_ids:
+            current_cluster_metric = cluster_metrics[(current_time_key, cluster_id)]
+            prev_cluster_metric = cluster_metrics[(prev_time_key, cluster_id)]
+            evolution_label = get_evolution_label(prev_cluster_metric.size, current_cluster_metric.size)
+
+            # yield each combination of reference layer metrics to clusters
+            yield [prev_layer_metric_tuple, current_layer_metric_tuple, int(cluster_id), evolution_label]
+
+        prev_time_key = current_time_key
+#####################
+import numpy as np
+
+def flatten_layer_metrics_datapoint(datapoint: list) -> Tuple['X', np.array]:
+    '''
+    Flattens a single layer metrics data point in the form:
+    [(n_nodes, n_clusters, entropy,
+     (relative_cluster_size)^M, (distance_from_global_centers)^M, 
+     (time1, time2))^N, 
+     cluster_number, evolution_label]
+    to:
+    (X, y: np.array)
+    '''
+    flat_list = []
+    for layer_metric_tuple in datapoint[:-2]: # for all x
+        flat_list.extend(layer_metric_tuple[0:-1]) # everything before time
+        flat_list.extend(layer_metric_tuple[-1]) # time1/2
+
+    flat_list.append(datapoint[-2]) # cluster num
+    flat_list.append(datapoint[-1]) # y
+
+    return np.asarray(flat_list)
+#########################
+import numpy as np
+import pandas as pd
+from pandas import DataFrame
+import collections
+import statistics as stat
+
+def balance_dataset(df: DataFrame) -> DataFrame:
+    # nothing happening here, balance only on real training, not during prep
+    return df
+
+def store_training_data(use_case: str, layer_name: str, reference_layer_name: str):
+    # load metrics data from disk
+    data: Iterable = create_layer_metrics_training_data(use_case=use_case, layer_name=layer_name, reference_layer=reference_layer_name)
+    
+    # convert to X and Y
+    df = convert_metrics_data_to_dataframe(data, columns=get_columns(N=2), flattening_method=flatten_layer_metrics_datapoint)
+    
+    # balance df
+    df = balance_dataset(df)
+    
+    # shuffle
+    df = df.sample(frac=1).reset_index(drop=True)
+
+    Path(f'data/{use_case}/ml_input/cross_context/').mkdir(parents=True, exist_ok=True)
+    df.to_csv(f'data/{use_case}/ml_input/cross_context/{layer_name}_{reference_layer_name}.csv')
+
+#########################
+
+from db.repository import Repository
+from db.dao import LayerDao
+from pathlib import Path
+
+repo = Repository()
+
+def run(use_case=None):
+    '''
+    Requires raw jsons and cluster metrics.
+    Working directory: data/
+    '''
+    if use_case is not None:
+        use_cases = [use_case]
+    else:
+        use_cases = repo.get_use_cases()
+
+    for use_case in use_cases:
+        print(f"Executing layer metrics calc for use case {use_case}")
+
+        layers = [[l.layer_name, l.properties] for l in repo.get_layers_for_use_case(use_case)]
+        layer_pairs = repo.get_layer_pairs(use_case)
+
+        ################
+        for layer in layers:
+            try:
+                store_metrics_for_layers(use_case, layer[0], layer[1])
+            except FileNotFoundError:
+                pass
+        ###############
+        for ld in layer_pairs:
+            print(f"Storing training data for {ld.layer} with L_R={ld.reference_layer}")
+            store_training_data(use_case, layer_name=ld.layer, reference_layer_name=ld.reference_layer)
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/processing/data_prep/main.py

+from processing.data_prep.cluster_metrics_calc import run as crun
+from processing.data_prep.layer_metrics_calc import run as lrun
+
+from pathlib import Path
+import json
+import os
+
+from db.repository import Repository
+
+
+repo = Repository()
+
+
+def store_clusters_as_files(use_case):
+    path_ = f'data/{use_case}/raw/clusters/'
+    Path(path_).mkdir(parents=True, exist_ok=True)
+
+    layers = repo.get_layers_for_use_case(use_case)
+    for l in layers:
+        clusters = repo.get_clusters_for_layer(use_case, l.use_case_table, l.layer_name)
+
+        with open(os.path.join(path_, f'{l.layer_name}.json'), 'w') as file_:
+            file_.write(json.dumps([c.to_serializable_dict() for c in clusters]))   
+            
+
+def store_time_slices_as_files(use_case):
+    path_ = f'data/{use_case}/raw/timeslices/'
+
+    layers = repo.get_layers_for_use_case(use_case)
+    for l in layers:
+        Path(os.path.join(path_, l.layer_name)).mkdir(parents=True, exist_ok=True)
+
+        time_slices = repo.get_time_slices_for_layer(use_case, l.use_case_table, l.layer_name)
+        for ts in time_slices:
+            with open(os.path.join(path_, l.layer_name, f'{ts.time}.json'), 'w') as file_:
+                file_.write(json.dumps(ts.to_serializable_dict()))   
+
+
+def run(use_case=None):
+    '''Prepares training data for single and cross-context using the file system (data/)'''
+    if use_case is not None:
+        use_cases = [use_case]
+    else:
+        use_cases = repo.get_use_cases()
+    
+
+    for use_case in use_cases:
+        store_clusters_as_files(use_case)
+        store_time_slices_as_files(use_case)
+
+        crun(use_case)
+        lrun(use_case)
+

src/data-hub/proactive-community-detection-microservice/app/processing/data_prep/metrics_base.py

+'''
+These functions are utilized for both single and cross-context data preparation, i.e.
+- cluster_metrics_main.py
+- layer_metrics_main.py
+'''
+
+#############################
+from typing import Tuple
+from processing import ClusterMetricsCalculatorFactory
+
+def calculate_center(cluster: dict, features: list) -> Tuple[float]:
+    calc = ClusterMetricsCalculatorFactory.create_metrics_calculator(cluster['nodes'], features, 1, 1)
+    return calc.get_center()
+#####################
+import numpy as np
+
+def get_cyclic_time_feature(time: int, max_time_value: int = 52) -> Tuple[float, float]:
+    return (np.sin(2*np.pi*time/max_time_value),
+            np.cos(2*np.pi*time/max_time_value))
+####################
+def get_evolution_label(old_size: int, new_size: int) -> int:
+    '''Returns the evolution label as int by mapping 0..4 to {continuing, shrinking, growing, dissolving, forming}.'''
+    if old_size == 0 and new_size == 0:
+        return -1 # STILL EMPTY
+    if old_size == new_size:
+        return 0 # continuing
+    if old_size == 0 and new_size > 0:
+        return 4 # forming
+    if old_size > 0 and new_size == 0:
+        return 3 # dissolving
+    if old_size > new_size:
+        return 1 # shrinking
+    if old_size < new_size:
+        return 2 # growing
+#########################
+from typing import Iterable
+import pandas as pd
+
+def convert_metrics_data_to_dataframe(data: Iterable, columns: list, flattening_method: 'callable') -> pd.DataFrame:
+    '''Flattens and splits metrics data to match ML conventions.'''
+    training_data = []
+
+    for element in data:
+        xy: 'np.array' = flattening_method(element)
+        
+        training_data.append(xy)
+
+    return pd.DataFrame(data=training_data, columns=columns)
+
+####################
+
+from entities import Cluster, Layer
+from typing import Dict, Tuple
+
+def get_cluster_metrics(cur_cluster: Cluster) -> Tuple:
+    return (cur_cluster.size, cur_cluster.std_dev, cur_cluster.scarcity, cur_cluster.importance1, cur_cluster.importance2, 
+            cur_cluster.range_, cur_cluster.global_center_distance, get_cyclic_time_feature(cur_cluster.get_time_info()))
+####################
+def get_layer_metrics(layer: Layer) -> Iterable:
+    res = [layer.n_nodes, layer.n_clusters, layer.entropy]
+    res += [layer.cluster_size_agg_metrics[k] for k in ['min', 'max', 'avg', 'sum']]
+    res += [layer.cluster_relative_size_agg_metrics[k] for k in ['min', 'max', 'avg', 'sum']]
+    res += [layer.cluster_center_distance_agg_metrics[k] for k in ['min', 'max', 'avg', 'sum']]
+    res.append(get_cyclic_time_feature(layer.get_time_info()))
+    return res
+###################
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/processing/fetching/fetching.py

+from security.token_manager import TokenManager
+import network_constants
+from db.repository import Repository
+from db.dao import *
+
+from typing import List, Dict
+import requests
+import json
+
+
+def _fetch_use_cases() -> List[str]:
+    jwt = TokenManager.getInstance().getToken()
+
+    url = f'https://{network_constants.BUSINESS_LOGIC_HOSTNAME}:{network_constants.BUSINESS_LOGIC_REST_PORT}/api/use-cases'
+
+    response = requests.get(
+            url,
+            verify = False, 
+            proxies = { "http":None, "https":None },
+            headers = {"Authorization": f"Bearer {jwt}"}
+    )
+
+    if response.status_code != 200:
+        raise ConnectionError(f"Could not fetch use-cases from business-logic microservice, statuscode: {response.status_code}!")
+
+    return [row["name"] for row in response.json()]
+
+
+def _fetch_tables(use_case: str) -> List[str]:
+    jwt = TokenManager.getInstance().getToken()
+
+    url = f'https://{network_constants.BUSINESS_LOGIC_HOSTNAME}:{network_constants.BUSINESS_LOGIC_REST_PORT}/api/use-cases/{use_case}/tables'
+
+    response = requests.get(
+            url,
+            verify = False, 
+            proxies = { "http":None, "https":None },
+            headers = {"Authorization": f"Bearer {jwt}"}
+    )
+
+    if response.status_code != 200:
+        raise ConnectionError(f"Could not fetch use-cases from business-logic microservice, statuscode: {response.status_code}!")
+
+    return [row["name"] for row in response.json()]    
+
+
+def _fetch_layers(use_case: str, table: str) -> List[LayerDao]:
+    jwt = TokenManager.getInstance().getToken()
+
+    url = f'https://{network_constants.BUSINESS_LOGIC_HOSTNAME}:{network_constants.BUSINESS_LOGIC_REST_PORT}/api/use-cases/{use_case}/tables/{table}/layers'
+
+    response = requests.get(
+            url,
+            verify = False, 
+            proxies = { "http":None, "https":None },
+            headers = {"Authorization": f"Bearer {jwt}"}
+    )
+
+    if response.status_code != 200:
+        raise ConnectionError(f"Could not fetch layers for {use_case} from business-logic microservice, statuscode: {response.status_code}!")
+
+    return [LayerDao.from_business_logic_dict(row) for row in response.json()]
+
+
+def _fetch_clusters(use_case: str, table: str, layer_name: str) -> List[str]:
+    jwt = TokenManager.getInstance().getToken()
+
+    url = f'https://{network_constants.ROLESTAGE_DISCOVERY_HOSTNAME}:{network_constants.ROLESTAGE_DISCOVERY_REST_PORT}/api/use-cases/{use_case}/tables/{table}/layers/{layer_name}/clusters'
+
+    response = requests.get(
+            url,
+            verify = False, 
+            proxies = { "http":None, "https":None },
+            headers = {"Authorization": f"Bearer {jwt}"}
+    )
+
+    if response.status_code != 200:
+        raise ConnectionError(f"Could not fetch clusters for {use_case}//{table}//{layer_name}, statuscode: {response.status_code}!")
+
+    return [ClusterDao(cluster_dict=row) for row in response.json()]
+
+
+def _fetch_timeslices(use_case: str, table: str, layer_name: str) -> List[Dict]:
+    jwt = TokenManager.getInstance().getToken()
+
+    url = f'https://{network_constants.ROLESTAGE_DISCOVERY_HOSTNAME}:{network_constants.ROLESTAGE_DISCOVERY_REST_PORT}/api/use-cases/{use_case}/tables/{table}/layers/{layer_name}/timeslices'
+
+    response = requests.get(
+            url,
+            verify = False, 
+            proxies = { "http":None, "https":None },
+            headers = {"Authorization": f"Bearer {jwt}"}
+    )
+
+    if response.status_code != 200:
+        raise ConnectionError(f"Could not fetch time slices for {use_case}//{table}//{layer_name}, statuscode: {response.status_code}!")
+
+    return [TimeSliceDao(time_slice_dict=row) for row in response.json()]
+
+
+def _fetch_layerpairs(use_case: str, table: str) -> List[Dict]:
+    jwt = TokenManager.getInstance().getToken()
+
+    url = f'https://{network_constants.BUSINESS_LOGIC_HOSTNAME}:{network_constants.BUSINESS_LOGIC_REST_PORT}/api/use-cases/{use_case}/tables/{table}/layer-pairs'
+
+    response = requests.get(
+            url,
+            verify = False, 
+            proxies = { "http":None, "https":None },
+            headers = {"Authorization": f"Bearer {jwt}"}
+    )
+
+    if response.status_code != 200:
+        raise ConnectionError(f"Could not fetch layer pairs for {use_case}//{table}, statuscode: {response.status_code}!")
+
+    return [LayerPairDao.create_from_dict(row) for row in response.json()]
+
+
+def fetch(selected_use_cases: List[str] = None, selected_use_case_tables: List[str] = None):
+    '''Fetches all the required data.'''
+    repo = Repository()
+    
+    for use_case in _fetch_use_cases():
+        if selected_use_cases is not None and use_case not in selected_use_cases:
+            continue
+
+        repo.add_use_case(use_case)
+
+        for table in _fetch_tables(use_case):
+            if selected_use_case_tables is not None and table not in selected_use_case_tables:
+                continue
+
+            print(f"Fetching for {use_case}//{table}")
+            
+            try:
+                # copy all layer pairs
+                layer_pairs: List[LayerPairDao] = _fetch_layerpairs(use_case, table)
+                for lp in layer_pairs:
+                    repo.add_layer_pair(lp)
+            except ConnectionError as e:
+                print(str(e))
+
+            # copy all layers
+            for layer in _fetch_layers(use_case, table):
+
+                db_layer = repo.get_layer_by_name(use_case, layer.use_case_table, layer.layer_name)
+                if db_layer == None:
+                    repo.add_layer(layer)
+                else:
+                    print(f"Layer already exists, skipping cluster and timeslice fetching: {db_layer.layer_name}")
+                    continue
+
+                try:
+                    # copy all clusters
+                    clusters = _fetch_clusters(use_case, layer.use_case_table, layer.layer_name)
+                    for cl in clusters:
+                        repo.add_cluster(cl)
+                except ConnectionError as e:
+                    print(str(e))
+                    
+                try:
+                    # copy all timeslices
+                    timeslices = _fetch_timeslices(use_case, layer.use_case_table, layer.layer_name)
+                    for ts in timeslices:
+                        repo.add_time_slice(ts)
+                except ConnectionError as e:
+                    print(str(e))
+            
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/processing/ml/predict_base.py

