risk-network 0.0.10__py3-none-any.whl → 0.0.12__py3-none-any.whl

risk/annotation/nltk_setup.py

@@ -0,0 +1,86 @@
+"""
+risk/annotation/nltk_setup
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+"""
+
+import os
+import zipfile
+from typing import List, Optional, Tuple
+
+import nltk
+from nltk.data import find
+from nltk.data import path as nltk_data_path
+
+from risk.log import logger
+
+
+def setup_nltk_resources(required_resources: Optional[List[Tuple[str, str]]] = None) -> None:
+    """Ensures all required NLTK resources are available and properly extracted.
+    Uses NLTK's default paths and mechanisms.
+
+    Args:
+        required_resources (List[Tuple[str, str]], optional): List of required resources
+            to download and extract. Each tuple should contain the resource path within
+            NLTK data and the package name. Defaults to None.
+    """
+    if required_resources is None:
+        required_resources = [
+            ("tokenizers/punkt", "punkt"),
+            ("tokenizers/punkt_tab", "punkt_tab"),
+            ("corpora/stopwords", "stopwords"),
+            ("corpora/wordnet", "wordnet"),
+        ]
+
+    # Process each resource
+    for resource_path, package_name in required_resources:
+        try:
+            # First try to find the resource - this is how NLTK checks if it's available
+            find(resource_path)
+        except LookupError:
+            # Resource not found, download it
+            logger.info(f"Downloading missing NLTK resource: {package_name}")
+            nltk.download(package_name, quiet=True)
+
+        # Even if find() succeeded, the resource might be a zip that failed to extract
+        # Check if we need to manually extract zips
+        verify_and_extract_if_needed(resource_path, package_name)
+
+
+def verify_and_extract_if_needed(resource_path: str, package_name: str) -> None:
+    """Verifies if the resource is properly extracted and extracts if needed. Respects
+    NLTK's directory structure where the extracted content should be in the same directory
+    as the zip file.
+
+    Args:
+        resource_path (str): Path to the resource within NLTK data.
+        package_name (str): Name of the NLTK package.
+    """
+    # Get the directory and base name from the resource path
+    path_parts = resource_path.split("/")
+    resource_type = path_parts[0]  # 'corpora', 'tokenizers', etc.
+    resource_name = path_parts[-1]  # 'wordnet', 'punkt', etc.
+
+    # Check all NLTK data directories
+    for base in nltk_data_path:
+        # For resource paths like 'corpora/wordnet', the zip file is at '~/nltk_data/corpora/wordnet.zip'
+        # and the extracted directory should be at '~/nltk_data/corpora/wordnet'
+        resource_dir = os.path.join(base, resource_type)
+        zip_path = os.path.join(resource_dir, f"{resource_name}.zip")
+        folder_path = os.path.join(resource_dir, resource_name)
+
+        # If zip exists but folder doesn't, extraction is needed
+        if os.path.exists(zip_path) and not os.path.exists(folder_path):
+            logger.info(f"Found unextracted zip for {package_name}, extracting...")
+            try:
+                with zipfile.ZipFile(zip_path, "r") as zf:
+                    # Extract files to the same directory where the zip file is located
+                    zf.extractall(path=resource_dir)
+
+                if os.path.exists(folder_path):
+                    logger.info(f"Successfully extracted {package_name}")
+                else:
+                    logger.warning(
+                        f"Extraction completed but resource directory not found for {package_name}"
+                    )
+            except Exception as e:
+                logger.error(f"Failed to extract {package_name}: {e}")

risk/log/__init__.py

@@ -3,7 +3,7 @@ risk/log
 ~~~~~~~~
 """
 
-from risk.log.console import logger, log_header, set_global_verbosity
+from risk.log.console import log_header, logger, set_global_verbosity
 from risk.log.parameters import Params
 
 # Initialize the global parameters logger

risk/log/parameters.py

@@ -11,7 +11,7 @@ from typing import Any, Dict
 
 import numpy as np
 
-from risk.log.console import logger, log_header
+from risk.log.console import log_header, logger
 
 # Suppress all warnings - this is to resolve warnings from multiprocessing
 warnings.filterwarnings("ignore")
@@ -21,7 +21,7 @@ class Params:
     """Handles the storage and logging of various parameters for network analysis.
