risk-network 0.0.11__py3-none-any.whl → 0.0.12b1__py3-none-any.whl

risk/network/graph/graph.py

@@ -65,8 +65,8 @@ class Graph:
         # NOTE: Below this point, instance attributes (i.e., self) will be used!
         self.domain_id_to_node_labels_map = self._create_domain_id_to_node_labels_map()
         # Unfold the network's 3D coordinates to 2D and extract node coordinates
-        self.network = _unfold_sphere_to_plane(network)
-        self.node_coordinates = _extract_node_coordinates(self.network)
+        self.network = self._unfold_sphere_to_plane(network)
+        self.node_coordinates = self._extract_node_coordinates(self.network)
 
         # NOTE: Only after the above attributes are initialized, we can create the summary
         self.summary = Summary(annotations, neighborhoods, self)
@@ -97,8 +97,7 @@ class Graph:
                 domain_info["domains"].remove(domain_id)
                 domain_info["significances"].pop(domain_id)
 
-    @staticmethod
-    def _create_domain_id_to_node_ids_map(domains: pd.DataFrame) -> Dict[int, Any]:
+    def _create_domain_id_to_node_ids_map(self, domains: pd.DataFrame) -> Dict[int, Any]:
         """Create a mapping from domains to the list of node IDs belonging to each domain.
 
         Args:
@@ -115,8 +114,9 @@ class Graph:
 
         return domain_id_to_node_ids_map
 
-    @staticmethod
-    def _create_domain_id_to_domain_terms_map(trimmed_domains: pd.DataFrame) -> Dict[int, Any]:
+    def _create_domain_id_to_domain_terms_map(
+        self, trimmed_domains: pd.DataFrame
+    ) -> Dict[int, Any]:
         """Create a mapping from domain IDs to their corresponding terms.
 
         Args:
@@ -132,8 +132,8 @@ class Graph:
             )
         )
 
-    @staticmethod
     def _create_domain_id_to_domain_info_map(
+        self,
         trimmed_domains: pd.DataFrame,
     ) -> Dict[int, Dict[str, Any]]:
         """Create a mapping from domain IDs to their corresponding full description and significance score,
@@ -169,8 +169,9 @@ class Graph:
 
         return domain_info_map
 
-    @staticmethod
-    def _create_node_id_to_domain_ids_and_significances(domains: pd.DataFrame) -> Dict[int, Dict]:
+    def _create_node_id_to_domain_ids_and_significances(
+        self, domains: pd.DataFrame
+    ) -> Dict[int, Dict]:
         """Creates a dictionary mapping each node ID to its corresponding domain IDs and significance values.
 
         Args:
@@ -216,54 +217,52 @@ class Graph:
 
         return domain_id_to_label_map
 
+    def _unfold_sphere_to_plane(self, G: nx.Graph) -> nx.Graph:
+        """Convert 3D coordinates to 2D by unfolding a sphere to a plane.
 
-def _unfold_sphere_to_plane(G: nx.Graph) -> nx.Graph:
-    """Convert 3D coordinates to 2D by unfolding a sphere to a plane.
+        Args:
+            G (nx.Graph): A network graph with 3D coordinates. Each node should have 'x', 'y', and 'z' attributes.
 
