risk-network 0.0.13b4__py3-none-any.whl → 0.0.14__py3-none-any.whl

risk/_network/_graph/__init__.py

@@ -0,0 +1,7 @@
+"""
+risk/_network/_graph
+~~~~~~~~~~~~~~~~~~~~
+"""
+
+from ._api import GraphAPI
+from ._graph import Graph

risk/{network/graph/api.py → _network/_graph/_api.py}

@@ -1,6 +1,6 @@
 """
-risk/network/graph/api
-~~~~~~~~~~~~~~~~~~~~~~
+risk/_network/_graph/_api
+~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 import copy
@@ -9,26 +9,24 @@ from typing import Any, Dict, Union
 import networkx as nx
 import pandas as pd
 
-from risk.annotation import define_top_annotation
-from risk.log import log_header, logger, params
-from risk.neighborhoods import (
+from ..._annotation import define_top_annotation
+from ..._log import log_header, logger, params
+from ..._neighborhoods import (
     define_domains,
     process_neighborhoods,
     trim_domains,
 )
-from risk.network.graph.graph import Graph
-from risk.network.graph.stats import calculate_significance_matrices
+from ._graph import Graph
+from ._stats import calculate_significance_matrices
 
 
 class GraphAPI:
-    """Handles the loading of network graphs and associated data.
+    """
+    Handles the loading of network graphs and associated data.
 
     The GraphAPI class provides methods to load and process network graphs, annotations, and neighborhoods.
     """
 
-    def __init__(self) -> None:
-        pass
-
     def load_graph(
         self,
         network: nx.Graph,
@@ -46,7 +44,8 @@ class GraphAPI:
         min_cluster_size: int = 5,
         max_cluster_size: int = 1000,
     ) -> Graph:
-        """Load and process the network graph, defining top annotations and domains.
+        """
+        Load and process the network graph, defining top annotations and domains.
 
         Args:
             network (nx.Graph): The network graph.
@@ -169,7 +168,8 @@ class GraphAPI:
         min_cluster_size: int = 5,
         max_cluster_size: int = 1000,
     ) -> pd.DataFrame:
-        """Define top annotations for the network.
+        """
+        Define top annotations for the network.
 
         Args:
             network (nx.Graph): The network graph.

risk/{network/graph/graph.py → _network/_graph/_graph.py}

@@ -1,6 +1,6 @@
 """
-risk/network/graph/graph
-~~~~~~~~~~~~~~~~~~~~~~~~
+risk/_network/_graph/_graph
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 from collections import defaultdict
@@ -10,11 +10,12 @@ import networkx as nx
 import numpy as np
 import pandas as pd
 
-from risk.network.graph.summary import Summary
+from ._summary import Summary
 
 
 class Graph:
-    """A class to represent a network graph and process its nodes and edges.
+    """
+    A class to represent a network graph and process its nodes and edges.
 
     The Graph class provides functionality to handle and manipulate a network graph,
     including managing domains, annotation, and node significance data. It also includes methods
@@ -32,7 +33,9 @@ class Graph:
         node_label_to_node_id_map: Dict[str, Any],
         node_significance_sums: np.ndarray,
     ):
-        """Initialize the Graph object.
+        """
+
+        Initialize the Graph object.
 
         Args:
             network (nx.Graph): The network graph.
@@ -72,7 +75,8 @@ class Graph:
         self.summary = Summary(annotation, neighborhoods, self)
 
     def pop(self, domain_id: int) -> List[str]:
-        """Remove a domain ID from the graph and return the corresponding node labels.
+        """
+        Remove a domain ID from the graph and return the corresponding node labels.
 
         Args:
             key (int): The domain ID key to be removed from each mapping.
@@ -104,7 +108,8 @@ class Graph:
         return node_labels
 
     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.
+        """
+        Create a mapping from domains to the list of node IDs belonging to each domain.
 
         Args:
             domains (pd.DataFrame): DataFrame containing domain information, including the 'primary domain' for each node.
@@ -123,7 +128,8 @@ class Graph:
     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.
+        """
+        Create a mapping from domain IDs to their corresponding terms.
 
         Args:
             trimmed_domains (pd.DataFrame): DataFrame containing domain IDs and their corresponding labels.
@@ -142,7 +148,8 @@ class Graph:
         self,
         trimmed_domains: pd.DataFrame,
     ) -> Dict[int, Dict[str, Any]]:
-        """Create a mapping from domain IDs to their corresponding full description and significance score,
+        """
+        Create a mapping from domain IDs to their corresponding full description and significance score,
         with scores sorted in descending order.
 
