Moving dependence from custom branch's tour_model to master's trip_model

emission/analysis/modelling/similarity/similarity_metric.py

@@ -27,15 +27,21 @@ def similarity(self, a: List[float], b: List[float]) -> List[float]:
         """
         pass
 
-    def similar(self, a: List[float], b: List[float], thresh: float) -> bool:
+    def similar(self, a: List[float], b: List[float], thresh: float, clusteringWay :str = 'origin-destination') -> bool:
         """compares the features, returning true if they are similar
         within some threshold
 
         :param a: features for a trip
         :param b: features for another trip
         :param thresh: threshold for similarity
+        :clusterinWay: clustering based on origin/destination/origin-destination-pair
         :return: true if the feature similarity is within some threshold
         """
         similarity_values = self.similarity(a, b)
-        is_similar = all(map(lambda sim: sim <= thresh, similarity_values))
+        if clusteringWay == 'origin':
+            is_similar = similarity_values[0] <= thresh
+        elif clusteringWay == 'destination':
+            is_similar = similarity_values[1] <= thresh
+        else:
+            is_similar = all(map(lambda sim: sim <= thresh, similarity_values))
         return is_similar

emission/analysis/modelling/trip_model/greedy_similarity_binning.py

@@ -119,6 +119,11 @@ class label to apply:
         self.sim_thresh = config['similarity_threshold_meters']
         self.apply_cutoff = config['apply_cutoff']
         self.is_incremental = config['incremental_evaluation']
+        if config.get('clustering_way') is None:
+            self.clusteringWay='origin-destination'   # previous default
+        else:
+            self.clusteringWay= config['clustering_way'] 
+        self.tripLabels=[]
 
         self.bins: Dict[str, Dict] = {}
 
@@ -184,9 +189,11 @@ def _assign_bins(self, trips: List[ecwc.Confirmedtrip]):
                 logging.debug(f"adding trip to bin {bin_id} with features {trip_features}")
                 self.bins[bin_id]['feature_rows'].append(trip_features)
                 self.bins[bin_id]['labels'].append(trip_labels)
+                self.tripLabels.append(bin_id)
             else:
                 # create new bin
                 new_bin_id = str(len(self.bins))
+                self.tripLabels.append(new_bin_id)
                 new_bin_record = {
                     'feature_rows': [trip_features],
                     'labels': [trip_labels],
@@ -204,7 +211,7 @@ def _find_matching_bin_id(self, trip_features: List[float]) -> Optional[str]:
         :return: the id of a bin if a match was found, otherwise None
         """
         for bin_id, bin_record in self.bins.items():
-                matches_bin = all([self.metric.similar(trip_features, bin_sample, self.sim_thresh)
+                matches_bin = all([self.metric.similar(trip_features, bin_sample, self.sim_thresh,self.clusteringWay)
                     for bin_sample in bin_record['feature_rows']])
                 if matches_bin:
                     return bin_id