-    Args:
-        G (nx.Graph): A network graph with 3D coordinates. Each node should have 'x', 'y', and 'z' attributes.
+        Returns:
+            nx.Graph: The network graph with updated 2D coordinates (only 'x' and 'y').
+        """
+        for node in G.nodes():
+            if "z" in G.nodes[node]:
+                # Extract 3D coordinates
+                x, y, z = G.nodes[node]["x"], G.nodes[node]["y"], G.nodes[node]["z"]
+                # Calculate spherical coordinates theta and phi from Cartesian coordinates
+                r = np.sqrt(x**2 + y**2 + z**2)
+                theta = np.arctan2(y, x)
+                phi = np.arccos(z / r)
+
+                # Convert spherical coordinates to 2D plane coordinates
+                unfolded_x = (theta + np.pi) / (2 * np.pi)  # Shift and normalize theta to [0, 1]
+                unfolded_x = unfolded_x + 0.5 if unfolded_x < 0.5 else unfolded_x - 0.5
+                unfolded_y = (np.pi - phi) / np.pi  # Reflect phi and normalize to [0, 1]
+                # Update network node attributes
+                G.nodes[node]["x"] = unfolded_x
+                G.nodes[node]["y"] = -unfolded_y
+                # Remove the 'z' coordinate as it's no longer needed
+                del G.nodes[node]["z"]
+
+        return G
+
+    def _extract_node_coordinates(self, G: nx.Graph) -> np.ndarray:
+        """Extract 2D coordinates of nodes from the graph.
 
-    Returns:
-        nx.Graph: The network graph with updated 2D coordinates (only 'x' and 'y').
-    """
-    for node in G.nodes():
-        if "z" in G.nodes[node]:
-            # Extract 3D coordinates
-            x, y, z = G.nodes[node]["x"], G.nodes[node]["y"], G.nodes[node]["z"]
-            # Calculate spherical coordinates theta and phi from Cartesian coordinates
-            r = np.sqrt(x**2 + y**2 + z**2)
-            theta = np.arctan2(y, x)
-            phi = np.arccos(z / r)
-
-            # Convert spherical coordinates to 2D plane coordinates
-            unfolded_x = (theta + np.pi) / (2 * np.pi)  # Shift and normalize theta to [0, 1]
-            unfolded_x = unfolded_x + 0.5 if unfolded_x < 0.5 else unfolded_x - 0.5
-            unfolded_y = (np.pi - phi) / np.pi  # Reflect phi and normalize to [0, 1]
-            # Update network node attributes
-            G.nodes[node]["x"] = unfolded_x
-            G.nodes[node]["y"] = -unfolded_y
-            # Remove the 'z' coordinate as it's no longer needed
-            del G.nodes[node]["z"]
-
-    return G
-
-
-def _extract_node_coordinates(G: nx.Graph) -> np.ndarray:
-    """Extract 2D coordinates of nodes from the graph.
-
-    Args:
-        G (nx.Graph): The network graph with node coordinates.
-
-    Returns:
-        np.ndarray: Array of node coordinates with shape (num_nodes, 2).
-    """
-    # Extract x and y coordinates from graph nodes
-    x_coords = dict(G.nodes.data("x"))
-    y_coords = dict(G.nodes.data("y"))
-    coordinates_dicts = [x_coords, y_coords]
-    # Combine x and y coordinates into a single array
-    node_positions = {
-        node: np.array([coords[node] for coords in coordinates_dicts]) for node in x_coords
-    }
-    node_coordinates = np.vstack(list(node_positions.values()))
-    return node_coordinates
+        Args:
+            G (nx.Graph): The network graph with node coordinates.
+
+        Returns:
+            np.ndarray: Array of node coordinates with shape (num_nodes, 2).
+        """
+        # Extract x and y coordinates from graph nodes
+        x_coords = dict(G.nodes.data("x"))
+        y_coords = dict(G.nodes.data("y"))
+        coordinates_dicts = [x_coords, y_coords]
+        # Combine x and y coordinates into a single array
+        node_positions = {
+            node: np.array([coords[node] for coords in coordinates_dicts]) for node in x_coords
+        }
+        node_coordinates = np.vstack(list(node_positions.values()))
+        return node_coordinates

risk/{stats/significance.py → network/graph/stats.py}

@@ -1,6 +1,6 @@
 """
-risk/stats/significance
-~~~~~~~~~~~~~~~~~~~~~~~
+risk/network/graph/stats
+~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 from typing import Any, Dict, Union

risk/network/graph/summary.py

@@ -9,7 +9,7 @@ import numpy as np
 import pandas as pd
 from statsmodels.stats.multitest import fdrcorrection
 
-from risk.log.console import logger, log_header
+from risk.log.console import log_header, logger
 
 
 class Summary:
@@ -170,8 +170,7 @@ class Summary:
 
         return results
 
-    @staticmethod
-    def _calculate_qvalues(pvals: np.ndarray) -> np.ndarray:
+    def _calculate_qvalues(self, pvals: np.ndarray) -> np.ndarray:
         """Calculate q-values (FDR) for each row of a p-value matrix.
 