 
     The Params class provides methods to log parameters related to different components of the analysis,
-    such as the network, annotations, neighborhoods, graph, and plotter settings. It also stores
+    such as the network, annotation, neighborhoods, graph, and plotter settings. It also stores
     the current datetime when the parameters were initialized.
     """
 
@@ -33,7 +33,7 @@ class Params:
     def initialize(self) -> None:
         """Initialize the parameter dictionaries for different components."""
         self.network = {}
-        self.annotations = {}
+        self.annotation = {}
         self.neighborhoods = {}
         self.graph = {}
         self.plotter = {}
@@ -46,13 +46,13 @@ class Params:
         """
         self.network = {**self.network, **kwargs}
 
-    def log_annotations(self, **kwargs) -> None:
+    def log_annotation(self, **kwargs) -> None:
         """Log annotation-related parameters.
 
         Args:
             **kwargs: Annotation parameters to log.
         """
-        self.annotations = {**self.annotations, **kwargs}
+        self.annotation = {**self.annotation, **kwargs}
 
     def log_neighborhoods(self, **kwargs) -> None:
         """Log neighborhood-related parameters.
@@ -137,9 +137,9 @@ class Params:
             Dict[str, Any]: A dictionary containing the processed parameters.
         """
         log_header("Loading parameters")
-        return _convert_ndarray_to_list(
+        return self._convert_ndarray_to_list(
             {
-                "annotations": self.annotations,
+                "annotation": self.annotation,
                 "datetime": self.datetime,
                 "graph": self.graph,
                 "neighborhoods": self.neighborhoods,
@@ -148,25 +148,24 @@ class Params:
             }
         )
 
+    def _convert_ndarray_to_list(self, d: Dict[str, Any]) -> Dict[str, Any]:
+        """Recursively convert all np.ndarray values in the dictionary to lists.
 
-def _convert_ndarray_to_list(d: Dict[str, Any]) -> Dict[str, Any]:
-    """Recursively convert all np.ndarray values in the dictionary to lists.
-
-    Args:
-        d (Dict[str, Any]): The dictionary to process.
+        Args:
+            d (Dict[str, Any]): The dictionary to process.
 
-    Returns:
-        Dict[str, Any]: The processed dictionary with np.ndarray values converted to lists.
-    """
-    if isinstance(d, dict):
-        # Recursively process each value in the dictionary
-        return {k: _convert_ndarray_to_list(v) for k, v in d.items()}
-    if isinstance(d, list):
-        # Recursively process each item in the list
-        return [_convert_ndarray_to_list(v) for v in d]
-    if isinstance(d, np.ndarray):
-        # Convert numpy arrays to lists
-        return d.tolist()
-
-    # Return the value unchanged if it's not a dict, List, or ndarray
-    return d
+        Returns:
+            Dict[str, Any]: The processed dictionary with np.ndarray values converted to lists.
+        """
+        if isinstance(d, dict):
+            # Recursively process each value in the dictionary
+            return {k: self._convert_ndarray_to_list(v) for k, v in d.items()}
+        if isinstance(d, list):
+            # Recursively process each item in the list
+            return [self._convert_ndarray_to_list(v) for v in d]
+        if isinstance(d, np.ndarray):
+            # Convert numpy arrays to lists
+            return d.tolist()
+
+        # Return the value unchanged if it's not a dict, List, or ndarray
+        return d

risk/neighborhoods/__init__.py

@@ -4,5 +4,4 @@ risk/neighborhoods
 """
 
 from risk.neighborhoods.domains import define_domains, trim_domains
-from risk.neighborhoods.api import NeighborhoodsAPI
 from risk.neighborhoods.neighborhoods import process_neighborhoods

risk/neighborhoods/api.py

@@ -10,9 +10,9 @@ import networkx as nx
 import numpy as np
 from scipy.sparse import csr_matrix
 
-from risk.log import logger, log_header, params
+from risk.log import log_header, logger, params
 from risk.neighborhoods.neighborhoods import get_network_neighborhoods
-from risk.stats import (
+from risk.neighborhoods.stats import (
     compute_binom_test,
     compute_chi2_test,
     compute_hypergeom_test,
@@ -28,13 +28,13 @@ class NeighborhoodsAPI:
     The NeighborhoodsAPI class provides methods to load neighborhood results from statistical tests.
