risk-network 0.0.8b18__py3-none-any.whl → 0.0.9b26__py3-none-any.whl

risk/neighborhoods/neighborhoods.py

@@ -5,7 +5,7 @@ risk/neighborhoods/neighborhoods
 
 import random
 import warnings
-from typing import Any, Dict, List, Tuple
+from typing import Any, Dict, List, Tuple, Union
 
 import networkx as nx
 import numpy as np
@@ -15,6 +15,7 @@ from sklearn.metrics.pairwise import cosine_similarity
 from risk.neighborhoods.community import (
     calculate_greedy_modularity_neighborhoods,
     calculate_label_propagation_neighborhoods,
+    calculate_leiden_neighborhoods,
     calculate_louvain_neighborhoods,
     calculate_markov_clustering_neighborhoods,
     calculate_spinglass_neighborhoods,
@@ -28,86 +29,119 @@ warnings.filterwarnings(action="ignore", category=DataConversionWarning)
 
 def get_network_neighborhoods(
     network: nx.Graph,
-    distance_metric: str = "louvain",
-    edge_length_threshold: float = 1.0,
-    louvain_resolution: float = 1.0,
+    distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
+    fraction_shortest_edges: Union[float, List, Tuple, np.ndarray] = 1.0,
+    louvain_resolution: float = 0.1,
+    leiden_resolution: float = 1.0,
     random_seed: int = 888,
 ) -> np.ndarray:
-    """Calculate the neighborhoods for each node in the network based on the specified distance metric.
+    """Calculate the combined neighborhoods for each node based on the specified community detection algorithm(s).
 
     Args:
         network (nx.Graph): The network graph.
-        distance_metric (str): The distance metric to use ('greedy_modularity', 'louvain', 'label_propagation',
-            'markov_clustering', 'walktrap', 'spinglass').
-        edge_length_threshold (float): The edge length threshold for the neighborhoods.
-        louvain_resolution (float, optional): Resolution parameter for the Louvain method. Defaults to 1.0.
-        random_seed (int, optional): Random seed for methods requiring random initialization. Defaults to 888.
+        distance_metric (str, List, Tuple, or np.ndarray, optional): The distance metric(s) to use.
+        fraction_shortest_edges (float, List, Tuple, or np.ndarray, optional): Shortest edge rank fraction threshold(s) for creating subgraphs.
+        louvain_resolution (float, optional): Resolution parameter for the Louvain method.
+        leiden_resolution (float, optional): Resolution parameter for the Leiden method.
+        random_seed (int, optional): Random seed for methods requiring random initialization.
 
     Returns:
-        np.ndarray: Neighborhood matrix calculated based on the selected distance metric.
+        np.ndarray: Summed neighborhood matrix from all selected algorithms.
     """
-    # Set random seed for reproducibility in all methods besides Louvain, which requires a separate seed
+    # Set random seed for reproducibility
     random.seed(random_seed)
     np.random.seed(random_seed)
 
-    # Create a subgraph based on the edge length percentile threshold
-    network = _create_percentile_limited_subgraph(
-        network, edge_length_percentile=edge_length_threshold
-    )
+    # Ensure distance_metric is a list/tuple for multi-algorithm handling
+    if isinstance(distance_metric, (str, np.ndarray)):
+        distance_metric = [distance_metric]
+    # Ensure fraction_shortest_edges is a list/tuple for multi-threshold handling
+    if isinstance(fraction_shortest_edges, (float, int)):
+        fraction_shortest_edges = [fraction_shortest_edges] * len(distance_metric)
+    # Check that the number of distance metrics matches the number of edge length thresholds
+    if len(distance_metric) != len(fraction_shortest_edges):
+        raise ValueError(
+            "The number of distance metrics must match the number of edge length thresholds."
+        )
 