         Args:

risk/network/io.py

@@ -15,8 +15,7 @@ import networkx as nx
 import numpy as np
 import pandas as pd
 
-from risk.network.geometry import assign_edge_lengths
-from risk.log import params, logger, log_header
+from risk.log import log_header, logger, params
 
 
 class NetworkIO:
@@ -49,8 +48,8 @@ class NetworkIO:
             min_edges_per_node=min_edges_per_node,
         )
 
-    @staticmethod
     def load_gpickle_network(
+        self,
         filepath: str,
         compute_sphere: bool = True,
         surface_depth: float = 0.0,
@@ -94,8 +93,8 @@ class NetworkIO:
         # Initialize the graph
         return self._initialize_graph(G)
 
-    @staticmethod
     def load_networkx_network(
+        self,
         network: nx.Graph,
         compute_sphere: bool = True,
         surface_depth: float = 0.0,
@@ -138,8 +137,8 @@ class NetworkIO:
         # Initialize the graph
         return self._initialize_graph(network_copy)
 
-    @staticmethod
     def load_cytoscape_network(
+        self,
         filepath: str,
         source_label: str = "source",
         target_label: str = "target",
@@ -194,6 +193,7 @@ class NetworkIO:
 
         Raises:
             ValueError: If no matching attribute metadata file is found.
+            KeyError: If the source or target label is not found in the attribute table.
         """
         filetype = "Cytoscape"
         # Log the loading of the Cytoscape file
@@ -307,8 +307,8 @@ class NetworkIO:
             if os.path.exists(tmp_dir):
                 shutil.rmtree(tmp_dir)
 
-    @staticmethod
     def load_cytoscape_json_network(
+        self,
         filepath: str,
         source_label: str = "source",
         target_label: str = "target",
@@ -437,7 +437,8 @@ class NetworkIO:
             G.remove_nodes_from(nodes_to_remove)
 
         # Remove isolated nodes
-        G.remove_nodes_from(nx.isolates(G))
+        isolates = list(nx.isolates(G))
+        G.remove_nodes_from(isolates)
 