+def increase_time_window(time_window_id: str) -> str:
+    tuple_ = eval(time_window_id)
+    
+    if tuple_[1] == 52:
+        # 1st week next year
+        return (tuple_[0]+1 , 1)
+    else:
+        # next week
+        return str((tuple_[0], tuple_[1]+1))
+######################
+from typing import Tuple
+import pickle
+
+def load_ml_models(use_case, method, layer_name, reference_layer_name=None) -> Tuple['scaler', 'clf']:
+    path_ = f'data/{use_case}/ml_output/{method}/{layer_name}'
+
+    if method == 'single_context':
+        with open(f'{path_}.model', 'rb') as file:
+            svc = pickle.load(file)
+        with open(f'{path_}_scaler.model', 'rb') as file:
+            scaler = pickle.load(file)
+
+    elif method == 'cross_context':
+        with open(f'{path_}_{reference_layer_name}.model', 'rb') as file:
+            svc = pickle.load(file)
+        with open(f'{path_}_{reference_layer_name}_scaler.model', 'rb') as file:
+            scaler = pickle.load(file)
+    
+    else:
+        raise NotImplementedError('Prediction method is not implemented')
+
+    return scaler, svc
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/processing/ml/predict_cross_context.py

+from processing.data_prep.metrics_base import get_cyclic_time_feature, get_layer_metrics
+from processing.ml.predict_base import increase_time_window, load_ml_models
+ 
+method = 'cross_context'
+N = 2 # Currently N is fixed to 2
+
+####################
+import pandas as pd
+from pandas import DataFrame
+#####################
+import json
+from entities import Layer, Cluster
+import collections
+import numpy as np
+from typing import Iterable, Tuple, List, Dict, Any
+####################
+import pickle 
+#####################
+import numpy as np
+
+def flatten_layer_metrics_datapoint(datapoint: list) -> np.array:
+    '''
+    Flattens a single layer metrics data point in the form:
+    [(n_nodes, n_clusters, entropy,
+     (relative_cluster_size)^M, (distance_from_global_centers)^M, 
+     (time1, time2))^N, 
+     cluster_number]
+    to:
+    (X)
+    '''
+    flat_list = []
+    for layer_metric_tuple in datapoint[:-1]: # for all x
+        flat_list.extend(layer_metric_tuple[0:-1]) # everything before time
+        flat_list.extend(layer_metric_tuple[-1]) # time1/2
+
+    flat_list.append(datapoint[-1]) # cluster num
+
+    return np.asarray(flat_list)
+#########################
+from db.repository import Repository
+from db.dao import PredictionResult
+
+repo = Repository()
+
+def run_prediction(use_case: str):
+    for layerpair in repo.get_layer_pairs(use_case):
+        layer_name = layerpair.layer
+        reference_layer_name = layerpair.reference_layer
+
+        print(f"Predicting {method} for {use_case}//{layer_name} based on {reference_layer_name}")
+        
+        ##########################
+        with open(f'data/{use_case}/cluster_metrics/{layer_name}.json') as file:
+            cluster_metrics: List[Cluster] = [Cluster.create_from_dict(e) for e in json.loads(file.read())]
+            cluster_ids = {c.cluster_id for c in cluster_metrics}
+            cluster_metrics: Dict[Any, Cluster] = {(c.time_window_id, c.cluster_id): c for c in cluster_metrics}
+                
+        with open(f'data/{use_case}/layer_metrics/{reference_layer_name}.json') as file:
+            layer_metrics: List[Layer] = [Layer.create_from_dict(e) for e in json.loads(file.read())]
+            layer_metrics: Dict[Any, Layer] = {l.time_window_id: l for l in layer_metrics}
+        ######################
+        # load the time keys chronologically
+        ordered_time_keys = list(layer_metrics.keys())
+        ordered_time_keys.sort(key=lambda x: eval(x))
+        ######################
+        ordered_time_keys = ordered_time_keys[-N:]
+        #################
+        prediction_metrics_raw = []
+
+        current_layer_metric = layer_metrics[ordered_time_keys[1]]
+        prev_layer_metric = layer_metrics[ordered_time_keys[0]]
+
+        current_layer_metric_tuple = get_layer_metrics(current_layer_metric)
+        prev_layer_metric_tuple = get_layer_metrics(prev_layer_metric)
+
+        for cluster_id in cluster_ids:
+            # yield each combination of reference layer metrics to clusters
+            prediction_metrics_raw.append([prev_layer_metric_tuple, current_layer_metric_tuple, int(cluster_id)])
+        #######################
+        scaler, svc = load_ml_models(use_case, method, layer_name, reference_layer_name)
+        ################
+        prediction_cluster_ids = []
+        prediction_time_window = increase_time_window(ordered_time_keys[1])
+        prediction_metrics = []
+            
+        for pred in  prediction_metrics_raw:
+            cluster_id = pred[-1]
+            prediction_cluster_ids.append(cluster_id)
+
+            flat_ = flatten_layer_metrics_datapoint(pred)
+            prediction_metrics.append(flat_)
+    
+        prediction_results = svc.predict(scaler.transform(np.array(prediction_metrics)))
+        print(np.unique(prediction_results, return_counts=True))
+
+        for i in range(len(prediction_cluster_ids)):
+            res = PredictionResult(use_case, use_case, method, layer_name, reference_layer_name, prediction_cluster_ids[i], prediction_time_window, prediction_results[i])
+            repo.add_prediction_result(res)

src/data-hub/proactive-community-detection-microservice/app/processing/ml/predict_single_context.py

+from processing.data_prep.metrics_base import get_cyclic_time_feature, get_cluster_metrics
+from processing.ml.predict_base import increase_time_window, load_ml_models
+ 
+N = 3 # Currently N is fixed to 3
+method = 'single_context'
+
+####################
+import pandas as pd
+from pandas import DataFrame
+#####################
+import json
+from entities import Cluster
+import collections
+import numpy as np
+from typing import Iterable, Tuple, Dict, List
+######################
+import pickle 
+#####################
+def flatten_metrics_datapoint(datapoint: list) -> np.array:
+    '''
+    Flattens a single metrics data point in the form:
+    [(cluster_size, cluster_variance, cluster_density, cluster_import1, cluster_import2, cluster_range, cluster_center, (time_f1, time_f2))^N]
+    to:
+    (X)
+    '''
+    flat_list = []
+    for entry in datapoint: # for all x
+        flat_list.extend(entry[:-1]) # add all number features except the time tuple
+        flat_list.extend(entry[-1]) # add time tuple
+
+    return np.asarray(flat_list)
+#########################
+from db.repository import Repository
+from db.dao import PredictionResult
+
+repo = Repository()
+
+def run_prediction(use_case: str):
+    for layer in repo.get_layers_for_use_case(use_case):
+        layer_name = layer.layer_name
+        print(f"Predicting {method} for {use_case}//{layer_name}")
+
+        #################
+        path_in = f"data/{use_case}/cluster_metrics/{layer_name}.json"
+        with open(path_in, 'r') as file:
+            data = [Cluster.create_from_dict(cl_d) for cl_d in json.loads(file.read())]
+
+        data.sort(key=lambda cl: (eval(cl.cluster_id), eval(cl.time_window_id)))
+        #####################
+        cluster_map: Dict['cluster_id', 'time_windows'] = {}
+
+        for cluster in data:
+            id_ = cluster.cluster_id
+
+            if id_ not in cluster_map:
+                cluster_map[id_] = []
+
+            cluster_map[id_].append(cluster)
+        ####################       
+        scaler, svc = load_ml_models(use_case, method, layer_name)
+        #####################
+        # store id, future time window, and flattened metrics to combine the latter during prediction
+        prediction_cluster_ids = []
+        prediction_time_windows = []
+        prediction_metrics = []
+
+        for cluster_id, time_windows in cluster_map.items():
+            v = [get_cluster_metrics(c) for c in time_windows[-N:]] # metrics for last N time windows
+            v_flattened = flatten_metrics_datapoint(v)
+
+            prediction_cluster_ids.append(cluster_id)
+            prediction_time_windows.append(increase_time_window(time_windows[-1].time_window_id))
+            prediction_metrics.append(v_flattened)
+            
+        # predict all at once for speedup
+        prediction_results = svc.predict(scaler.transform(np.array(prediction_metrics)))
+        print(np.unique(prediction_results, return_counts=True))
+        
+        for i in range(len(prediction_cluster_ids)):
+            res = PredictionResult(use_case, use_case, method, layer_name, None, prediction_cluster_ids[i], prediction_time_windows[i], prediction_results[i])
+            repo.add_prediction_result(res)

src/data-hub/proactive-community-detection-microservice/app/processing/ml/train_base.py

+import numpy as np
+import collections
+from typing import Tuple
+
+def split_data(dataframe, test_dataset_frac=.2, shuffle=False) -> Tuple['training_data', 'test_data']:
+    if shuffle:
+        dataframe = dataframe.sample(frac=1).reset_index(drop=True)
+
+    training_size = int(len(dataframe) * (1-test_dataset_frac))
+
+    train = dataframe[:training_size].reset_index(drop=True)
+    test = dataframe[training_size:].reset_index(drop=True)
+
+    y_train = train[train.columns[-1]]
+    y_test = test[test.columns[-1]]
+  
+    return train, test
+#######################
+import pandas as pd
+from pandas import DataFrame
+
+def remove_empty_community_class(df):
+    '''Removes evolution_label -1 from dataset indicating the community stays empty.'''
+    # res = df.loc[df['evolution_label'] != -1.0]
+    # res = res.reset_index(drop=True)
+    # return res
+    df['evolution_label'] = df['evolution_label'].replace(-1.0, 0)
+    return df
+########################
+import sklearn.metrics
+
+def print_report(clfs: list, test_Xs: list, test_Y: 'y', titles: list):
+    """
+    Prints all reports.
+    :param clfs: list of classifiers to evaluate
+    :param test_Xs: list of test_X for the corresponding classifier at idx
+    :param test_Y: true classes
+    :param titles: list of titles for the classifiers at idx
+    """
+    for clf, test_X, title in zip(clfs, test_Xs, titles):
+        pred_Y = clf.predict(test_X)        
+        print(f"### {title} ###\n", sklearn.metrics.classification_report(y_true=test_Y, y_pred=pred_Y))
+########################
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/processing/ml/train_cross_context.py