         Args:
@@ -178,7 +185,8 @@ class Graph:
     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.
+        """
+        Creates a dictionary mapping each node ID to its corresponding domain IDs and significance values.
 
         Args:
             domains (pd.DataFrame): A DataFrame containing domain information for each node. Assumes the last
@@ -210,7 +218,8 @@ class Graph:
         return node_id_to_domain_ids_and_significances
 
     def _create_domain_id_to_node_labels_map(self) -> Dict[int, List[str]]:
-        """Create a map from domain IDs to node labels.
+        """
+        Create a map from domain IDs to node labels.
 
         Returns:
             Dict[int, List[str]]: A dictionary mapping domain IDs to the corresponding node labels.
@@ -224,7 +233,8 @@ 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.
+        """
+        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.
@@ -254,7 +264,8 @@ class Graph:
         return G
 
     def _extract_node_coordinates(self, G: nx.Graph) -> np.ndarray:
-        """Extract 2D coordinates of nodes from the graph.
+        """
+        Extract 2D coordinates of nodes from the graph.
 
         Args:
             G (nx.Graph): The network graph with node coordinates.

risk/{network/graph/stats.py → _network/_graph/_stats.py}

@@ -1,6 +1,6 @@
 """
-risk/network/graph/stats
-~~~~~~~~~~~~~~~~~~~~~~~~
+risk/_network/_graph/_stats
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 from typing import Any, Dict, Union
@@ -16,7 +16,8 @@ def calculate_significance_matrices(
     pval_cutoff: float = 0.05,
     fdr_cutoff: float = 0.05,
 ) -> Dict[str, Any]:
-    """Calculate significance matrices based on p-values and specified tail.
+    """
+    Calculate significance matrices based on p-values and specified tail.
 
     Args:
         depletion_pvals (np.ndarray): Matrix of depletion p-values.
@@ -89,7 +90,8 @@ def _select_significance_matrices(
     log_enrichment_matrix: np.ndarray,
     enrichment_alpha_threshold_matrix: np.ndarray,
 ) -> tuple:
-    """Select significance matrices based on the specified tail type.
+    """
+    Select significance matrices based on the specified tail type.
 
     Args:
         tail (str): The tail type for significance selection. Options are 'left', 'right', or 'both'.
@@ -143,7 +145,8 @@ def _compute_threshold_matrix(
     pval_cutoff: float = 0.05,
     fdr_cutoff: float = 0.05,
 ) -> np.ndarray:
-    """Compute a threshold matrix indicating significance based on p-value and FDR cutoffs.
+    """
+    Compute a threshold matrix indicating significance based on p-value and FDR cutoffs.
 
     Args:
         pvals (np.ndarray): Array of p-values for statistical tests.

risk/{network/graph/summary.py → _network/_graph/_summary.py}

@@ -1,6 +1,6 @@
 """
-risk/network/graph/summary
-~~~~~~~~~~~~~~~~~~~~~~~~~~
+risk/_network/_graph/_summary
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 from typing import Any, Dict, Tuple, Union
@@ -9,11 +9,12 @@ import numpy as np
 import pandas as pd
 from statsmodels.stats.multitest import fdrcorrection
 
-from risk.log.console import log_header, logger
+from ..._log import log_header, logger
 
 
 class Summary:
-    """Handles the processing, storage, and export of network analysis results.
+    """
+    Handles the processing, storage, and export of network analysis results.
 
     The Results class provides methods to process significance and depletion data, compute
     FDR-corrected q-values, and structure information on domains and annotations into a
@@ -27,7 +28,8 @@ class Summary:
         neighborhoods: Dict[str, Any],
         graph,  # Avoid type hinting Graph to prevent circular imports
     ):
-        """Initialize the Results object with analysis components.
+        """
+        Initialize the Results object with analysis components.
 
         Args:
             annotation (Dict[str, Any]): Annotation data, including ordered annotations and matrix of associations.
@@ -39,7 +41,8 @@ class Summary:
         self.graph = graph
 
     def to_csv(self, filepath: str) -> None:
-        """Export significance results to a CSV file.
+        """
+        Export significance results to a CSV file.
 
         Args:
             filepath (str): The path where the CSV file will be saved.
@@ -50,7 +53,8 @@ class Summary:
         logger.info(f"Analysis summary exported to CSV file: {filepath}")
 
     def to_json(self, filepath: str) -> None:
-        """Export significance results to a JSON file.
+        """
+        Export significance results to a JSON file.
 