     """
 
-    def __init__() -> None:
+    def __init__(self) -> None:
         pass
 
-    def load_neighborhoods_by_binom(
+    def load_neighborhoods_binom(
         self,
         network: nx.Graph,
-        annotations: Dict[str, Any],
+        annotation: Dict[str, Any],
         distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
         louvain_resolution: float = 0.1,
         leiden_resolution: float = 1.0,
@@ -46,7 +46,7 @@ class NeighborhoodsAPI:
 
         Args:
             network (nx.Graph): The network graph.
-            annotations (Dict[str, Any]): The annotations associated with the network.
+            annotation (Dict[str, Any]): The annotation associated with the network.
             distance_metric (str, List, Tuple, or np.ndarray, optional): The distance metric(s) to use. Can be a string for one
                 metric or a list/tuple/ndarray of metrics ('greedy_modularity', 'louvain', 'leiden', 'label_propagation',
                 'markov_clustering', 'walktrap', 'spinglass'). Defaults to 'louvain'.
@@ -55,7 +55,7 @@ class NeighborhoodsAPI:
             fraction_shortest_edges (float, List, Tuple, or np.ndarray, optional): Shortest edge rank fraction threshold(s) for creating subgraphs.
                 Can be a single float for one threshold or a list/tuple of floats corresponding to multiple thresholds.
                 Defaults to 0.5.
-            null_distribution (str, optional): Type of null distribution ('network' or 'annotations'). Defaults to "network".
+            null_distribution (str, optional): Type of null distribution ('network' or 'annotation'). Defaults to "network".
             random_seed (int, optional): Seed for random number generation. Defaults to 888.
 
         Returns:
@@ -65,7 +65,7 @@ class NeighborhoodsAPI:
         # Compute neighborhood significance using the binomial test
         return self._load_neighborhoods_by_statistical_test(
             network=network,
-            annotations=annotations,
+            annotation=annotation,
             distance_metric=distance_metric,
             louvain_resolution=louvain_resolution,
             leiden_resolution=leiden_resolution,
@@ -76,10 +76,10 @@ class NeighborhoodsAPI:
             statistical_test_function=compute_binom_test,
         )
 
-    def load_neighborhoods_by_chi2(
+    def load_neighborhoods_chi2(
         self,
         network: nx.Graph,
-        annotations: Dict[str, Any],
+        annotation: Dict[str, Any],
         distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
         louvain_resolution: float = 0.1,
         leiden_resolution: float = 1.0,
@@ -91,7 +91,7 @@ class NeighborhoodsAPI:
 
         Args:
             network (nx.Graph): The network graph.
-            annotations (Dict[str, Any]): The annotations associated with the network.
+            annotation (Dict[str, Any]): The annotation associated with the network.
             distance_metric (str, List, Tuple, or np.ndarray, optional): The distance metric(s) to use. Can be a string for one
                 metric or a list/tuple/ndarray of metrics ('greedy_modularity', 'louvain', 'leiden', 'label_propagation',
                 'markov_clustering', 'walktrap', 'spinglass'). Defaults to 'louvain'.
@@ -100,7 +100,7 @@ class NeighborhoodsAPI:
             fraction_shortest_edges (float, List, Tuple, or np.ndarray, optional): Shortest edge rank fraction threshold(s) for creating subgraphs.
                 Can be a single float for one threshold or a list/tuple of floats corresponding to multiple thresholds.
                 Defaults to 0.5.