-    if distance_metric == "louvain":
-        return calculate_louvain_neighborhoods(network, louvain_resolution, random_seed=random_seed)
-    if distance_metric == "greedy_modularity":
-        return calculate_greedy_modularity_neighborhoods(network)
-    if distance_metric == "label_propagation":
-        return calculate_label_propagation_neighborhoods(network)
-    if distance_metric == "markov_clustering":
-        return calculate_markov_clustering_neighborhoods(network)
-    if distance_metric == "walktrap":
-        return calculate_walktrap_neighborhoods(network)
-    if distance_metric == "spinglass":
-        return calculate_spinglass_neighborhoods(network)
-
-    raise ValueError(
-        "Incorrect distance metric specified. Please choose from 'greedy_modularity', 'louvain',"
-        "'label_propagation', 'markov_clustering', 'walktrap', 'spinglass'."
-    )
+    # Initialize combined neighborhood matrix
+    num_nodes = network.number_of_nodes()
+    combined_neighborhoods = np.zeros((num_nodes, num_nodes), dtype=int)
 
+    # Loop through each distance metric and corresponding edge rank fraction
+    for metric, percentile in zip(distance_metric, fraction_shortest_edges):
+        # Call the appropriate neighborhood function based on the metric
+        if metric == "greedy_modularity":
+            neighborhoods = calculate_greedy_modularity_neighborhoods(
+                network, fraction_shortest_edges=percentile
+            )
+        elif metric == "label_propagation":
+            neighborhoods = calculate_label_propagation_neighborhoods(
+                network, fraction_shortest_edges=percentile
+            )
+        elif metric == "leiden":
+            neighborhoods = calculate_leiden_neighborhoods(
+                network,
+                resolution=leiden_resolution,
+                fraction_shortest_edges=percentile,
+                random_seed=random_seed,
+            )
+        elif metric == "louvain":
+            neighborhoods = calculate_louvain_neighborhoods(
+                network,
+                resolution=louvain_resolution,
+                fraction_shortest_edges=percentile,
+                random_seed=random_seed,
+            )
+        elif metric == "markov_clustering":
+            neighborhoods = calculate_markov_clustering_neighborhoods(
+                network, fraction_shortest_edges=percentile
+            )
+        elif metric == "spinglass":
+            neighborhoods = calculate_spinglass_neighborhoods(
+                network, fraction_shortest_edges=percentile
+            )
+        elif metric == "walktrap":
+            neighborhoods = calculate_walktrap_neighborhoods(
+                network, fraction_shortest_edges=percentile
+            )
+        else:
+            raise ValueError(
+                "Incorrect distance metric specified. Please choose from 'greedy_modularity', 'label_propagation',"
+                "'leiden', 'louvain', 'markov_clustering', 'spinglass', 'walktrap'."
+            )
 
-def _create_percentile_limited_subgraph(G: nx.Graph, edge_length_percentile: float) -> nx.Graph:
-    """Create a subgraph containing all nodes and edges where the edge length is below the
-    specified percentile of all edge lengths in the input graph.
+        # Sum the neighborhood matrices
+        combined_neighborhoods += neighborhoods
 
-    Args:
-        G (nx.Graph): The input graph with 'length' attributes on edges.
-        edge_length_percentile (float): The percentile (between 0 and 1) to filter edges by length.
+    # Ensure that the maximum value in each row is set to 1
+    # This ensures that for each row, only the strongest relationship (the maximum value) is retained,
+    # while all other values are reset to 0. This transformation simplifies the neighborhood matrix by
+    # focusing on the most significant connection per row (or nodes).
+    combined_neighborhoods = _set_max_row_value_to_one(combined_neighborhoods)
 
-    Returns:
-        nx.Graph: A subgraph with all nodes and edges where the edge length is below the
-        calculated threshold length.
-    """
-    # Extract edge lengths and handle missing lengths
-    edge_lengths = [d["length"] for _, _, d in G.edges(data=True) if "length" in d]
-    if not edge_lengths:
-        raise ValueError(
-            "No edge lengths found in the graph. Ensure edges have 'length' attributes."
-        )
+    return combined_neighborhoods
 
