risk-network 0.0.13b3__tar.gz → 0.0.13b5__tar.gz

{risk_network-0.0.13b3/src/risk_network.egg-info → risk_network-0.0.13b5}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: risk-network
-Version: 0.0.13b3
-Summary: A Python package for biological network analysis.
+Version: 0.0.13b5
+Summary: A Python package for scalable network analysis and high-quality visualization.
 Author-email: Ira Horecka <ira89@icloud.com>
 License: GPL-3.0-or-later
 Project-URL: Homepage, https://github.com/riskportal/network

{risk_network-0.0.13b3 → risk_network-0.0.13b5}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "risk-network"
 dynamic = ["version"]
-description = "A Python package for biological network analysis."
+description = "A Python package for scalable network analysis and high-quality visualization."
 authors = [
     { name = "Ira Horecka", email = "ira89@icloud.com" },
 ]

risk_network-0.0.13b5/src/risk/__init__.py

@@ -0,0 +1,11 @@
+"""
+risk
+~~~~
+
+RISK: Regional Inference of Significant Kinships
+"""
+
+from .risk import RISK
+
+__all__ = ["RISK"]
+__version__ = "0.0.13-beta.5"

risk_network-0.0.13b5/src/risk/_annotation/__init__.py

@@ -0,0 +1,10 @@
+"""
+risk/_annotation
+~~~~~~~~~~~~~~~~
+"""
+
+from ._annotation import (
+    define_top_annotation,
+    get_weighted_description,
+)
+from ._io import AnnotationIO

risk_network-0.0.13b3/src/risk/annotation/annotation.py → risk_network-0.0.13b5/src/risk/_annotation/_annotation.py

@@ -1,6 +1,6 @@
 """
-risk/annotation/annotation
-~~~~~~~~~~~~~~~~~~~~~~~~~~
+risk/_annotation/_annotation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 import re
@@ -14,12 +14,13 @@ import pandas as pd
 from nltk.tokenize import word_tokenize
 from scipy.sparse import coo_matrix
 
-from risk.annotation.nltk_setup import setup_nltk_resources
-from risk.log import logger
+from .._log import logger
+from ._nltk_setup import setup_nltk_resources
 
 
 def initialize_nltk():
-    """Initialize all required NLTK components."""
+    """
+    Initialize all required NLTK components."""
     setup_nltk_resources()
 
     # After resources are available, initialize the components
@@ -36,15 +37,21 @@ initialize_nltk()
 
 
 def load_annotation(
-    network: nx.Graph, annotation_input: Dict[str, Any], min_nodes_per_term: int = 2
+    network: nx.Graph,
+    annotation_input: Dict[str, Any],
+    min_nodes_per_term: int = 1,
+    max_nodes_per_term: int = 10_000,
 ) -> Dict[str, Any]:
-    """Convert annotation input to a sparse matrix and reindex based on the network's node labels.
+    """
+    Convert annotation input to a sparse matrix and reindex based on the network's node labels.
 
     Args:
         network (nx.Graph): The network graph.
         annotation_input (Dict[str, Any]): An annotation dictionary.
         min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
-            term to be included. Defaults to 2.
+            term to be included. Defaults to 1.
+        max_nodes_per_term (int, optional): The maximum number of network nodes allowed for each annotation
+            term. Defaults to 10_000.
 
     Returns:
         Dict[str, Any]: A dictionary containing ordered nodes, ordered annotations, and the sparse binary annotations
@@ -52,7 +59,6 @@ def load_annotation(
 