-            null_distribution (str, optional): Type of null distribution ('network' or 'annotations'). Defaults to "network".
+            null_distribution (str, optional): Type of null distribution ('network' or 'annotation'). Defaults to "network".
             random_seed (int, optional): Seed for random number generation. Defaults to 888.
 
         Returns:
@@ -110,7 +110,7 @@ class NeighborhoodsAPI:
         # Compute neighborhood significance using the chi-squared test
         return self._load_neighborhoods_by_statistical_test(
             network=network,
-            annotations=annotations,
+            annotation=annotation,
             distance_metric=distance_metric,
             louvain_resolution=louvain_resolution,
             leiden_resolution=leiden_resolution,
@@ -121,10 +121,10 @@ class NeighborhoodsAPI:
             statistical_test_function=compute_chi2_test,
         )
 
-    def load_neighborhoods_by_hypergeom(
+    def load_neighborhoods_hypergeom(
         self,
         network: nx.Graph,
-        annotations: Dict[str, Any],
+        annotation: Dict[str, Any],
         distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
         louvain_resolution: float = 0.1,
         leiden_resolution: float = 1.0,
@@ -136,7 +136,7 @@ class NeighborhoodsAPI:
 
         Args:
             network (nx.Graph): The network graph.
-            annotations (Dict[str, Any]): The annotations associated with the network.
+            annotation (Dict[str, Any]): The annotation associated with the network.
             distance_metric (str, List, Tuple, or np.ndarray, optional): The distance metric(s) to use. Can be a string for one
                 metric or a list/tuple/ndarray of metrics ('greedy_modularity', 'louvain', 'leiden', 'label_propagation',
                 'markov_clustering', 'walktrap', 'spinglass'). Defaults to 'louvain'.
@@ -145,7 +145,7 @@ class NeighborhoodsAPI:
             fraction_shortest_edges (float, List, Tuple, or np.ndarray, optional): Shortest edge rank fraction threshold(s) for creating subgraphs.
                 Can be a single float for one threshold or a list/tuple of floats corresponding to multiple thresholds.
                 Defaults to 0.5.
-            null_distribution (str, optional): Type of null distribution ('network' or 'annotations'). Defaults to "network".
+            null_distribution (str, optional): Type of null distribution ('network' or 'annotation'). Defaults to "network".
             random_seed (int, optional): Seed for random number generation. Defaults to 888.
 
         Returns:
@@ -155,7 +155,7 @@ class NeighborhoodsAPI:
         # Compute neighborhood significance using the hypergeometric test
         return self._load_neighborhoods_by_statistical_test(
             network=network,
-            annotations=annotations,
+            annotation=annotation,
             distance_metric=distance_metric,
             louvain_resolution=louvain_resolution,
             leiden_resolution=leiden_resolution,
@@ -166,10 +166,10 @@ class NeighborhoodsAPI:
             statistical_test_function=compute_hypergeom_test,
         )
 
-    def load_neighborhoods_by_permutation(
+    def load_neighborhoods_permutation(
         self,
         network: nx.Graph,
-        annotations: Dict[str, Any],
+        annotation: Dict[str, Any],
         distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
         louvain_resolution: float = 0.1,
         leiden_resolution: float = 1.0,
@@ -184,7 +184,7 @@ class NeighborhoodsAPI:
 
         Args:
             network (nx.Graph): The network graph.
-            annotations (Dict[str, Any]): The annotations associated with the network.
+            annotation (Dict[str, Any]): The annotation associated with the network.
             distance_metric (str, List, Tuple, or np.ndarray, optional): The distance metric(s) to use. Can be a string for one
                 metric or a list/tuple/ndarray of metrics ('greedy_modularity', 'louvain', 'leiden', 'label_propagation',
                 'markov_clustering', 'walktrap', 'spinglass'). Defaults to 'louvain'.
@@ -194,7 +194,7 @@ class NeighborhoodsAPI:
                 Can be a single float for one threshold or a list/tuple of floats corresponding to multiple thresholds.