-    # Calculate the specific edge length for the given percentile
-    percentile_length = np.percentile(edge_lengths, edge_length_percentile * 100)
-    # Create the subgraph by directly filtering edges during iteration
-    subgraph = nx.Graph()
-    subgraph.add_nodes_from(G.nodes(data=True))  # Retain all nodes from the original graph
-    # Add edges below the specified percentile length in a single pass
-    for u, v, d in G.edges(data=True):
-        if d.get("length", 1) <= percentile_length:
-            subgraph.add_edge(u, v, **d)
 
-    # Return the subgraph; optionally check if it's too sparse
-    if subgraph.number_of_edges() == 0:
-        raise Warning("The resulting subgraph has no edges. Consider adjusting the percentile.")
+def _set_max_row_value_to_one(matrix: np.ndarray) -> np.ndarray:
+    """For each row in the input matrix, set the maximum value(s) to 1 and all other values to 0. This is particularly
+    useful for neighborhood matrices that have undergone multiple neighborhood detection algorithms, where the
+    maximum value in each row represents the most significant relationship per node in the combined neighborhoods.
+
+    Args:
+        matrix (np.ndarray): A 2D numpy array representing the neighborhood matrix.
 
-    return subgraph
+    Returns:
+        np.ndarray: The modified matrix where only the maximum value(s) in each row is set to 1, and others are set to 0.
+    """
+    # Find the maximum value in each row (column-wise max operation)
+    max_values = np.max(matrix, axis=1, keepdims=True)
+    # Create a boolean mask where elements are True if they are the max value in their row
+    max_mask = matrix == max_values
+    # Set all elements to 0, and then set the maximum value positions to 1
+    matrix[:] = 0  # Set everything to 0
+    matrix[max_mask] = 1  # Set only the max values to 1
+    return matrix
 
 
 def process_neighborhoods(
@@ -120,157 +154,170 @@ def process_neighborhoods(
 
     Args:
         network (nx.Graph): The network data structure used for imputing and pruning neighbors.
-        neighborhoods (dict): Dictionary containing 'enrichment_matrix', 'binary_enrichment_matrix', and 'significant_enrichment_matrix'.
+        neighborhoods (Dict[str, Any]): Dictionary containing 'significance_matrix', 'significant_binary_significance_matrix', and 'significant_significance_matrix'.
         impute_depth (int, optional): Depth for imputing neighbors. Defaults to 0.
         prune_threshold (float, optional): Distance threshold for pruning neighbors. Defaults to 0.0.
 
     Returns:
-        dict: Processed neighborhoods data, including the updated matrices and enrichment counts.
+        Dict[str, Any]: Processed neighborhoods data, including the updated matrices and significance counts.
     """
-    enrichment_matrix = neighborhoods["enrichment_matrix"]
-    binary_enrichment_matrix = neighborhoods["binary_enrichment_matrix"]
-    significant_enrichment_matrix = neighborhoods["significant_enrichment_matrix"]
+    significance_matrix = neighborhoods["significance_matrix"]
+    significant_binary_significance_matrix = neighborhoods["significant_binary_significance_matrix"]
+    significant_significance_matrix = neighborhoods["significant_significance_matrix"]
     logger.debug(f"Imputation depth: {impute_depth}")
     if impute_depth:
         (
-            enrichment_matrix,
-            binary_enrichment_matrix,
-            significant_enrichment_matrix,
+            significance_matrix,
+            significant_binary_significance_matrix,
+            significant_significance_matrix,
         ) = _impute_neighbors(
             network,
-            enrichment_matrix,
-            binary_enrichment_matrix,
+            significance_matrix,
+            significant_binary_significance_matrix,
             max_depth=impute_depth,
         )
 
     logger.debug(f"Pruning threshold: {prune_threshold}")
     if prune_threshold:
         (
-            enrichment_matrix,
-            binary_enrichment_matrix,
-            significant_enrichment_matrix,
+            significance_matrix,
+            significant_binary_significance_matrix,
+            significant_significance_matrix,
         ) = _prune_neighbors(
             network,
-            enrichment_matrix,
-            binary_enrichment_matrix,
+            significance_matrix,
+            significant_binary_significance_matrix,
             distance_threshold=prune_threshold,
         )
 