     Raises:
         ValueError: If no annotation is found for the nodes in the network.
-        ValueError: If no annotation has at least min_nodes_per_term nodes in the network.
     """
     # Step 1: Map nodes and annotations to indices
     node_label_order = [attr["label"] for _, attr in network.nodes(data=True) if "label" in attr]
@@ -72,9 +78,18 @@ def load_annotation(
     # Create a sparse binary matrix
     num_nodes = len(node_to_idx)
     num_annotation = len(annotation_to_idx)
-    annotation_pivot = coo_matrix((data, (row, col)), shape=(num_nodes, num_annotation)).tocsr()
-    # Step 3: Filter out annotations with fewer than min_nodes_per_term occurrences
-    valid_annotation = annotation_pivot.sum(axis=0).A1 >= min_nodes_per_term
+    # Convert to a sparse matrix and set the data type to uint8 for binary representation
+    annotation_pivot = (
+        coo_matrix((data, (row, col)), shape=(num_nodes, num_annotation)).tocsr().astype(np.uint8)
+    )
+    # Step 3: Filter out annotations with too few or too many nodes
+    valid_annotation = np.array(
+        [
+            annotation_pivot[:, i].sum() >= min_nodes_per_term
+            and annotation_pivot[:, i].sum() <= max_nodes_per_term
+            for i in range(num_annotation)
+        ]
+    )
     annotation_pivot = annotation_pivot[:, valid_annotation]
     # Step 4: Raise errors for empty matrices
     if annotation_pivot.nnz == 0:
@@ -83,7 +98,7 @@ def load_annotation(
     num_remaining_annotation = annotation_pivot.shape[1]
     if num_remaining_annotation == 0:
         raise ValueError(
-            f"No annotation terms found with at least {min_nodes_per_term} nodes in the network."
+            f"No annotation terms found with at least {min_nodes_per_term} nodes and at most {max_nodes_per_term} nodes."
         )
 
     # Step 5: Extract ordered nodes and annotations
@@ -94,6 +109,7 @@ def load_annotation(
 
     # Log the filtering details
     logger.info(f"Minimum number of nodes per annotation term: {min_nodes_per_term}")
+    logger.info(f"Maximum number of nodes per annotation term: {max_nodes_per_term}")
     logger.info(f"Number of input annotation terms: {num_annotation}")
     logger.info(f"Number of remaining annotation terms: {num_remaining_annotation}")
 
@@ -113,7 +129,8 @@ def define_top_annotation(
     min_cluster_size: int = 5,
     max_cluster_size: int = 1000,
 ) -> pd.DataFrame:
-    """Define top annotations based on neighborhood significance sums and binary significance matrix.
+    """
+    Define top annotations based on neighborhood significance sums and binary significance matrix.
 
     Args:
         network (NetworkX graph): The network graph.
@@ -122,7 +139,7 @@ def define_top_annotation(
         significant_significance_matrix (np.ndarray): Enrichment matrix below alpha threshold.
         significant_binary_significance_matrix (np.ndarray): Binary significance matrix below alpha threshold.
         min_cluster_size (int, optional): Minimum cluster size. Defaults to 5.
-        max_cluster_size (int, optional): Maximum cluster size. Defaults to 1000.
+        max_cluster_size (int, optional): Maximum cluster size. Defaults to 10_000.
 
     Returns:
         pd.DataFrame: DataFrame with top annotations and their properties.
@@ -204,7 +221,8 @@ def define_top_annotation(
 
 
 def get_weighted_description(words_column: pd.Series, scores_column: pd.Series) -> str:
-    """Generate a weighted description from words and their corresponding scores,
+    """
+    Generate a weighted description from words and their corresponding scores,
     using improved weighting logic with normalization, lemmatization, and aggregation.
 
     Args:
@@ -272,7 +290,8 @@ def get_weighted_description(words_column: pd.Series, scores_column: pd.Series)
 
 
 def _simplify_word_list(words: List[str], threshold: float = 0.80) -> List[str]:
-    """Filter out words that are too similar based on the Jaccard index,
+    """
+    Filter out words that are too similar based on the Jaccard index,
     keeping the word with the higher aggregated count.
 
     Args:
@@ -312,7 +331,8 @@ def _simplify_word_list(words: List[str], threshold: float = 0.80) -> List[str]:
 
 
 def _calculate_jaccard_index(set1: Set[Any], set2: Set[Any]) -> float:
-    """Calculate the Jaccard index between two sets.
+    """
+    Calculate the Jaccard index between two sets.
 
