Feat: improve downstream node performance

.gitignore

@@ -55,3 +55,6 @@ PYPI_VERSION
 build/
 wheelhouse/
 _build/
+
+# Jupyter Notebook
+.ipynb_checkpoints

VERSION

@@ -1 +1 @@
-1.0
+1.1

docs/examples/utils/grid_from_txt_examples.ipynb

@@ -28,13 +28,22 @@
     "- A _transformer_ is defined as `<from_node> <to_node> transformer`\n",
     "  - e.g.: `8 9 transformer`\n",
     "- A _grid opening_ is defined by adding `open`\n",
-    "  - e.g.: `4 5 open` for _lines_ or `6 7 transformer,open` for _transformers_\n",
-    "\n",
+    "  - e.g.: `4 5 open` for _lines_ or `6 7 transformer,open` for _transformers_\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
     "### Loading a drawn grid into pgm-ds\n",
     "\n",
-    "Once you've created a grid, copy the _Graph Data_ of your grid to a text file (e.g. `my_grid.txt`).\n",
+    "There are two ways of loading a text grid into a pgm-ds:\n",
+    "- load grid from a .txt file\n",
+    "- load grid from a list of strings\n",
     "\n",
-    "For example, your file could contain the following data:\n",
+    "#### Load a grid from a .txt file\n",
+    "Copy the _Graph Data_ of your grid to a text file (e.g. `my_grid.txt`).\n",
+    "For the example above, the file should contain the following data:\n",
     "\n",
     "```text\n",
     "S1 2\n",
@@ -52,7 +61,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -68,12 +77,36 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "**You should now have a grid loaded from your drawn graph data!**\n"
+    "\n",
+    "#### Load grid from a list of strings\n",
+    "You can also load a grid directly from a list of strings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from power_grid_model_ds import Grid\n",
+    "\n",
+    "grid = Grid.from_txt(\n",
+    "    [\n",
+    "        \"S1 2\",\n",
+    "        \"S1 3 open\",\n",
+    "        \"2 7\",\n",
+    "        \"3 5\",\n",
+    "        \"3 6 transformer\",\n",
+    "        \"5 7\",\n",
+    "        \"7 8\",\n",
+    "        \"8 9\",\n",
+    "    ]\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -99,7 +132,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -113,9 +146,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.3"
+   "version": "3.13.1"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

src/power_grid_model_ds/_core/model/graphs/models/base.py

@@ -235,8 +235,49 @@ def get_connected(
             nodes_to_ignore=self._externals_to_internals(nodes_to_ignore),
             inclusive=inclusive,
         )
+
         return self._internals_to_externals(nodes)
 
+    def find_first_connected(self, node_id: int, candidate_node_ids: list[int]) -> int:
+        """Find the first connected node to the node_id from the candidate_node_ids
+
+        Note:
+            If multiple candidate nodes are connected to the node, the first one found is returned.
+            There is no guarantee that the same candidate node will be returned each time.
+
+        Raises:
+            MissingNodeError: if no connected node is found
+            ValueError: if the node_id is in candidate_node_ids
+        """
+        internal_node_id = self.external_to_internal(node_id)
+        internal_candidates = self._externals_to_internals(candidate_node_ids)
+        if internal_node_id in internal_candidates:
+            raise ValueError("node_id cannot be in candidate_node_ids")
+        return self.internal_to_external(self._find_first_connected(internal_node_id, internal_candidates))
+
+    def get_downstream_nodes(self, node_id: int, start_node_ids: list[int], inclusive: bool = False) -> list[int]:
+        """Find all nodes downstream of the node_id with respect to the start_node_ids
+
+        Example:
+            given this graph: [1] - [2] - [3] - [4]
+            >>> graph.get_downstream_nodes(2, [1]) == [3, 4]
+            >>> graph.get_downstream_nodes(2, [1], inclusive=True) == [2, 3, 4]
+
+        args:
+            node_id: node id to start the search from
+            start_node_ids: list of node ids considered 'above' the node_id
+            inclusive: whether to include the given node id in the result
+        returns:
+            list of node ids sorted by distance, downstream of to the node id
+        """
+        connected_node = self.find_first_connected(node_id, start_node_ids)
+        path, _ = self.get_shortest_path(node_id, connected_node)
+        _, upstream_node, *_ = (
+            path  # path is at least 2 elements long or find_first_connected would have raised an error
+        )
+
+        return self.get_connected(node_id, [upstream_node], inclusive)
+
     def find_fundamental_cycles(self) -> list[list[int]]:
         """Find all fundamental cycles in the graph.
         Returns:
@@ -273,6 +314,9 @@ def _branch_is_relevant(self, branch: BranchArray) -> bool:
     @abstractmethod
     def _get_connected(self, node_id: int, nodes_to_ignore: list[int], inclusive: bool = False) -> list[int]: ...
 