+import pandas as pd
+from pandas import DataFrame
+from processing.ml.train_base import split_data, remove_empty_community_class, print_report
+
+
+approach = 'cross_context'
+#######################
+import pickle
+from pathlib import Path
+
+def export_model(model, use_case, layer_name, reference_layer_name, scaler=False):
+    fpath = f'data/{use_case}/ml_output/{approach}'
+    Path(fpath).mkdir(parents=True, exist_ok=True)
+    with open(f'{fpath}/{layer_name}_{reference_layer_name}{"_scaler" if scaler else ""}.model', 'wb') as f:
+        pickle.dump(model, f)
+###################
+from sklearn.ensemble import RandomForestClassifier
+n_estimators = 50
+criterion = 'gini'
+max_depth = None
+min_samples_leaf = 2
+min_impurity_decrease= 1E-5
+bootstrap=True
+
+
+###############
+
+
+from db.repository import Repository
+
+repo = Repository()
+
+def run_training(use_case):
+    for layerpair in repo.get_layer_pairs(use_case):
+        layer_name = layerpair.layer
+        reference_layer_name = layerpair.reference_layer
+
+
+        df: DataFrame = pd.read_csv(f'data/{use_case}/ml_input/cross_context/{layer_name}_{reference_layer_name}.csv', index_col=0)
+        #######################
+        training, testing = split_data(df, shuffle=False)
+        #####################
+        training = remove_empty_community_class(training)
+        testing = remove_empty_community_class(testing)
+        #####################
+        from sklearn.preprocessing import StandardScaler
+        scaler = StandardScaler()
+
+        train_X = scaler.fit_transform(training[training.columns[:-1]]) # all except y
+        train_Y = training[training.columns[-1]]
+
+        test_X = scaler.transform(testing[testing.columns[:-1]]) # all except y
+        test_Y = testing[testing.columns[-1]]
+
+        export_model(scaler, use_case, layer_name, reference_layer_name, scaler=True)
+        ########################
+        from processing import DataSampler
+
+        sampler = DataSampler()
+        try:
+            train_X, train_Y = sampler.sample_median_size(train_X, train_Y, max_size=100000)
+        except ValueError as e: # not enough points for oversampling
+            print(f"Could not sample training data, using original distribution: {e}")
+        ####################
+        rfc = RandomForestClassifier(n_estimators=n_estimators, criterion=criterion, max_depth=max_depth,
+                                    min_samples_leaf=min_samples_leaf, min_impurity_decrease=min_impurity_decrease, 
+                                    bootstrap=bootstrap)
+        rfc.fit(train_X, train_Y)
+        
+        print_report([rfc], [test_X], test_Y, ["X"])
+        
+        export_model(rfc, use_case, layer_name, reference_layer_name)
+        
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/processing/ml/train_single_context.py

+import pandas as pd
+from pandas import DataFrame
+from processing.ml.train_base import split_data, remove_empty_community_class, print_report
+
+
+approach = 'single_context'
+#######################
+import pickle 
+from pathlib import Path
+
+def export_model(model, use_case, layer_name, scaler=False):
+    fpath = f'data/{use_case}/ml_output/{approach}'
+    Path(fpath).mkdir(parents=True, exist_ok=True)
+    with open(f'{fpath}/{layer_name}{"_scaler" if scaler else ""}.model', 'wb') as f:
+        pickle.dump(model, f)
+#####################
+from sklearn.ensemble import RandomForestClassifier
+n_estimators = 100
+criterion = 'gini'
+max_depth = None
+min_samples_leaf = 2
+min_impurity_decrease = 1E-5
+bootstrap=True
+
+
+###############
+
+
+from db.repository import Repository
+
+repo = Repository()
+
+def run_training(use_case):
+    for layer in repo.get_layers_for_use_case(use_case):
+        layer_name = layer.layer_name
+
+
+        df: DataFrame = pd.read_csv(f'data/{use_case}/ml_input/single_context/{layer_name}.csv', index_col=0)
+        #######################
+        training, testing = split_data(df, shuffle=False)
+        #####################
+        training = remove_empty_community_class(training)
+        testing = remove_empty_community_class(testing)
+        #####################
+        from sklearn.preprocessing import StandardScaler
+        scaler = StandardScaler()
+
+        train_X = scaler.fit_transform(training[training.columns[:-1]]) # all except y
+        train_Y = training[training.columns[-1]]
+
+        test_X = scaler.transform(testing[testing.columns[:-1]]) # all except y
+        test_Y = testing[testing.columns[-1]]
+
+        export_model(scaler, use_case, layer_name, scaler=True)
+        ########################
+        from processing import DataSampler
+
+        sampler = DataSampler()
+        try:
+            train_X, train_Y = sampler.sample_median_size(train_X, train_Y, max_size=100000)
+        except ValueError as e: # not enough points for oversampling
+            print(f"Could not sample training data, using original distribution: {e}")
+        ####################
+        rfc = RandomForestClassifier(n_estimators=n_estimators, criterion=criterion, max_depth=max_depth,
+                                    min_samples_leaf=min_samples_leaf, min_impurity_decrease=min_impurity_decrease, 
+                                    bootstrap=bootstrap)
+        rfc.fit(train_X, train_Y)
+        ####################
+        print_report([rfc], [test_X], test_Y, ["X"])
+        ####################
+        export_model(rfc, use_case, layer_name)
+        
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/requirements.txt

+attrs==21.2.0
+backcall==0.2.0
+beautifulsoup4==4.9.3
+certifi==2021.5.30
+chardet==4.0.0
+charset-normalizer==2.0.3
+click==7.1.2
+clickclick==20.10.2
+colorama==0.4.4
+connexion==2.9.0
+cycler==0.10.0
+debugpy==1.4.0
+decorator==5.0.9
+Flask==1.1.4
+Flask-Cors==3.0.10
+idna==3.2
+imbalanced-learn==0.8.0
+imblearn==0.0
+importlib-metadata==3.10.1
+inflection==0.5.1
+ipykernel==6.0.3
+ipython==7.25.0
+ipython-genutils==0.2.0
+isodate==0.6.0
+itsdangerous==1.1.0
+jedi==0.18.0
+Jinja2==2.11.3
+joblib==1.0.1
+jsonschema==3.2.0
+jupyter-client==6.1.12
+jupyter-core==4.7.1
+kiwisolver==1.3.1
+libpysal==4.5.1
+MarkupSafe==2.0.1
+matplotlib==3.4.2
+matplotlib-inline==0.1.2
+numpy==1.21.1
+openapi-schema-validator==0.1.5
+openapi-spec-validator==0.3.1
+opencv-contrib-python==4.5.3.56
+pandas==1.3.0
+parso==0.8.2
+pickleshare==0.7.5
+Pillow==8.3.1
+pointpats==2.2.0
+prance==0.21.2
+prompt-toolkit==3.0.19
+Pygments==2.9.0
+pymongo==3.12.0
+pyparsing==2.4.7
+pyrsistent==0.18.0
+python-dateutil==2.8.2
+pytz==2021.1
+pywin32==301
+PyYAML==5.4.1
+pyzmq==22.1.0
+requests==2.26.0
+scikit-learn==0.24.2
+scipy==1.7.0
+semver==2.13.0
+six==1.16.0
+soupsieve==2.2.1
+swagger-ui-bundle==0.0.8
+threadpoolctl==2.2.0
+tornado==6.1
+traitlets==5.0.5
+typing-extensions==3.10.0.0
+urllib3==1.26.6
+wcwidth==0.2.5
+Werkzeug==1.0.1
+zipp==3.5.0

src/data-hub/proactive-community-detection-microservice/app/routes/predictions.py

+from flask import request, Response
+from db.repository import Repository
+from db.dao import PredictionResult
+
+repo = Repository()
+
+def get(use_case, table, layer_name):
+    res = repo.get_prediction_results(use_case)
+    if res is None or len(res) == 0:
+        return Response(status=404)
+    else:
+        return [c.__dict__ for c in res]

src/data-hub/proactive-community-detection-microservice/app/run_dataprep.py

+import sys
+import os
+modules_path = '../../../modules/'
+if os.path.exists(modules_path):
+    sys.path.insert(1, modules_path)
+
+
+from processing.data_prep.main import run
+
+if __name__ == '__main__':
+    '''Creates data/raw files'''
+    run(use_case='community-prediction-youtube-n')
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/run_layerpair_upload.py

+import sys
+import os
+modules_path = '../../../modules/'
+if os.path.exists(modules_path):
+    sys.path.insert(1, modules_path)
+
+from security.token_manager import TokenManager
+import network_constants
+from db.repository import Repository
+from db.dao import LayerPairDao
+
+from typing import List, Dict
+import requests
+import json
+
+
+def get_youtube_dependencies() -> List[LayerPairDao]:
+    uc = 'community-prediction-youtube-n'
+    layer_dependencies = [
+        ('CategoryLayer', 'CountryLayer'),
+        ('ViewsLayer', 'CountryLayer'),
+
+        ('ViewsLayer', 'CategoryLayer'),
+
+        ('LikesLayer', 'ViewsLayer'),
+        ('DislikesLayer', 'ViewsLayer'),
+        ('CommentCountLayer', 'ViewsLayer'),
+        ('TrendDelayLayer', 'ViewsLayer'),
+    ]
+    
+    return [LayerPairDao(uc, uc, ld[0], ld[1]) for ld in layer_dependencies]
+
+
+def get_taxi_dependencies() -> List[LayerPairDao]:
+    uc = 'community-prediction-taxi'
+    layer_dependencies = [
+        ('CallTypeLayer', 'DayTypeLayer'),
+
+        ('OriginCallLayer', 'CallTypeLayer'),
+        ('OriginStandLayer', 'CallTypeLayer'),
+
+        ('TaxiIdLayer', 'OriginStandLayer'),
+        ('StartLocationLayer', 'OriginStandLayer'),
+        ('EndLocationLayer', 'OriginStandLayer'),
+
+        ('StartLocationLayer', 'DayTypeLayer'),
+        ('EndLocationLayer', 'DayTypeLayer'),
+    ]
+    
+    return [LayerPairDao(uc, uc, ld[0], ld[1]) for ld in layer_dependencies]
+    
+
+def upload_layerpair(layerpair:LayerPairDao):
+    jwt = TokenManager.getInstance().getToken()
+
+    url = f'https://{network_constants.BUSINESS_LOGIC_HOSTNAME}:{network_constants.BUSINESS_LOGIC_REST_PORT}/api/use-cases/{layerpair.use_case}/tables/{layerpair.table}/layer-pairs'
+
+    response = requests.post(
+            url,
+            verify = False, 
+            proxies = { "http":None, "https":None },
+            headers = {"Authorization": f"Bearer {jwt}"},
+            json = layerpair.__dict__
+    )
+
+    if response.status_code != 200:
+        raise ConnectionError(f"Could not upload layer pair, statuscode: {response.status_code}!")
+
+
+if __name__ == '__main__':
+    '''Uploads the cross-context dependencies for all use-cases.'''
+    
+    assert False, 'replace with true to upload now'
+
+    for lp in get_youtube_dependencies():
+        upload_layerpair(lp)
+        
+    for lp in get_taxi_dependencies():
+        upload_layerpair(lp)
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/run_node_fetching.py

+import sys
+import os
+modules_path = '../../../modules/'
+if os.path.exists(modules_path):
+    sys.path.insert(1, modules_path)
+
+import json
+import urllib3
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+from processing.fetching import fetching
+
+if __name__ == "__main__":
+    '''Fetches all required data from business-logic and role-stage-discovery.'''
+    
+    fetching.fetch(selected_use_cases=['community-prediction-youtube-n'], selected_use_case_tables=None)
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/run_prediction.py

+import sys
+import os
+modules_path = '../../../modules/'
+if os.path.exists(modules_path):
+    sys.path.insert(1, modules_path)
+
+
+from db.repository import Repository
+from processing.ml.predict_single_context import run_prediction as run_single_prediction
+from processing.ml.predict_cross_context import run_prediction as run_cross_prediction
+
+
+if __name__ == '__main__':
+    '''Executes the predictions.'''
+
+    use_case='community-prediction-youtube-n'
+
+    repo = Repository()
+    repo.delete_all_prediction_results()
+
+    run_single_prediction(use_case)
+    run_cross_prediction(use_case)
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/run_training.py

+import sys
+import os
+modules_path = '../../../modules/'
+if os.path.exists(modules_path):
+    sys.path.insert(1, modules_path)
+
+
+from processing.ml.train_single_context import run_training as run_single_training
+from processing.ml.train_cross_context import run_training as run_cross_training
+
+if __name__ == '__main__':
+    '''Executes the training.'''
+
+    use_case='community-prediction-youtube-n'
+    run_single_training(use_case)
+    run_cross_training(use_case)
\ No newline at end of file

src/data-hub/proactive-community-detection-microservice/app/tests/test_ClusterMetricsCalculator.py

+import unittest
+import sys
+for path in ['../', './']:
+    sys.path.insert(1, path)
+
+# python -m unittest discover
+from processing import ClusterMetricsCalculator2D
+
+
+class TestClusterMetricsCalculator(unittest.TestCase):
+    
+    def test__get_standard_deviation__same_points_many_decimals__zero_and_not_nan(self):
+        nodes = [{'f1': -8.58564, 'f2': 41.148567},
+                {'f1': -8.58564, 'f2': 41.148567},
+                {'f1': -8.58564, 'f2': 41.148567},
+                {'f1': -8.58564, 'f2': 41.148567},
+                {'f1': -8.58564, 'f2': 41.148567},
+                {'f1': -8.58564, 'f2': 41.148567},
+                {'f1': -8.58564, 'f2': 41.148567},
+                {'f1': -8.58564, 'f2': 41.148567},
+                {'f1': -8.58564, 'f2': 41.148567}]
+        calc = ClusterMetricsCalculator2D(nodes, ['f1','f2'], len(nodes), 1)
+        
+        self.assertAlmostEqual(0, calc.get_standard_deviation())
+
+    def test__get_range__almost_linear_distribution_in_2d__euclidean_distance(self):
+        l = [(-8.657802, 41.160978), (-8.65782, 41.160969), (-8.657838, 41.16096)]
+        nodes = [{'f1': e[0], 'f2': e[1]} for e in l]
+        
+        calc = ClusterMetricsCalculator2D(nodes, ['f1','f2'], len(nodes), 1)
+        
+        # https://www.calculatorsoup.com/calculators/geometry-plane/distance-two-points.php
+        self.assertAlmostEqual(4.0E-5, calc.get_range(), 5)
+    
+
+if __name__ == '__main__':
+    unittest.main()

src/data-hub/proactive-community-detection-microservice/app/tests/test_cluster.py