     Args:
         set1 (Set[Any]): The first set.
@@ -327,7 +347,8 @@ def _calculate_jaccard_index(set1: Set[Any], set2: Set[Any]) -> float:
 
 
 def _generate_coherent_description(words: List[str]) -> str:
-    """Generate a coherent description from a list of words.
+    """
+    Generate a coherent description from a list of words.
 
     If there is only one unique entry, return it directly.
     Otherwise, order the words by frequency and join them into a single string.

risk_network-0.0.13b3/src/risk/annotation/io.py → risk_network-0.0.13b5/src/risk/_annotation/_io.py

@@ -1,6 +1,6 @@
 """
-risk/annotation/io
-~~~~~~~~~~~~~~~~~~
+risk/_annotation/_io
+~~~~~~~~~~~~~~~~~~~~
 """
 
 import json
@@ -9,27 +9,35 @@ from typing import Any, Dict
 import networkx as nx
 import pandas as pd
 
-from risk.annotation.annotation import load_annotation
-from risk.log import log_header, logger, params
+from .._log import log_header, logger, params
+from ._annotation import load_annotation
 
 
 class AnnotationIO:
-    """Handles the loading and exporting of annotation in various file formats.
+    """
+    Handles the loading and exporting of annotation in various file formats.
 
     The AnnotationIO class provides methods to load annotation from different file types (JSON, CSV, Excel, etc.)
     and to export parameter data to various formats like JSON, CSV, and text files.
     """
 
     def load_annotation_json(
-        self, network: nx.Graph, filepath: str, min_nodes_per_term: int = 2
+        self,
+        network: nx.Graph,
+        filepath: str,
+        min_nodes_per_term: int = 1,
+        max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
-        """Load annotation from a JSON file and convert them to a DataFrame.
+        """
+        Load annotation from a JSON file and convert them to a DataFrame.
 
         Args:
             network (NetworkX graph): The network to which the annotation is related.
             filepath (str): Path to the JSON annotation file.
             min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
-                term to be included. Defaults to 2.
+                term to be included. Defaults to 1.
+            max_nodes_per_term (int, optional): The maximum number of network nodes allowed for each annotation
+                term to be included. Defaults to 10_000.
 
         Returns:
             Dict[str, Any]: A dictionary containing ordered nodes, ordered annotations, and the annotation matrix.
@@ -37,7 +45,10 @@ class AnnotationIO:
         filetype = "JSON"
         # Log the loading of the JSON file
         params.log_annotation(
-            filetype=filetype, filepath=filepath, min_nodes_per_term=min_nodes_per_term
+            filetype=filetype,
+            filepath=filepath,
+            min_nodes_per_term=min_nodes_per_term,
+            max_nodes_per_term=max_nodes_per_term,
         )
         self._log_loading_annotation(filetype, filepath=filepath)
 
@@ -45,7 +56,7 @@ class AnnotationIO:
         with open(filepath, "r", encoding="utf-8") as file:
             annotation_input = json.load(file)
 
-        return load_annotation(network, annotation_input, min_nodes_per_term)
+        return load_annotation(network, annotation_input, min_nodes_per_term, max_nodes_per_term)
 
     def load_annotation_excel(
         self,
@@ -55,9 +66,11 @@ class AnnotationIO:
         nodes_colname: str = "nodes",
         sheet_name: str = "Sheet1",
         nodes_delimiter: str = ";",
-        min_nodes_per_term: int = 2,
+        min_nodes_per_term: int = 1,
+        max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
-        """Load annotation from an Excel file and associate them with the network.
+        """
+        Load annotation from an Excel file and associate them with the network.
 
         Args:
             network (nx.Graph): The NetworkX graph to which the annotation is related.
@@ -67,7 +80,9 @@ class AnnotationIO:
             sheet_name (str, optional): The name of the Excel sheet to load (default is 'Sheet1').
             nodes_delimiter (str, optional): Delimiter used to separate multiple nodes within the nodes column (default is ';').
             min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
-                term to be included. Defaults to 2.
+                term to be included. Defaults to 1.
+            max_nodes_per_term (int, optional): The maximum number of network nodes allowed for each annotation
+                term to be included. Defaults to 10_000.
 
