black linter run

stable_gnn/embedding/embedding_factory.py

@@ -84,7 +84,13 @@ def _get_emb_settings(loss_name: str) -> Dict[str, Any]:
             raise NameError
 
     def build_embeddings(
-        self, loss_name: str, conv: str, data: List[Graph], device: device, number_of_trials: int, tune_out: bool = False
+        self,
+        loss_name: str,
+        conv: str,
+        data: List[Graph],
+        device: device,
+        number_of_trials: int,
+        tune_out: bool = False,
     ) -> NDArray:
         """Build embeddings based on passed dataset and settings
 

stable_gnn/explain.py

@@ -78,7 +78,11 @@ def _perturb_features_on_node(feature_matrix: NDArray, target: int, use_random:
         return features_perturb
 
     def _data_generation(
-        self, target: Optional[int] = None, index_to_perturb: Optional[list] = None, num_samples: int = 100, pred_threshold: float = 0.1
+        self,
+        target: Optional[int] = None,
+        index_to_perturb: Optional[list] = None,
+        num_samples: int = 100,
+        pred_threshold: float = 0.1,
     ) -> Tuple[pd.DataFrame, NDArray]:
         if target is None:
             neighbors = list(range(self.adj_matrix.shape[0]))
@@ -206,7 +210,11 @@ def _data_generation(
             return data, neighbors
 
     def _variable_selection(
-        self, target: Optional[int] = None, top_node: Optional[int] = None, num_samples: int = 100, pred_threshold: float = 0.1
+        self,
+        target: Optional[int] = None,
+        top_node: Optional[int] = None,
+        num_samples: int = 100,
+        pred_threshold: float = 0.1,
     ) -> Tuple[List[int], pd.DataFrame, Dict[int, float]]:
         if target is None:
             data, neighbors = self._data_generation(

stable_gnn/model_link_predict.py

@@ -36,7 +36,9 @@ def __init__(
         self.emb_conv_name = emb_conv_name
         self.device = device
 
-    def train_test_edges(self, dataset: Graph) -> Tuple[List[List[int]], List[List[int]], List[List[int]], List[List[int]]]:
+    def train_test_edges(
+        self, dataset: Graph
+    ) -> Tuple[List[List[int]], List[List[int]], List[List[int]], List[List[int]]]:
         """
         Split dataset to train and test and calculate negative samples