-    neighborhood_enrichment_counts = np.sum(binary_enrichment_matrix, axis=0)
-    node_enrichment_sums = np.sum(enrichment_matrix, axis=1)
+    neighborhood_significance_counts = np.sum(significant_binary_significance_matrix, axis=0)
+    node_significance_sums = np.sum(significance_matrix, axis=1)
     return {
-        "enrichment_matrix": enrichment_matrix,
-        "binary_enrichment_matrix": binary_enrichment_matrix,
-        "significant_enrichment_matrix": significant_enrichment_matrix,
-        "neighborhood_enrichment_counts": neighborhood_enrichment_counts,
-        "node_enrichment_sums": node_enrichment_sums,
+        "significance_matrix": significance_matrix,
+        "significant_binary_significance_matrix": significant_binary_significance_matrix,
+        "significant_significance_matrix": significant_significance_matrix,
+        "neighborhood_significance_counts": neighborhood_significance_counts,
+        "node_significance_sums": node_significance_sums,
     }
 
 
 def _impute_neighbors(
     network: nx.Graph,
-    enrichment_matrix: np.ndarray,
-    binary_enrichment_matrix: np.ndarray,
+    significance_matrix: np.ndarray,
+    significant_binary_significance_matrix: np.ndarray,
     max_depth: int = 3,
 ) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
-    """Impute rows with sums of zero in the enrichment matrix based on the closest non-zero neighbors in the network graph.
+    """Impute rows with sums of zero in the significance matrix based on the closest non-zero neighbors in the network graph.
 
     Args:
         network (nx.Graph): The network graph with nodes having IDs matching the matrix indices.
-        enrichment_matrix (np.ndarray): The enrichment matrix with rows to be imputed.
-        binary_enrichment_matrix (np.ndarray): The alpha threshold matrix to be imputed similarly.
+        significance_matrix (np.ndarray): The significance matrix with rows to be imputed.
+        significant_binary_significance_matrix (np.ndarray): The alpha threshold matrix to be imputed similarly.
         max_depth (int): Maximum depth of nodes to traverse for imputing values.
 
     Returns:
-        tuple: A tuple containing:
-            - np.ndarray: The imputed enrichment matrix.
+        Tuple[np.ndarray, np.ndarray, np.ndarray]:
+            - np.ndarray: The imputed significance matrix.
             - np.ndarray: The imputed alpha threshold matrix.
-            - np.ndarray: The significant enrichment matrix with non-significant entries set to zero.
+            - np.ndarray: The significant significance matrix with non-significant entries set to zero.
     """
     # Calculate the distance threshold value based on the shortest distances
-    enrichment_matrix, binary_enrichment_matrix = _impute_neighbors_with_similarity(
-        network, enrichment_matrix, binary_enrichment_matrix, max_depth=max_depth
+    significance_matrix, significant_binary_significance_matrix = _impute_neighbors_with_similarity(
+        network, significance_matrix, significant_binary_significance_matrix, max_depth=max_depth
     )
     # Create a matrix where non-significant entries are set to zero
-    significant_enrichment_matrix = np.where(binary_enrichment_matrix == 1, enrichment_matrix, 0)
+    significant_significance_matrix = np.where(
+        significant_binary_significance_matrix == 1, significance_matrix, 0
+    )
 
-    return enrichment_matrix, binary_enrichment_matrix, significant_enrichment_matrix
+    return (
+        significance_matrix,
+        significant_binary_significance_matrix,
+        significant_significance_matrix,
+    )
 
 
 def _impute_neighbors_with_similarity(
     network: nx.Graph,
-    enrichment_matrix: np.ndarray,
-    binary_enrichment_matrix: np.ndarray,
+    significance_matrix: np.ndarray,
+    significant_binary_significance_matrix: np.ndarray,
     max_depth: int = 3,
 ) -> Tuple[np.ndarray, np.ndarray]:
-    """Impute non-enriched nodes based on the closest enriched neighbors' profiles and their similarity.
+    """Impute non-significant nodes based on the closest significant neighbors' profiles and their similarity.
 