         Returns:
             Dict[str, Any]: A dictionary where each label is paired with its respective list of nodes,
@@ -76,7 +91,10 @@ class AnnotationIO:
         filetype = "Excel"
         # Log the loading of the Excel file
         params.log_annotation(
-            filetype=filetype, filepath=filepath, min_nodes_per_term=min_nodes_per_term
+            filetype=filetype,
+            filepath=filepath,
+            min_nodes_per_term=min_nodes_per_term,
+            max_nodes_per_term=max_nodes_per_term,
         )
         self._log_loading_annotation(filetype, filepath=filepath)
 
@@ -89,7 +107,7 @@ class AnnotationIO:
         # Convert the DataFrame to a dictionary pairing labels with their corresponding nodes
         annotation_input = annotation.set_index(label_colname)[nodes_colname].to_dict()
 
-        return load_annotation(network, annotation_input, min_nodes_per_term)
+        return load_annotation(network, annotation_input, min_nodes_per_term, max_nodes_per_term)
 
     def load_annotation_csv(
         self,
@@ -98,9 +116,11 @@ class AnnotationIO:
         label_colname: str = "label",
         nodes_colname: str = "nodes",
         nodes_delimiter: str = ";",
-        min_nodes_per_term: int = 2,
+        min_nodes_per_term: int = 1,
+        max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
-        """Load annotation from a CSV file and associate them with the network.
+        """
+        Load annotation from a CSV file and associate them with the network.
 
         Args:
             network (nx.Graph): The NetworkX graph to which the annotation is related.
@@ -109,7 +129,9 @@ class AnnotationIO:
             nodes_colname (str): Name of the column containing the nodes associated with each label.
             nodes_delimiter (str, optional): Delimiter used to separate multiple nodes within the nodes column (default is ';').
             min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
-                term to be included. Defaults to 2.
+                term to be included. Defaults to 1.
+            max_nodes_per_term (int, optional): The maximum number of network nodes allowed for each annotation
+                term to be included. Defaults to 10_000.
 
         Returns:
             Dict[str, Any]: A dictionary where each label is paired with its respective list of nodes,
@@ -118,7 +140,10 @@ class AnnotationIO:
         filetype = "CSV"
         # Log the loading of the CSV file
         params.log_annotation(
-            filetype=filetype, filepath=filepath, min_nodes_per_term=min_nodes_per_term
+            filetype=filetype,
+            filepath=filepath,
+            min_nodes_per_term=min_nodes_per_term,
+            max_nodes_per_term=max_nodes_per_term,
         )
         self._log_loading_annotation(filetype, filepath=filepath)
 
@@ -127,7 +152,7 @@ class AnnotationIO:
             filepath, label_colname, nodes_colname, delimiter=",", nodes_delimiter=nodes_delimiter
         )
 
-        return load_annotation(network, annotation_input, min_nodes_per_term)
+        return load_annotation(network, annotation_input, min_nodes_per_term, max_nodes_per_term)
 
     def load_annotation_tsv(
         self,
@@ -136,9 +161,11 @@ class AnnotationIO:
         label_colname: str = "label",
         nodes_colname: str = "nodes",
         nodes_delimiter: str = ";",
-        min_nodes_per_term: int = 2,
+        min_nodes_per_term: int = 1,
+        max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
-        """Load annotation from a TSV file and associate them with the network.
+        """
+        Load annotation from a TSV file and associate them with the network.
 
         Args:
             network (nx.Graph): The NetworkX graph to which the annotation is related.
@@ -147,7 +174,9 @@ class AnnotationIO:
             nodes_colname (str): Name of the column containing the nodes associated with each label.
             nodes_delimiter (str, optional): Delimiter used to separate multiple nodes within the nodes column (default is ';').
             min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
-                term to be included. Defaults to 2.
+                term to be included. Defaults to 1.
+            max_nodes_per_term (int, optional): The maximum number of network nodes allowed for each annotation
+                term to be included. Defaults to 10_000.
 