                 Defaults to 0.5.
             score_metric (str, optional): Scoring metric for neighborhood significance. Defaults to "sum".
-            null_distribution (str, optional): Type of null distribution ('network' or 'annotations'). Defaults to "network".
+            null_distribution (str, optional): Type of null distribution ('network' or 'annotation'). Defaults to "network".
             num_permutations (int, optional): Number of permutations for significance testing. Defaults to 1000.
             random_seed (int, optional): Seed for random number generation. Defaults to 888.
             max_workers (int, optional): Maximum number of workers for parallel computation. Defaults to 1.
@@ -210,7 +210,7 @@ class NeighborhoodsAPI:
         # Compute neighborhood significance using the permutation test
         return self._load_neighborhoods_by_statistical_test(
             network=network,
-            annotations=annotations,
+            annotation=annotation,
             distance_metric=distance_metric,
             louvain_resolution=louvain_resolution,
             leiden_resolution=leiden_resolution,
@@ -224,10 +224,10 @@ class NeighborhoodsAPI:
             max_workers=max_workers,
         )
 
-    def load_neighborhoods_by_poisson(
+    def load_neighborhoods_poisson(
         self,
         network: nx.Graph,
-        annotations: Dict[str, Any],
+        annotation: Dict[str, Any],
         distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
         louvain_resolution: float = 0.1,
         leiden_resolution: float = 1.0,
@@ -239,7 +239,7 @@ class NeighborhoodsAPI:
 
         Args:
             network (nx.Graph): The network graph.
-            annotations (Dict[str, Any]): The annotations associated with the network.
+            annotation (Dict[str, Any]): The annotation associated with the network.
             distance_metric (str, List, Tuple, or np.ndarray, optional): The distance metric(s) to use. Can be a string for one
                 metric or a list/tuple/ndarray of metrics ('greedy_modularity', 'louvain', 'leiden', 'label_propagation',
                 'markov_clustering', 'walktrap', 'spinglass'). Defaults to 'louvain'.
@@ -248,7 +248,7 @@ class NeighborhoodsAPI:
             fraction_shortest_edges (float, List, Tuple, or np.ndarray, optional): Shortest edge rank fraction threshold(s) for creating subgraphs.
                 Can be a single float for one threshold or a list/tuple of floats corresponding to multiple thresholds.
                 Defaults to 0.5.
-            null_distribution (str, optional): Type of null distribution ('network' or 'annotations'). Defaults to "network".
+            null_distribution (str, optional): Type of null distribution ('network' or 'annotation'). Defaults to "network".
             random_seed (int, optional): Seed for random number generation. Defaults to 888.
 
         Returns:
@@ -258,7 +258,7 @@ class NeighborhoodsAPI:
         # Compute neighborhood significance using the Poisson test
         return self._load_neighborhoods_by_statistical_test(
             network=network,
-            annotations=annotations,
+            annotation=annotation,
             distance_metric=distance_metric,
             louvain_resolution=louvain_resolution,
             leiden_resolution=leiden_resolution,
@@ -269,10 +269,10 @@ class NeighborhoodsAPI:
             statistical_test_function=compute_poisson_test,
         )
 
-    def load_neighborhoods_by_zscore(
+    def load_neighborhoods_zscore(
         self,
         network: nx.Graph,
-        annotations: Dict[str, Any],
+        annotation: Dict[str, Any],
         distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
         louvain_resolution: float = 0.1,
         leiden_resolution: float = 1.0,
@@ -284,7 +284,7 @@ class NeighborhoodsAPI:
 
         Args:
             network (nx.Graph): The network graph.
-            annotations (Dict[str, Any]): The annotations associated with the network.
+            annotation (Dict[str, Any]): The annotation associated with the network.
             distance_metric (str, List, Tuple, or np.ndarray, optional): The distance metric(s) to use. Can be a string for one
                 metric or a list/tuple/ndarray of metrics ('greedy_modularity', 'louvain', 'leiden', 'label_propagation',
                 'markov_clustering', 'walktrap', 'spinglass'). Defaults to 'louvain'.