+    @abstractmethod
+    def _find_first_connected(self, node_id: int, candidate_node_ids: list[int]) -> int: ...
+
     @abstractmethod
     def _has_branch(self, from_node_id, to_node_id) -> bool: ...
 

src/power_grid_model_ds/_core/model/graphs/models/rustworkx.py

@@ -6,7 +6,7 @@
 
 import rustworkx as rx
 from rustworkx import NoEdgeBetweenNodes
-from rustworkx.visit import BFSVisitor, PruneSearch
+from rustworkx.visit import BFSVisitor, PruneSearch, StopSearch
 
 from power_grid_model_ds._core.model.graphs.errors import MissingBranchError, MissingNodeError, NoPathBetweenNodes
 from power_grid_model_ds._core.model.graphs.models._rustworkx_search import find_fundamental_cycles_rustworkx
@@ -99,6 +99,13 @@ def _get_connected(self, node_id: int, nodes_to_ignore: list[int], inclusive: bo
 
         return connected_nodes
 
+    def _find_first_connected(self, node_id: int, candidate_node_ids: list[int]) -> int:
+        visitor = _NodeFinder(candidate_nodes=candidate_node_ids)
+        rx.bfs_search(self._graph, [node_id], visitor)
+        if visitor.found_node is None:
+            raise MissingNodeError(f"node {node_id} is not connected to any of the candidate nodes")
+        return visitor.found_node
+
     def _find_fundamental_cycles(self) -> list[list[int]]:
         """Find all fundamental cycles in the graph using Rustworkx.
 
@@ -117,3 +124,16 @@ def discover_vertex(self, v):
         if v in self.nodes_to_ignore:
             raise PruneSearch
         self.nodes.append(v)
+
+
+class _NodeFinder(BFSVisitor):
+    """Visitor that stops the search when a candidate node is found"""
+
+    def __init__(self, candidate_nodes: list[int]):
+        self.candidate_nodes = candidate_nodes
+        self.found_node: int | None = None
+
+    def discover_vertex(self, v):
+        if v in self.candidate_nodes:
+            self.found_node = v
+            raise StopSearch

src/power_grid_model_ds/_core/model/grids/_text_sources.py

@@ -5,7 +5,6 @@
 """Create a grid from text a text file"""
 
 import logging
-from pathlib import Path
 from typing import TYPE_CHECKING
 
 from power_grid_model_ds._core.model.enums.nodes import NodeType
@@ -35,29 +34,28 @@ class TextSource:
     def __init__(self, grid_class: type["Grid"]):
         self.grid = grid_class.empty()
 
-    def load_grid_from_path(self, path: Path):
-        """Load assets from text file & sort them by id so that
-        they are ready to be appended to the grid"""
+    def load_from_txt(self, *args: str) -> "Grid":
+        """Load a grid from text"""
 