+import unittest
+import sys
+for path in ['../', './']:
+    sys.path.insert(1, path)
+
+# python -m unittest discover
+from entities import Cluster, TimeWindow
+
+from typing import Any, Tuple
+from datetime import date, datetime
+import json
+from math import sqrt
+import statistics as stat
+
+
+class TestCluster(unittest.TestCase):
+    def test__init__single_cluster__all_values_set(self):
+        tw, centers = self._get_timewindow_single_cluster_same_feature()
+
+        c = Cluster("time_abc", "clusterId 1", list(tw.clusters.values())[0], "feature", nr_layer_nodes=3, layer_diversity=1, global_cluster_center=centers['1'])
+        
+        self.assertEqual("time_abc", c.time_window_id)
+        self.assertEqual("clusterId 1", c.cluster_id)
+        self.assert_cluster((3, 0, 0, 1, 1), c)
+        self.assertEqual(c.range_, 0)
+        self.assertEqual(c.center, (1,0))
+        self.assertEqual(c.global_center_distance, 0)
+
+    def test__create_multiple_from_time_window__single_cluster__all_values_set(self):
+        tw, centers = self._get_timewindow_single_cluster_same_feature()
+        
+        clusters = list(Cluster.create_multiple_from_time_window(tw, "feature", centers))
+        self.assertEqual(1, len(clusters))
+        c = clusters[0]
+
+        self.assertEqual("KW1", c.time_window_id)
+        self.assertEqual("1", c.cluster_id)
+        self.assert_cluster((3, 0, 0, 1, 1), c)
+
+    def test__create_multiple_from_time_window__two_clusters__correct_time_id_cluster_id(self):
+        tw, centers = self._get_timewindow_two_clusters_same_feature()
+        
+        clusters = Cluster.create_multiple_from_time_window(tw, "feature", centers)
+        expected = [("KW1", "1"), ("KW1", "2")]
+
+        for c, exp in zip(clusters, expected):
+            self.assertEqual(exp[0], c.time_window_id)
+            self.assertEqual(exp[1], c.cluster_id)
+
+    def test__create_multiple_from_time_window__two_clusters_same_features__correct_calculation(self):
+        tw, centers = self._get_timewindow_two_clusters_same_feature()
+
+        clusters = Cluster.create_multiple_from_time_window(tw, "feature", centers)
+        expected = [(3, 0, 0, 3/5, 1/2), (2, 0, 0, 2/5, 1/2)]
+
+        for c, exp in zip(clusters, expected):
+            self.assert_cluster(exp, c)
+
+    def test__create_multiple_from_time_window__two_clusters_same_features_and_feature_names_list__correct_calculation(self):
+        tw, centers = self._get_timewindow_two_clusters_same_feature()
+
+        clusters = Cluster.create_multiple_from_time_window(tw, ["feature"], centers)
+        expected = [(3, 0, 0, 3/5, 1/2), (2, 0, 0, 2/5, 1/2)]
+
+        for c, exp in zip(clusters, expected):
+            self.assert_cluster(exp, c)
+
+    def test__create_multiple_from_time_window__two_clusters_different_features__correct_calculation(self):
+        tw = TimeWindow("CW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature":1})
+        tw.add_node_to_cluster("1", {"feature":2})
+        tw.add_node_to_cluster("1", {"feature":3})
+        tw.add_node_to_cluster("2", {"feature":70})
+        tw.add_node_to_cluster("2", {"feature":75})
+
+        centers = {'1':(2,0),'2':(72.5,0)}
+
+        clusters = Cluster.create_multiple_from_time_window(tw, "feature", centers)
+        # variance for stddev calculated with: http://www.alcula.com/calculators/statistics/variance/
+        expected = [(3, sqrt(2.0/3), 2.0/3, 3/5, 1/2), (2, sqrt(6.25), 5.0/2, 2/5, 1/2)]
+
+        for cluster, exp in zip(clusters, expected):
+            self.assert_cluster(exp, cluster)
+
+    def test__create_multiple_from_time_window__empty_cluster__all_zero_for_empty_cluster(self):
+        tw = TimeWindow("CW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature":1})
+        tw.add_node_to_cluster("1", {"feature":2})
+        tw.add_node_to_cluster("1", {"feature":3})
+        tw.add_node_to_cluster("2", {"feature":70})
+        tw.add_node_to_cluster("2", {"feature":75})
+        tw.clusters["3"] = []
+
+        centers = {'1':(2,0),'2':(72.5,0),'3':(0,0)}
+
+        clusters = Cluster.create_multiple_from_time_window(tw, "feature", centers)
+        expected = [(3, sqrt(2.0/3), 2.0/3, 3/5, 1/2), # diversity is still 2 as len=0 is ignored
+                    (2, sqrt(6.25), 5.0/2, 2/5, 1/2),
+                    (0, 0, 0, 0, 0)] # len 0 -> everything 0
+
+        for cluster, exp in zip(clusters, expected):
+            self.assert_cluster(exp, cluster)
+
+    def test__create_multiple_from_time_window__2d_clustering_single_feature_value__no_stddev_no_scarcity(self):
+        tw = TimeWindow("CW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"f1":1, "f2":1})
+        tw.add_node_to_cluster("1", {"f1":1, "f2":1})
+        tw.add_node_to_cluster("1", {"f1":1, "f2":1})
+        tw.add_node_to_cluster("2", {"f1":70, "f2":70})
+        tw.add_node_to_cluster("2", {"f1":70, "f2":70})
+        
+        centers = {'1':(1,1),'2':(70,70)}
+
+        clusters = Cluster.create_multiple_from_time_window(tw, ["f1", "f2"], centers)
+        expected = [(3, 0, 0, 3/5, 1/2), (2, 0, 0, 2/5, 1/2)]
+
+        for cluster, exp in zip(clusters, expected):
+            self.assert_cluster(exp, cluster)
+
+    def test__create_multiple_from_time_window__2d_clustering__correct_stddev_and_scarcity(self):
+        tw = TimeWindow("CW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"f1":1, "f2":1})
+        tw.add_node_to_cluster("1", {"f1":2, "f2":1})
+        tw.add_node_to_cluster("1", {"f1":1, "f2":3})
+        tw.add_node_to_cluster("2", {"f1":70, "f2":70})
+        tw.add_node_to_cluster("2", {"f1":72, "f2":75})
+
+        centers = {'1':(4/3,5/3),'2':(71,72.5)}
+
+        clusters = Cluster.create_multiple_from_time_window(tw, ["f1", "f2"], centers)
+        # stddev calculated manually as in: https://glenbambrick.com/tag/standard-distance/
+        # area of the polygon calculated with: https://www.mathopenref.com/coordpolygonareacalc.html
+        expected = [(3, sqrt(2/9+8/9), sqrt(1/3), 3/5, 1/2), (2, sqrt(7.25), sqrt(2*2+5*5)/2, 2/5, 1/2)] 
+
+        for cluster, exp in zip(clusters, expected):
+            self.assert_cluster(exp, cluster)
+                        
+    def test__create_multiple_from_time_window__2d_clustering_complex__correct_stddev_and_scarcity(self):
+        tw = TimeWindow("CW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"f1":0, "f2":0})
+        tw.add_node_to_cluster("1", {"f1":1, "f2":3})
+        tw.add_node_to_cluster("1", {"f1":3, "f2":2})
+        tw.add_node_to_cluster("1", {"f1":0, "f2":2})
+        tw.add_node_to_cluster("1", {"f1":1, "f2":2}) # inside the convex hull
+        tw.add_node_to_cluster("1", {"f1":2, "f2":2}) # inside the convex hull
+        tw.add_node_to_cluster("1", {"f1":2, "f2":1})
+
+        centers = {'1':((1+3+1+2+2)/7,(3+2+2+2+2+1)/7)}
+
+        clusters = Cluster.create_multiple_from_time_window(tw, ["f1", "f2"], centers)
+
+        # stddev calculated manually as in: https://glenbambrick.com/tag/standard-distance/
+        X = [0,1,3,0,1,2,2]
+        Y = [0,3,2,2,2,2,1]
+        x_mean = stat.mean(X)
+        y_mean = stat.mean(Y)
+        sum_x = 0
+        for x in X:
+            sum_x += (x - x_mean)**2
+        sum_y = 0
+        for y in Y:
+            sum_y += (y - y_mean)**2
+        sd = sqrt(sum_x/7 + sum_y/7)
+
+        # area of the polygon calculated with: https://www.mathopenref.com/coordpolygonareacalc.html
+        area = 5
+        scarcity = sqrt(area / 7)
+
+        expected = [[7, sd, scarcity, 1, 1]]
+
+        for cluster, exp in zip(clusters, expected):
+            self.assert_cluster(exp, cluster)
+
+    def test__create_multiple_from_time_window__2d_clustering_1d_single_feature_value__correct_calculation(self):
+        tw = TimeWindow("CW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"f1":1, "f2":1})
+        tw.add_node_to_cluster("1", {"f1":1, "f2":2})
+        tw.add_node_to_cluster("1", {"f1":1, "f2":3})
+        tw.add_node_to_cluster("2", {"f1":70, "f2":70})
+        tw.add_node_to_cluster("2", {"f1":75, "f2":70})
+        tw.add_node_to_cluster("2", {"f1":72, "f2":70})
+        tw.add_node_to_cluster("2", {"f1":71, "f2":70})
+
+        centers = {'1':(1,2),'2':((70+75+72+71)/4,70)}
+
+        clusters = Cluster.create_multiple_from_time_window(tw, ["f1", "f2"], centers)
+        # variance/stddev calculated as for 1d cluster (as f1/f2 is always the same)
+        # scarcity calculated as for 1d cluster 
+        expected = [(3, sqrt(2/3), 2/3, 3/7, 1/2), 
+                    (4, sqrt(3.5), 5/4, 4/7, 1/2)] 
+
+        for cluster, exp in zip(clusters, expected):
+            self.assert_cluster(exp, cluster)
+
+    def test__create_multiple_from_time_window__1d_clusters__correct_cluster_range_and_center(self):
+        tw = TimeWindow("CW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"f1":1})
+        tw.add_node_to_cluster("1", {"f1":2})
+        tw.add_node_to_cluster("1", {"f1":1})
+        tw.add_node_to_cluster("2", {"f1":70})
+        tw.add_node_to_cluster("2", {"f1":72})
+
+        centers = {'1':(4/3, 0),'2':(71,0)}
+
+        clusters = Cluster.create_multiple_from_time_window(tw, ["f1"], centers)
+        expected = [(1, (4/3,0)), (2, (71,0))] # (range, center)
+
+        for c, exp in zip(clusters, expected):
+            self.assertEqual(c.range_, exp[0])
+            self.assertEqual(c.center, exp[1])
+
+    def test__create_multiple_from_time_window__2d_clusters__correct_cluster_range_and_center(self):
+        tw = TimeWindow("CW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"f1":1, "f2":1})
+        tw.add_node_to_cluster("1", {"f1":2, "f2":1})
+        tw.add_node_to_cluster("1", {"f1":1, "f2":3})
+        tw.add_node_to_cluster("2", {"f1":70, "f2":70})
+        tw.add_node_to_cluster("2", {"f1":72, "f2":75})
+        
+        centers = {'1':(4/3,5/3),'2':(71,72.5)}
+
+        clusters = Cluster.create_multiple_from_time_window(tw, ["f1","f2"], centers)
+        # https://www.triangle-calculator.com/de/?what=vc&a=1&a1=1&3dd=3D&a2=&b=2&b1=1&b2=&c=1&c1=3&c2=&submit=Berechnen&3d=0
+        # https://www.calculatorsoup.com/calculators/geometry-plane/distance-two-points.php
+        expected = [(1, (4/3,5/3)), (5.385165, (71,72.5))] # (range, center)
+
+        for c, exp in zip(clusters, expected):
+            self.assertAlmostEqual(c.range_, exp[0], places=6)
+            self.assertEqual(c.center, exp[1])
+
+    def test__create_multiple_from_time_window__2d_clusters__correct_linear_global_center_distance(self):
+        tw = TimeWindow("CW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"f1":1, "f2":2})
+        tw.add_node_to_cluster("1", {"f1":1, "f2":2})
+        tw.add_node_to_cluster("1", {"f1":1, "f2":2})
+        tw.add_node_to_cluster("2", {"f1":70, "f2":70})
+        tw.add_node_to_cluster("2", {"f1":72, "f2":75})
+        
+        centers = {'1':(1,1),'2':(71,70)}
+
+        clusters = Cluster.create_multiple_from_time_window(tw, ["f1","f2"], centers)
+        expected = [1, 2.5] # euclidean dist
+
+        for c, exp in zip(clusters, expected):
+            self.assertAlmostEqual(c.global_center_distance, exp, places=6)
+
+    def test__create_multiple_from_time_window__1d_clusters__correct_euclidean_global_center_distance(self):
+        tw = TimeWindow("CW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"f1":1})
+        tw.add_node_to_cluster("1", {"f1":1})
+        tw.add_node_to_cluster("1", {"f1":1})
+        tw.add_node_to_cluster("2", {"f1":70})
+        tw.add_node_to_cluster("2", {"f1":72})
+        
+        centers = {'1':(1,0),'2':(70,0)}
+
+        clusters = Cluster.create_multiple_from_time_window(tw, ["f1"], centers)
+        # https://www.calculatorsoup.com/calculators/geometry-plane/distance-two-points.php
+        expected = [0, 1] # euclidean dist
+
+        for c, exp in zip(clusters, expected):
+            self.assertAlmostEqual(c.global_center_distance, exp, places=6)
+            
+    def test__create_multiple_from_time_window__2d_clusters__correct_euclidean_global_center_distance(self):
+        tw = TimeWindow("CW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"f1":1, "f2":2})
+        tw.add_node_to_cluster("1", {"f1":1, "f2":2})
+        tw.add_node_to_cluster("1", {"f1":1, "f2":2})
+        tw.add_node_to_cluster("2", {"f1":70, "f2":70})
+        tw.add_node_to_cluster("2", {"f1":72, "f2":75})
+        
+        centers = {'1':(0,0),'2':(70,70)}
+
+        clusters = Cluster.create_multiple_from_time_window(tw, ["f1","f2"], centers)
+        # https://www.calculatorsoup.com/calculators/geometry-plane/distance-two-points.php
+        expected = [2.236068,  2.692582] # euclidean dist
+
+        for c, exp in zip(clusters, expected):
+            self.assertAlmostEqual(c.global_center_distance, exp, places=6)
+
+
+#region setup methods
+    def _get_timewindow_single_cluster_same_feature(self) -> TimeWindow:
+        '''Returns a TimeWindow with time=KW1 and three nodes in cluster 1, all feature values = 1.'''
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature":1})
+        tw.add_node_to_cluster("1", {"feature":1})
+        tw.add_node_to_cluster("1", {"feature":1})
+
+        global_centers = {'1':(1,0)}
+
+        return tw, global_centers
+
+    def _get_timewindow_two_clusters_same_feature(self) -> TimeWindow:
+        '''
+        Returns a TimeWindow with time=KW1 and:
+        Three nodes in cluster 1, all feature values = 1.
+        Two nodes in cluster 2, all feature values = 2.
+        '''
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature":1})
+        tw.add_node_to_cluster("1", {"feature":1})
+        tw.add_node_to_cluster("1", {"feature":1})
+        tw.add_node_to_cluster("2", {"feature":2})
+        tw.add_node_to_cluster("2", {"feature":2})
+
+        global_centers = {'1':(1,0),'2':(2,0)}
+
+        return tw, global_centers
+
+#endregion setup methods
+
+#region custom asserts
+    def assert_cluster(self, expected_values: Tuple[Any], cluster: Cluster):
+        """
+        Checks if the cluster values equal the expected_values.
+
+        :param expected_values: A tuple (exp_size, exp_stddev, exp_scarcity, exp_import1, exp_import2)
+        """
+        self.assertEqual(expected_values[0], cluster.size)
+        self.assertAlmostEqual(expected_values[1], cluster.std_dev)
+        self.assertAlmostEqual(expected_values[2], cluster.scarcity)
+        
+        self.assertAlmostEqual(expected_values[3], cluster.importance1)
+        self.assertAlmostEqual(expected_values[4], cluster.importance2)
+
+#endregion custom asserts
+
+
+if __name__ == '__main__':
+    unittest.main()