         # Log the number of nodes and edges before and after cleaning
         num_final_nodes = G.number_of_nodes()
@@ -523,11 +524,153 @@ class NetworkIO:
         Args:
             G (nx.Graph): The input network graph.
         """
-        assign_edge_lengths(
+        G_transformed = self._prepare_graph_for_edge_length_assignment(
             G,
             compute_sphere=self.compute_sphere,
             surface_depth=self.surface_depth,
         )
+        self._calculate_and_set_edge_lengths(G_transformed, self.compute_sphere)
+
+    def _prepare_graph_for_edge_length_assignment(
+        self,
+        G: nx.Graph,
+        compute_sphere: bool = True,
+        surface_depth: float = 0.0,
+    ) -> nx.Graph:
+        """Prepare the graph by normalizing coordinates and optionally mapping nodes to a sphere.
+
+        Args:
+            G (nx.Graph): The input graph.
+            compute_sphere (bool): Whether to map nodes to a sphere. Defaults to True.
+            surface_depth (float): The surface depth for mapping to a sphere. Defaults to 0.0.
+
+        Returns:
+            nx.Graph: The graph with transformed coordinates.
+        """
+        self._normalize_graph_coordinates(G)
+
+        if compute_sphere:
+            self._map_to_sphere(G)
+            G_depth = self._create_depth(G, surface_depth=surface_depth)
+        else:
+            G_depth = G
+
+        return G_depth
+
+    def _calculate_and_set_edge_lengths(self, G: nx.Graph, compute_sphere: bool) -> None:
+        """Compute and assign edge lengths in the graph.
+
+        Args:
+            G (nx.Graph): The input graph.
+            compute_sphere (bool): Whether to compute spherical distances.
+        """
+
+        def compute_distance_vectorized(coords, is_sphere):
+            """Compute Euclidean or spherical distances between edges in bulk."""
+            u_coords, v_coords = coords[:, 0, :], coords[:, 1, :]
+            if is_sphere:
+                u_coords /= np.linalg.norm(u_coords, axis=1, keepdims=True)
+                v_coords /= np.linalg.norm(v_coords, axis=1, keepdims=True)
+                dot_products = np.einsum("ij,ij->i", u_coords, v_coords)
+                return np.arccos(np.clip(dot_products, -1.0, 1.0))
+            return np.linalg.norm(u_coords - v_coords, axis=1)
+
+        # Precompute edge coordinate arrays and compute distances in bulk
+        edge_data = np.array(
+            [
+                [
+                    np.array([G.nodes[u]["x"], G.nodes[u]["y"], G.nodes[u].get("z", 0)]),
+                    np.array([G.nodes[v]["x"], G.nodes[v]["y"], G.nodes[v].get("z", 0)]),
+                ]
+                for u, v in G.edges
+            ]
+        )
+        # Compute distances
+        distances = compute_distance_vectorized(edge_data, compute_sphere)
+        # Assign Euclidean or spherical distances to edges
+        for (u, v), distance in zip(G.edges, distances):
+            G.edges[u, v]["length"] = distance
+
+    def _map_to_sphere(self, G: nx.Graph) -> None:
+        """Map the x and y coordinates of graph nodes onto a 3D sphere.
+
+        Args:
+            G (nx.Graph): The input graph with nodes having 'x' and 'y' coordinates.
+        """
+        # Extract x, y coordinates as a NumPy array
+        nodes = list(G.nodes)