-        txt_nodes, txt_branches = self.read_txt(path)
+        text_lines = [line for arg in args for line in arg.strip().split("\n")]
+
+        txt_nodes, txt_branches = self.read_txt(text_lines)
         self.add_nodes(txt_nodes)
         self.add_branches(txt_branches)
         self.grid.set_feeder_ids()
         return self.grid
 
     @staticmethod
-    def read_txt(path: Path) -> tuple[set, dict]:
+    def read_txt(txt_lines: list[str]) -> tuple[set, dict]:
         """Extract assets from text"""
-        with open(path, "r", encoding="utf-8") as f:
-            txt_rows = f.readlines()
 
         txt_nodes = set()
         txt_branches = {}
-        for text_line in txt_rows:
+        for text_line in txt_lines:
             if not text_line.strip() or text_line.startswith("#"):
                 continue  # skip empty lines and comments
             try:
-                from_node_str, to_node_str, *comments = text_line.strip().split(" ")
+                from_node_str, to_node_str, *comments = text_line.strip().split()
             except ValueError as err:
                 raise ValueError(f"Text line '{text_line}' is invalid. Skipping...") from err
             comments = comments[0].split(",") if comments else []
@@ -116,4 +114,4 @@ def add_branch(self, branch: tuple[str, str], comments: list[str]):
             new_branch.to_status = 0
         else:
             new_branch.to_status = 1
-        self.grid.append(new_branch)
+        self.grid.append(new_branch, check_max_id=False)

src/power_grid_model_ds/_core/model/grids/base.py

@@ -408,6 +408,21 @@ def _from_pickle(cls, pickle_path: Path):
             raise TypeError(f"{pickle_path.name} is not a valid {cls.__name__} cache.")
         return grid
 
+    @classmethod
+    def from_txt(cls, *args: str):
+        """Build a grid from a list of strings
+
+        See the documentation for the expected format of the txt_lines
+
+        Args:
+            *args (str): The lines of the grid
+
+        Examples:
+            >>> Grid.from_txt("1 2", "2 3", "3 4 transformer", "4 5", "S1 6")
+            alternative: Grid.from_txt("1 2\n2 3\n3 4 transformer\n4 5\nS1 6")
+        """
+        return TextSource(grid_class=cls).load_from_txt(*args)
+
     @classmethod
     # pylint: disable=arguments-differ
     def from_txt_file(cls, txt_file_path: Path):
@@ -416,8 +431,9 @@ def from_txt_file(cls, txt_file_path: Path):
         Args:
             txt_file_path (Path): The path to the txt file
         """
-        text_source = TextSource(grid_class=cls)
-        return text_source.load_grid_from_path(txt_file_path)
+        with open(txt_file_path, "r", encoding="utf-8") as f:
+            txt_lines = f.readlines()
+        return TextSource(grid_class=cls).load_from_txt(*txt_lines)
 
     def set_feeder_ids(self):
         """Sets feeder and substation id properties in the grids arrays"""

tests/unit/model/graphs/test_graph_model.py

@@ -320,3 +320,20 @@ def test_get_connected_ignore_multiple_nodes(self, graph_with_2_routes):
         connected_nodes = graph.get_connected(node_id=1, nodes_to_ignore=[2, 4])
 
         assert {5} == set(connected_nodes)
+
+
+class TestFindFirstConnected:
+    def test_find_first_connected(self, graph_with_2_routes):
+        graph = graph_with_2_routes
+        assert 2 == graph.find_first_connected(1, candidate_node_ids=[2, 3, 4])
+
+    def test_find_first_connected_same_node(self, graph_with_2_routes):
+        graph = graph_with_2_routes
+        with pytest.raises(ValueError):
+            graph.find_first_connected(1, candidate_node_ids=[1, 3, 5])
+
+    def test_find_first_connected_no_match(self, graph_with_2_routes):
+        graph = graph_with_2_routes
+        graph.add_node(99)
+        with pytest.raises(MissingNodeError):
+            graph.find_first_connected(1, candidate_node_ids=[99])