@@ -293,7 +293,7 @@ class NeighborhoodsAPI:
             fraction_shortest_edges (float, List, Tuple, or np.ndarray, optional): Shortest edge rank fraction threshold(s) for creating subgraphs.
                 Can be a single float for one threshold or a list/tuple of floats corresponding to multiple thresholds.
                 Defaults to 0.5.
-            null_distribution (str, optional): Type of null distribution ('network' or 'annotations'). Defaults to "network".
+            null_distribution (str, optional): Type of null distribution ('network' or 'annotation'). Defaults to "network".
             random_seed (int, optional): Seed for random number generation. Defaults to 888.
 
         Returns:
@@ -303,7 +303,7 @@ class NeighborhoodsAPI:
         # Compute neighborhood significance using the z-score test
         return self._load_neighborhoods_by_statistical_test(
             network=network,
-            annotations=annotations,
+            annotation=annotation,
             distance_metric=distance_metric,
             louvain_resolution=louvain_resolution,
             leiden_resolution=leiden_resolution,
@@ -317,7 +317,7 @@ class NeighborhoodsAPI:
     def _load_neighborhoods_by_statistical_test(
         self,
         network: nx.Graph,
-        annotations: Dict[str, Any],
+        annotation: Dict[str, Any],
         distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
         louvain_resolution: float = 0.1,
         leiden_resolution: float = 1.0,
@@ -332,7 +332,7 @@ class NeighborhoodsAPI:
 
         Args:
             network (nx.Graph): The input network graph.
-            annotations (Dict[str, Any]): Annotation data associated with the network, including a "matrix" key with annotation values.
+            annotation (Dict[str, Any]): Annotation data associated with the network, including a "matrix" key with annotation values.
             distance_metric (Union[str, List, Tuple, np.ndarray], optional): The distance metric or clustering method to define neighborhoods.
                 Can be a string specifying one method (e.g., 'louvain', 'leiden') or a collection of methods.
                 Defaults to "louvain".
@@ -340,13 +340,13 @@ class NeighborhoodsAPI:
             leiden_resolution (float, optional): Resolution parameter for Leiden clustering. Defaults to 1.0.
             fraction_shortest_edges (Union[float, List, Tuple, np.ndarray], optional): Fraction of shortest edges to consider for creating subgraphs.
                 Can be a single value or a collection of thresholds for flexibility. Defaults to 0.5.
-            null_distribution (str, optional): The type of null distribution to use ('network' or 'annotations').
+            null_distribution (str, optional): The type of null distribution to use ('network' or 'annotation').
                 Defaults to "network".
             random_seed (int, optional): Seed for random number generation to ensure reproducibility. Defaults to 888.
             statistical_test_key (str, optional): Key or name of the statistical test to be applied (e.g., "hypergeom", "poisson").
                 Used for logging and debugging. Defaults to "hypergeom".
             statistical_test_function (Any, optional): The function implementing the statistical test.
-                It should accept neighborhoods, annotations, null distribution, and additional kwargs.
+                It should accept neighborhoods, annotation, null distribution, and additional kwargs.
                 Defaults to `compute_hypergeom_test`.
             **kwargs: Additional parameters to be passed to the statistical test function.
 
@@ -381,7 +381,7 @@ class NeighborhoodsAPI:
         # Apply statistical test function to compute neighborhood significance
         neighborhood_significance = statistical_test_function(
             neighborhoods=neighborhoods,
-            annotations=annotations["matrix"],
+            annotation=annotation["matrix"],
             null_distribution=null_distribution,
             **kwargs,
         )

risk/neighborhoods/community.py

@@ -8,7 +8,7 @@ import igraph as ig
 import markov_clustering as mc
 import networkx as nx
 import numpy as np
-from leidenalg import find_partition, RBConfigurationVertexPartition
+from leidenalg import RBConfigurationVertexPartition, find_partition
 from networkx.algorithms.community import greedy_modularity_communities
 from scipy.sparse import csr_matrix
 
@@ -27,6 +27,10 @@ def calculate_greedy_modularity_neighborhoods(
 
     Returns:
         csr_matrix: A binary neighborhood matrix (CSR) where nodes in the same community have 1, and others have 0.