src/data-hub/proactive-community-detection-microservice/app/tests/test_layer.py

+import unittest
+import sys
+for path in ['../', './']:
+    sys.path.insert(1, path)
+
+# python -m unittest discover
+from entities import Layer, TimeWindow
+from entities.layer import InternalCluster
+
+
+from typing import Any, Tuple, List
+from datetime import date, datetime
+import json
+from math import sqrt
+import statistics as stat
+
+
+class TestInternalCluster(unittest.TestCase):
+    def test__init__1d_features__all_values_set(self):
+        cluster_nodes = [{"feature":1}, {"feature":1}, {"feature":1}]
+
+        c = InternalCluster("123", cluster_nodes, feature_names=["feature"], global_cluster_center=(1.5,0), n_layer_nodes=len(cluster_nodes))
+        
+        self.assert_internal_cluster(c, '123', 3, .5)
+
+    def test__init__2d_features__all_values_set(self):
+        cluster_nodes = [{"feature1":1,'feature2':1}, {"feature1":1,'feature2':1}, {"feature1":1,'feature2':1}]
+
+        c = InternalCluster("123", cluster_nodes, feature_names=["feature1", 'feature2'], global_cluster_center=(1.5,1.5), n_layer_nodes=len(cluster_nodes))
+        
+        # distance: https://www.calculatorsoup.com/calculators/geometry-plane/distance-two-points.php
+        self.assert_internal_cluster(c, '123', 3, sqrt(.5))
+
+    def test__get_current_cluster_center__1d(self):
+        cluster_nodes = [{"feature":1}, {"feature":2}, {"feature":3}]
+
+        c = InternalCluster("123", cluster_nodes, feature_names=["feature"], global_cluster_center=(2, 0), n_layer_nodes=len(cluster_nodes))
+
+        self.assert_internal_cluster(c, '123', 3, 0)
+        
+
+    def test__get_current_cluster_center__1d_weighted_result(self):
+        cluster_nodes = [{"feature":1}, {"feature":1}, {"feature":3}]
+
+        c = InternalCluster("123", cluster_nodes, feature_names=["feature"], global_cluster_center=(5/3, 0), n_layer_nodes=len(cluster_nodes))
+        
+        self.assert_internal_cluster(c, '123', 3, 0)
+
+    def test__get_current_cluster_center__2d_weighted_result(self):
+        cluster_nodes = [{"feature1":1,"feature2":1},
+                         {"feature1":1,"feature2":1},
+                         {"feature1":2,"feature2":2},
+                         {"feature1":3,"feature2":1}]
+
+        c = InternalCluster("123", cluster_nodes, feature_names=["feature1", 'feature2'], global_cluster_center=(1.75, 1.25), n_layer_nodes=len(cluster_nodes))
+        
+        self.assert_internal_cluster(c, '123', 4, 0)
+
+    def assert_internal_cluster(self, actual_cluster: InternalCluster, expected_id, expected_size, expected_distance):
+        self.assertEqual(expected_id, actual_cluster.cluster_id)
+        self.assertEqual(expected_size, actual_cluster.size)
+        self.assertAlmostEqual(expected_distance, actual_cluster.global_center_distance) 
+
+
+class TestLayer(unittest.TestCase):
+    def test__init__1d_single_cluster(self):
+        cluster_nodes = list(self._get_timewindow_single_cluster_1d_same_feature().clusters.values())[0]
+        c = InternalCluster("123", cluster_nodes, feature_names=["feature"], global_cluster_center=(1,0), n_layer_nodes=len(cluster_nodes))
+
+        l = Layer('123', [c])
+
+        self.assert_layer(l, [1], 0, [0])
+
+    def test__create_from_time_window__1d_single_cluster(self):
+        tw = self._get_timewindow_single_cluster_1d_same_feature()
+        l = Layer.create_from_time_window(tw, feature_names=['feature'], global_cluster_centers={'1': (1,0)})
+
+        self.assert_layer(l, [1], 0, [0])
+
+    def test__create_from_time_window__2d_single_cluster(self):
+        tw = self._get_timewindow_single_cluster_2d_same_feature()
+        l = Layer.create_from_time_window(tw, feature_names=['feature1', 'feature2'], global_cluster_centers={'1': (1,1)})
+
+        self.assert_layer(l, [1], 0, [0])
+
+    def test__create_from_time_window__1d_two_clusters(self):
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature1":1})
+        tw.add_node_to_cluster("1", {"feature1":1})
+        tw.add_node_to_cluster("2", {"feature1":5})
+        tw.add_node_to_cluster("2", {"feature1":5})
+        tw.add_node_to_cluster("2", {"feature1":7})
+        tw.add_node_to_cluster("2", {"feature1":6})
+
+        l = Layer.create_from_time_window(tw, feature_names=['feature1'], global_cluster_centers={'1': (1.5,0), '2': (5,0)})
+
+        # entropy: https://planetcalc.com/2476/
+        # distance: https://www.calculatorsoup.com/calculators/geometry-plane/distance-two-points.php
+        self.assert_layer(l, [2/6, 4/6], 0.91829583, [.5, .75])
+
+    def test__create_from_time_window__2d_two_clusters(self):
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":1})
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":2})
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":2})
+        tw.add_node_to_cluster("2", {"feature1":5,"feature2":5})
+        tw.add_node_to_cluster("2", {"feature1":7,"feature2":4})
+
+        l = Layer.create_from_time_window(tw, feature_names=['feature1', 'feature2'], global_cluster_centers={'1': (1,1), '2': (6.5,5)})
+
+        # entropy: https://planetcalc.com/2476/
+        # distance: https://www.calculatorsoup.com/calculators/geometry-plane/distance-two-points.php
+        self.assert_layer(l, [3/5, 2/5], 0.97095059, [2/3, sqrt(.5)])
+
+    def test__create_from_time_window__1d_clusters_correct_nodes_clusters(self):
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature1":1})
+        tw.add_node_to_cluster("1", {"feature1":1})
+        tw.add_node_to_cluster("1", {"feature1":1})
+        tw.add_node_to_cluster("2", {"feature1":5,"feature2":5})
+        tw.add_node_to_cluster("2", {"feature1":7})
+
+        l = Layer.create_from_time_window(tw, feature_names=['feature1'], global_cluster_centers={'1': (1,1), '2': (6.5,5)})
+
+        self.assertEqual(l.n_nodes, 5)
+        self.assertEqual(l.n_clusters, 2)
+        
+    def test__create_from_time_window__2d_clusters_correct_nodes_clusters(self):
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":1})
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":2})
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":2})
+        tw.add_node_to_cluster("2", {"feature1":5,"feature2":5})
+        tw.add_node_to_cluster("2", {"feature1":7,"feature2":4})
+
+        l = Layer.create_from_time_window(tw, feature_names=['feature1', 'feature2'], global_cluster_centers={'1': (1,1), '2': (6.5,5)})
+
+        self.assertEqual(l.n_nodes, 5)
+        self.assertEqual(l.n_clusters, 2)
+
+    def test__create_from_time_window__1d_clusters__correct_size_aggregate_metrics(self):
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature1":1})
+        tw.add_node_to_cluster("1", {"feature1":1})
+        tw.add_node_to_cluster("1", {"feature1":1})
+        tw.add_node_to_cluster("2", {"feature1":5,"feature2":5})
+        tw.add_node_to_cluster("2", {"feature1":7})
+
+        l = Layer.create_from_time_window(tw, feature_names=['feature1'], global_cluster_centers={'1': (1,0), '2': (6.5,5)})
+
+        self.assertEqual(l.cluster_size_agg_metrics, {'min':2, 'max':3, 'sum':5, 'avg':2.5})
+        self.assertEqual(l.cluster_relative_size_agg_metrics, {'min':2/5, 'max':3/5, 'sum':1, 'avg':(1/2)})
+
+    def test__create_from_time_window__2d_clusters__correct_size_aggregate_metrics(self):
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":1})
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":2})
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":2})
+        tw.add_node_to_cluster("2", {"feature1":5,"feature2":5})
+        tw.add_node_to_cluster("2", {"feature1":7,"feature2":4})
+
+        l = Layer.create_from_time_window(tw, feature_names=['feature1', 'feature2'], global_cluster_centers={'1': (1,1), '2': (6.5,5)})
+
+        self.assertEqual(l.cluster_size_agg_metrics, {'min':2, 'max':3, 'sum':5, 'avg':2.5})
+        self.assertEqual(l.cluster_relative_size_agg_metrics, {'min':2/5, 'max':3/5, 'sum':1, 'avg':(1/2)})
+                
+    def test__create_from_time_window__1d_clusters__correct_center_distance_aggregate_metrics(self):
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature1":1})
+        tw.add_node_to_cluster("1", {"feature1":1})
+        tw.add_node_to_cluster("1", {"feature1":1})
+        tw.add_node_to_cluster("2", {"feature1":5,"feature2":5})
+        tw.add_node_to_cluster("2", {"feature1":7})
+
+        l = Layer.create_from_time_window(tw, feature_names=['feature1'], global_cluster_centers={'1': (1.1,0), '2': (6.5,0)})
+        expected = {'min':0.1, 'max':0.5, 'sum':0.6, 'avg':0.3}
+
+        self.assertEqual(len(l.cluster_center_distance_agg_metrics.items()), 4)
+        for k in ['min', 'max', 'sum', 'avg']:
+            self.assertAlmostEqual(l.cluster_center_distance_agg_metrics[k], expected[k])
+
+    def test__create_from_time_window__2d_clusters__correct_center_distance_aggregate_metrics(self):
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":1})
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":2})
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":2})
+        tw.add_node_to_cluster("2", {"feature1":5,"feature2":5})
+        tw.add_node_to_cluster("2", {"feature1":7,"feature2":4})
+
+        l = Layer.create_from_time_window(tw, feature_names=['feature1', 'feature2'], global_cluster_centers={'1': (1,1), '2': (6.5,5)})
+        expected = {'min':2/3, 'max':sqrt(.5), 'sum':sqrt(.5)+2/3, 'avg':(sqrt(.5)+2/3)/2}        
+
+        self.assertEqual(len(l.cluster_center_distance_agg_metrics.items()), 4)
+        for k in ['min', 'max', 'sum', 'avg']:
+            self.assertAlmostEqual(l.cluster_center_distance_agg_metrics[k], expected[k])
+
+    def test__create_from_time_window__empty_layer__correct_size_and_centerdist_aggregate_metrics(self):
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+
+        l = Layer.create_from_time_window(tw, feature_names=['feature1'], global_cluster_centers={'1': (1,0), '2': (6.5,5)})
+        expected = {'min':0, 'max':0, 'sum':0, 'avg':0}
+
+        self.assertEqual(l.cluster_size_agg_metrics, expected)
+        self.assertEqual(l.cluster_relative_size_agg_metrics, expected)
+        self.assertEqual(l.cluster_center_distance_agg_metrics, expected)
+
+    def test__create_from_time_window__1d_clusters_correct_centers(self):
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":1})
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":2})
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":2})
+        tw.add_node_to_cluster("2", {"feature1":5,"feature2":5})
+        tw.add_node_to_cluster("2", {"feature1":7,"feature2":4})
+
+        l = Layer.create_from_time_window(tw, feature_names=['feature1'], global_cluster_centers={'1': (1,1), '2': (6.5,5)})
+
+        for exp, act in zip([(1,0), (6,0)], l.centers):
+            for exp_dim, act_dim in zip(exp, act):
+                self.assertAlmostEqual(exp_dim, act_dim)
+
+    def test__create_from_time_window__2d_clusters_correct_centers(self):
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":1})
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":2})
+        tw.add_node_to_cluster("1", {"feature1":1,"feature2":2})
+        tw.add_node_to_cluster("2", {"feature1":5,"feature2":5})
+        tw.add_node_to_cluster("2", {"feature1":7,"feature2":4})
+
+        l = Layer.create_from_time_window(tw, feature_names=['feature1', 'feature2'], global_cluster_centers={'1': (1,1), '2': (6.5,5)})
+
+        for exp, act in zip([(1,1.66666666666), (6,4.5)], l.centers):
+            for exp_dim, act_dim in zip(exp, act):
+                self.assertAlmostEqual(exp_dim, act_dim)
+
+
+    #region setup methods
+    def _get_timewindow_single_cluster_1d_same_feature(self) -> TimeWindow:
+        '''Returns a TimeWindow with time=KW1 and three nodes in cluster 1, all feature values = 1.'''
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature":1})
+        tw.add_node_to_cluster("1", {"feature":1})
+        tw.add_node_to_cluster("1", {"feature":1})
+        return tw
+
+    def _get_timewindow_single_cluster_2d_same_feature(self) -> TimeWindow:
+        '''Returns a TimeWindow with time=KW1 and three nodes in cluster 1, all feature1 & feature2 values = 1.'''
+        tw = TimeWindow("KW1", "uc", "uct", "ln")
+        tw.add_node_to_cluster("1", {"feature1":1, "feature2":1})
+        tw.add_node_to_cluster("1", {"feature1":1, "feature2":1})
+        tw.add_node_to_cluster("1", {"feature1":1, "feature2":1})
+        return tw
+
+    #endregion setup methods
+
+    def assert_layer(self, actual_layer: Layer, relative_sizes: List[float], entropy: float, center_dist: List[float]):
+        self.assertEqual(len(actual_layer.relative_cluster_sizes), len(relative_sizes))
+        for i in range(len(relative_sizes)):
+            self.assertAlmostEqual(relative_sizes[i], actual_layer.relative_cluster_sizes[i])
+
+        self.assertAlmostEqual(entropy, actual_layer.entropy)
+
+        self.assertEqual(len(actual_layer.distances_from_global_centers), len(center_dist))   
+        for i in range(len(center_dist)):
+            self.assertAlmostEqual(center_dist[i], actual_layer.distances_from_global_centers[i])
+
+
+if __name__ == '__main__':
+    unittest.main()