         Args:
             filepath (str): The path where the JSON file will be saved.
@@ -61,7 +65,8 @@ class Summary:
         logger.info(f"Analysis summary exported to JSON file: {filepath}")
 
     def to_txt(self, filepath: str) -> None:
-        """Export significance results to a text file.
+        """
+        Export significance results to a text file.
 
         Args:
             filepath (str): The path where the text file will be saved.
@@ -74,11 +79,12 @@ class Summary:
         logger.info(f"Analysis summary exported to text file: {filepath}")
 
     def load(self) -> pd.DataFrame:
-        """Load and process domain and annotation data into a DataFrame with significance metrics.
+        """
+        Load and process domain and annotation data into a DataFrame with significance metrics.
 
         Returns:
             pd.DataFrame: Processed DataFrame containing significance scores, p-values, q-values,
-                and annotation member information.
+                and matched annotation members information.
         """
         log_header("Loading analysis summary")
         # Calculate significance and depletion q-values from p-value matrices in annotation
@@ -103,9 +109,9 @@ class Summary:
         # Add minimum p-values and q-values to DataFrame
         results[
             [
-                "Enrichment P-Value",
+                "Enrichment P-value",
                 "Enrichment Q-value",
-                "Depletion P-Value",
+                "Depletion P-value",
                 "Depletion Q-value",
             ]
         ] = results.apply(
@@ -120,13 +126,13 @@ class Summary:
             axis=1,
             result_type="expand",
         )
-        # Add annotation members and their counts
-        results["Annotation Members in Network"] = results["Annotation"].apply(
+        # Add matched annotation members and their counts
+        results["Matched Members"] = results["Annotation"].apply(
             lambda desc: self._get_annotation_members(desc)
         )
-        results["Annotation Members in Network Count"] = results[
-            "Annotation Members in Network"
-        ].apply(lambda x: len(x.split(";")) if x else 0)
+        results["Matched Count"] = results["Matched Members"].apply(
+            lambda x: len(x.split(";")) if x else 0
+        )
 
         # Reorder columns and drop rows with NaN values
         results = (
@@ -134,12 +140,12 @@ class Summary:
                 [
                     "Domain ID",
                     "Annotation",
-                    "Annotation Members in Network",
-                    "Annotation Members in Network Count",
+                    "Matched Members",
+                    "Matched Count",
                     "Summed Significance Score",
-                    "Enrichment P-Value",
+                    "Enrichment P-value",
                     "Enrichment Q-value",
-                    "Depletion P-Value",
+                    "Depletion P-value",
                     "Depletion Q-value",
                 ]
             ]
@@ -153,25 +159,24 @@ class Summary:
         results = pd.merge(ordered_annotation, results, on="Annotation", how="left").fillna(
             {
                 "Domain ID": -1,
-                "Annotation Members in Network": "",
-                "Annotation Members in Network Count": 0,
+                "Matched Members": "",
+                "Matched Count": 0,
                 "Summed Significance Score": 0.0,
-                "Enrichment P-Value": 1.0,
+                "Enrichment P-value": 1.0,
                 "Enrichment Q-value": 1.0,
-                "Depletion P-Value": 1.0,
+                "Depletion P-value": 1.0,
                 "Depletion Q-value": 1.0,
             }
         )
-        # Convert "Domain ID" and "Annotation Members in Network Count" to integers
+        # Convert "Domain ID" and "Matched Count" to integers
         results["Domain ID"] = results["Domain ID"].astype(int)
-        results["Annotation Members in Network Count"] = results[
-            "Annotation Members in Network Count"
-        ].astype(int)
+        results["Matched Count"] = results["Matched Count"].astype(int)
 
         return results
 
     def _calculate_qvalues(self, pvals: np.ndarray) -> np.ndarray:
-        """Calculate q-values (FDR) for each row of a p-value matrix.
+        """
+        Calculate q-values (FDR) for each row of a p-value matrix.
 
         Args:
             pvals (np.ndarray): 2D array of p-values.
@@ -190,7 +195,8 @@ class Summary:
         enrichment_qvals: np.ndarray,
         depletion_qvals: np.ndarray,
     ) -> Tuple[Union[float, None], Union[float, None], Union[float, None], Union[float, None]]:
-        """Retrieve the most significant p-values and q-values (FDR) for a given annotation.
+        """
+        Retrieve the most significant p-values and q-values (FDR) for a given annotation.
 
         Args:
             domain_id (int): The domain ID associated with the annotation.
@@ -226,7 +232,8 @@ class Summary:
         )
 
     def _get_annotation_members(self, description: str) -> str:
-        """Retrieve node labels associated with a given annotation description.
+        """
+        Retrieve node labels associated with a given annotation description.
 
         Args:
             description (str): The annotation description.