     Args:
         network (nx.Graph): The network graph with nodes having IDs matching the matrix indices.
-        enrichment_matrix (np.ndarray): The enrichment matrix with rows to be imputed.
-        binary_enrichment_matrix (np.ndarray): The alpha threshold matrix to be imputed similarly.
+        significance_matrix (np.ndarray): The significance matrix with rows to be imputed.
+        significant_binary_significance_matrix (np.ndarray): The alpha threshold matrix to be imputed similarly.
         max_depth (int): Maximum depth of nodes to traverse for imputing values.
 
     Returns:
-        Tuple[np.ndarray, np.ndarray]: A tuple containing:
-            - The imputed enrichment matrix.
+        Tuple[np.ndarray, np.ndarray]:
+            - The imputed significance matrix.
             - The imputed alpha threshold matrix.
     """
     depth = 1
-    rows_to_impute = np.where(binary_enrichment_matrix.sum(axis=1) == 0)[0]
+    rows_to_impute = np.where(significant_binary_significance_matrix.sum(axis=1) == 0)[0]
     while len(rows_to_impute) and depth <= max_depth:
-        # Iterate over all enriched nodes
-        for row_index in range(binary_enrichment_matrix.shape[0]):
-            if binary_enrichment_matrix[row_index].sum() != 0:
-                enrichment_matrix, binary_enrichment_matrix = _process_node_imputation(
-                    row_index, network, enrichment_matrix, binary_enrichment_matrix, depth
+        # Iterate over all significant nodes
+        for row_index in range(significant_binary_significance_matrix.shape[0]):
+            if significant_binary_significance_matrix[row_index].sum() != 0:
+                (
+                    significance_matrix,
+                    significant_binary_significance_matrix,
+                ) = _process_node_imputation(
+                    row_index,
+                    network,
+                    significance_matrix,
+                    significant_binary_significance_matrix,
+                    depth,
                 )
 
         # Update rows to impute for the next iteration
-        rows_to_impute = np.where(binary_enrichment_matrix.sum(axis=1) == 0)[0]
+        rows_to_impute = np.where(significant_binary_significance_matrix.sum(axis=1) == 0)[0]
         depth += 1
 
-    return enrichment_matrix, binary_enrichment_matrix
+    return significance_matrix, significant_binary_significance_matrix
 
 
 def _process_node_imputation(
     row_index: int,
     network: nx.Graph,
-    enrichment_matrix: np.ndarray,
-    binary_enrichment_matrix: np.ndarray,
+    significance_matrix: np.ndarray,
+    significant_binary_significance_matrix: np.ndarray,
     depth: int,
 ) -> Tuple[np.ndarray, np.ndarray]:
-    """Process the imputation for a single node based on its enriched neighbors.
+    """Process the imputation for a single node based on its significant neighbors.
 
     Args:
-        row_index (int): The index of the enriched node being processed.
+        row_index (int): The index of the significant node being processed.
         network (nx.Graph): The network graph with nodes having IDs matching the matrix indices.
-        enrichment_matrix (np.ndarray): The enrichment matrix with rows to be imputed.
-        binary_enrichment_matrix (np.ndarray): The alpha threshold matrix to be imputed similarly.
+        significance_matrix (np.ndarray): The significance matrix with rows to be imputed.
+        significant_binary_significance_matrix (np.ndarray): The alpha threshold matrix to be imputed similarly.
         depth (int): Current depth for traversal.
 