src/data-hub/role-stage-discovery-microservice/app/_predictions/.gitignore

+# ignore this folder because it contains raw jsons for the community-prediction task
+**
+!.gitignore
\ No newline at end of file

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

@@ -162,7 +162,7 @@ paths:
             '404':
                 description: "Layer not found"
 
-  /use-cases/{use_case}/tables{table}/layers/{layer_name}/timeslices:
+  /use-cases/{use_case}/tables/{table}/layers/{layer_name}/timeslices:
     get:
         operationId: "routes.timeslices.get_by_name"
         security:

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

@@ -23,14 +23,22 @@ class TimeSlice:
         if time_slice_dict is not None:
             self.from_serializable_dict(time_slice_dict, from_db)
 
+    def init_all_clusters(self, cluster_labels: List[str]):
+        '''Initializes internal clusters for all labels with an empty list.'''
+        for cluster_label in cluster_labels:
+            # only string keys can be stored in json
+            cluster_label = str(cluster_label)
+            self.clusters[cluster_label] = []
+
     def add_node_to_cluster(self, cluster_label: str, node):
         # only string keys can be stored in json
         cluster_label = str(cluster_label)
 
         if cluster_label not in self.clusters:
-            self.clusters[cluster_label] = []
+            # self.clusters[cluster_label] = []
+            raise KeyError(f"self::init_all_clusters must be used to add all global cluster labels beforehand (got {cluster_label})")
 
-        node = self._get_unique_id(node)
+        # node = self._get_unique_id(node)
         self.clusters[cluster_label].append(node)
 
     def get_nodes_for_cluster(self, cluster_label: str):

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

@@ -73,7 +73,7 @@ class Repository(MongoRepositoryBase):
     def add_layer_nodes(self, nodes:List[dict]):
         super().insert_many(self._layer_nodes_collection, nodes)
 
-    def get_layer_nodes(self, use_case: str, use_case_table: str, layer_name: str) -> dict:
+    def get_layer_nodes(self, use_case: str, use_case_table: str, layer_name: str) -> List[dict]:
         '''Returns all nodes for the use-case and layer.'''
         entries = super().get_entries(self._layer_nodes_collection, selection={'use_case': use_case, 'use_case_table': use_case_table, 'layer_name': layer_name}, projection={'_id': 0})
         return [e for e in entries]

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

@@ -13,12 +13,16 @@ from typing import Tuple, Dict, Any, List
 TimeSliceKey = Tuple[int, int]
 
 # TODO extract information about time features (maybe from table mapping)
-TIME_PROPERTY_NAMES = ['Timestamp']
+TIME_PROPERTY_NAMES = ['timestamp']
+
+repo = Repository()
+
 
 def convert_to_time_slice_key(timestamp: str) -> TimeSliceKey:
     '''Returns the tuple (year, week_of_year) from a timestamp. This is used as the key for the slicing.'''
     # time = datetime.utcfromtimestamp(float(timestamp[0:10]))
-    time = datetime.strptime(timestamp, '%Y-%m-%d %H:%M:%S')
+    # time = datetime.strptime(timestamp, '%Y-%m-%d %H:%M:%S')
+    time = datetime.utcfromtimestamp(float(timestamp))
     (y, w, _) = time.isocalendar()
     return (y, w)
 
@@ -34,10 +38,16 @@ def split_clusterset_by_time(layer: Layer, clusters: List[Cluster]) -> Dict[Time
     '''
 
     time_slices: Dict[Any, TimeSlice] = {} 
-    for cluster_no in clusters:
-        for node in cluster_no.nodes:
+    all_cluster_labels = [cluster.cluster_label for cluster in clusters if cluster.cluster_label != -1]
+
+    for cluster in clusters:
+        if cluster.cluster_label == -1:
+            print("Noise cluster was ignored.")
+            continue
+
+        for node in cluster.nodes:
 
-            # retrieve times the node is located in based on the defined time properties in the schema
+            # retrieve times where the node is located inas (year, week), based on the defined timestamp fields in the schema
             time_keys = set()
             for time_property in TIME_PROPERTY_NAMES:
                 if time_property in node:
@@ -46,28 +56,66 @@ def split_clusterset_by_time(layer: Layer, clusters: List[Cluster]) -> Dict[Time
             for time_key in time_keys:
                 if time_key not in time_slices:
                     time_slices[time_key] = TimeSlice(time_key, layer.use_case, layer.use_case_table, layer.layer_name)
+                    time_slices[time_key].init_all_clusters(all_cluster_labels)
 
-                time_slices[time_key].add_node_to_cluster(cluster_no.cluster_label, node)
+                time_slices[time_key].add_node_to_cluster(cluster.cluster_label, node)
 
     return time_slices
         
 
-if __name__ == "__main__":
-    repo = Repository()
+def get_layers() -> List[Layer]:
+    return repo.get_layers()
+
+def get_clusters_for_layer(use_case, use_case_table, layer_name)-> List[Cluster]:
+    # return repo.get_clusters_for_layer(use_case, use_case_table, layer_name)
+    json_path = f'_predictions/clusters/{layer_name}.json'
+
+    if os.path.exists(json_path):
+        with open(json_path, 'r') as file:
+            return [Cluster(cluster_dict=e, from_db=False) for e in json.loads(file.read())]
+
+    return []
 
-    repo.remove_all_time_slices()
+def get_layer_nodes(use_case, use_case_table, layer_name)-> List[dict]:
+    # return repo.get_layer_nodes(use_case, use_case_table, layer_name)
+    return []
 
-    layers = repo.get_layers()
+def add_time_slice(timeslice):
+    try:
+        repo.add_time_slice(timeslice)  
+        pass
+    except:
+        print(f"Error while storing time slice in db for {timeslice.layer_name}")
+
+    # try:
+    #     json_path = f'_predictions/timeslices/{timeslice.layer_name}/{timeslice.time}.json'.replace(', ', '_').replace('(', '').replace(')', '')
+    #     if not os.path.exists(os.path.dirname(json_path)):
+    #         os.makedirs(os.path.dirname(json_path))
+
+    #     with open(json_path, 'w') as file:
+    #         file.write(json.dumps(timeslice.to_serializable_dict(for_db=False)))
+    # except Exception as e:
+    #     print(f"Error while writing json for {timeslice.layer_name}: {e}")
+
+def run_time_slicing(selected_use_cases: List[str] = None, selected_use_case_tables: List[str] = None, selected_layer_names: List[str] = None):
+    layers = get_layers()
     for layer in layers:
         layer_name = layer.layer_name
         use_case = layer.use_case
         use_case_table = layer.use_case_table
+
+        # skip layers not in the params
+        if selected_use_cases is not None and use_case not in selected_use_cases \
+            or selected_use_case_tables is not None and use_case_table not in selected_use_case_tables \
+            or selected_layer_names is not None and layer_name not in selected_layer_names:
+            continue
+
         print(f"Working on {use_case}//{use_case_table}//{layer_name}.")
 