+        xy_coords = np.array([[G.nodes[node]["x"], G.nodes[node]["y"]] for node in nodes])
+        # Normalize coordinates between [0, 1]
+        min_vals = xy_coords.min(axis=0)
+        max_vals = xy_coords.max(axis=0)
+        normalized_xy = (xy_coords - min_vals) / (max_vals - min_vals)
+        # Convert normalized coordinates to spherical coordinates
+        theta = normalized_xy[:, 0] * np.pi * 2
+        phi = normalized_xy[:, 1] * np.pi
+        # Compute 3D Cartesian coordinates
+        x = np.sin(phi) * np.cos(theta)
+        y = np.sin(phi) * np.sin(theta)
+        z = np.cos(phi)
+        # Assign coordinates back to graph nodes in bulk
+        xyz_coords = {node: {"x": x[i], "y": y[i], "z": z[i]} for i, node in enumerate(nodes)}
+        nx.set_node_attributes(G, xyz_coords)
+
+    def _normalize_graph_coordinates(self, G: nx.Graph) -> None:
+        """Normalize the x and y coordinates of the nodes in the graph to the [0, 1] range.
+
+        Args:
+            G (nx.Graph): The input graph with nodes having 'x' and 'y' coordinates.
+        """
+        # Extract x, y coordinates from the graph nodes
+        xy_coords = np.array([[G.nodes[node]["x"], G.nodes[node]["y"]] for node in G.nodes()])
+        # Calculate min and max values for x and y
+        min_vals = np.min(xy_coords, axis=0)
+        max_vals = np.max(xy_coords, axis=0)
+        # Normalize the coordinates to [0, 1]
+        normalized_xy = (xy_coords - min_vals) / (max_vals - min_vals)
+        # Update the node coordinates with the normalized values
+        for i, node in enumerate(G.nodes()):
+            G.nodes[node]["x"], G.nodes[node]["y"] = normalized_xy[i]
+
+    def _create_depth(self, G: nx.Graph, surface_depth: float = 0.0) -> nx.Graph:
+        """Adjust the 'z' attribute of each node based on the subcluster strengths and normalized surface depth.
+
+        Args:
+            G (nx.Graph): The input graph.
+            surface_depth (float): The maximum surface depth to apply for the strongest subcluster.
+
+        Returns:
+            nx.Graph: The graph with adjusted 'z' attribute for each node.
+        """
+        if surface_depth >= 1.0:
+            surface_depth -= 1e-6  # Cap the surface depth to prevent a value of 1.0
+
+        # Compute subclusters as connected components
+        connected_components = list(nx.connected_components(G))
+        subcluster_strengths = {}
+        max_strength = 0
+        # Precompute strengths and track the maximum strength
+        for component in connected_components:
+            size = len(component)
+            max_strength = max(max_strength, size)
+            for node in component:
+                subcluster_strengths[node] = size
+
+        # Avoid repeated lookups and computations by pre-fetching node data
+        nodes = list(G.nodes(data=True))
+        node_updates = {}
+        for node, attrs in nodes:
+            strength = subcluster_strengths[node]
+            normalized_surface_depth = (strength / max_strength) * surface_depth
+            x, y, z = attrs["x"], attrs["y"], attrs["z"]
+            norm = np.sqrt(x**2 + y**2 + z**2)
+            adjusted_z = z - (z / norm) * normalized_surface_depth
+            node_updates[node] = {"z": adjusted_z}
+
+        # Batch update node attributes
+        nx.set_node_attributes(G, node_updates)
+
+        return G
 