     Returns:
-        Tuple[np.ndarray, np.ndarray]: The modified enrichment matrix and binary threshold matrix.
+        Tuple[np.ndarray, np.ndarray]: The modified significance matrix and binary threshold matrix.
     """
     # Check neighbors at the current depth
     neighbors = nx.single_source_shortest_path_length(network, row_index, cutoff=depth)
-    # Filter annotated neighbors (already enriched)
+    # Filter annotated neighbors (already significant)
     annotated_neighbors = [
         n
         for n in neighbors
         if n != row_index
-        and binary_enrichment_matrix[n].sum() != 0
-        and enrichment_matrix[n].sum() != 0
+        and significant_binary_significance_matrix[n].sum() != 0
+        and significance_matrix[n].sum() != 0
     ]
-    # Filter non-enriched neighbors
+    # Filter non-significant neighbors
     valid_neighbors = [
         n
         for n in neighbors
         if n != row_index
-        and binary_enrichment_matrix[n].sum() == 0
-        and enrichment_matrix[n].sum() == 0
+        and significant_binary_significance_matrix[n].sum() == 0
+        and significance_matrix[n].sum() == 0
     ]
-    # If there are valid non-enriched neighbors
+    # If there are valid non-significant neighbors
     if valid_neighbors and annotated_neighbors:
         # Calculate distances to annotated neighbors
         distances_to_annotated = [
@@ -281,7 +328,7 @@ def _process_node_imputation(
         iqr = q3 - q1
         lower_bound = q1 - 1.5 * iqr
         upper_bound = q3 + 1.5 * iqr
-        # Filter valid non-enriched neighbors that fall within the IQR bounds
+        # Filter valid non-significant neighbors that fall within the IQR bounds
         valid_neighbors_within_iqr = [
             n
             for n in valid_neighbors
@@ -295,8 +342,8 @@ def _process_node_imputation(
                 def sum_pairwise_cosine_similarities(neighbor):
                     return sum(
                         cosine_similarity(
-                            enrichment_matrix[neighbor].reshape(1, -1),
-                            enrichment_matrix[other_neighbor].reshape(1, -1),
+                            significance_matrix[neighbor].reshape(1, -1),
+                            significance_matrix[other_neighbor].reshape(1, -1),
                         )[0][0]
                         for other_neighbor in valid_neighbors_within_iqr
                         if other_neighbor != neighbor
@@ -308,40 +355,46 @@ def _process_node_imputation(
             else:
                 most_similar_neighbor = valid_neighbors_within_iqr[0]
 
-            # Impute the most similar non-enriched neighbor with the enriched node's data, scaled by depth
-            enrichment_matrix[most_similar_neighbor] = enrichment_matrix[row_index] / np.sqrt(
+            # Impute the most similar non-significant neighbor with the significant node's data, scaled by depth
+            significance_matrix[most_similar_neighbor] = significance_matrix[row_index] / np.sqrt(
                 depth + 1
             )
-            binary_enrichment_matrix[most_similar_neighbor] = binary_enrichment_matrix[row_index]
+            significant_binary_significance_matrix[most_similar_neighbor] = (
+                significant_binary_significance_matrix[row_index]
+            )
 
-    return enrichment_matrix, binary_enrichment_matrix
+    return significance_matrix, significant_binary_significance_matrix
 
 
 def _prune_neighbors(
     network: nx.Graph,
-    enrichment_matrix: np.ndarray,
-    binary_enrichment_matrix: np.ndarray,
+    significance_matrix: np.ndarray,
+    significant_binary_significance_matrix: np.ndarray,
     distance_threshold: float = 0.9,
 ) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
     """Remove outliers based on their rank for edge lengths.
 
     Args:
         network (nx.Graph): The network graph with nodes having IDs matching the matrix indices.
-        enrichment_matrix (np.ndarray): The enrichment matrix.
-        binary_enrichment_matrix (np.ndarray): The alpha threshold matrix.
+        significance_matrix (np.ndarray): The significance matrix.
+        significant_binary_significance_matrix (np.ndarray): The alpha threshold matrix.
         distance_threshold (float): Rank threshold (0 to 1) to determine outliers.
 