-        clusters_for_layer = repo.get_clusters_for_layer(use_case, use_case_table, layer_name)
+        clusters_for_layer = get_clusters_for_layer(use_case, use_case_table, layer_name)
         # if no clusters were generated use one large cluster instead of skipping the layer
         if clusters_for_layer is None or len(clusters_for_layer) == 0:
-            nodes = repo.get_layer_nodes(use_case, use_case_table, layer_name)
+            nodes = get_layer_nodes(use_case, use_case_table, layer_name)
             if nodes is None or len(nodes) == 0:
                 print("Skipping, because there are no clusters and no nodes for the layer.")
                 continue
@@ -76,4 +124,9 @@ if __name__ == "__main__":
         time_slices = split_clusterset_by_time(layer, clusters_for_layer)
 
         for k,v in time_slices.items():
-            repo.add_time_slice(v)
+            add_time_slice(v)
+
+
+if __name__ == "__main__":
+    # repo.remove_all_time_slices()
+    run_time_slicing(selected_use_cases=['community-prediction-youtube-n'])
\ No newline at end of file

src/data-hub/semantic-linking-microservice/app/dummy_upload/community-prediction-taxi/.gitignore

+# this file contains all the training data but is around 1.8 GB.
+train.csv
\ No newline at end of file

src/data-hub/semantic-linking-microservice/app/dummy_upload/community-prediction-taxi/dummy_upload.py

+import csv
+import hashlib
+
+import sys
+import os
+modules_paths = ['.', '../../../modules/']
+for modules_path in modules_paths:
+    if os.path.exists(modules_path):
+        sys.path.insert(1, modules_path)
+
+from messaging.MessageHandler import MessageHandler
+from db.repository import Repository
+
+# file to read the data from
+CSV_FILE = r'dummy_upload/community-prediction-taxi/train.csv'
+handler = MessageHandler(Repository())
+
+
+import csv
+import json
+from datetime import datetime
+from typing import Iterator
+
+enum_mapping = {'A': 1, 'B': 2, 'C': 3}
+
+def load_csv_content() -> Iterator:
+    '''Returns a generator for all lines in the csv file with correct field types.'''
+    
+    with open(CSV_FILE) as csv_file:
+        reader = csv.reader(csv_file)    
+
+        headers = [h.lower() for h in next(reader)]
+
+        for line in reader:
+            # convert line fields to correct type
+            for i in range(len(headers)):
+                # trip_id AS string
+                if i == 0:
+                    continue
+                # call_type, day_type 
+                if i in [1, 6]:
+                    line[i] = enum_mapping[line[i]]
+                # origin_call, origin_stand, taxi_id AS int
+                elif i in [2, 3, 4]:
+                    line[i] = int(line[i]) if line[i] != "" else ""
+                # timestamp AS timestamp
+                elif i == 5:
+                    # datetime is not serializable
+                    # line[i] = datetime.fromtimestamp(int(line[i]))
+                    line[i] = int(line[i])
+                # missing_data AS bool
+                elif i == 7: 
+                    line[i] = line[i].lower() == 'true'
+                # polyline AS List[List[float]]
+                elif i == 8:
+                    line[i] = json.loads(line[i])
+
+            entry = dict(zip(headers, line))
+            yield entry
+
+
+def upload_transaction(transaction):
+    # manually flatten based on table mapping
+    uid = transaction['trip_id']
+
+    transaction['UniqueID'] = uid
+
+    if len(transaction['polyline']) == 0:
+        print(f"skipping transaction: {transaction}")
+        return
+
+    transaction['start_location_lat'] = transaction['polyline'][0][0]
+    transaction['start_location_long'] = transaction['polyline'][0][1]
+    transaction['end_location_lat'] = transaction['polyline'][-1][0]
+    transaction['end_location_long'] = transaction['polyline'][-1][1]
+
+    del transaction['trip_id']
+    del transaction['polyline']
+
+    t = {        
+        'use_case':  'community-prediction-taxi',
+        'table':  'community-prediction-taxi',
+        'id': uid,
+        'properties': transaction,
+    }
+    handler.handle_new_trace(t)
+
+
+if __name__ == '__main__':    
+    entries = load_csv_content()
+
+    for idx, transaction in enumerate(entries):
+        upload_transaction(transaction)
+
+        if idx % 1000 == 0:
+            print(f"Progress: {str(float(idx) / 1710671)} %")
\ No newline at end of file

src/data-hub/semantic-linking-microservice/app/dummy_upload/community-prediction-youtube/.gitignore

+# this file contains all the training data but is large.
+videos.csv
\ No newline at end of file

src/data-hub/semantic-linking-microservice/app/dummy_upload/community-prediction-youtube/dummy_upload.py

+import csv
+import hashlib
+
+import sys
+import os
+modules_paths = ['.', '../../../modules/']
+for modules_path in modules_paths:
+    if os.path.exists(modules_path):
+        sys.path.insert(1, modules_path)
+
+from messaging.MessageHandler import MessageHandler
+from db.repository import Repository
+
+# file to read the data from
+CSV_FILE = r'dummy_upload/community-prediction-youtube/videos.csv'
+handler = MessageHandler(Repository())
+
+
+import csv
+import json
+from datetime import datetime
+from typing import Iterator
+import pandas as pd
+from pandas import DataFrame
+
+
+def load_csv_content() -> Iterator:
+    '''Returns a generator for all lines in the csv file with correct field types.'''
+    dfs: DataFrame = pd.read_csv(CSV_FILE)
+    return dfs.iterrows()
+
+def upload_transaction(transaction):
+    # manually flatten based on table mapping
+    uid = transaction['video_id']
+
+    transaction['UniqueID'] = uid
+    transaction['trend_delay'] = transaction['trend_duration']
+    transaction['timestamp'] = transaction['trending_timestamp']
+
+    del transaction['trend_duration']
+    del transaction['trending_timestamp']
+
+    t = {        
+        'use_case':  'community-prediction-youtube-n',
+        'table':  'community-prediction-youtube-n',
+        'id': uid,
+        'properties': transaction,
+    }
+    handler.handle_new_trace(t)
+
+
+if __name__ == '__main__':    
+    entries = load_csv_content()
+
+    for idx, transaction in entries:
+        transaction = transaction.to_dict()
+        upload_transaction(transaction)
+
+        if idx % 1000 == 0:
+            print(f"Progress: {str(float(idx) / 375942)} %")
\ No newline at end of file

src/modules/env_info.py

@@ -7,8 +7,8 @@ def get_resources_path():
         try:
             return os.environ['ARTICONF_RESOURCES_PATH']
         except:
-            return '/srv/articonf'
-    else:
+            pass
+
     return '/srv/articonf'
 
 def is_running_locally():

src/modules/network_constants.py

@@ -55,6 +55,17 @@ else:
     ROLESTAGE_DISCOVERY_DB_HOSTNAME = 'articonf1.itec.aau.at'
     ROLESTAGE_DISCOVERY_DB_PORT = 30104
 
+## Proactive Community Detection
+if server:
+    PROACTIVE_COMMUNITY_DETECTION_HOSTNAME = 'proactive-community-detection'
+    PROACTIVE_COMMUNITY_DETECTION_REST_PORT = 80
+    PROACTIVE_COMMUNITY_DETECTION_DB_HOSTNAME = f'{ROLESTAGE_DISCOVERY_HOSTNAME}-db'
+    PROACTIVE_COMMUNITY_DETECTION_DB_PORT = 27017
+else:
+    PROACTIVE_COMMUNITY_DETECTION_HOSTNAME = 'articonf1.itec.aau.at'
+    PROACTIVE_COMMUNITY_DETECTION_REST_PORT = 30105
+    PROACTIVE_COMMUNITY_DETECTION_DB_HOSTNAME = 'articonf1.itec.aau.at'
+    PROACTIVE_COMMUNITY_DETECTION_DB_PORT = 30106
 #endregion Data Hub
 
 #region Rest Gateway

src/participation-hub/business-logic-microservice/app/_add_use_case_scripts/community-prediction/taxi/add_schema.py

+import sys
+import os
+from pathlib import Path
+from typing import Dict, Any
+import requests
+
+modules_path = '../../../modules/'
+if os.path.exists(modules_path):
+    sys.path.insert(1, modules_path)
+
+import network_constants as nc
+from security.token_manager import TokenManager
+
+import tables.add_table as add_table
+
+def add_use_case(use_case: str):
+    jwt = TokenManager.getInstance().getToken()
+    url = f"https://articonf1.itec.aau.at:30420/api/use-cases"
+    response = requests.post(
+            url,
+            verify=False, 
+            proxies = { "http":None, "https":None },
+            headers = { "Authorization": f"Bearer {jwt}"},
+            json = {"name": use_case}
+        )
+    
+    print(url+": "+str(response.status_code))
+        
+
+if __name__ == "__main__":
+    # TODO strategy pattern for all the use cases where add_use_case() etc. is clear duplicate code
+    # The same for add table, where almost everything is the same (UniqueId, Timestamp for every Layer)
+    # Only need to get jwt token once in the strategy impl
+    use_case = "community-prediction-taxi"
+    
+    # disable ssl warnings :) 
+    requests.packages.urllib3.disable_warnings() 
+
+    add_use_case(use_case)
+    add_table.main(use_case=use_case)
\ No newline at end of file

src/participation-hub/business-logic-microservice/app/_add_use_case_scripts/community-prediction/taxi/tables/add_table.py

+import network_constants as nc
+from security.token_manager import TokenManager
+
+import requests
+
+
+def add_table(use_case: str, table_name: str):
+    ''' Adds the use-case table with all the mappings as dict Internal -> External. '''
+    jwt = TokenManager.getInstance().getToken()
+    
+    mapping = { c : c for c in [
+        # mapping does not change any of the names for these properties
+        'call_type', 
+        'origin_call', 
+        'origin_stand', 
+        'taxi_id', 
+        'timestamp', 
+        'day_type', 
+        'missing_data', 
+        ] } 
+
+    mapping['start_location_lat'] = 'ployline[0][0]'
+    mapping['start_location_long'] = 'ployline[0][1]'
+    mapping['end_location_lat'] = 'ployline[-1][0]'
+    mapping['end_location_long'] = 'ployline[-1][1]'
+    mapping["UniqueID"] = "trip_id"
+    
+    url = f"https://articonf1.itec.aau.at:30420/api/use-cases/{use_case}/tables"
+
+    table = {
+        "name": table_name,
+        "mappings": mapping
+    }
+
+    response = requests.post(
+            url,
+            verify=False, 
+            proxies = { "http":None, "https":None },
+            headers = { "Authorization": f"Bearer {jwt}"},
+            json = table
+        )
+
+    print(url+": "+str(response.status_code))
+
+
+def add_layers(use_case:str, table_name: str):
+    jwt = TokenManager.getInstance().getToken()
+
+    layers = [
+        {
+            "name": "CallTypeLayer",
+            "properties": [
+                "UniqueID",
+                "call_type",
+            ],
+            "cluster_properties": [
+                "call_type"
+            ]
+        },
+        {
+            "name": "DayTypeLayer",
+            "properties": [
+                "UniqueID",
+                "day_type",
+            ],
+            "cluster_properties": [
+                "day_type"
+            ]
+        },
+        {
+            "name": "OriginCallLayer",
+            "properties": [
+                "UniqueID",
+                "call_type",
+                "origin_call",
+            ],
+            "cluster_properties": [
+                "call_type",
+                "origin_call",
+            ]
+        },
+        {
+            "name": "OriginStandLayer",
+            "properties": [
+                "UniqueID",
+                "call_type",
+                "origin_stand",
+            ],
+            "cluster_properties": [
+                "call_type",
+                "origin_stand",
+            ]
+        },
+        {
+            "name": "TaxiIdLayer",
+            "properties": [
+                "UniqueID",
+                "taxi_id",
+            ],
+            "cluster_properties": [
+                "taxi_id",
+            ]
+        },
+        {
+            "name": "StartLocationLayer",
+            "properties": [
+                "UniqueID",
+                "start_location_lat",
+                "start_location_long",
+            ],
+            "cluster_properties": [
+                "start_location_lat",
+                "start_location_long",
+            ]
+        },
+        {
+            "name": "EndLocationLayer",
+            "properties": [
+                "UniqueID",
+                "end_location_lat",
+                "end_location_long",
+            ],
+            "cluster_properties": [
+                "end_location_lat",
+                "end_location_long",
+            ]
+        },
+    ]
+
+    for layer in layers:
+        # add basic info to each layer
+        layer["use_case"] = use_case
+        layer["table"] = table_name
+        layer["properties"].append("timestamp") 
+
+        url = f"https://articonf1.itec.aau.at:30420/api/layers"
+
+        response = requests.post(
+            url,
+            verify=False, 
+            proxies = { "http":None, "https":None },
+            headers = { "Authorization": f"Bearer {jwt}"},
+            json = layer
+        )
+
+        print(url+": "+str(response.status_code))
+
+
+def main(use_case: str, table_name: str = "community-prediction-taxi"):
+    add_table(use_case, table_name)
+    add_layers(use_case, table_name)
\ No newline at end of file

src/participation-hub/business-logic-microservice/app/_add_use_case_scripts/community-prediction/youtube/add_schema.py

+import sys
+import os
+from pathlib import Path
+from typing import Dict, Any
+import requests
+
+modules_path = '../../../modules/'
+if os.path.exists(modules_path):
+    sys.path.insert(1, modules_path)
+
+import network_constants as nc
+from security.token_manager import TokenManager
+
+import tables.add_table as add_table
+
+def add_use_case(use_case: str):
+    jwt = TokenManager.getInstance().getToken()
+    url = f"https://articonf1.itec.aau.at:30420/api/use-cases"
+    response = requests.post(
+            url,
+            verify=False, 
+            proxies = { "http":None, "https":None },
+            headers = { "Authorization": f"Bearer {jwt}"},
+            json = {"name": use_case}
+        )
+    
+    print(url+": "+str(response.status_code))
+        
+
+if __name__ == "__main__":
+    # TODO strategy pattern for all the use cases where add_use_case() etc. is clear duplicate code
+    # The same for add table, where almost everything is the same (UniqueId, Timestamp for every Layer)
+    # Only need to get jwt token once in the strategy impl
+    use_case = "community-prediction-youtube"
+    
+    # disable ssl warnings :) 
+    requests.packages.urllib3.disable_warnings() 
+
+    add_use_case(use_case)
+    add_table.main(use_case=use_case)
\ No newline at end of file

src/participation-hub/business-logic-microservice/app/_add_use_case_scripts/community-prediction/youtube/tables/add_table.py