     def _log_loading(
         self,

risk/network/plotter/__init__.py

@@ -2,5 +2,3 @@
 risk/network/plotter
 ~~~~~~~~~~~~~~~~~~~~
 """
-
-from risk.network.plotter.api import PlotterAPI

risk/network/plotter/api.py

@@ -18,7 +18,7 @@ class PlotterAPI:
     The PlotterAPI class provides methods to load and configure Plotter objects for plotting network graphs.
     """
 
-    def __init__() -> None:
+    def __init__(self) -> None:
         pass
 
     def load_plotter(

risk/network/plotter/canvas.py

@@ -158,7 +158,7 @@ class Canvas:
         # Calculate the center and radius of the bounding box around the network
         center, radius = calculate_bounding_box(node_coordinates)
         # Adjust the center based on user-defined offsets
-        adjusted_center = _calculate_adjusted_center(
+        adjusted_center = self._calculate_adjusted_center(
             center, radius, center_offset_x, center_offset_y
         )
         # Scale the radius by the scale factor
@@ -250,42 +250,42 @@ class Canvas:
             fill_alpha=fill_alpha,
         )
 
+    def _calculate_adjusted_center(
+        self,
+        center: Tuple[float, float],
+        radius: float,
+        center_offset_x: float = 0.0,
+        center_offset_y: float = 0.0,
+    ) -> Tuple[float, float]:
+        """Calculate the adjusted center for the network perimeter circle based on user-defined offsets.
 
-def _calculate_adjusted_center(
-    center: Tuple[float, float],
-    radius: float,
-    center_offset_x: float = 0.0,
-    center_offset_y: float = 0.0,
-) -> Tuple[float, float]:
-    """Calculate the adjusted center for the network perimeter circle based on user-defined offsets.
-
-    Args:
-        center (Tuple[float, float]): Original center coordinates of the network graph.
-        radius (float): Radius of the bounding box around the network.
-        center_offset_x (float, optional): Horizontal offset as a fraction of the diameter.
-            Negative values shift the center left, positive values shift it right. Allowed
-            values are in the range [-1, 1]. Defaults to 0.0.
-        center_offset_y (float, optional): Vertical offset as a fraction of the diameter.
-            Negative values shift the center down, positive values shift it up. Allowed
-            values are in the range [-1, 1]. Defaults to 0.0.
+        Args:
+            center (Tuple[float, float]): Original center coordinates of the network graph.
+            radius (float): Radius of the bounding box around the network.
+            center_offset_x (float, optional): Horizontal offset as a fraction of the diameter.
+                Negative values shift the center left, positive values shift it right. Allowed
+                values are in the range [-1, 1]. Defaults to 0.0.
+            center_offset_y (float, optional): Vertical offset as a fraction of the diameter.
+                Negative values shift the center down, positive values shift it up. Allowed
+                values are in the range [-1, 1]. Defaults to 0.0.
 
-    Returns:
-        Tuple[float, float]: Adjusted center coordinates after applying the offsets.
+        Returns:
+            Tuple[float, float]: Adjusted center coordinates after applying the offsets.
 
-    Raises:
-        ValueError: If the center offsets are outside the valid range [-1, 1].
-    """
-    # Flip the y-axis to match the plot orientation
-    flipped_center_offset_y = -center_offset_y
-    # Validate the center offsets
-    if not -1 <= center_offset_x <= 1:
-        raise ValueError("Horizontal center offset must be in the range [-1, 1].")
-    if not -1 <= center_offset_y <= 1:
-        raise ValueError("Vertical center offset must be in the range [-1, 1].")
+        Raises:
+            ValueError: If the center offsets are outside the valid range [-1, 1].
+        """
+        # Flip the y-axis to match the plot orientation
+        flipped_center_offset_y = -center_offset_y
+        # Validate the center offsets
+        if not -1 <= center_offset_x <= 1:
+            raise ValueError("Horizontal center offset must be in the range [-1, 1].")
+        if not -1 <= center_offset_y <= 1:
+            raise ValueError("Vertical center offset must be in the range [-1, 1].")
 
-    # Calculate adjusted center by applying offset fractions of the diameter
-    adjusted_center_x = center[0] + (center_offset_x * radius * 2)
-    adjusted_center_y = center[1] + (flipped_center_offset_y * radius * 2)
+        # Calculate adjusted center by applying offset fractions of the diameter
+        adjusted_center_x = center[0] + (center_offset_x * radius * 2)
+        adjusted_center_y = center[1] + (flipped_center_offset_y * radius * 2)
 
-    # Return the adjusted center coordinates
-    return adjusted_center_x, adjusted_center_y
+        # Return the adjusted center coordinates
+        return adjusted_center_x, adjusted_center_y

risk/network/plotter/contour.py

@@ -11,7 +11,7 @@ from scipy import linalg
 from scipy.ndimage import label
 from scipy.stats import gaussian_kde
 
-from risk.log import params, logger
+from risk.log import logger, params
 from risk.network.graph.graph import Graph
 from risk.network.plotter.utils.colors import get_annotated_domain_colors, to_rgba
 
@@ -213,7 +213,7 @@ class Contour:
                 ]
                 z = kde(np.vstack([x.ravel(), y.ravel()])).reshape(x.shape)
                 # Check if the KDE forms a single connected component
-                connected = _is_connected(z)
+                connected = self._is_connected(z)
                 if not connected:
                     bandwidth += 0.05  # Increase bandwidth slightly and retry
             except linalg.LinAlgError:
@@ -316,15 +316,14 @@ class Contour:
             random_seed=random_seed,
         )
 
+    def _is_connected(self, z: np.ndarray) -> bool:
+        """Determine if a thresholded grid represents a single, connected component.
 
-def _is_connected(z: np.ndarray) -> bool:
-    """Determine if a thresholded grid represents a single, connected component.
-
-    Args:
-        z (np.ndarray): A binary grid where the component connectivity is evaluated.
+        Args:
+            z (np.ndarray): A binary grid where the component connectivity is evaluated.
 
-    Returns:
-        bool: True if the grid represents a single connected component, False otherwise.
-    """
-    _, num_features = label(z)
-    return num_features == 1  # Return True if only one connected component is found
+        Returns:
+            bool: True if the grid represents a single connected component, False otherwise.
+        """
+        _, num_features = label(z)
+        return num_features == 1  # Return True if only one connected component is found