         Returns:
             Dict[str, Any]: A dictionary where each label is paired with its respective list of nodes,
@@ -156,7 +185,10 @@ class AnnotationIO:
         filetype = "TSV"
         # Log the loading of the TSV file
         params.log_annotation(
-            filetype=filetype, filepath=filepath, min_nodes_per_term=min_nodes_per_term
+            filetype=filetype,
+            filepath=filepath,
+            min_nodes_per_term=min_nodes_per_term,
+            max_nodes_per_term=max_nodes_per_term,
         )
         self._log_loading_annotation(filetype, filepath=filepath)
 
@@ -165,18 +197,25 @@ class AnnotationIO:
             filepath, label_colname, nodes_colname, delimiter="\t", nodes_delimiter=nodes_delimiter
         )
 
-        return load_annotation(network, annotation_input, min_nodes_per_term)
+        return load_annotation(network, annotation_input, min_nodes_per_term, max_nodes_per_term)
 
     def load_annotation_dict(
-        self, network: nx.Graph, content: Dict[str, Any], min_nodes_per_term: int = 2
+        self,
+        network: nx.Graph,
+        content: Dict[str, Any],
+        min_nodes_per_term: int = 1,
+        max_nodes_per_term: int = 10_000,
     ) -> Dict[str, Any]:
-        """Load annotation from a provided dictionary and convert them to a dictionary annotation.
+        """
+        Load annotation from a provided dictionary and convert them to a dictionary annotation.
 
         Args:
             network (NetworkX graph): The network to which the annotation is related.
             content (Dict[str, Any]): The annotation dictionary to load.
             min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
-                term to be included. Defaults to 2.
+                term to be included. Defaults to 1.
+            max_nodes_per_term (int, optional): The maximum number of network nodes allowed for each annotation
+                term to be included. Defaults to 10_000.
 
         Returns:
             Dict[str, Any]: A dictionary containing ordered nodes, ordered annotations, and the annotation matrix.
@@ -192,11 +231,16 @@ class AnnotationIO:
 
         filetype = "Dictionary"
         # Log the loading of the annotation from the dictionary
-        params.log_annotation(filepath="In-memory dictionary", filetype=filetype)
+        params.log_annotation(
+            filepath="In-memory dictionary",
+            filetype=filetype,
+            min_nodes_per_term=min_nodes_per_term,
+            max_nodes_per_term=max_nodes_per_term,
+        )
         self._log_loading_annotation(filetype, "In-memory dictionary")
 
         # Load the annotation as a dictionary from the provided dictionary
-        return load_annotation(network, content, min_nodes_per_term)
+        return load_annotation(network, content, min_nodes_per_term, max_nodes_per_term)
 
     def _load_matrix_file(
         self,
@@ -206,7 +250,8 @@ class AnnotationIO:
         delimiter: str = ",",
         nodes_delimiter: str = ";",
     ) -> Dict[str, Any]:
-        """Load annotation from a CSV or TSV file and convert them to a dictionary.
+        """
+        Load annotation from a CSV or TSV file and convert them to a dictionary.
 
         Args:
             filepath (str): Path to the annotation file.
@@ -229,7 +274,8 @@ class AnnotationIO:
         return label_node_dict
 
     def _log_loading_annotation(self, filetype: str, filepath: str = "") -> None:
-        """Log the loading of annotation files.
+        """
+        Log the loading of annotation files.
 
         Args:
             filetype (str): The type of the file being loaded (e.g., 'Cytoscape').

risk_network-0.0.13b3/src/risk/annotation/nltk_setup.py → risk_network-0.0.13b5/src/risk/_annotation/_nltk_setup.py

@@ -1,6 +1,6 @@
 """
-risk/annotation/nltk_setup
-~~~~~~~~~~~~~~~~~~~~~~~~~~
+risk/_annotation/_nltk_setup
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 import os
@@ -11,11 +11,12 @@ import nltk
 from nltk.data import find
 from nltk.data import path as nltk_data_path
 
-from risk.log import logger
+from .._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.
+    """
+    Ensures all required NLTK resources are available and properly extracted.
     Uses NLTK's default paths and mechanisms.
 