+import network_constants as nc
+from security.token_manager import TokenManager
+
+import requests
+
+
+def add_table(use_case: str, table_name: str):
+    ''' Adds the use-case table with all the mappings as dict Internal -> External. '''
+    jwt = TokenManager.getInstance().getToken()
+    
+    mapping = { c : c for c in [
+        # mapping does not change any of the names for these properties
+        'trending_date', 
+        'title', 
+        'channel_title', 
+        'category_id', 
+        'category_name', 
+        'publish_time', 
+        'tags', 
+        'views', 
+        'likes', 
+        'dislikes', 
+        'comment_count', 
+        'comments_disabled', 
+        'ratings_disabled', 
+        'video_error_or_removed', 
+        'country_code', 
+        'country_id', 
+        'publish_timestamp',         
+        ] } 
+
+    mapping["UniqueID"] = "video_id"
+    mapping["trend_delay"] = "trend_duration"
+    mapping["timestamp"] = "trending_timestamp"
+    
+    url = f"https://articonf1.itec.aau.at:30420/api/use-cases/{use_case}/tables"
+
+    table = {
+        "name": table_name,
+        "mappings": mapping
+    }
+
+    response = requests.post(
+            url,
+            verify=False, 
+            proxies = { "http":None, "https":None },
+            headers = { "Authorization": f"Bearer {jwt}"},
+            json = table
+        )
+
+    print(url+": "+str(response.status_code))
+
+
+def add_layers(use_case:str, table_name: str):
+    jwt = TokenManager.getInstance().getToken()
+
+    layers = [
+        {
+            "name": "CategoryLayer",
+            "properties": [
+                "UniqueID",
+                "category_id",
+                "category_name",
+            ],
+            "cluster_properties": [
+                "category_id"
+            ]
+        },
+        {
+            "name": "ViewsLayer",
+            "properties": [
+                "UniqueID",
+                "views",
+            ],
+            "cluster_properties": [
+                "views"
+            ]
+        },
+        {
+            "name": "LikesLayer",
+            "properties": [
+                "UniqueID",
+                "likes",
+            ],
+            "cluster_properties": [
+                "likes"
+            ]
+        },
+        {
+            "name": "DislikesLayer",
+            "properties": [
+                "UniqueID",
+                "dislikes",
+            ],
+            "cluster_properties": [
+                "dislikes"
+            ]
+        },
+        {
+            "name": "CommentCountLayer",
+            "properties": [
+                "UniqueID",
+                "comment_count",
+            ],
+            "cluster_properties": [
+                "comment_count"
+            ]
+        },
+        {
+            "name": "CountryLayer",
+            "properties": [
+                "UniqueID",
+                "country_code",
+                "country_id",
+            ],
+            "cluster_properties": [
+                "country_id"
+            ]
+        },
+        {
+            "name": "TrendDelayLayer",
+            "properties": [
+                "UniqueID",
+                "trend_delay",
+            ],
+            "cluster_properties": [
+                "trend_delay"
+            ]
+        },
+    ]
+
+    for layer in layers:
+        # add basic info to each layer
+        layer["use_case"] = use_case
+        layer["table"] = table_name
+        layer["properties"].append("timestamp") 
+
+        url = f"https://articonf1.itec.aau.at:30420/api/layers"
+
+        response = requests.post(
+            url,
+            verify=False, 
+            proxies = { "http":None, "https":None },
+            headers = { "Authorization": f"Bearer {jwt}"},
+            json = layer
+        )
+
+        print(url+": "+str(response.status_code))
+
+
+def main(use_case: str, table_name: str = "community-prediction-youtube"):
+    add_table(use_case, table_name)
+    add_layers(use_case, table_name)
\ No newline at end of file

src/participation-hub/business-logic-microservice/app/configs/routes.yml

 paths:
-  #####
-  # USE-CASES
-  #####
+  
   /use-cases:
     post:
       security:
@@ -57,9 +55,8 @@ paths:
           description: "Successful Request"
         '403':
           description: "Confirmation required"
-  #####
-  # TABLES
-  #####
+  
+  # region tables
   /tables:
     get:
       security:
@@ -187,13 +184,9 @@ paths:
       responses:
         '200':
           description: "Successful Request"
-  #####
-  # END-TABLES
-  #####
+  # endregion tables
 
-  #####
-  # LAYERS
-  #####
+  # region layers
   /layers:
     get:
       security:
@@ -515,13 +508,9 @@ paths:
           description: "Field in request is missing"
         '403':
           description: "Confirmation required"
-  #####
-  # END LAYERS
-  #####
+  # endregion layers
 
-  #####
-  # ENUMS
-  #####
+  # region enums
   /enums:
     get:
       security:
@@ -618,6 +607,66 @@ paths:
           description: "Successful Request"
         '404':
           description: "Enum does not exist"
+  # endregion enums
+
+  # region context dependencies for community prediction
+  /use-cases/{use_case}/tables/{table}/layer-pairs:
+    get:
+      security:
+        - JwtRegular: []
+      operationId: "routes.context_pairs.get_all"
+      tags:
+        - "LayerPairs"
+      summary: "Retrieve all layer pairs for cluster prediction"
+      description: "Retrieve all layer pairs for cluster prediction"
+      parameters:
+        - name: "use_case"
+          in: "path"
+          description: "Name of the use-case"
+          required: true
+          type: "string"
+        - name: "table"
+          in: "path"
+          description: "Name of the table"
+          required: true
+          type: "string"
+      responses:
+        '200':
+          description: "Successful Request"
+          schema:
+            $ref: '#/definitions/LayerPair'
+        '404':
+          description: "pairs do not exist"
+    post:
+      security:
+        - JwtRegular: []
+      operationId: "routes.context_pairs.insert"
+      tags:
+        - "LayerPairs"
+      summary: "Add a new layer pair for cluster prediction"
+      description: "Add a new layer pair for cluster prediction"
+      parameters:
+        - name: "use_case"
+          in: "path"
+          description: "Name of the use-case"
+          required: true
+          type: "string"
+        - name: "table"
+          in: "path"
+          description: "Name of the table"
+          required: true
+          type: "string"
+        - name: "layer_pair"
+          in: "body"          
+          required: true
+          schema:
+            $ref: '#/definitions/LayerPair'
+      responses:
+        '200':
+          description: "Successful Request"
+        '400':
+          description: "incorrect format etc"
+  # endregion context dependencies
 
 definitions:
   LayerMapping:
@@ -685,3 +734,15 @@ definitions:
         items:
           type: string
           example: "internal_property_1"
+
+  LayerPair:
+    type: "object"
+    properties:
+      use_case:
+        type: string
+      table:
+        type: string
+      layer:
+        type: string
+      reference_layer:
+        type: string
\ No newline at end of file

src/participation-hub/business-logic-microservice/app/db/entities/layer_pair.py

+from typing import List, Dict
+
+class LayerPair:
+    def __init__(self, use_case: str, table: str, layer: str, reference_layer: str):
+        self.use_case = use_case
+        self.table = table
+        self.layer = layer
+        self.reference_layer = reference_layer
+    
+    @staticmethod
+    def create_from_dict(dict_) -> 'LayerPair':
+        lp = LayerPair(None, None, None, None)
+        lp.__dict__.update(dict_)
+        return lp

src/participation-hub/business-logic-microservice/app/db/repository.py

@@ -3,13 +3,14 @@ import network_constants as netconst
 from database.MongoRepositoryBase import MongoRepositoryBase
 from db.entities.layer_adapter import LayerAdapter
 from db.entities.use_case import UseCase
+from db.entities.layer_pair import LayerPair
 
 import pymongo
 import json
 from typing import List, Dict
 
 class Repository(MongoRepositoryBase):
-    '''This is a repository for MongoDb.'''
+    '''This is a LAYER repository for MongoDb.'''
 
     def __init__(self):
         super().__init__(netconst.BUSINESS_LOGIC_DB_HOSTNAME,
@@ -18,6 +19,7 @@ class Repository(MongoRepositoryBase):
 
         self._adapter_collection = 'layer_adapters'
         self._use_case_collection = 'use_cases'
+        self._layer_pair_collection = 'contextpairs'
     
     def all(self) -> List[Dict]:
         result = super().get_entries(self._adapter_collection, projection={'_id': False})
@@ -60,3 +62,16 @@ class Repository(MongoRepositoryBase):
     def delete(self, adapter : LayerAdapter):
         collection = self._database[self._adapter_collection]
         collection.delete_many({"name": adapter.name, "use_case": adapter.use_case, "table": adapter.table})
+
+
+    # region context pairs
+    def get_layer_pairs(self, use_case, table) -> List[LayerPair]:
+        return \
+            [LayerPair.create_from_dict(entry) for entry in
+            super().get_entries(self._layer_pair_collection, projection={'_id': False}, selection={"use_case": use_case, "table": table})
+            ]
+
+    def insert_layer_pair(self, uc, table, pair: LayerPair):
+        super().insert_entry(self._layer_pair_collection, pair.__dict__)
+
+    # endregion context pairs
\ No newline at end of file

src/participation-hub/business-logic-microservice/app/routes/context_pairs.py

+import json
+from flask import Response, request
+from db.repository import Repository
+from db.entities.layer_pair import LayerPair
+
+repo = Repository()
+
+
+def get_all(use_case: str, table: str):
+    return [e.__dict__ for e in repo.get_layer_pairs(use_case, table)]
+
+
+def insert(use_case: str, table: str, layer_pair: dict):
+    repo.insert_layer_pair(use_case, table, LayerPair.create_from_dict(layer_pair))
+    return Response(status=200)
\ No newline at end of file

tools/check-use-case-data/check_mog.py

@@ -4,7 +4,7 @@ from icecream import ic
 
 
 def httpget(url):
-    token = 'eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJ1c2VybmFtZSI6InJlZ3VsYXJAaXRlYy5hYXUuYXQiLCJjcmVhdGVkX2F0IjoiMjAyMS0wMy0yNCAxMDoxMzo1MS4wMjkwNDkiLCJ2YWxpZF91bnRpbCI6IjIwMjEtMDMtMjUgMTA6MTM6NTEuMDI5MDQ5In0.V6kYV5Lmb_tUIsF-6AKNB8_lIifmJP_Dm8gHhGa5w_o'
+    token = 'eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJ1c2VybmFtZSI6InJlZ3VsYXJAaXRlYy5hYXUuYXQiLCJjcmVhdGVkX2F0IjoiMjAyMS0wNC0wNyAwODo0MDo0NS4yODEwOTYiLCJ2YWxpZF91bnRpbCI6IjIwMjEtMDQtMDggMDg6NDA6NDUuMjgxMDk2In0.oIDOEYy8bmIR3AHDRU-T0upYU0Wcz7V4FYzO5tSaSzk'
     res = requests.get(url, 
                     verify=False, 
                     headers = { "Authorization": f"Bearer {token}"})
@@ -32,6 +32,9 @@ count_data(res.json())
 res_f = httpget(url = 'https://articonf1.itec.aau.at:30001/api/use_cases/crowd-journalism/transactions-failed')
 count_data(res_f.json(), 'docType')
 
+res_d = httpget(url = 'https://articonf1.itec.aau.at:30001/api/use_cases/crowd-journalism/transactions-duplicated')
+count_data(res_d.json())
+
 # failed tags: the "tag" is missing, but is called name
 # failed purchases: duplicate keys generated from (userid, videoid, ownerid)
 # failed classifications: impact is missing

tools/check-use-case-data/check_uc.py

+import requests
+requests.packages.urllib3.disable_warnings() 
+from icecream import ic
+
+uc = 'community-prediction-youtube'
+
+def httpget(url):
+    token = 'eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJ1c2VybmFtZSI6InJlZ3VsYXJAaXRlYy5hYXUuYXQiLCJjcmVhdGVkX2F0IjoiMjAyMS0wNS0wNSAxMTozNjozOC4yMzAxODEiLCJ2YWxpZF91bnRpbCI6IjIwMjEtMDUtMDYgMTE6MzY6MzguMjMwMTgxIn0.Fz6iPpA0CnrXlOCj-VuCHFzc58H9Of2cBYHOb_RqvzI'
+    res = requests.get(url, 
+                    verify=False, 
+                    headers = { "Authorization": f"Bearer {token}"})
+    return res
+
+# list tables
+res = httpget(url = f'https://articonf1.itec.aau.at:30420/api/use-cases/{uc}/tables')
+print("Tables: ", [entry['name'] for entry in res.json()])
+
+# count pushed data
+def count_data(json_res, table_identifier='table'):
+    tables = {}
+    for entry in json_res:
+        key = entry[table_identifier]
+        if key not in tables:
+            tables[key] = 0
+        tables[key] += 1
+    ic(tables)
+
+res = httpget(url = f'https://articonf1.itec.aau.at:30001/api/use_cases/{uc}/transactions')
+count_data(res.json())
+
+res_f = httpget(url = f'https://articonf1.itec.aau.at:30001/api/use_cases/{uc}/transactions-failed')
+count_data(res_f.json(), 'docType')
+
+res_d = httpget(url = f'https://articonf1.itec.aau.at:30001/api/use_cases/{uc}/transactions-duplicated')
+count_data(res_d.json())
\ No newline at end of file