+
+    Raises:
+        ValueError: If the subgraph has no edges after filtering.
+        Warning: If the resulting subgraph has no edges after filtering.
     """
     # Create a subgraph with the shortest edges based on the rank fraction
     subnetwork = _create_percentile_limited_subgraph(
@@ -67,6 +71,10 @@ def calculate_label_propagation_neighborhoods(
 
     Returns:
         csr_matrix: A binary neighborhood matrix (CSR) on Label Propagation.
+
+    Raises:
+        ValueError: If the subgraph has no edges after filtering.
+        Warning: If the resulting subgraph has no edges after filtering.
     """
     # Create a subgraph with the shortest edges based on the rank fraction
     subnetwork = _create_percentile_limited_subgraph(
@@ -115,6 +123,10 @@ def calculate_leiden_neighborhoods(
 
     Returns:
         csr_matrix: A binary neighborhood matrix (CSR) where nodes in the same community have 1, and others have 0.
+
+    Raises:
+        ValueError: If the subgraph has no edges after filtering.
+        Warning: If the resulting subgraph has no edges after filtering.
     """
     # Create a subgraph with the shortest edges based on the rank fraction
     subnetwork = _create_percentile_limited_subgraph(
@@ -167,6 +179,10 @@ def calculate_louvain_neighborhoods(
 
     Returns:
         csr_matrix: A binary neighborhood matrix in CSR format.
+
+    Raises:
+        ValueError: If the subgraph has no edges after filtering.
+        Warning: If the resulting subgraph has no edges after filtering.
     """
     # Create a subgraph with the shortest edges based on the rank fraction
     subnetwork = _create_percentile_limited_subgraph(
@@ -215,9 +231,10 @@ def calculate_markov_clustering_neighborhoods(
     Returns:
         csr_matrix: A binary neighborhood matrix (CSR) on Markov Clustering.
 
-    Warning:
-        This function temporarily converts the adjacency matrix to a dense format, which may lead to
-        high memory consumption for large graphs.
+    Raises:
+        ValueError: If the subgraph has no edges after filtering.
+        RuntimeError: If MCL fails to run.
+        Warning: If the resulting subgraph has no edges after filtering.
     """
     # Create a subgraph with the shortest edges based on the rank fraction
     subnetwork = _create_percentile_limited_subgraph(
@@ -283,6 +300,10 @@ def calculate_spinglass_neighborhoods(
 
     Returns:
         csr_matrix: A binary neighborhood matrix (CSR) based on Spinglass communities.
+
+    Raises:
+        ValueError: If the subgraph has no edges after filtering.
+        Warning: If the resulting subgraph has no edges after filtering.
     """
     # Create a subgraph with the shortest edges based on the rank fraction
     subnetwork = _create_percentile_limited_subgraph(
@@ -343,6 +364,10 @@ def calculate_walktrap_neighborhoods(
 
     Returns:
         csr_matrix: A binary neighborhood matrix (CSR) on Walktrap communities.
+
+    Raises:
+        ValueError: If the subgraph has no edges after filtering.
+        Warning: If the resulting subgraph has no edges after filtering.
     """
     # Create a subgraph with the shortest edges based on the rank fraction
     subnetwork = _create_percentile_limited_subgraph(
@@ -384,6 +409,10 @@ def _create_percentile_limited_subgraph(G: nx.Graph, fraction_shortest_edges: fl
     Returns:
         nx.Graph: A subgraph with nodes and edges where the edges are within the shortest
         specified rank fraction.
+
+    Raises:
+        ValueError: If no edges with 'length' attributes are found in the graph.
+        Warning: If the resulting subgraph has no edges after filtering.
     """
     # Step 1: Extract edges with their lengths
     edges_with_length = [(u, v, d) for u, v, d in G.edges(data=True) if "length" in d]