     Args:
@@ -47,7 +48,8 @@ def setup_nltk_resources(required_resources: Optional[List[Tuple[str, str]]] = N
 
 
 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
+    """
+    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.
 

risk_network-0.0.13b5/src/risk/_log/__init__.py

@@ -0,0 +1,11 @@
+"""
+risk/_log
+~~~~~~~~~
+"""
+
+from ._console import log_header, logger, set_global_verbosity
+from ._parameters import Params
+
+# Initialize the global parameters logger
+params = Params()
+params.initialize()

risk_network-0.0.13b3/src/risk/log/console.py → risk_network-0.0.13b5/src/risk/_log/_console.py

@@ -1,13 +1,14 @@
 """
-risk/log/console
-~~~~~~~~~~~~~~~~
+risk/_log/_console
+~~~~~~~~~~~~~~~~~~
 """
 
 import logging
 
 
 def in_jupyter():
-    """Check if the code is running in a Jupyter notebook environment.
+    """
+    Check if the code is running in a Jupyter notebook environment.
 
     Returns:
         bool: True if running in a Jupyter notebook or QtConsole, False otherwise.
@@ -26,7 +27,8 @@ def in_jupyter():
 
 # Define the MockLogger class to replicate logging behavior with print statements in Jupyter
 class MockLogger:
-    """MockLogger: A lightweight logger replacement using print statements in Jupyter.
+    """
+    MockLogger: A lightweight logger replacement using print statements in Jupyter.
 
     The MockLogger class replicates the behavior of a standard logger using print statements
     to display messages. This is primarily used in a Jupyter environment to show outputs
@@ -35,7 +37,8 @@ class MockLogger:
     """
 
     def __init__(self, verbose: bool = True):
-        """Initialize the MockLogger with verbosity settings.
+        """
+        Initialize the MockLogger with verbosity settings.
 
         Args:
             verbose (bool): If True, display all log messages (info, debug, warning).
@@ -44,7 +47,8 @@ class MockLogger:
         self.verbose = verbose
 
     def info(self, message: str) -> None:
-        """Display an informational message.
+        """
+        Display an informational message.
 
         Args:
             message (str): The informational message to be printed.
@@ -53,7 +57,8 @@ class MockLogger:
             print(message)
 
     def debug(self, message: str) -> None:
-        """Display a debug message.
+        """
+        Display a debug message.
 
         Args:
             message (str): The debug message to be printed.
@@ -62,7 +67,8 @@ class MockLogger:
             print(message)
 
     def warning(self, message: str) -> None:
-        """Display a warning message.
+        """
+        Display a warning message.
 
         Args:
             message (str): The warning message to be printed.
@@ -70,7 +76,8 @@ class MockLogger:
         print(message)
 
     def error(self, message: str) -> None:
-        """Display an error message.
+        """
+        Display an error message.
 
         Args:
             message (str): The error message to be printed.
@@ -78,7 +85,8 @@ class MockLogger:
         print(message)
 
     def setLevel(self, level: int) -> None:
-        """Adjust verbosity based on the logging level.
+        """
+        Adjust verbosity based on the logging level.
 
         Args:
             level (int): Logging level to control message display.
@@ -108,7 +116,8 @@ else:
 
 
 def set_global_verbosity(verbose):
-    """Set the global verbosity level for the logger.
+    """
+    Set the global verbosity level for the logger.
 
     Args:
         verbose (bool): Whether to display all log messages (True) or only error messages (False).
@@ -130,7 +139,8 @@ def set_global_verbosity(verbose):
 
 
 def log_header(input_string: str) -> None:
-    """Log the input string as a header with a line of dashes above and below it.
+    """
+    Log the input string as a header with a line of dashes above and below it.
 
     Args:
         input_string (str): The string to be printed as a header.