     Returns:
-        tuple: A tuple containing:
-            - np.ndarray: The updated enrichment matrix with outliers set to zero.
+        Tuple[np.ndarray, np.ndarray, np.ndarray]:
+            - np.ndarray: The updated significance matrix with outliers set to zero.
             - np.ndarray: The updated alpha threshold matrix with outliers set to zero.
-            - np.ndarray: The significant enrichment matrix, where non-significant entries are set to zero.
+            - np.ndarray: The significant significance matrix, where non-significant entries are set to zero.
     """
-    # Identify indices with non-zero rows in the binary enrichment matrix
-    non_zero_indices = np.where(binary_enrichment_matrix.sum(axis=1) != 0)[0]
+    # Identify indices with non-zero rows in the binary significance matrix
+    non_zero_indices = np.where(significant_binary_significance_matrix.sum(axis=1) != 0)[0]
     median_distances = []
     for node in non_zero_indices:
-        neighbors = [n for n in network.neighbors(node) if binary_enrichment_matrix[n].sum() != 0]
+        neighbors = [
+            n
+            for n in network.neighbors(node)
+            if significant_binary_significance_matrix[n].sum() != 0
+        ]
         if neighbors:
             median_distance = np.median(
                 [_get_euclidean_distance(node, n, network) for n in neighbors]
@@ -353,20 +406,28 @@ def _prune_neighbors(
     # Prune nodes that are outliers based on the distance threshold
     for row_index in non_zero_indices:
         neighbors = [
-            n for n in network.neighbors(row_index) if binary_enrichment_matrix[n].sum() != 0
+            n
+            for n in network.neighbors(row_index)
+            if significant_binary_significance_matrix[n].sum() != 0
         ]
         if neighbors:
             median_distance = np.median(
                 [_get_euclidean_distance(row_index, n, network) for n in neighbors]
             )
             if median_distance >= distance_threshold_value:
-                enrichment_matrix[row_index] = 0
-                binary_enrichment_matrix[row_index] = 0
+                significance_matrix[row_index] = 0
+                significant_binary_significance_matrix[row_index] = 0
 
     # Create a matrix where non-significant entries are set to zero
-    significant_enrichment_matrix = np.where(binary_enrichment_matrix == 1, enrichment_matrix, 0)
+    significant_significance_matrix = np.where(
+        significant_binary_significance_matrix == 1, significance_matrix, 0
+    )
 
-    return enrichment_matrix, binary_enrichment_matrix, significant_enrichment_matrix
+    return (
+        significance_matrix,
+        significant_binary_significance_matrix,
+        significant_significance_matrix,
+    )
 
 
 def _get_euclidean_distance(node1: Any, node2: Any, network: nx.Graph) -> float:
@@ -408,7 +469,7 @@ def _calculate_threshold(median_distances: List, distance_threshold: float) -> f
     """Calculate the distance threshold based on the given median distances and a percentile threshold.
 
     Args:
-        median_distances (list): An array of median distances.
+        median_distances (List): An array of median distances.
         distance_threshold (float): A percentile threshold (0 to 1) used to determine the distance cutoff.
 
     Returns:
@@ -416,7 +477,7 @@ def _calculate_threshold(median_distances: List, distance_threshold: float) -> f
     """
     # Sort the median distances
     sorted_distances = np.sort(median_distances)
-    # Compute the rank percentiles for the sorted distances
+    # Compute the rank fractions for the sorted distances
     rank_percentiles = np.linspace(0, 1, len(sorted_distances))
     # Interpolating the ranks to 1000 evenly spaced percentiles
     interpolated_percentiles = np.linspace(0, 1, 1000)

risk/network/__init__.py

@@ -3,6 +3,4 @@ risk/network
 ~~~~~~~~~~~~
 """
 
-from .graph import NetworkGraph
-from .io import NetworkIO
-from .plot import NetworkPlotter
+from risk.network.io import NetworkIO